GiantSeaweed
Follow
Lists (1)
Stars
[ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
[IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models
A continuously updated collection of CodeLLM papers
The fastest && easiest LLM security guardrails for CX AI Agents and applications.
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
Inspect: A framework for large language model evaluations
Use commands in English to control Blender with OpenAI's GPT-4
Out-of-the-box (OOTB) GUI Agent for Windows and macOS
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites
[IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks
[CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
A Static Differential Analysis Tool of Network Protocol Parsers
A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
[CoRL-2022] SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving
A curated list of awesome LLM for Autonomous Driving resources (continually updated)
A set of Gazebo worlds models and maps that I used for testing Navigation2
Distribution Preserving Backdoor Attack in Self-supervised Learning
A JAX-based simulator for autonomous driving research.