TaoSR-SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
arxiv.org·15h
Who watches the watchers? LLM on LLM evaluations
stackoverflow.blog·1d
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
arxiv.org·15h
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.org·15h
GPT-5 for AI-assisted discovery
johndcook.com·4h
Loading...Loading more...