Tag
DeAR is a decentralized agentic reasoning framework that enhances accuracy in knowledge-intensive reasoning tasks through capability grounding and collaborative thought navigation, outperforming centralized methods on multimodal benchmarks.
The paper proposes Trident, a method that enhances long-document visual question answering through structured multi-aspect page annotation for reranking and synthesis, improving evidence selection and answer generation accuracy.
CLIR-Bench is a benchmark for multimodal question answering over irregularly sampled clinical time series, constructed from ICU records with 6,600 QA instances across 11 clinical variables. It reveals that existing generalist models struggle with sparse temporal evidence, highlighting the need for stronger irregular time-series reasoning methods.
PhysBrain 1.0 is a technical report presenting a method that uses human egocentric video to generate physical commonsense supervision for vision-language-action models, achieving state-of-the-art results on embodied control benchmarks including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa.