Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Paper ā¢ 2606.02684 ā¢ Published ā¢ 16
Zhu
zzzhu
AI & ML interests
None yet
Recent Activity
upvoted a paper 15 days ago
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation liked a dataset 23 days ago
TengfeiLiuCoder/LongAV-Compass liked a model 23 days ago
meituan-longcat/LongCat-Video-Avatar-1.5Organizations
upvoted a paper 15 days ago
upvoted 2
papers 23 days ago
Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks
Paper ā¢ 2604.19697 ā¢ Published ā¢ 1
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
Paper ā¢ 2605.26244 ā¢ Published ā¢ 38
upvoted 5
papers about 1 month ago
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
Paper ā¢ 2605.18984 ā¢ Published ā¢ 22
MMSkills: Towards Multimodal Skills for General Visual Agents
Paper ā¢ 2605.13527 ā¢ Published ā¢ 120
Qwen-Image-VAE-2.0 Technical Report
Paper ā¢ 2605.13565 ā¢ Published ā¢ 61
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
Paper ā¢ 2605.13062 ā¢ Published ā¢ 33
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
Paper ā¢ 2605.10780 ā¢ Published ā¢ 33
upvoted a paper about 2 months ago
upvoted 3
papers 3 months ago
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper ā¢ 2603.27538 ā¢ Published ā¢ 147
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
Paper ā¢ 2603.25804 ā¢ Published ā¢ 30
VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining
Paper ā¢ 2603.15030 ā¢ Published ā¢ 21
upvoted a paper 5 months ago
upvoted 2
papers 9 months ago