16Show HN: Open-source playground to red-team AI agents with exploits publishedHACKER_NEWS Hacker News AI Agent阅读文章 arrow_forward
15Learning athletic humanoid tennis skills from imperfect human motion dataHACKER_NEWS Hacker News阅读文章 arrow_forward
15The Webpage Has Instructions. The Agent Has Your CredentialsHACKER_NEWS Hacker News AI Agent阅读文章 arrow_forward
15The 100 hour gap between a vibecoded prototype and a working productHACKER_NEWS Hacker News阅读文章 arrow_forward
14Show HN: GitAgent – An open standard that turns any Git repo into an AI agentHACKER_NEWS Hacker News AI Agent阅读文章 arrow_forward
141M context is now generally available for Opus 4.6 and Sonnet 4.6HACKER_NEWS Hacker News阅读文章 arrow_forward
14Show HN: Simple plugin to get Claude Code to listen to youHACKER_NEWS Hacker News阅读文章 arrow_forward
13Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time TrainingARXIV ArXiv阅读文章 arrow_forward
13Separable neural architectures as a primitive for unified predictive and generative intelligenceARXIV ArXiv阅读文章 arrow_forward
13SciMDR: Benchmarking and Advancing Scientific Multimodal Document ReasoningARXIV ArXiv阅读文章 arrow_forward
13P-EAGLE: Faster LLM inference with Parallel Speculative Decoding in vLLM | Amazon Web ServicesBLOGS_PODCASTS 博客与播客 大语言模型阅读文章 arrow_forward
13Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language ModelsARXIV ArXiv阅读文章 arrow_forward
13Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-TrainingARXIV ArXiv 大语言模型阅读文章 arrow_forward
13EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion ModelsARXIV ArXiv 大语言模型阅读文章 arrow_forward
13BiGain: Unified Token Compression for Joint Generation and ClassificationARXIV ArXiv阅读文章 arrow_forward