{"id":1107987,"date":"2024-11-28T19:44:00","date_gmt":"2024-11-29T03:44:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-blog-post&#038;p=1107987"},"modified":"2024-12-01T19:09:00","modified_gmt":"2024-12-02T03:09:00","slug":"msra-neurips-2024-papers","status":"publish","type":"msr-blog-post","link":"https:\/\/www.microsoft.com\/en-us\/research\/articles\/msra-neurips-2024-papers\/","title":{"rendered":"NeurIPS 2024 Papers from Microsoft Research Asia"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\" id=\"oral-papers\">Oral papers<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/not-all-tokens-are-what-you-need-for-pretraining\/\">Not All Tokens Are What You Need for Pretraining<\/a><\/strong><br><em>Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that \u201cNot all tokens in a corpus are equally important for language model training\u201d. Our initial analysis examines token-level training dynamics of language model, revealing distinct loss patterns for different tokens. Leveraging these insights, we introduce a new language model called Rho-1. Unlike traditional LMs that learn to predict every next token in a corpus, Rho-1 employs Selective Language Modeling (SLM), which selectively trains on useful tokens that aligned with the desired distribution. This approach involves scoring pretraining tokens using a reference model, and then training the language model with a focused loss on tokens with higher scores. When continual pretraining on 15B OpenWebMath corpus, Rho-1 yields an absolute improvement in few-shot accuracy of up to 30% in 9 math tasks. After fine-tuning, Rho-1-1B and 7B achieved state-of-the-art results of 40.6% and 51.8% on MATH dataset, respectively \u2013 matching DeepSeekMath with only 3% of the pretraining tokens. Furthermore, when pretraining on 80B general tokens, Rho-1 achieves 6.8% average enhancement across 15 diverse tasks, increasing both efficiency and performance of the language model pre-training.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/vasa-1-lifelike-audio-driven-talking-faces-generated-in-real-time\/\"><strong>VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time<\/strong><br><\/a><em>We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only producing lip movements that are exquisitely synchronized with the audio, but also capturing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expressive and disentangled face latent space using videos. Through extensive experiments including evaluation on a set of new metrics, we show that our method significantly outperforms previous methods along various dimensions comprehensively. Our method not only delivers high video quality with realistic facial and head dynamics but also supports the online generation of 512\u00d7512 videos at up to 40 FPS with negligible starting latency. It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/you-only-cache-once-decoder-decoder-architectures-for-language-models\/\"><strong>You Only Cache Once: Decoder-Decoder Architectures for Language Models<\/strong><br><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><em>We introduce a decoder-decoder architecture, YOCO, for large language models, which only caches key-value pairs once. It consists of two components, i.e., a cross-decoder stacked upon a self-decoder. The self-decoder efficiently encodes global key-value (KV) caches that are reused by the cross-decoder via cross-attention. The overall model behaves like a decoder-only Transformer, although YOCO only caches once. The design substantially reduces GPU memory demands, yet retains global attention capability. Additionally, the computation flow enables prefilling to early exit without changing the final output, thereby significantly speeding up the prefill stage. Experimental results demonstrate that YOCO achieves favorable performance compared to Transformer in various settings of scaling up model size and number of training tokens. We also extend YOCO to 1M context length with near-perfect needle retrieval accuracy. The profiling results show that YOCO improves inference memory, prefill latency, and throughput by orders of magnitude across context lengths and model sizes. Code is available at\u00a0<a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/YOCO\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/aka.ms\/YOCO<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/em><\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"spotlight-papers\">Spotlight papers<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/advancing-spiking-neural-networks-for-sequential-modeling-with-central-pattern-generators\/\"><strong>Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators<\/strong><br><\/a><em>Spiking neural networks (SNNs) represent a promising approach to developing artificial neural networks that are both energy-efficient and biologically plausible. However, applying SNNs to sequential tasks, such as text classification and time-series forecasting, has been hindered by the challenge of creating an effective and hardware-friendly spike-form positional encoding (PE) strategy. Drawing inspiration from the central pattern generators (CPGs) in the human brain, which produce rhythmic patterned outputs without requiring rhythmic inputs, we propose a novel PE technique for SNNs, termed CPG-PE. We demonstrate that the commonly used sinusoidal PE is mathematically a specific solution to the membrane potential dynamics of a particular CPG. Moreover, extensive experiments across various domains, including time-series forecasting, natural language processing, and image classification, show that SNNs with CPG-PE outperform their conventional counterparts. Additionally, we perform analysis experiments to elucidate the mechanism through which SNNs encode positional information and to explore the function of CPGs in the human brain. This investigation may offer valuable insights into the fundamental principles of neural computation.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/bpqp-a-differentiable-convex-optimization-framework-for-efficient-end-to-end-learning\/\"><strong>BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning<\/strong><br><\/a><em>Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical optimization problems, leading to the emergence of differentiable optimization layers that permit gradient back-propagation. However, real-world scenarios often involve large-scale datasets and numerous constraints, presenting significant challenges. Current methods for differentiating optimization problems typically rely on implicit differentiation, which necessitates costly computations on the Jacobian matrices, resulting in low efficiency. In this paper, we introduce BPQP, a differentiable convex optimization framework designed for efficient end-to-end learning. To enhance efficiency, we reformulate the backward pass as a simplified and decoupled quadratic programming problem by leveraging the structural properties of the Karush\u2013Kuhn\u2013Tucker (KKT) matrix. This reformulation enables the use of first-order optimization algorithms in calculating the backward pass gradients, allowing our framework to potentially utilize any state-of-the-art solver. As solver technologies evolve, BPQP can continuously adapt and improve its efficiency. Extensive experiments on both simulated and real-world datasets demonstrate that BPQP achieves a significant improvement in efficiency\u2014typically an order of magnitude faster in overall execution time compared to other differentiable optimization layers. Our results not only highlight the efficiency gains of BPQP but also underscore its superiority over differential optimization layer baselines.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/diffusion-model-with-cross-attention-as-an-inductive-bias-for-disentanglement\/\"><strong>Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement<\/strong><br><\/a><em>Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific structural designs. In this paper, we introduce a new perspective and framework, demonstrating that diffusion models with cross-attention can serve as a powerful inductive bias to facilitate the learning of disentangled representations. We propose to encode an image to a set of concept tokens and treat them as the condition of the latent diffusion for image reconstruction, where cross-attention over the concept tokens is used to bridge the interaction between the encoder and diffusion. Without any additional regularization, this framework achieves superior disentanglement performance on the benchmark datasets, surpassing all previous methods with intricate designs. We have conducted comprehensive ablation studies and visualization analysis, shedding light on the functioning of this model. This is the first work to reveal the potent disentanglement capability of diffusion models with cross-attention, requiring no complex designs. We anticipate that our findings will inspire more investigation on exploring diffusion for disentangled representation learning towards more sophisticated data analysis and understanding.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/erbench-an-entity-relationship-based-automatically-verifiable-hallucination-benchmark-for-large-language-models\/\"><strong>ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models<\/strong><br><\/a><em>Large language models (LLMs) have achieved unprecedented performance in various applications, yet their evaluation remains a critical issue. Existing hallucination benchmarks are either static or lack adjustable complexity for thorough analysis. We contend that utilizing existing relational databases is a promising approach for constructing benchmarks due to their accurate knowledge description via functional dependencies. We propose ERBench to automatically convert any relational database into a benchmark based on the entity-relationship (ER) model. Our key idea is to construct questions using the database schema, records, and functional dependencies such that they can be automatically verified. In addition, we use foreign key constraints to join relations and construct multihop questions, which can be arbitrarily complex and used to debug the intermediate answers of LLMs. Finally, ERBench supports continuous evaluation, multimodal questions, and various prompt engineering techniques. In our experiments, we construct an LLM benchmark using databases of multiple domains and make an extensive comparison of contemporary LLMs. We observe that better LLMs like GPT-4 can handle a larger variety of question types, but are by no means perfect. Also, correct answers do not necessarily imply correct rationales, which is an important evaluation that ERBench does better than other benchmarks for various question types. Code is available at .<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/human-aware-vision-and-language-navigation-bridging-simulation-to-reality-with-dynamic-human-interactions\/\"><strong>Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions<\/strong><br><\/a><em>Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments and optimal expert supervision, limiting their real-world applicability. To address this, we introduce Human-Aware Vision-and-Language Navigation (HA-VLN), extending traditional VLN by incorporating dynamic human activities and relaxing key assumptions. We propose the Human-Aware 3D (HA3D) simulator, which combines dynamic human activities with the Matterport3D dataset, and the Human-Aware Room-to-Room (HA-R2R) dataset, extending R2R with human activity descriptions. To tackle HA-VLN challenges, we present the Expert-Supervised Cross-Modal (VLN-CM) and Non-Expert-Supervised Decision Transformer (VLN-DT) agents, utilizing cross-modal fusion and diverse training strategies for effective navigation in dynamic human environments. A comprehensive evaluation, including metrics considering human activities, and systematic analysis of HA-VLN\u2019s unique challenges, underscores the need for further research to enhance HA-VLN agents\u2019 real-world robustness and adaptability. Ultimately, this work provides benchmarks and insights for future research on embodied AI and Sim2Real transfer, paving the way for more realistic and applicable VLN systems in human-populated environments.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/minference-1-0-accelerating-pre-filling-for-long-context-llms-via-dynamic-sparse-attention\/\"><strong>MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention<\/strong><br><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><em>The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method designed to accelerate pre-filling of long-sequence processing. Specifically, we identify three unique patterns in long-context attention matrices-the A-shape, Vertical-Slash, and Block-Sparsethat can be leveraged for efficient sparse computation on GPUs. We determine the optimal pattern for each attention head offline and dynamically build sparse indices based on the assigned pattern during inference. With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs. Our proposed technique can be directly applied to existing LLMs without any modifications to the pre-training setup or additional fine-tuning. By evaluating on a wide range of downstream tasks, including InfiniteBench, RULER, PG-19, and Needle In A Haystack, and models including LLaMA-3-1M, GLM4-1M, Yi-200K, Phi-3-128K, and Qwen2-128K, we demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy. Our code is available at\u00a0<a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/MInference\">https:\/\/aka.ms\/MInference<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/voila-a-aligning-vision-language-models-with-users-gaze-attention\/\"><strong>Voila-A: Aligning Vision-Language Models with User\u2019s Gaze Attention<\/strong><br><\/a><em>In recent years, the integration of vision and language understanding has led to significant advancements in artificial intelligence, particularly through Vision-Language Models (VLMs). However, existing VLMs face challenges in handling real-world applications with complex scenes and multiple objects, as well as aligning their focus with the diverse attention patterns of human users. In this paper, we introduce gaze information, feasibly collected by AR or VR devices, as a proxy for human attention to guide VLMs and propose a novel approach, Voila-A, for gaze alignment to enhance the interpretability and effectiveness of these models in real-world applications. First, we collect hundreds of minutes of gaze data to demonstrate that we can mimic human gaze modalities using localized narratives. We then design an automatic data annotation pipeline utilizing GPT-4 to generate the VOILA-COCO dataset. Additionally, we innovate the Voila Perceiver modules to integrate gaze information into VLMs while preserving their pretrained knowledge. We evaluate Voila-A using a hold-out validation set and a newly collected VOILA-GAZE Testset, which features real-life scenarios captured with a gaze-tracking device. Our experimental results demonstrate that Voila-A significantly outperforms several baseline models. By aligning model attention with human gaze patterns, Voila-A paves the way for more intuitive, user-centric VLMs and fosters engaging human-AI interaction across a wide range of applications.<\/em><\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"more-papers\">More papers<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/alpine-unveiling-the-planning-capability-of-autoregressive-learning-in-language-models\/\">ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models<br><\/a><\/strong><em>In this paper, we present the findings of our Project ALPINE which stands for \u201cAutoregressive Learning for Planning In NEtworks.\u201d Project ALPINE initiates a theoretical investigation into the development of planning capabilities in Transformer-based language models through their autoregressive learning mechanisms, aiming to identify any potential limitations in their planning abilities. We abstract planning as a network path-finding task where the objective is to generate a valid path from a specified source node to a designated target node. In terms of expressiveness, we show that the Transformer is capable of executing path-finding by embedding the adjacency and reachability matrices within its weights. Our theoretical analysis of the gradient-based learning dynamic of the Transformer reveals that the Transformer is capable of learning both the adjacency matrix and a limited form of the reachability matrix. These theoretical insights are then validated through experiments, which demonstrate that the Transformer indeed learns the adjacency matrix and an incomplete reachability matrix, which aligns with the predictions made in our theoretical analysis. Additionally, when applying our methodology to a real-world planning benchmark, called Blocksworld, our observations remain consistent. Our theoretical and empirical analyses further unveil a potential limitation of Transformer in path-finding: it cannot identify reachability relationships through transitivity, and thus would fail when path concatenation is needed to generate a path. In summary, our findings shed new light on how the internal mechanisms of autoregressive learning enable planning in networks. This study may contribute to our understanding of the general planning capabilities in other related domains.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/query-efficient-correlation-clustering-with-noisy-oracle\/\">Query-Efficient Correlation Clustering with Noisy Oracle<br><\/a><\/strong><em>We study a general clustering setting in which we have n elements to be clustered, and we aim to perform as few queries as possible to an oracle that returns a noisy sample of the weighted similarity between two elements. Our setting encompasses many application domains in which the similarity function is costly to compute and inherently noisy. We introduce two novel formulations of online learning problems rooted in the paradigm of Pure Exploration in Combinatorial Multi-Armed Bandits (PE-CMAB): fixed confidence and fixed budget settings. For both settings, we design algorithms that combine a sampling strategy with a classic approximation algorithm for correlation clustering and study their theoretical guarantees. Our results are the first examples of polynomial-time algorithms that work for the case of PE-CMAB in which the underlying offline optimization problem is NP-hard.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/aligning-vision-models-with-human-aesthetics-in-retrieval-benchmarks-and-algorithms\/\">Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms<br><\/a><\/strong><em>Modern vision models are trained on very large noisy datasets. While these models acquire strong capabilities, they may not follow the user\u2019s intent to output the desired results in certain aspects, e.g., visual aesthetic, preferred style, and responsibility. In this paper, we target the realm of visual aesthetics and aim to align vision models with human aesthetic standards in a retrieval system. Advanced retrieval systems usually adopt a cascade of aesthetic models as re-rankers or filters, which are limited to low-level features like saturation and perform poorly when stylistic, cultural or knowledge contexts are involved. We find that utilizing the reasoning ability of large language models (LLMs) to rephrase the search query and extend the aesthetic expectations can make up for this shortcoming. Based on the above findings, we propose a preference-based reinforcement learning method that fine-tunes the vision models to distill the knowledge from both LLMs reasoning and the aesthetic models to better align the vision models with human aesthetics. Meanwhile, with rare benchmarks designed for evaluating retrieval systems, we leverage large multi-modality model (LMM) to evaluate the aesthetic performance with their strong abilities. As aesthetic assessment is one of the most subjective tasks, to validate the robustness of LMM, we further propose a novel dataset named HPIR to benchmark the alignment with human aesthetics. Experiments demonstrate that our method significantly enhances the aesthetic behaviors of the vision models, under several metrics. We believe the proposed algorithm can be a general practice for aligning vision models with human values.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/autoformalize-mathematical-statements-by-symbolic-equivalence-and-semantic-consistency\/\">Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency<br><\/a><\/strong><em>Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models (LLMs) have unveiled their promising capabilities to formalize even competition-level math problems. However, we observe a considerable discrepancy between pass@1 and pass@k accuracies in LLM-generated formalizations. To address this gap, we introduce a novel framework that scores and selects the best result from k autoformalization candidates based on two complementary self-consistency methods: symbolic equivalence and semantic consistency. Elaborately, symbolic equivalence identifies the logical homogeneity among autoformalization candidates using automated theorem provers, and semantic consistency evaluates the preservation of the original meaning by informalizing the candidates and computing the similarity between the embeddings of the original and informalized texts. Our extensive experiments on the MATH and miniF2F datasets demonstrate that our approach significantly enhances autoformalization accuracy, achieving up to 0.22-1.35x relative improvements across various LLMs and baseline methods.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/boosting-text-to-video-generative-model-with-mllms-feedback\/\">Boosting Text-to-Video Generative Model with MLLMs Feedback<br><\/a><\/strong><em>Recent advancements in text-to-video generative models, such as Sora, have showcased impressive capabilities. These models have attracted significant interest for their potential applications. However, they often rely on extensive datasets of variable quality, which can result in generated videos that lack aesthetic appeal and do not accurately reflect the input text prompts. A promising approach to mitigate these issues is to leverage Reinforcement Learning from Human Feedback (RLHF), which aims to align the outputs of text-to-video generative with human preferences. However, the considerable costs associated with manual annotation have led to a scarcity of comprehensive preference datasets. In response to this challenge, our study begins by investigating the efficacy of Multimodal Large Language Models (MLLMs) generated annotations in capturing video preferences, discovering a high degree of concordance with human judgments. Building upon this finding, we utilize MLLMs to perform fine-grained video preference annotations across two dimensions, resulting in the creation of VideoPrefer, which includes 135,000 preference annotations. Utilizing this dataset, we introduce VideoRM, the first general-purpose reward model tailored for video preference in the text-to-video domain. Our comprehensive experiments confirm the effectiveness of both VideoPrefer and VideoRM, representing a significant step forward in the field.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/can-graph-learning-improve-task-planning\/\">Can Graph Learning Improve Task Planning?<br><\/a><\/strong><em>Task planning is emerging as an important research topic alongside the development of large language models (LLMs). It aims to break down complex user requests into solvable sub-tasks, thereby fulfilling the original requests. In this context, the sub-tasks can be naturally viewed as a graph, where the nodes represent the sub-tasks, and the edges denote the dependencies among them. Consequently, task planning is a decision-making problem that involves selecting a connected path or subgraph within the corresponding graph and invoking it. In this paper, we explore graph learning-based methods for task planning, a direction that is orthogonal to the prevalent focus on prompt design. Our interest in graph learning stems from a theoretical discovery: the biases of attention and auto-regressive loss impede LLMs\u2019 ability to effectively navigate decision-making on graphs, which is adeptly addressed by graph neural networks (GNNs). This theoretical insight led us to integrate GNNs with LLMs to enhance overall performance. Extensive experiments demonstrate that GNN-based methods surpass existing solutions even without training, and minimal training can further enhance their performance. Additionally, our approach complements prompt engineering and fine-tuning techniques, with performance further enhanced by improved prompts or a fine-tuned model.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/clave-an-adaptive-framework-for-evaluating-values-of-llm-generated-responses\/\"><strong>CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses<br><\/strong><\/a><em>The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs\u2019 values can help expose their misalignment, but relies on reference-free evaluators, e.g., fine-tuned LLMs or close-source ones like GPT-4, to identify values reflected in generated responses. Nevertheless, these evaluators face two challenges in open-ended value evaluation: they should align with changing human value definitions with minimal annotation, against their own bias (adaptability), and detect varying value expressions and scenarios robustly (generalizability). To handle these challenges, we introduce CLAVE, a novel framework which integrates two complementary LLMs, a large one to extract high-level value concepts from a few human labels, leveraging its extensive knowledge and generalizability, and a smaller one fine-tuned on such concepts to better align with human value understanding. This dual-model approach enables calibration with any value systems using<100 human-labeled samples per value type. Then we present ValEval, a comprehensive dataset comprising 13k+ (text,value,label) tuples across diverse domains, covering three major value systems. We benchmark the capabilities of 12+ popular LLM evaluators and analyze their strengths and weaknesses. Our findings reveal that combining fine-tuned small models and prompt-based large ones serves as a superior balance in value evaluation.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/compositional-3d-aware-video-generation-with-llm-director\/\">Compositional 3D-aware Video Generation with LLM Director<br><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/strong><em>Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual concepts within the generated video, such as the motion and appearance of specific characters and the movement of viewpoints. In this work, we propose a novel paradigm that generates each concept in 3D representation separately and then composes them with priors from Large Language Models (LLM) and 2D diffusion models. Specifically, given an input textual prompt, our scheme consists of three stages: 1) We leverage LLM as the director to first decompose the complex query into several sub-prompts that indicate individual concepts within the video~(\\textit{e.g.}, scene, objects, motions), then we let LLM to invoke pre-trained expert models to obtain corresponding 3D representations of concepts. 2) To compose these representations, we prompt multi-modal LLM to produce coarse guidance on the scales and coordinates of trajectories for the objects. 3) To make the generated frames adhere to natural image distribution, we further leverage 2D diffusion priors and use Score Distillation Sampling to refine the composition. Extensive experiments demonstrate that our method can generate high-fidelity videos from text with diverse motion and flexible control over each concept. Project page:\u00a0<a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/c3v\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/aka.ms\/c3v<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/covomix-advancing-zero-shot-speech-generation-for-human-like-multi-talker-conversations\/\">CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations<br><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/strong><em>Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix first converts dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These token streams are then fed into a flow-matching based acoustic model to generate mixed mel-spectrograms. Finally, the speech waveforms are produced using a HiFi-GAN model. Furthermore, we devise a comprehensive set of metrics for measuring the effectiveness of dialogue modeling and generation. Our experimental results show that CoVoMix can generate dialogues that are not only human-like in their naturalness and coherence but also involve multiple talkers engaging in multiple rounds of conversation. This is exemplified by instances generated in a single channel where one speaker\u2019s utterance is seamlessly mixed with another\u2019s interjections or laughter, indicating the latter\u2019s role as an attentive listener. Audio samples are available at\u00a0<a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/covomix\">https:\/\/aka.ms\/covomix<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/culturellm-incorporating-cultural-differences-into-large-language-models\/\">CultureLLM: Incorporating Cultural Differences into Large Language Models<br><\/a><\/strong><em>Large language models (LLMs) are reported to be partial to certain cultures owing to the training data dominance from the English corpora. Since multilingual cultural data are often expensive to collect, existing efforts handle this by prompt engineering or culture-specific pre-training. However, they might overlook the knowledge deficiency of low-resource culture and require extensive computing resources. In this paper, we propose CultureLLM, a cost-effective solution to incorporate cultural differences into LLMs. CultureLLM adopts World Value Survey (WVS) as seed data and generates semantically equivalent training data via the proposed semantic data augmentation. Using only 50 seed samples from WVS with augmented data, we fine-tune culture-specific LLMs and one unified model (CultureLLM-One) for 9 cultures covering rich and low-resource languages. Extensive experiments on 60 culture-related datasets demonstrate that CultureLLM significantly outperforms various counterparts such as GPT-3.5 (by 8.1%) and Gemini Pro (by 9.5%) with comparable performance to GPT-4 or even better. Our human study shows that the generated samples are semantically equivalent to the original samples, providing an effective solution for LLMs augmentation.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/culturepark-boosting-cross-cultural-understanding-in-large-language-models\/\">CulturePark: Boosting Cross-cultural Understanding in Large Language Models<br><\/a><\/strong><em>Cultural bias is pervasive in many large language models (LLMs), largely due to the deficiency of data representative of different cultures. Typically, cultural datasets and benchmarks are constructed either by extracting subsets of existing datasets or by aggregating from platforms such as Wikipedia and social media. However, these approaches are highly dependent on real-world data and human annotations, making them costly and difficult to scale. Inspired by cognitive theories on social communication, this paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. CulturePark simulates cross-cultural human communication with LLM-based agents playing roles in different cultures. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. Using CulturePark, we generated 41,000 cultural samples to fine-tune eight culture-specific LLMs. We evaluated these models across three downstream tasks: content moderation, cultural alignment, and cultural education. Results show that for content moderation, our GPT-3.5-based models either match or outperform GPT-4 on datasets. Regarding cultural alignment, our models surpass GPT-4 on Hofstede\u2019s VSM 13 framework. Furthermore, for cultural education of human participants, our models demonstrate superior outcomes in both learning efficacy and user experience compared to GPT-4. CulturePark proves an important step in addressing cultural bias and advancing the democratization of AI, highlighting the critical role of culturally inclusive data in model training.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/eeg2video-towards-decoding-dynamic-visual-perception-from-eeg-signals\/\">EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals<br><\/a><\/strong><em>Our visual experience in daily life are dominated by dynamic change. Decoding such dynamic information from brain activity can enhance the understanding of the brain\u2019s visual processing system. However, previous studies predominately focus on reconstructing static visual stimuli. In this paper, we explore to decode dynamic visual perception from electroencephalography (EEG), a neuroimaging technique able to record brain activity with high temporal resolution (1000 Hz) for capturing rapid changes in brains. Our contributions are threefold: Firstly, we develop a large dataset recording signals from 20 subjects while they were watching 1400 dynamic video clips of 40 concepts. This dataset fills the gap in the lack of EEG-video pairs. Secondly, we annotate each video clips to investigate the potential for decoding some specific meta information (e.g., color, dynamic, human or not) from EEG. Thirdly, we propose a novel baseline EEG2Video for video reconstruction from EEG signals that better aligns dynamic movements with high temporal resolution brain signals by Seq2Seq architecture. EEG2Video achieves a 2-way accuracy of 79.8% in semantic classification tasks and 0.256 in structural similarity index (SSIM). Overall, our works takes an important step towards decoding dynamic visual perception from EEG signals. Our dataset and code will be released soon.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/elastst-towards-robust-varied-horizon-forecasting-with-elastic-time-series-transformer\/\">ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer<br><\/a><\/strong><em>Numerous industrial sectors necessitate models capable of providing robust forecasts across various horizons. Despite the recent strides in crafting specific architectures for time-series forecasting and developing pre-trained universal models, a comprehensive examination of their capability in accommodating varied-horizon forecasting during inference is still lacking. This paper bridges this gap through the design and evaluation of the Elastic Time-Series Transformer (ElasTST). The ElasTST model incorporates a non-autoregressive design with placeholders and structured self-attention masks, warranting future outputs that are invariant to adjustments in inference horizons. A tunable version of rotary position embedding is also integrated into ElasTST to capture time-series-specific periods and enhance adaptability to different horizons. Additionally, ElasTST employs a multi-scale patch design, effectively integrating both fine-grained and coarse-grained information. Through comprehensive experiments and comparisons with state-of-the-art time-series architectures and contemporary foundation models, we demonstrate the efficacy of ElasTST\u2019s unique design elements. Our findings position ElasTST as a robust solution for the practical necessity of varied-horizon forecasting.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/gaussiancube-a-structured-and-explicit-radiance-representation-for-3d-generative-modeling\/\">GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling<br><\/a><\/strong><em>We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. Existing radiance representations either require an implicit feature decoder, which significantly degrades the modeling power of the representation, or are spatially unstructured, making them difficult to integrate with mainstream 3D diffusion methods. We derive GaussianCube by first using a novel densification-constrained Gaussian fitting algorithm, which yields high-accuracy fitting using a fixed number of free Gaussians, and then rearranging these Gaussians into a predefined voxel grid via Optimal Transport. Since GaussianCube is a structured grid representation, it allows us to use standard 3D U-Net as our backbone in diffusion modeling without elaborate designs. More importantly, the high-accuracy fitting of the Gaussians allows us to achieve a high-quality representation with orders of magnitude fewer parameters than previous structured representations for comparable quality, ranging from one to two orders of magnitude. The compactness of GaussianCube greatly eases the difficulty of 3D generative modeling. Extensive experiments conducted on unconditional and class-conditioned object generation, digital avatar creation, and text-to-3D synthesis all show that our model achieves state-of-the-art generation results both qualitatively and quantitatively, underscoring the potential of GaussianCube as a highly accurate and versatile radiance representation for 3D generative modeling. Project page: https:\/\/gaussiancube.github.io\/.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/imprecise-label-learning-a-unified-framework-for-learning-with-various-imprecise-label-configurations\/\"><strong>Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations<br><\/strong><\/a><em>Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \\textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label configuration, which is usually unsustainable when multiple configurations of imprecision coexist. In this paper, we introduce imprecise label learning (ILL), a framework for the unification of learning with various imprecise label configurations. ILL leverages expectation-maximization (EM) for modeling the imprecise label information, treating the precise labels as latent variables.Instead of approximating the correct labels for training, it considers the entire distribution of all possible labeling entailed by the imprecise information. We demonstrate that ILL can seamlessly adapt to partial label learning, semi-supervised learning, noisy label learning, and, more importantly, a mixture of these settings. Notably, ILL surpasses the existing specified techniques for handling imprecise labels, marking the first unified framework with robust and effective performance across various challenging settings. We hope our work will inspire further research on this topic, unleashing the full potential of ILL in wider scenarios where precise labels are expensive and complicated to obtain.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/minds-eye-of-llms-visualization-of-thought-elicits-spatial-reasoning-in-large-language-models\/\">Mind\u2019s Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models<br><\/a><\/strong><em>Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as the Mind\u2019s Eye, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (VoT) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guiding subsequent reasoning steps. We employed VoT for multi-hop spatial reasoning tasks, including natural language navigation, visual navigation, and visual tiling in 2D grid worlds. Experimental results demonstrated that VoT significantly enhances the spatial reasoning abilities of LLMs. Notably, VoT outperformed existing multimodal large language models (MLLMs) in these tasks. While VoT works surprisingly well on LLMs, the ability to generate mental images to facilitate spatial reasoning resembles the mind\u2019s eye process, suggesting its potential viability in MLLMs.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/multi-head-mixture-of-experts\/\">Multi-Head Mixture-of-Experts<br><\/a><\/strong><em>Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activation, where only a small subset of experts are activated for optimization. (2) Lacking fine-grained analytical capabilities for multiple semantic concepts within individual tokens. We propose Multi-Head Mixture-of-Experts (MH-MoE), which employs a multi-head mechanism to split each token into multiple sub-tokens. These sub-tokens are then assigned to and processed by a diverse set of experts in parallel, and seamlessly reintegrated into the original token form. The multi-head mechanism enables the model to collectively attend to information from various representation spaces within different experts, while significantly enhances expert activation, thus deepens context understanding and alleviate overfitting. Moreover, our MH-MoE is straightforward to implement and decouples from other SMoE optimization methods, making it easy to integrate with other SMoE models for enhanced performance. Extensive experimental results across three tasks: English-focused language modeling, Multi-lingual language modeling and Masked multi-modality modeling tasks, demonstrate the effectiveness of MH-MoE.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/multimodal-large-language-models-make-text-to-image-generative-models-align-better\/\">Multimodal Large Language Models Make Text-to-Image Generative Models Align Better<br><\/a><\/strong><em>Recent studies have demonstrated the exceptional potentials of leveraging human preference datasets to refine text-to-image generative models, enhancing the alignment between generated images and textual prompts. Despite these advances, current human preference datasets are either prohibitively expensive to construct or suffer from a lack of diversity in preference dimensions, resulting in limited applicability for instruction tuning in open-source text-to-image generative models and hinder further exploration. To address these challenges and promote the alignment of generative models through instruction tuning, we leverage multimodal large language models to create VisionPrefer, a high-quality and fine-grained preference dataset that captures multiple preference aspects. We aggregate feedback from AI annotators across four aspects: prompt-following, aesthetic, fidelity, and harmlessness to construct VisionPrefer. To validate the effectiveness of VisionPrefer, we train a reward model VP-Score over VisionPrefer to guide the training of text-to-image generative models and the preference prediction accuracy of VP-Score is comparable to human annotators. Furthermore, we use two reinforcement learning methods to supervised fine-tune generative models to evaluate the performance of VisionPrefer, and extensive experimental results demonstrate that VisionPrefer significantly improves text-image alignment in compositional image generation across diverse aspects, e.g., aesthetic, and generalizes better than previous human-preference metrics across various image distributions. Moreover, VisionPrefer indicates that the integration of AI-generated synthetic data as a supervisory signal is a promising avenue for achieving improved alignment with human preferences in vision generative models.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/neuro-symbolic-data-generation-for-math-reasoning\/\">Neuro-Symbolic Data Generation for Math Reasoning<br><\/a><\/strong><em>A critical question about Large Language Models (LLMs) is whether their apparent deficiency in mathematical reasoning is inherent, or merely a result of insufficient exposure to high-quality mathematical data. To explore this, we developed an automated method for generating high-quality, supervised mathematical datasets. The method carefully mutates existing math problems, ensuring both diversity and validity of the newly generated problems. This is achieved by a neuro-symbolic data generation framework combining the intuitive informalization strengths of LLMs, and the precise symbolic reasoning of math solvers along with projected Markov chain Monte Carlo sampling in the highly-irregular symbolic space. Empirical experiments demonstrate the high quality of data generated by the proposed method, and that the LLMs, specifically LLaMA-2 and Mistral, when realigned with the generated data, surpass their state-of-the-art counterparts.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/predictor-corrector-enhanced-transformers-with-exponential-moving-average-coefficient-learning\/\">Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning<br><\/a><\/strong><em>Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems. The precision of the solution to ODEs significantly affects parameter optimization, thereby impacting model performance. In this work, we present a series of advanced explorations of Transformer architecture design to minimize the error compared to the true \u201csolution.\u201d First, we introduce a predictor-corrector learning framework to minimize truncation errors, which consist of a high-order predictor and a multistep corrector. Second, we propose an exponential moving average-based coefficient learning method to further strengthen our higher-order predictor. Extensive experiments on large-scale machine translation, abstractive summarization, language modeling, and natural language understanding benchmarks demonstrate the superiority of our approach. On the WMT\u201914 English-German and English-French tasks, our model achieved BLEU scores of 30.95 and 44.27, respectively. Additionally, on the OPUS multilingual machine translation task, our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only one-third of the parameters.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/probts-benchmarking-point-and-distributional-forecasting-across-diverse-prediction-horizons\/\">ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons<br><\/a><\/strong><em>Delivering precise point and distributional forecasts across a spectrum of prediction horizons represents a significant and enduring challenge in the application of time-series forecasting within various industries. Prior research on developing deep learning models for time-series forecasting has often concentrated on isolated aspects, such as long-term point forecasting or short-term probabilistic estimations. This narrow focus may result in skewed methodological choices and hinder the adaptability of these models to uncharted scenarios. While there is a rising trend in developing universal forecasting models, a thorough understanding of their advantages and drawbacks, especially regarding essential forecasting needs like point and distributional forecasts across short and long horizons, is still lacking. In this paper, we present ProbTS, a benchmark tool designed as a unified platform to evaluate these fundamental forecasting needs and to conduct a rigorous comparative analysis of numerous cutting-edge studies from recent years. We dissect the distinctive data characteristics arising from disparate forecasting requirements and elucidate how these characteristics can skew methodological preferences in typical research trajectories, which often fail to fully accommodate essential forecasting needs. Building on this, we examine the latest models for universal time-series forecasting and discover that our analyses of methodological strengths and weaknesses are also applicable to these universal models. Finally, we outline the limitations inherent in current research and underscore several avenues for future exploration.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/promptfix-you-prompt-and-we-fix-the-photo\/\">PromptFix: You Prompt and We Fix the Photo<br><\/a><\/strong><em>Diffusion models equipped with language models demonstrate excellent controllability in image generation tasks, allowing image processing to adhere to human instructions. However, the lack of diverse instruction-following data hampers the development of models that effectively recognize and execute user-customized instructions, particularly in low-level tasks. Moreover, the stochastic nature of the diffusion process leads to deficiencies in image generation or editing tasks that require the detailed preservation of the generated images. To address these limitations, we propose PromptFix, a comprehensive framework that enables diffusion models to follow human instructions to perform a wide variety of image-processing tasks. First, we construct a large-scale instruction-following dataset that covers comprehensive image-processing tasks, including low-level tasks, image editing, and object creation. Next, we propose a high-frequency guidance sampling method to explicitly control the denoising process and preserve high-frequency details in unprocessed areas. Finally, we design an auxiliary prompting adapter, utilizing Vision-Language Models (VLMs) to enhance text prompts and improve the model\u2019s task generalization. Experimental results show that PromptFix outperforms previous methods in various image-processing tasks. Our proposed model also achieves comparable inference efficiency with these baseline models and exhibits superior zero-shot capabilities in blind restoration and combination tasks. The dataset and code are available at https:\/\/www.yongshengyu.com\/PromptFix-Page.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/protecting-your-llms-with-information-bottleneck\/\">Protecting Your LLMs with Information Bottleneck<br><\/a><\/strong><em>The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be circumvented by jailbreaking attacks through optimized or manual adversarial prompts. To address this, we introduce the Information Bottleneck Protector (IBProtector), a defense mechanism grounded in the information bottleneck principle, and we modify the objective to avoid trivial solutions. The IBProtector selectively compresses and perturbs prompts, facilitated by a lightweight and trainable extractor, preserving only essential information for the target LLMs to respond with the expected answer. Moreover, we further consider a situation where the gradient is not visible to be compatible with any LLM. Our empirical evaluations show that IBProtector outperforms current defense methods in mitigating jailbreak attempts, without overly affecting response quality or inference speed. Its effectiveness and adaptability across various attack methods and target LLMs underscore the potential of IBProtector as a novel, transferable defense that bolsters the security of LLMs without requiring modifications to the underlying models.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/scaling-the-codebook-size-of-vq-gan-to-100000-with-a-utilization-rate-of-99\/\">Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%<br><\/a><\/strong><em>In the realm of image quantization exemplified by VQGAN, the process encodes images into discrete tokens drawn from a codebook with a predefined size. Recent advancements, particularly with LLAMA 3, reveal that enlarging the codebook significantly enhances model performance. However, VQGAN and its derivatives, such as VQGAN-FC (Factorized Codes) and VQGAN-EMA, continue to grapple with challenges related to expanding the codebook size and enhancing codebook utilization. For instance, VQGAN-FC is restricted to learning a codebook with a maximum size of 16,384, maintaining a typically low utilization rate of less than 12% on ImageNet. In this work, we propose a novel image quantization model named VQGAN-LC (Large Codebook), which extends the codebook size to 100,000, achieving an utilization rate exceeding 99%. Unlike previous methods that optimize each codebook entry, our approach begins with a codebook initialized with 100,000 features extracted by a pre-trained vision encoder. Optimization then focuses on training a projector that aligns the entire codebook with the feature distributions of the encoder in VQGAN-LC. We demonstrate the superior performance of our model over its counterparts across a variety of tasks, including image reconstruction, image classification, auto-regressive image generation using GPT, and image creation with diffusion- and flow-based generative models.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/slot-vlm-slowfast-slots-for-video-language-modeling\/\">Slot-VLM: SlowFast Slots for Video-Language Modeling<br><\/a><\/strong><em>Video-Language Models (VLMs), powered by the advancements in Large Language Models (LLMs), are charting new frontiers in video understanding. A pivotal challenge is the development of an efficient method to encapsulate video content into a set of representative tokens to align with LLMs. In this work, we introduce Slot-VLM, a novel framework designed to generate semantically decomposed video tokens, in terms of object-wise and event-wise visual representations, to facilitate LLM inference. Particularly, we design a SlowFast Slots module, i.e., SF-Slots, that adaptively aggregates the dense video tokens from the CLIP vision encoder to a set of representative slots. In order to take into account both the spatial object details and the varied temporal dynamics, SF-Slots is built with a dual-branch structure. The Slow-Slots branch focuses on extracting object-centric slots from features at high spatial resolution but low (slow) frame sample rate, emphasizing detailed object information. Conversely, Fast-Slots branch is engineered to learn event-centric slots from high temporal sample rate but low spatial resolution features. These complementary slots are combined to form the vision context, serving as the input to the LLM for efficient question answering. Our experimental results demonstrate the effectiveness of our Slot-VLM, which achieves the state-of-the-art performance on video question-answering.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/taskbench-benchmarking-large-language-models-for-task-automation\/\">TaskBench: Benchmarking Large Language Models for Task Automation<br><\/a><\/strong><em>Recently, the incredible progress of large language models (LLMs) has ignited the spark of task automation, which decomposes the complex tasks described by user instructions into sub-tasks, and invokes external tools to execute them, and plays a central role in autonomous agents. However, there lacks a systematic and standardized benchmark to foster the development of LLMs in task automation. To this end, we introduce TaskBench to evaluate the capability of LLMs in task automation. Specifically, task automation can be formulated into three critical stages: task decomposition, tool invocation, and parameter prediction to fulfill user intent. This complexity makes data collection and evaluation more challenging compared to common NLP tasks. To generate high-quality evaluation datasets, we introduce the concept of Tool Graph to represent the decomposed tasks in user intent, and adopt a back-instruct method to simulate user instruction and annotations. Furthermore, we propose TaskEval to evaluate the capability of LLMs from different aspects, including task decomposition, tool invocation, and parameter prediction. Experimental results demonstrate that TaskBench can effectively reflects the capability of LLMs in task automation. Benefiting from the mixture of automated data construction and human verification, TaskBench achieves a high consistency compared to the human evaluation, which can be utilized as a comprehensive and faithful benchmark for LLM-based autonomous agents.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/towards-editing-time-series\/\">Towards Editing Time Series<br><span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/strong><em>Synthesizing time series data is pivotal in modern society, aiding effective decision making and ensuring privacy preservation in various scenarios. Time series are associated with various attributes, including trends, seasonality, and external information such as location. Recent research has predominantly focused on random unconditional synthesis or conditional synthesis. Nonetheless, these paradigms generate time series from scratch and are incapable of manipulating existing time series samples. This paper introduces a novel task, called Time Series Editing (TSE), to synthesize time series by manipulating existing time series. The objective is to modify the given time series according to the specified attributes while preserving other properties unchanged. This task is not trivial due to the inadequacy of data coverage and the intricate relationships between time series and their attributes. To address these issues, we introduce a novel diffusion model, called TEdit. The proposed TEdit is trained using a novel bootstrap learning algorithm that effectively enhances the coverage of the original data. It is also equipped with an innovative multi-resolution modeling and generation paradigm to capture the complex relationships between time series and their attributes. Experimental results demonstrate the efficacy of TEdit for editing specified attributes upon the existing time series data. The project page is at\u00a0<a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/seqml.github.io\/tse\">https:\/\/seqml.github.io\/tse<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/transvip-speech-to-speech-translation-system-with-voice-and-isochrony-preservation\/\"><strong>TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation<br><\/strong><\/a><em>There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition, machine translation and text-to-speech models. The primary challenges stem from the inherent complexities involved in direct translation tasks and the scarcity of data. In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates end-to-end inference through joint probability. Furthermore, we propose two separated encoders to preserve the speaker\u2019s voice characteristics and isochrony from the source speech during the translation process, making it highly suitable for scenarios such as video dubbing. Our experiments on the French-English language pair demonstrate that our model outperforms the current state-of-the-art speech-to-speech translation model.<\/em><\/li>\n\n\n\n<li><strong><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/understanding-and-improving-training-free-loss-based-diffusion-guidance\/\">Understanding and Improving Training-free Loss-based Diffusion Guidance<br><\/a><\/strong><em>Adding additional control to pretrained diffusion models has become an increasingly popular research area, with extensive applications in computer vision, reinforcement learning, and AI for science. Recently, several studies have proposed training-free loss-based guidance by using off-the-shelf networks pretrained on clean images. This approach enables zero-shot conditional generation for universal control formats, which appears to offer a free lunch in diffusion guidance. In this paper, we aim to develop a deeper understanding of training-free guidance, as well as overcome its limitations. We offer a theoretical analysis that supports training-free guidance from the perspective of optimization, distinguishing it from classifier-based (or classifier-free) guidance. To elucidate their drawbacks, we theoretically demonstrate that training-free guidance is more susceptible to adversarial gradients and exhibits slower convergence rates compared to classifier guidance. We then introduce a collection of techniques designed to overcome the limitations, accompanied by theoretical rationale and empirical evidence. Our experiments in image and motion generation confirm the efficacy of these techniques.<\/em><\/li>\n\n\n\n<li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/xrag-extreme-context-compression-for-retrieval-augmented-generation-with-one-token\/\"><strong>xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token<br><\/strong><\/a><em>This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval\u2013traditionally used solely for retrieval\u2013as features from the retrieval modality. By employing a modality fusion methodology, xRAG seamlessly integrates these embeddings into the language model representation space, effectively eliminating the need for their textual counterparts and achieving an extreme compression rate. In xRAG, the only trainable component is the modality bridge, while both the retriever and the language model remain frozen. This design choice allows for the reuse of offline-constructed document embeddings and preserves the plug-and-play nature of retrieval augmentation. Experimental results demonstrate that xRAG achieves an average improvement of over 10% across six knowledge-intensive tasks, adaptable to various language model backbones, ranging from a dense 7B model to an 8x7B Mixture of Experts configuration. xRAG not only significantly outperforms previous context compression methods but also matches the performance of uncompressed models on several datasets, while reducing overall FLOPs by a factor of 3.53. Our work pioneers new directions in retrieval-augmented generation from the perspective of multimodality fusion, and we hope it lays the foundation for future efficient and scalable retrieval-augmented systems<\/em><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":34512,"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":true,"_classifai_error":"","msr-content-parent":0,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-post-option":[],"class_list":["post-1107987","msr-blog-post","type-msr-blog-post","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_assoc_parent":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post\/1107987","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-blog-post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/users\/34512"}],"version-history":[{"count":8,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post\/1107987\/revisions"}],"predecessor-version":[{"id":1108374,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-blog-post\/1107987\/revisions\/1108374"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1107987"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1107987"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1107987"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1107987"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}