Bingzheng Wei

Bingzheng's activity

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

upvoted a paper about 7 hours ago

daVinci-Env: Open SWE Environment Synthesis at Scale

Paper • 2603.13023 • Published 3 days ago • 19

upvoted a paper about 12 hours ago

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Paper • 2603.12793 • Published 3 days ago • 25

upvoted a paper about 14 hours ago

LMEB: Long-horizon Memory Embedding Benchmark

Paper • 2603.12572 • Published 4 days ago • 49

upvoted 2 papers about 15 hours ago

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Paper • 2603.12648 • Published 4 days ago • 8

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Paper • 2603.12180 • Published 4 days ago • 56

upvoted 2 papers 3 days ago

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

Paper • 2603.12247 • Published 4 days ago • 22

DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning

Paper • 2603.12257 • Published 4 days ago • 27

upvoted 8 papers 4 days ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published 6 days ago • 36

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published 4 days ago • 78

In-Context Reinforcement Learning for Tool Use in Large Language Models

Paper • 2603.08068 • Published 7 days ago • 30

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

Paper • 2603.10160 • Published 6 days ago • 20

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published 6 days ago • 68

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 6 days ago • 105

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Paper • 2603.09906 • Published 6 days ago • 63

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published 13 days ago • 137

upvoted 5 papers 6 days ago

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Paper • 2603.06577 • Published 10 days ago • 43

Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs

Paper • 2603.09095 • Published 7 days ago • 26

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 7 days ago • 46

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 11 days ago • 83

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Paper • 2603.06713 • Published 11 days ago • 15