KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding Paper • 2609.32182 • Published Sep 26 • 8
Can Computation from Earlier Problems Help LLMs Solve New Ones? Paper • 2609.39394 • Published Sep 30 • 6
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 40
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Paper • 2609.32259 • Published Sep 29 • 27
Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows Paper • 2610.02122 • Published Oct 1 • 22
Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts Paper • 2610.00314 • Published Sep 29 • 12