Pinned Loading

1. OpenThinkIMG OpenThinkIMG Public

   OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.

   Jupyter Notebook 355 8

2. Awesome_Think_With_Images Awesome_Think_With_Images Public

   Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

   1.4k 41

3. conflictbank conflictbank Public

   Code and data for "ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM" (NeurIPS 2024 Track Datasets and Benchmarks)

   Python 65 1

4. hkust-nlp/AgentVista hkust-nlp/AgentVista Public

   Benchmarking multimodal agents on realistic, ultra-challenging visual scenarios requiring long-horizon hybrid tool use.

   Python 35 3