Lists (1)
Stars
A Multi-Modal Large Language Model with Retrieval-augmented In-context Learning capacity designed for generalisable and explainable end-to-end driving
YOLOv12: Attention-Centric Real-Time Object Detectors
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning methods. All features: benchmarks, methods, evaluations, models etc. are easily ext…
Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24]
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access
[NeurIPS-2023] Annual Conference on Neural Information Processing Systems
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
Algorithms to recover input data from their gradient signal through a neural network
Interfacing Carla with MATLAB using Python and ROS
The code of traffic obstacles detection based on YOLOv8.
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
Benchmark and model for step-by-step reasoning in autonomous driving.
[ICLR'25] Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving
A caret input tip extension for vscode
[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering
[ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
利用HuggingFace的官方下载工具从镜像网站进行高速下载。
VioHawk: Detecting Traffic Violations of Autonomous Driving Systems through Criticality-guided Simulation Testing