Bozhou Li

zooblastlbz's activity

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

upvoted a paper 18 days ago

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published 22 days ago • 75

upvoted 6 papers about 1 month ago

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

Paper • 2605.26244 • Published May 25 • 38

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 • 121

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

upvoted 2 papers about 2 months ago

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 • 28

upvoted a paper 2 months ago

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

Paper • 2604.11547 • Published Apr 13 • 5

authored 9 papers 3 months ago

Are Bigger Encoders Always Better in Vision Large Models?

Paper • 2408.00620 • Published Aug 1, 2024

The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-based Code Generation

Paper • 2411.06774 • Published Nov 11, 2024

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

Paper • 2512.15560 • Published Dec 17, 2025 • 25

The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss

Paper • 2512.08374 • Published Dec 9, 2025

DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models

Paper • 2601.19267 • Published Jan 27

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

Paper • 2602.01630 • Published Feb 2 • 50

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

Paper • 2602.04804 • Published Feb 4 • 50

Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

Paper • 2602.03510 • Published Feb 3 • 27

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published Apr 6 • 204

upvoted a paper 3 months ago

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

Paper • 2604.04771 • Published Apr 6 • 124