每天自动聚合 AI 领域最新动态
Recent work has applied Mamba style state space models (SSMs) to video anomaly detection, yet existing approaches sti...
Large language models are increasingly used for knowledge graph question answering (KGQA), but can fail to correctly ...
The rapid expansion of large-scale assessments and the growing adoption of automatic item generation have intensified...
Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI...
We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific...
Real-world data for knowledge graph question answering is often distributed across different organizations due to gov...
Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and var...
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state a...
When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the...
Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize inter...
Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level ...
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state a...