Highlights
- Pro
Lists (9)
Stars
QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.
Claude Code 源码深度研究，包括 Foundations/Execution/Infrastructure 三大章节和 23 个子系统的架构分析拆解。
The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.
AgentOpt automatically finds the best LLM model combination for each step of your agent — optimizing for accuracy, cost, and latency.
[EMNLP 2026 Demo] "PalmClaw: A Native On-Device Agent Framework for Mobile Phones"
GISA: A Benchmark for General Information-Seeking Assistant
[ICML 2026 & EMNLP 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of searc…
GRID: Generative Recommendation with Semantic IDs
The implementation for ACL 2026: MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching.
A set of examples based on verl for end-to-end RL training recipes.
OpenTinker is an RL-as-a-Service infrastructure for foundation models
Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.
[ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
A framework for researchers to build and study web agents for real-world applications. It features: 1. Robust handling of complex, dynamic web pages without hassle. 2. Support for both automated an…
Paper list about hyperbolic embedding, hyperbolic models,hyperbolic applications
Bridging LLM and Recommender System.
This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.
[ACL 2025 Findings] Implicit Reasoning in Transformers is Reasoning through Shortcuts