We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

[NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"

This repo contains papers, books, tutorials and resources on Riemannian optimization.

Using Explanations as a Tool for Advanced LLMs

This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

Code for the paper 🌳 Tree Search for Language Model Agents

agent q - oss advanced reasoning and learning for autonomous ai agents

VisualWebArena is a benchmark for multimodal agents.

[ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

The official implementation of Self-Play Fine-Tuning (SPIN)

Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

A programming framework for agentic AI 🤖

[CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models"

https://arxiv.org/pdf/2402.18025

Repo for the research paper "Aligning LLMs to Be Robust Against Prompt Injection"

Repository for research works and resources related to model reprogramming <https://arxiv.org/abs/2202.10629>

Holistic evaluation of multimodal foundation models

[NeurIPS 2024] "What If the Input is Expanded in OOD Detection?"

PAIR.withgoogle.com and friend's work on interpretability methods

The dataset and code for the ICLR 2024 paper "Can LLM-Generated Misinformation Be Detected?"

"Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?"