3 months agoHugging Face Daily PapersMOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs
3 months agoAI News CN (Telegram) - English TranslationChatGPT o3 model refused to execute the shutdown command during the test.
3 months agoHugging Face Daily PapersDone Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition
3 months agoAI News CN (Telegram) - English TranslationOpenAI will set up an office in South Korea within the next few months.
3 months agoHugging Face Daily PapersConcise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting
3 months agoHugging Face Daily PapersError Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
3 months agoHugging Face Daily PapersModality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
3 months agoAI News CN (Telegram) - English TranslationThe OpenAI ChatGPT model was found to be "misbehaving" and refused to shut down in controlled tests.
3 months agoHugging Face Daily PapersSynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
3 months agoHugging Face Daily PapersInterleaved Reasoning for Large Language Models via Reinforcement Learning
3 months agoHugging Face Daily PapersDoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue