Skip to content

@cxcscmu cxcscmu

All

    Repositories list

    48 repositories

    • SkillLearnBench

      Public
      [COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
      benchmarkautomaticcontinual-learning
      benchmarkautomaticcontinual-learningagent-skillsskill-generation
      Python
      •
      MIT License
      •7•83•6•0•Updated Oct 2, 2026Oct 2, 2026

    • ReScraper

      Public
      Official repository of paper "ReScraper: Unified Scraping and Cleaning of Web Data for Effective LLM Pretraining"
      Python
      •
      Apache License 2.0
      •0•5•0•0•Updated Oct 1, 2026Oct 1, 2026

    • prefetchable-store-release

      Public
      Python
      •
      MIT License
      •0•0•0•0•Updated Sep 26, 2026Sep 26, 2026

    • Discovery-Certification-Protocol

      Public
      The Discovery Certification Protocol for Auditing AI Research Agents
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Sep 26, 2026Sep 26, 2026

    • lora-rank-demand

      Public
      Can cheap pre-training descriptors predict LoRA rank demand? A pre-registered six-checkpoint study on mathematical reasoning.
      Python
      •0•0•0•0•Updated Aug 17, 2026Aug 17, 2026

    • GameTheory-GEO

      Public
      Code implementation for "Mechanism Design for Generative Engine: From Exploitation to Win-Win Equilibrium"
      Python
      •0•0•0•0•Updated Aug 11, 2026Aug 11, 2026

    • Auto-Research-AI-Scientist

      Public
      Auto-Research-AI-Scientist
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Jul 19, 2026Jul 19, 2026

    • AgentWebBench

      Public
      [ICML'26] AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web
      benchmarkwebmulti-agent
      benchmarkwebmulti-agentllmagentic-aiagentic-web
      Python
      •
      MIT License
      •0•3•0•0•Updated Jul 13, 2026Jul 13, 2026

    • VLAFactory

      Public
      Python
      •
      Other
      •0•3•0•0•Updated Jul 11, 2026Jul 11, 2026

    • simlingo

      Public
      [CVPR 2025, Spotlight] SimLingo (CarLLava): Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment
      Python
      •
      Apache License 2.0
      •69•0•0•0•Updated Jul 9, 2026Jul 9, 2026

    • FaithMed

      Public
      Python
      •0•4•0•0•Updated Jul 1, 2026Jul 1, 2026

    • Auto-Research-Molprop

      Public
      Auto Research for molecular property prediction
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Jun 21, 2026Jun 21, 2026

    • SynPro

      Public
      Official Repository for Generating Pretraining Tokens from Organic Data for Data-Bound Scaling
      Python
      •
      Other
      •0•2•0•0•Updated Jun 18, 2026Jun 18, 2026

    • diverse-query-initialization

      Public
      Python
      •
      MIT License
      •0•2•0•0•Updated Jun 17, 2026Jun 17, 2026

    • AutoGEO

      Public
      [ICLR'26] AutoGEO: a Generative Engine Optimization framework to automatically learn generative engine preferences, and rewrite web contents for more traction.
      searchvisibilityiclr
      searchvisibilityiclrlarge-language-modelsgenerative-aigenerative-searchai-search-enginecontent-optimizationretrieval-augmented-generationgrpo
      Python
      •
      MIT License
      •28•223•0•0•Updated Jun 14, 2026Jun 14, 2026

    • dpo-query-generation

      Public
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Jun 8, 2026Jun 8, 2026

    • agentic_search_query_recycling

      Public
      0•0•0•0•Updated Jun 3, 2026Jun 3, 2026

    • starVLA

      Public
      StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
      Python
      •
      Other
      •497•0•0•0•Updated May 16, 2026May 16, 2026

    • Auto-Research-Recipes

      Public
      Closed-loop auto research turns agent-written code, real experiments, and evaluator feedback into an autonomous feedback loop that develops non-trivial trainin…
      Python
      •
      Apache License 2.0
      •1•18•0•0•Updated May 8, 2026May 8, 2026

    • ai-cofounder-skills

      Public
      1•1•0•0•Updated Apr 27, 2026Apr 27, 2026

    • General-AgentBench

      Public
      Benchmark Test-Time Scaling of General LLM Agents
      Python
      •
      MIT License
      •1•25•0•0•Updated Apr 14, 2026Apr 14, 2026

    • LlamaFactory

      Public
      Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
      Python
      •
      Apache License 2.0
      •9.2k•0•0•0•Updated Apr 6, 2026Apr 6, 2026

    • ai-search

      Public
      0•0•0•0•Updated Mar 31, 2026Mar 31, 2026

    • OLMo

      Public
      Modeling, training, eval, and inference code for OLMo
      Python
      •
      Apache License 2.0
      •799•0•0•0•Updated Mar 12, 2026Mar 12, 2026

    • search_agent_synthetic_query

      Public
      Python
      •0•2•0•0•Updated Mar 10, 2026Mar 10, 2026

    • deepresearch_benchmarking

      Public
      Python
      •1•29•0•0•Updated Mar 10, 2026Mar 10, 2026

    • large-scale-embeddings

      Public
      Python
      •1•14•0•0•Updated Feb 18, 2026Feb 18, 2026

    • RePro

      Public
      Official repository for RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
      Python
      •1•11•2•0•Updated Feb 18, 2026Feb 18, 2026

    • 11787-ai-cofounder

      Public
      repo for the 11787 course
      HTML
      •
      MIT License
      •260•0•0•0•Updated Jan 15, 2026Jan 15, 2026

    • verl-agent-deepresearch

      Public
      The deep research agent RL framework for paper https://arxiv.org/abs/2510.06534
      Python
      •
      Apache License 2.0
      •229•4•0•0•Updated Dec 20, 2025Dec 20, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.