Fangyun Wei

Senior Research SDE

Publications

View by:

- Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
  
  Dong Chen, Fangyun Wei, Ziyu Wan, Dongdong Chen, Jiawei Zhang, Jinjing Zhao, Sirui Zhang, Yang Yue, Zhiyang Liang, Baining Guo, Chong Luo, Jianmin Bao, Ji Li, Lei Shi, Qinhong Yang, Xiuyu Wu, Xuelu Feng, Yan Lu, Yanchen Dong, Yitong Wang, Yun Chen
  
  May 2026
  
  Publication
- InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
  
  Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Junliang Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen
  
  May 2026
  
  Publication
- Animate Any Character in Any World
  
  Yitong Wang, Fangyun Wei, Hongyang Zhang, Bo Dai, Yan Lu
  
  December 2025
  
  Publication
- Spatia: Video Generation with Updatable Spatial Memory
  
  Jinjing Zhao, Fangyun Wei, Zhening Liu, Hongyang Zhang, Chang Xu, Yan Lu
  
  December 2025
  
  Publication
- RoboSeer: Video Generators Can Be Generalizable Robot Manipulators
  
  Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo
  
  NeurIPS 2025 | October 2025
  
  Publication
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
  
  Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
  
  NeurIPS 2025 | March 2025
  
  DOI
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
  
  Wenbo Wang, Fangyun Wei, Lei Zhou, Xi Chen, Lin Luo, Xiaohan Yi, Yizhong Zhang, Yaobo Liang, Chang Xu, Yan Lu, Jiaolong Yang, Baining Guo
  
  CVPR 2025 | December 2024
  
  DOI Publication Publication
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  
  Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo, Xi Chen, Mozheng Liao, Fangyun Wei, Yu Deng, Sicheng Xu, Yizhong Zhang, Xiaofan Wang, Bei Liu, Jianlong Fu, Jianmin Bao, Dong Chen, Yuanchun Shi, Jiaolong Yang, Baining Guo
  
  November 2024
  
  DOI Publication Publication
- LORASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning
  
  Yifan Yang, Yifei Shen, Yuqing Yang, Lili Qiu, Fangyun Wei
  
  2024 Empirical Methods in Natural Language Processing | November 2024
  
  Publication
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
  
  Fangyun Wei
  
  October 2024
- Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
  
  Fangyun Wei, Dong Chen
  
  October 2024
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
  
  Fangyun Wei, Xi Chen, Linzi Luo
  
  ICML 2024 | March 2024
  
  DOI Publication Publication
- AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  
  Yu Du, Fangyun Wei, Hongyang Zhang
  
  ICML 2024 | February 2024
  
  DOI Publication Publication
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
  
  Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang, Fangyun Wei
  
  ICML 2024 | January 2024
  
  DOI Publication Publication
- RAIN: Your Language Models Can Align Themselves without Finetuning
  
  Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang
  
  ICLR 2024 | September 2023
  
  DOI PDF
- CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
  
  Yiting Cheng, Fangyun Wei, Jianmin Bao, Dong Chen, Wenqiang Zhang
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Iterative Proposal Refinement for Weakly-Supervised Video Grounding
  
  Meng Cao, Fangyun Wei, Can Xu, Xiubo Geng, Long Cheng, Can Zhang, Yuexian Zou, Tao Shen, Daxin Jiang (姜大昕)
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Natural Language-Assisted Sign Language Recognition
  
  Ronglai Zuo, Fangyun Wei, Brian Mak
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition
  
  Yinghao Xu, Fangyun Wei, Xiao Sun, Ceyuan Yang, Yujun Shen, Bo Dai, Bolei Zhou, Stephen Lin
  
  2022 Computer Vision and Pattern Recognition | April 2022
  
  Publication Publication
- Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
  
  Minghao Chen, Fangyun Wei, Chong Li, Deng Cai
  
  2022 Computer Vision and Pattern Recognition | March 2022
  
  Publication Publication
- A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
  
  Yutong Chen, Fangyun Wei, Xiao Sun, Zhirong Wu, Stephen Lin
  
  2022 Computer Vision and Pattern Recognition | March 2022
  
  Publication Publication

- Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
  
  Dong Chen, Fangyun Wei, Ziyu Wan, Dongdong Chen, Jiawei Zhang, Jinjing Zhao, Sirui Zhang, Yang Yue, Zhiyang Liang, Baining Guo, Chong Luo, Jianmin Bao, Ji Li, Lei Shi, Qinhong Yang, Xiuyu Wu, Xuelu Feng, Yan Lu, Yanchen Dong, Yitong Wang, Yun Chen
  
  May 2026
  
  Publication
- InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
  
  Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Junliang Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen
  
  May 2026
  
  Publication
- Animate Any Character in Any World
  
  Yitong Wang, Fangyun Wei, Hongyang Zhang, Bo Dai, Yan Lu
  
  December 2025
  
  Publication
- Spatia: Video Generation with Updatable Spatial Memory
  
  Jinjing Zhao, Fangyun Wei, Zhening Liu, Hongyang Zhang, Chang Xu, Yan Lu
  
  December 2025
  
  Publication
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
  
  Wenbo Wang, Fangyun Wei, Lei Zhou, Xi Chen, Lin Luo, Xiaohan Yi, Yizhong Zhang, Yaobo Liang, Chang Xu, Yan Lu, Jiaolong Yang, Baining Guo
  
  CVPR 2025 | December 2024
  
  DOI Publication Publication
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  
  Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo, Xi Chen, Mozheng Liao, Fangyun Wei, Yu Deng, Sicheng Xu, Yizhong Zhang, Xiaofan Wang, Bei Liu, Jianlong Fu, Jianmin Bao, Dong Chen, Yuanchun Shi, Jiaolong Yang, Baining Guo
  
  November 2024
  
  DOI Publication Publication
- CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
  
  Yiting Cheng, Fangyun Wei, Jianmin Bao, Dong Chen, Wenqiang Zhang
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Natural Language-Assisted Sign Language Recognition
  
  Ronglai Zuo, Fangyun Wei, Brian Mak
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Iterative Proposal Refinement for Weakly-Supervised Video Grounding
  
  Meng Cao, Fangyun Wei, Can Xu, Xiubo Geng, Long Cheng, Can Zhang, Yuexian Zou, Tao Shen, Daxin Jiang (姜大昕)
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition
  
  Yinghao Xu, Fangyun Wei, Xiao Sun, Ceyuan Yang, Yujun Shen, Bo Dai, Bolei Zhou, Stephen Lin
  
  2022 Computer Vision and Pattern Recognition | April 2022
  
  Publication Publication
- Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
  
  Minghao Chen, Fangyun Wei, Chong Li, Deng Cai
  
  2022 Computer Vision and Pattern Recognition | March 2022
  
  Publication Publication
- A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
  
  Yutong Chen, Fangyun Wei, Xiao Sun, Zhirong Wu, Stephen Lin
  
  2022 Computer Vision and Pattern Recognition | March 2022
  
  Publication Publication
- InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
  
  Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Junliang Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen
  
  May 2026
  
  Publication
- RoboSeer: Video Generators Can Be Generalizable Robot Manipulators
  
  Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo
  
  NeurIPS 2025 | October 2025
  
  Publication
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
  
  Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
  
  NeurIPS 2025 | March 2025
  
  DOI
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
  
  Wenbo Wang, Fangyun Wei, Lei Zhou, Xi Chen, Lin Luo, Xiaohan Yi, Yizhong Zhang, Yaobo Liang, Chang Xu, Yan Lu, Jiaolong Yang, Baining Guo
  
  CVPR 2025 | December 2024
  
  DOI Publication Publication
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  
  Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo, Xi Chen, Mozheng Liao, Fangyun Wei, Yu Deng, Sicheng Xu, Yizhong Zhang, Xiaofan Wang, Bei Liu, Jianlong Fu, Jianmin Bao, Dong Chen, Yuanchun Shi, Jiaolong Yang, Baining Guo
  
  November 2024
  
  DOI Publication Publication
- LORASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning
  
  Yifan Yang, Yifei Shen, Yuqing Yang, Lili Qiu, Fangyun Wei
  
  2024 Empirical Methods in Natural Language Processing | November 2024
  
  Publication
- Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
  
  Fangyun Wei, Dong Chen
  
  October 2024
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
  
  Fangyun Wei
  
  October 2024
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
  
  Fangyun Wei, Xi Chen, Linzi Luo
  
  ICML 2024 | March 2024
  
  DOI Publication Publication
- AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  
  Yu Du, Fangyun Wei, Hongyang Zhang
  
  ICML 2024 | February 2024
  
  DOI Publication Publication
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
  
  Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang, Fangyun Wei
  
  ICML 2024 | January 2024
  
  DOI Publication Publication
- RAIN: Your Language Models Can Align Themselves without Finetuning
  
  Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang
  
  ICLR 2024 | September 2023
  
  DOI PDF
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
  
  Wenbo Wang, Fangyun Wei, Lei Zhou, Xi Chen, Lin Luo, Xiaohan Yi, Yizhong Zhang, Yaobo Liang, Chang Xu, Yan Lu, Jiaolong Yang, Baining Guo
  
  CVPR 2025 | December 2024
  
  DOI Publication Publication
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  
  Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo, Xi Chen, Mozheng Liao, Fangyun Wei, Yu Deng, Sicheng Xu, Yizhong Zhang, Xiaofan Wang, Bei Liu, Jianlong Fu, Jianmin Bao, Dong Chen, Yuanchun Shi, Jiaolong Yang, Baining Guo
  
  November 2024
  
  DOI Publication Publication

- Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
  
  Dong Chen, Fangyun Wei, Ziyu Wan, Dongdong Chen, Jiawei Zhang, Jinjing Zhao, Sirui Zhang, Yang Yue, Zhiyang Liang, Baining Guo, Chong Luo, Jianmin Bao, Ji Li, Lei Shi, Qinhong Yang, Xiuyu Wu, Xuelu Feng, Yan Lu, Yanchen Dong, Yitong Wang, Yun Chen
  
  May 2026
  
  Publication
- InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
  
  Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Junliang Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen
  
  May 2026
  
  Publication
- Animate Any Character in Any World
  
  Yitong Wang, Fangyun Wei, Hongyang Zhang, Bo Dai, Yan Lu
  
  December 2025
  
  Publication
- Spatia: Video Generation with Updatable Spatial Memory
  
  Jinjing Zhao, Fangyun Wei, Zhening Liu, Hongyang Zhang, Chang Xu, Yan Lu
  
  December 2025
  
  Publication
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  
  Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo, Xi Chen, Mozheng Liao, Fangyun Wei, Yu Deng, Sicheng Xu, Yizhong Zhang, Xiaofan Wang, Bei Liu, Jianlong Fu, Jianmin Bao, Dong Chen, Yuanchun Shi, Jiaolong Yang, Baining Guo
  
  November 2024
  
  DOI Publication Publication
- RoboSeer: Video Generators Can Be Generalizable Robot Manipulators
  
  Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo
  
  NeurIPS 2025 | October 2025
  
  Publication
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
  
  Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
  
  NeurIPS 2025 | March 2025
  
  DOI
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
  
  Wenbo Wang, Fangyun Wei, Lei Zhou, Xi Chen, Lin Luo, Xiaohan Yi, Yizhong Zhang, Yaobo Liang, Chang Xu, Yan Lu, Jiaolong Yang, Baining Guo
  
  CVPR 2025 | December 2024
  
  DOI Publication Publication
- LORASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning
  
  Yifan Yang, Yifei Shen, Yuqing Yang, Lili Qiu, Fangyun Wei
  
  2024 Empirical Methods in Natural Language Processing | November 2024
  
  Publication
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
  
  Fangyun Wei, Xi Chen, Linzi Luo
  
  ICML 2024 | March 2024
  
  DOI Publication Publication
- AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  
  Yu Du, Fangyun Wei, Hongyang Zhang
  
  ICML 2024 | February 2024
  
  DOI Publication Publication
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
  
  Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang, Fangyun Wei
  
  ICML 2024 | January 2024
  
  DOI Publication Publication
- RAIN: Your Language Models Can Align Themselves without Finetuning
  
  Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang
  
  ICLR 2024 | September 2023
  
  DOI PDF
- CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
  
  Yiting Cheng, Fangyun Wei, Jianmin Bao, Dong Chen, Wenqiang Zhang
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Natural Language-Assisted Sign Language Recognition
  
  Ronglai Zuo, Fangyun Wei, Brian Mak
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Iterative Proposal Refinement for Weakly-Supervised Video Grounding
  
  Meng Cao, Fangyun Wei, Can Xu, Xiubo Geng, Long Cheng, Can Zhang, Yuexian Zou, Tao Shen, Daxin Jiang (姜大昕)
  
  CVPR 2023 | June 2023
  
  PDF Publication
- Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition
  
  Yinghao Xu, Fangyun Wei, Xiao Sun, Ceyuan Yang, Yujun Shen, Bo Dai, Bolei Zhou, Stephen Lin
  
  2022 Computer Vision and Pattern Recognition | April 2022
  
  Publication Publication
- Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
  
  Minghao Chen, Fangyun Wei, Chong Li, Deng Cai
  
  2022 Computer Vision and Pattern Recognition | March 2022
  
  Publication Publication
- A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
  
  Yutong Chen, Fangyun Wei, Xiao Sun, Zhirong Wu, Stephen Lin
  
  2022 Computer Vision and Pattern Recognition | March 2022
  
  Publication Publication
- Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
  
  Fangyun Wei, Dong Chen
  
  October 2024
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
  
  Fangyun Wei
  
  October 2024

Fangyun Wei

Publications

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Animate Any Character in Any World

Spatia: Video Generation with Updatable Spatial Memory

RoboSeer: Video Generators Can Be Generalizable Robot Manipulators

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

LORASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning

A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era

Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%

Rethinking Generative Large Language Model Evaluation for Semantic Comprehension

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

RAIN: Your Language Models Can Align Themselves without Finetuning

CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning

Iterative Proposal Refinement for Weakly-Supervised Video Grounding

Natural Language-Assisted Sign Language Recognition

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Animate Any Character in Any World

Spatia: Video Generation with Updatable Spatial Memory

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning

Natural Language-Assisted Sign Language Recognition

Iterative Proposal Refinement for Weakly-Supervised Video Grounding

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

RoboSeer: Video Generators Can Be Generalizable Robot Manipulators

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

LORASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning

Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%

A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era

Rethinking Generative Large Language Model Evaluation for Semantic Comprehension

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

RAIN: Your Language Models Can Align Themselves without Finetuning

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Animate Any Character in Any World

Spatia: Video Generation with Updatable Spatial Memory

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

RoboSeer: Video Generators Can Be Generalizable Robot Manipulators

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

LORASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning

Rethinking Generative Large Language Model Evaluation for Semantic Comprehension

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

RAIN: Your Language Models Can Align Themselves without Finetuning

CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning

Natural Language-Assisted Sign Language Recognition

Iterative Proposal Refinement for Weakly-Supervised Video Grounding

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%

A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era