Bingzheng Wei

Bingzheng's activity

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

upvoted 2 papers about 11 hours ago

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

Paper • 2605.18018 • Published 8 days ago • 28

Rethinking Cross-Layer Information Routing in Diffusion Transformers

Paper • 2605.20708 • Published 6 days ago • 81

upvoted 3 papers about 12 hours ago

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

Paper • 2605.21573 • Published 6 days ago • 87

StepAudio 2.5 Technical Report

Paper • 2605.23463 • Published 4 days ago • 35

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published 6 days ago • 198

upvoted 6 papers 3 days ago

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Paper • 2605.18233 • Published 8 days ago • 89

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning

Paper • 2605.22012 • Published 5 days ago • 43

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Paper • 2605.14678 • Published 7 days ago • 94

FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

Paper • 2605.20910 • Published 6 days ago • 24

Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning

Paper • 2605.22642 • Published 5 days ago • 33

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

Paper • 2605.14747 • Published 12 days ago • 143

upvoted 2 papers 4 days ago

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond

Paper • 2605.19660 • Published 7 days ago • 39

Generative Recursive Reasoning

Paper • 2605.19376 • Published 6 days ago • 27

upvoted 6 papers 5 days ago

When Vision Speaks for Sound

Paper • 2605.16403 • Published 13 days ago • 147

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published 14 days ago • 190

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Paper • 2605.19577 • Published 7 days ago • 57

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

Paper • 2605.19769 • Published 7 days ago • 57

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published 11 days ago • 52

Code as Agent Harness

Paper • 2605.18747 • Published 8 days ago • 200

upvoted a paper 6 days ago

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published 8 days ago • 109