Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models
Paper • 2610.22217 • Published • 12
Pengcheng Huang
chengpingan
·
AI & ML interests
AI & Agent
Recent Activity
upvoted a paper about 7 hours ago
Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models upvoted a paper about 7 hours ago
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers submitted a paper 3 days ago
Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent ExecutionOrganizations
None yet
upvoted 2
papers about 7 hours ago
submitted a
paper to Daily Papers 3 days ago
authored 8
papers 4 days ago
Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
Paper • 2610.17816 • Published • 13
SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation
Paper • 2606.27786 • Published
MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration
Paper • 2604.14889 • Published
Causal Autoregressive Diffusion Language Model
Paper • 2601.22031 • Published • 1
Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
Paper • 2601.12762 • Published
Revealing the Attention Floating Mechanism in Masked Diffusion Models
Paper • 2601.07894 • Published • 1
PC-Sampler: Position-Aware Calibration of Decoding Bias in Masked Diffusion Models
Paper • 2508.13021 • Published
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
Paper • 2505.24388 • Published • 1
updated a
dataset 4 days ago
upvoted a paper 4 days ago
updated a
collection 4 days ago
updated a
dataset 4 days ago
liked a
model about 2 months ago
updated a
dataset 5 months ago
published 2
datasets 5 months ago