Microsoft at NeurIPS 2024

Microsoft is a proud sponsor of the 38th Conference on Neural Information Processing Systems (opens in new tab) (NeurIPS). This interdisciplinary conference brings together researchers in machine learning, neuroscience, statistics, optimization, computer vision, natural language processing, life sciences, natural sciences, social sciences, and other adjacent fields.

We are pleased to share Microsoft has over 100 accepted papers at this year’s conference. Stop by our booth (#445) toward the back of hall A to talk to our team, learn more about research at Microsoft, and explore our open career positions.

Invited Keynote

Congratulations to Lidong Zhou, who has been selected as a keynote speaker. Lidong will speak on co-innovation of AI and Systems.

Orals

• CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark: Pranjal Chitale
• Not All Tokens Are What You Need for Pretraining: Yeyun Gong, Xiao Liu, Yelong Shen, Ruochen Xu, Jian Jiao, Nan Duan, Weizhu Chen
• Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity: Dylan J Foster, Akshay Krishnamurthy
• VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time: Sicheng Xu, Guojun Chen, Yu-Xiao Guo, Jiaolong Yang, Chong Li, Zhenyu Zang, Yizhong Zhang, Xin Tong, Baining Gu
• You Only Cache Once: Decoder-Decoder Architectures for Language Models: Li Dong, Yi Zhu, Shaohan Huang, Wenhui Wang, Quanlu Zhang, Furu Wei

Spotlight Sessions

• A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning: Jordan Ash
• Advancing Spiking Neural Networks for Sequential Modeling through Central Pattern Generators: Dongqi Han, Yansen Wang
• Beyond Assouad, Fano, and Le Cam: Toward Unified Lower Bounds for Statistical Estimation and Interactive Decision Making: Dylan J Foster
• BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning: Xiao Yang, Xu Yang, Weiqing Liu, Lewen Wang, Jiang Bian
• Compositional Generalization Across Distributional Shifts with Sparse Tree Operations: Paul Smolensky, Jianfeng Gao, Roland Fernandez
• Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition: Reshmi Ghosh, Ahmed Salem, Giovanni Cherubin, Santiago Zanella-Beguelin, Sahar Abdelnabi
• Diffusion for World Modeling: Visual Details Matter in Atari: Anssi Kanervisto, Tim Pearce, Cuiling Lan, Yan Lu
• DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents: Marc-Alexandre Côté
• Efficient Adversarial Training in LLMs with Continuous Attacks: Alessandro Sordoni
• ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models: Ruochen Xu, Xing Xie
• Generalized Linear Bandits with Limited Adaptivity: Nirjhar Das, Gaurav Sinha
• Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions: Qi Dai
• Identifying Equivalent Training Dynamics: Juan Bello-Rivas
• Implicit Curriculum in Procgen Made Explicit: Kaixin Wang
• Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning: Dylan J Foster, Adam Block
• MInference: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention: Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir Abdi, Chin-Yew Lin, Yuqing Yang, Lili Qiu
• The Power of Resets in Online Reinforcement Learning: Dylan J Foster
• VideoGUI: A Benchmark for GUI Automation from Instructional Videos: Linjie Li, Lijuan Wang
• Voila-A: Aligning Vision-Language Models with User’s Gaze Attention: Lei Ji, Nan Duan

General Chair: Lester Mackey

Program Chair Assistant: Babak Rahmani

Competition Chair: Tao Qin

Workshop Chair: Adil Salim

Communication Chair: Alex X Lu