TaoSR-SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
arxiv.orgยท15h
Who watches the watchers? LLM on LLM evaluations
stackoverflow.blogยท1d
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
arxiv.orgยท15h
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.orgยท15h
GPT-5 for AI-assisted discovery
johndcook.comยท4h
Loading...Loading more...