A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every time the prompt is sent. We test a memory layer, ...

Collection of our second set of text embedding models ...

Join the discussion on this paper page OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video ...

Join the discussion on this paper page SuperNav: An Agentic Navigation System for Any Task in Any Scene ...

Join the discussion on this paper page OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs ...

Join the discussion on this paper page Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict ...

Join the discussion on this paper page TestPrism: Rethinking Test Evaluation Beyond a Single Reference ...

Join the discussion on this paper page SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference ...

Join the discussion on this paper page TokenRouter: Efficient Serving System for Token-Level LLM Routing ...

Join the discussion on this paper page Simulated users offer a scalable alternative to costly human feedback, but they must both resemble real user behavior and provide useful learning experiences for ...

Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score ...

Join the discussion on this paper page Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching ...