Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a three-stage framework comprising condition feature extraction (Perception), discrete token generation (Planning), and diffusion-based motion synthesis (Control). Central to this framework is MoTok, a diffusion-based discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction by delegating motion recovery to a diffusion decoder, enabling compact single-layer tokens while preserving motion fidelity. For kinematic conditions, coarse constraints guide token generation during planning, while fine-grained constraints are enforced during control through diffusion-based optimization. This design prevents kinematic details from disrupting semantic token planning. On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens, reducing trajectory error from 0.72 cm to 0.08 cm and FID from 0.083 to 0.029. Unlike prior methods that degrade under stronger kinematic constraints, ours improves fidelity, reducing FID from 0.033 to 0.014.
WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);WeChat Vision, Tencent Inc.(腾讯微信视觉部);Shanghai Jiao Tong University(上海交通大学)
FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所基础模型研究中心);School of Artificial Intelligence, University of Chinese Academy of Science(中国科学院大学人工智能学院);Peng Cheng Laboratory, Shenzhen, China(鹏城实验室);Wuhan AI Research, Wuhan, China(武汉人工智能研究所)
Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation
Zhejiang University(浙江大学);Hong Kong Polytechnic University(香港理工大学);IROOTECH TECHNOLOGY(IROOTECH技术);Wolf 1069 b Lab, Sany Group(Wolf 1069 b实验室,三一集团);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation
Chinese Academy of Sciences(中国科学院);Microsoft Research(微软研究院);Sun Yat-sen University(中山大学);Zhejiang University(浙江大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Xi’an Jiaotong University(西安交通大学)
EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)(智能信息处理重点实验室,计算技术研究所(ICT),中国科学院(CAS));Jilin University (JLU)(吉林大学(JLU));Beijing University of Posts and Telecommunications (BUPT)(北京邮电大学(BUPT));University of the Chinese Academy of Sciences(中国科学院大学)
LAD-Drive: Bridging Language and Trajectory with Action-Aware Diffusion Transformers
Institute for Intelligent Systems, Esslingen University of Applied Sciences(智能系统研究所,埃斯林根应用科学大学);Department of Computer Science, University of Freiburg(计算机科学系,弗赖堡大学)
Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
The University of Hong Kong(香港大学);ARC Lab, Tencent PCG(腾讯PCG实验室);The Chinese University of Hong Kong(香港中文大学);University of California, Berkeley(加州大学伯克利分校)
PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation
School of Electronic Science and Engineering, Nanjing University(南京大学电子科学与工程学院);Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE, Nanjing University(南京大学极端性能光电技术与系统教育部重点实验室);BNRist, Tsinghua University(清华大学北京信息科学与技术国家研究中心)