Cluster 651001

8 repos

Python · 7

Jupyter Notebook · 1

safety ·537

multi-modal ·521

gpt-4 ·457

trustworthy-ai ·321

jailbreak ·295

toolbox ·242

benchmark ·242

privacy ·242

truthfulness ·242

llm ·216

Related clusters

Large Language Models and Multimodal AI34 Cluster 63778338 LLM-Powered Chatbots & Plugins36 Multimodal LLM Evaluation & Benchmarking10 Developer Tools and AI Integration23 Cluster 63381337

thu-ml/MMTrustEval

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS…

Python

178

216 commits

thu-ml/MLA-Trust

A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness,…

Python

44 commits

ThuCCSLab/FigStep

[AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts

Python

216

41 commits

ZichenWen1/DIJA

(ICLR 2026 🔥) Code for "The Devil behind the mask: An emergent safety vulnerability of Diffusion…

Python

43 commits

mbzuai-oryx/ALM-Bench

[CVPR 2025 🔥] ALM-Bench is a multilingual multi-modal diverse cultural benchmark for 100 languages…

Python

37 commits

Agora-Lab-AI/Atom

a suite of finetuned LLMs for atomically precise function calling 🧪

Python

19 commits

wangyouze/Trust-videoLLMs

No description

Python

12 commits

AI-secure/MMDT

Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models

Jupyter Notebook

77 commits