…Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model (2026) MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents (2026) TTF: Temporal Token Fusion for Efficient Video-Language…
…AI-generated summary While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, with unified omnimodal benchmarking that jointly covers text, image, and…
…AI-generated summary Long-term memory is crucial for agents in specialized web environments , where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmark…
…Our findings further offer architectural insights for integrating 2D foundation models with 3D tasks, informing the design of 3D-native multimodal systems. Project Page: https://www.seeles.ai/research/pages/EVA01 View…
…There is no good reason for restricting learning to being in-context or in-weights. Moreover, humans also likely learn at different time scales (e.g., System 1 vs 2). To this…
…It further coordinates a system-aware SD toggle policy with acceptance-aware draft-length adaptation , enabling speculation only in beneficial regimes while matching the drafting budget to evolving drafter quality. EfficientRollout reduces…
…🤫 the combo of iterative discovery and reusable thought templates hits a real blind spot in proactive ai: surface multiple hidden problems without drowning you in noise. iteration surfaces small batches conditioned…
…AI-generated summary Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments. However, existing robotic…
…Haebin Seong , , Abstract A two-level framework automates AI agent deployment by optimizing task-specific harnesses through evolutionary loops and meta-learning protocols, eliminating the need for manual harness engineering. AI-generated…
…Evaluating and Advancing Retrievers in Agentic Search Systems Published on May 5 Submitted by Yilun Zhao on May 7 Yale University Authors: Yilun Zhao , , Tingyu Song , , , Abstract Researchers introduce BRIGHT-Pro, an…