Stars
MemVerse: Multimodal Memory for Lifelong Learning Agents
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…
The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"
SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expandi…
Official PyTorch implementation of "MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks"
[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
This is the official code repository for the paper: Towards General Continuous Memory for Vision-Language Models.
😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.
The official implementation for "Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation(IROS 2025)"
✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
[ICRA 2025] Official implementation of Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs
InternRobotics' open platform for building generalized navigation foundation models.
📚这个仓库是在arxiv上收集的有关VLN，VLA，World Model，SLAM，Gaussian Splatting,非线性优化等相关论文。每天都会自动更新！issue区域是最新10篇论文
A package that achieves 95%+ transfer attack success rate against GPT-4
[VLM-Attack-Survey-2024] Paper list and projects for VLM attacks
Code for paper "Membership Inference Attacks Against Vision-Language Models"
Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
[NeurIPS-2023] Annual Conference on Neural Information Processing Systems
Universal Adversarial Attack on Aligned Multimodal LLMs
[ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
This is the official code and dataset repository of 2025 IEEE TVCG/VR paper: ViDDAR: Vision Language Model-based Detrimental Content Detection for Augmented Reality
GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models