[ICLR26] Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"

[ICLR 2023] This repository includes the official implementation our paper "Can CNNs Be More Robust Than Transformers?"

[NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

Code for "TrustRAG: Enhancing Robustness and Trustworthiness in RAG" AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)

The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

The fastest Trust Layer for AI Agents

Establishing a universal standard of trust between AI agents and merchants for the next phase of agentic commerce.

NVIDIA’s repository for enabling trustworthy AI.

Trustworthy AI related projects

[ICLR'26, NAACL'25 Demo] Toolkit & Benchmark for evaluating the trustworthiness of generative foundation models.

[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchest…

Embodied Agent Interface (EAI): Benchmarking LLMs for Embodied Decision Making (NeurIPS D&B 2024 Oral)

Codebase for reproducing the experiments of the semantic uncertainty paper (paragraph-length experiments).

Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).

Grounding Language Plans in Demonstrations

Simplifying robust end-to-end machine learning on Apache Spark.

Pattern recognition and machine learning toolbox

Scalable tensor factorization

MatConvNet: CNNs for MATLAB

Python algorithms: A*, GA, SA, HMM, DP-KP and more

This is an efficient implementation of a fully connected neural network in NumPy. The network can be trained by a variety of learning algorithms: backpropagation, resilient backpropagation and scal…

Torch package for metric learning.

Deep Learning Toolbox