Representation Forcing for Bottleneck-Free Unified Multimodal Models
Paper • 2605.31604 • Published • 58
weekly unseen papers
-
-
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Paper • 2605.31584 • Published • 41 -
Task-Focused Memorization for Multimodal Agents
Paper • 2605.31075 • Published • 34 -
Exploring Autonomous Agentic Data Engineering for Model Specialization
Paper • 2605.30407 • Published • 23 -
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
Paper • 2605.29447 • Published • 20 -
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
Paper • 2605.31042 • Published • 18