Pinned Loading

1. wmw wmw Public

   Framework for auditing the physical state-transition commitments of vision-language models. Instead of scoring only the answer, it elicits a typed trace, verifies it with a hybrid checker, and surf…

   Python

2. voiceagentguard voiceagentguard Public

   Contract-gated safety layer for tool-using voice agents (EMNLP2026)

   Python

3. UK_BOB UK_BOB Public

   Large-scale semi-supervised framework with 1B+ labeled masks from 48K+ datasets with test-time adaptation to new domains (ICCV 2025).

   Python 52 2

4. mm-ragbench mm-ragbench Public

   Benchmark dataset for evaluating multimodal Retrieval-Augmented Generation (RAG) systems.

   Python

5. MVDiff MVDiff Public

   Scalable multi-view diffusion model with flexible viewpoint generation using epipolar geometry to improve multi-view consistency in 3D reconstruction (CVPRW 2024).

   Python 4 1

6. X-Diffusion X-Diffusion Public

   Novel diffusion model approach with cross-sectional conditioning for generating 3D medical volumes from sparse views (ICCVW 2025 Oral).

   Jupyter Notebook 8 1