Skip to content
@OSU-NLP-Group

OSU Natural Language Processing

Popular repositories Loading

  1. HippoRAG HippoRAG Public

    [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…

    Python 2.3k 188

  2. Mind2Web Mind2Web Public

    [NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web"

    Jupyter Notebook 818 108

  3. SeeAct SeeAct Public

    [ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

    Python 739 95

  4. MagicBrush MagicBrush Public

    [NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".

    Python 350 14

  5. TravelPlanner TravelPlanner Public

    [ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

    Python 349 51

  6. GUI-Agents-Paper-List GUI-Agents-Paper-List Public

    Building a comprehensive and handy list of papers for GUI agents

    Python 307 16

Repositories

Showing 10 of 53 repositories
  • ScienceAgentBench Public

    [ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

    Python 81 MIT 12 4 1 Updated Apr 28, 2025
  • saev Public

    Sparse autoencoders for vision

    Elm 28 MIT 5 2 0 Updated Apr 26, 2025
  • InsightAgent Public

    Code & Data for "Completing A Systematic Review in Hours instead of Months with Interactive AI Agents"

    Python 5 MIT 1 0 0 Updated Apr 22, 2025
  • Online-Mind2Web Public

    An Illusion of Progress? Assessing the Current State of Web Agents

    Python 38 0 0 0 Updated Apr 20, 2025
  • hal-harness Public Forked from princeton-pli/hal-harness
    Python 0 12 0 0 Updated Apr 20, 2025
  • SkillWeaver Public

    SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.

    Python 70 MIT 6 0 0 Updated Apr 14, 2025
  • HippoRAG Public

    [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

    Python 2,283 MIT 188 11 1 Updated Apr 12, 2025
  • WebDreamer Public

    "Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents"

    Python 69 5 3 0 Updated Apr 9, 2025
  • Mind2Web Public

    [NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web"

    Jupyter Notebook 818 MIT 108 6 6 Updated Apr 3, 2025
  • reversal-curse-binding Public
    Python 22 2 0 0 Updated Apr 3, 2025
View all repositories

Most used topics

Loading…