RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM Paper • 2607.11683 • Published 12 days ago • 143
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors Paper • 2606.32029 • Published 25 days ago • 14
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published Jun 11 • 113
AdaState: Self-Evolving Anchors for Streaming Video Generation Paper • 2605.30349 • Published May 28 • 12
LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know? Paper • 2605.28721 • Published May 27 • 18
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows Paper • 2605.14678 • Published May 19 • 108