Bozhou Li

zooblastlbz's activity

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

upvoted a paper 5 days ago

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Paper • 2607.28590 • Published 10 days ago • 45

upvoted a paper 9 days ago

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published 10 days ago • 44

upvoted 2 papers 23 days ago

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Paper • 2607.14202 • Published 25 days ago • 42

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Paper • 2607.14189 • Published 25 days ago • 34

upvoted 2 papers 2 months ago

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published Jun 5 • 75

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Paper • 2605.26244 • Published May 25 • 38

upvoted 7 papers 3 months ago

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

Paper • 2605.22012 • Published May 21 • 46

Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

Paper • 2605.18984 • Published May 18 • 22

MMSkills: Towards Multimodal Skills for General Visual Agents

Paper • 2605.13527 • Published May 14 • 123

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

Paper • 2605.12882 • Published May 13 • 274

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling

Paper • 2605.13062 • Published May 13 • 33

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization

Paper • 2605.10780 • Published May 12 • 33

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Paper • 2605.05204 • Published May 6 • 29

upvoted 4 papers 4 months ago

Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach

Paper • 2604.11547 • Published Apr 13 • 5

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

Paper • 2604.04771 • Published Apr 6 • 125

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published Apr 6 • 203

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published Mar 27 • 366

upvoted a paper 5 months ago

Kling-MotionControl Technical Report

Paper • 2603.03160 • Published Mar 3 • 27

upvoted 2 papers 6 months ago

GENIUS: Generative Fluid Intelligence Evaluation Suite

Paper • 2602.11144 • Published Feb 11 • 55

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Paper • 2602.04804 • Published Feb 4 • 50