Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics Paper • 2609.38847 • Published 18 days ago • 69
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations Paper • 2609.32522 • Published 22 days ago • 71
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality Paper • 2609.33757 • Published 21 days ago • 239
Transferring the Intelligence of VLMs to Robotic Control Paper • 2609.22966 • Published 29 days ago • 94