about 1 month agoHugging Face Daily PapersQwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
about 1 month agoHugging Face Daily PapersTowards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
about 1 month agoHugging Face Daily PapersRethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
about 1 month agoHugging Face Daily PapersPreMoe: Lightening MoEs on Constrained Memory by Expert Pruning and Retrieval
about 1 month agoAI News CN (Telegram) - English TranslationMicrosoft's new Sora - based tool, Bing Video Creator, challenges Veo. It can be used for free on all platforms.
about 1 month agoAI News CN (Telegram) - English TranslationAnthropic CEO said that artificial intelligence models actually produce fewer hallucinations than humans.
about 1 month agoAI News CN (Telegram) - English Translation🎬 Xiao Hu: The in - game screen directly output from Veo 3
about 1 month agoHugging Face Daily PapersScaling Image and Video Generation via Test-Time Evolutionary Search
about 1 month agoHugging Face Daily PapersMMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation
about 1 month agoHugging Face Daily PapersDistilling LLM Agent into Small Models with Retrieval and Code Tools
about 1 month agoAI News CN (Telegram) - English TranslationUse Cursor to deeply experience 3 MCP Servers. Is it amazing but not practical?
about 1 month agoHugging Face Daily PapersModel Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
about 1 month agoHugging Face Daily PapersTeaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection