-
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Paper • 2605.31604 • Published • 51 -
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Paper • 2605.31584 • Published • 38 -
Task-Focused Memorization for Multimodal Agents
Paper • 2605.31075 • Published • 29 -
Exploring Autonomous Agentic Data Engineering for Model Specialization
Paper • 2605.30407 • Published • 19
yinfeng wang
wyf666
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
SkillOpt: Executive Strategy for Self-Evolving Agent Skills updated a collection 2 days ago
weekly unseen papers updated a collection 2 days ago
weekly unseen papersOrganizations
None yet