力扣百题通 — 一套面向 Obsidian + Claudian 打造的 LeetCode Hot 100 个人知识库与 14 天速成刷题路线。通过 Claudian 插件将 Claude 深度集成到 Obsidian 中，实现 AI 驱动的自适应学习闭环。 融合 labuladong 框架思维 + 代码随想录系统专题法 + 灵茶山艾府题单驱动法 三大体系，配合 AI 自适应教学系统，帮你高…

A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

[ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

[ACL2026 Main] ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants

SearchAgent-Zero: A Scalable Multi-Turn Search Agent RL Framework

A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.

CMedTEB & CARE: Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders

An benchmark dataset for personalized product search built on Amazon review data

The codebase and database of KuaiSearch: A Large-Scale E-Commerce Search Dataset for Recall, Ranking, and Relevance

可运行的Claude Code源码

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search

Code for "Multi-level Relevance Document Identifier Learning for Generative Retrieval". ACL 2025.

Code for "HierGR: Hierarchical Semantic Representation Enhancement for Generative Retrieval in Food Delivery Search". ACL 2025.

[ICLR 2025 Oral] "Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free"

Generative Representational Instruction Tuning

Community-maintained faiss wheel builder

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

[ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

LaTeX template for USTC thesis

Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).

LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment

About Toolkit for Universal Retrieval, such as text retrieval, item recommendation, image retrieval, etc.

[SIGIR'24] The official implementation code of MOELoRA.