UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
Paper • 2604.19734 • Published • 20
Bingzheng Wei
Bingzheng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 hour ago
UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling upvoted a paper about 23 hours ago
Near-Future Policy Optimization upvoted a paper about 23 hours ago
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language ModelOrganizations
None yet
upvoted a paper about 1 hour ago
upvoted 2
papers about 23 hours ago
upvoted a paper 1 day ago
upvoted 8
papers 3 days ago
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
Paper • 2604.18168 • Published • 94
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Paper • 2604.18292 • Published • 77
OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Paper • 2604.18486 • Published • 83
PersonaVLM: Long-Term Personalized Multimodal LLMs
Paper • 2604.13074 • Published • 45
Qwen3.5-Omni Technical Report
Paper • 2604.15804 • Published • 52
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
Paper • 2502.07408 • Published • 53
Elucidating the SNR-t Bias of Diffusion Probabilistic Models
Paper • 2604.16044 • Published • 72
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
Paper • 2604.14164 • Published • 34
upvoted 5
papers 7 days ago
DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation
Paper • 2604.14683 • Published • 35
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Paper • 2604.14125 • Published • 20
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
Paper • 2604.15308 • Published • 28
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Paper • 2604.14268 • Published • 110
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Paper • 2604.11626 • Published • 100
upvoted 3
papers 8 days ago
TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 13
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Paper • 2604.14144 • Published • 62
Seedance 2.0: Advancing Video Generation for World Complexity
Paper • 2604.14148 • Published • 151