Stars
[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
The loss landscape of Large Language Models resemble basin!
A survey on harmful fine-tuning attack for large language model
Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".
Universal and Transferable Attacks on Aligned Language Models
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]
A curation of awesome tools, documents and projects about LLM Security.
ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)
[ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
(ICLR 2023 Spotlight) MPCFormer: fast, performant, and private transformer inference with MPC
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
Code and data for ACL 2024 paper on 'Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space'
A curated list of resources dedicated to the safety of Large Vision-Language Models. This repository aligns with our survey titled A Survey of Safety on Large Vision-Language Models: Attacks, Defen…
[CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"
Efficient Multimodal Large Language Models: A Survey
Research and Materials on Hardware implementation of Transformer Model
The official implementation of the paper "RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction"
InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)
Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference