28Reflective Translation: Improving Low-Resource Machine Translation via Structured Self-ReflectionARXIV ArXiv 大语言模型阅读文章 arrow_forward
28Evaluation of Oncotimia: An LLM based system for supporting tumour boardsARXIV ArXiv RAG阅读文章 arrow_forward
28Apple MacBook Pro order deliveries delayed until mid MarchHACKER_NEWS Hacker News阅读文章 arrow_forward
28AISLE’s autonomous analyzer found all CVEs in the January OpenSSL releaseHACKER_NEWS Hacker News阅读文章 arrow_forward
28AI Cap-and-Trade: Efficiency Incentives for Accessibility and SustainabilityARXIV ArXiv阅读文章 arrow_forward
28TikTok settles just before social media addiction trial to beginHACKER_NEWS Hacker News阅读文章 arrow_forward
28Thief of $90M in seized U.S.-controlled crypto is gov't contractor's sonHACKER_NEWS Hacker News阅读文章 arrow_forward
28A few random notes from Claude coding quite a bit last few weeksHACKER_NEWS Hacker News阅读文章 arrow_forward
27Unsupervised Text Segmentation via Kernel Change-Point Detection on Sentence EmbeddingsARXIV ArXiv 大语言模型阅读文章 arrow_forward
27Teaching Models to Teach Themselves: Reasoning at the Edge of LearnabilityARXIV ArXiv 大语言模型阅读文章 arrow_forward
27Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia GlottosetsARXIV ArXiv阅读文章 arrow_forward
27Show HN: One Human + One Agent = One Browser From Scratch in 20K LOCHACKER_NEWS Hacker News AI Agent阅读文章 arrow_forward
27Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy PrefixesARXIV ArXiv 大语言模型阅读文章 arrow_forward
27POPE: Learning to Reason on Hard Problems via Privileged On-Policy ExplorationARXIV ArXiv 大语言模型阅读文章 arrow_forward
27Multi-Objective Reinforcement Learning for Efficient Tactical Decision Making for Trucks in Highway TrafficARXIV ArXiv阅读文章 arrow_forward
27MortalMATH: Evaluating the Conflict Between Reasoning Objectives and Emergency ContextsARXIV ArXiv 大语言模型阅读文章 arrow_forward
27Lennart Poettering, Christian Brauner founded a new companyHACKER_NEWS Hacker News阅读文章 arrow_forward
27Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer SystemARXIV ArXiv 大语言模型阅读文章 arrow_forward
27ctELM: Decoding and Manipulating Embeddings of Clinical Trials with Embedding Language ModelsARXIV ArXiv 大语言模型阅读文章 arrow_forward
27Chuck Klosterman on why we've never actually seen a real football gameHACKER_NEWS Hacker News阅读文章 arrow_forward
27430k-year-old well-preserved wooden tools are the oldest ever foundHACKER_NEWS Hacker News阅读文章 arrow_forward
27OpenSSL: Stack buffer overflow in CMS AuthEnvelopedData parsingHACKER_NEWS Hacker News阅读文章 arrow_forward
27Management as AI superpower: Thriving in a world of agentic AIHACKER_NEWS Hacker News AI Agent阅读文章 arrow_forward