AIApril 3, 2025Snowflake Proposes ExCoT: A Novel AI Framework that Iteratively Optimizes Open-Source LLMs by Combining CoT Reasoning with off-Policy and on-Policy DPO, Relying Solely on Execution Accuracy as Feedback
AIApril 2, 2025Open AI Releases PaperBench: A Challenging Benchmark for Assessing AI Agents’ Abilities to Replicate Cutting-Edge Machine Learning Research
AIApril 2, 2025Meta AI Proposes Multi-Token Attention (MTA): A New Attention Method which Allows LLMs to Condition their Attention Weights on Multiple Query and Key Vectors
AIMarch 30, 2025Tencent AI Researchers Introduce Hunyuan-T1: A Mamba-Powered Ultra-Large Language Model Redefining Deep Reasoning, Contextual Efficiency, and Human-Centric Reinforcement Learning
