Bingzheng Wei

Bingzheng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 6 hours ago

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published 8 days ago • 171

AgentGarten: Code Worlds for Evolving Agents

Paper • 2610.12374 • Published 4 days ago • 258

upvoted a paper 2 days ago

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper • 2610.12242 • Published 4 days ago • 130

upvoted 16 papers 4 days ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published 6 days ago • 211

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published 6 days ago • 93

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

Paper • 2610.03543 • Published 10 days ago • 101

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Paper • 2610.06647 • Published 7 days ago • 150

Does Learning Protein Folding Generalize to Broader Reasoning?

Paper • 2609.38879 • Published 12 days ago • 63

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 14 days ago • 202

LoopVL: Recurrent Visual Intelligence

Paper • 2609.38426 • Published 13 days ago • 476

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 13 days ago • 556

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 12 days ago • 653

Scaling Properties of Same-Family On-Policy Distillation

Paper • 2609.32722 • Published 16 days ago • 326

In-Context Learning for Robots: Methods and Applications

Paper • 2609.36012 • Published 14 days ago • 403

Omni-IO Skills: Harnessing Your Agent Omni-Native

Paper • 2609.31847 • Published 17 days ago • 451

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published 15 days ago • 675

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published 15 days ago • 342

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

Paper • 2609.33757 • Published 15 days ago • 234

Post-Training Leaves Behavioral Shadows on Unrelated Decisions

Paper • 2609.29233 • Published 18 days ago • 275

upvoted a paper 13 days ago

Diffusion Reward Models

Paper • 2609.33803 • Published 15 days ago • 35