OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models Paper • 2608.03812 • Published 5 days ago • 26
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published 14 days ago • 102