[ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

[NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents".

MTEB: Massive Text Embedding Benchmark

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…

Training PyTorch models with differential privacy

FunctionBench : A Suite of Workloads for Serverless Cloud Function Service

Source code for Consistent ensemble distillation for audio tagging

Are CAPTCHAs Still Bot-hard? Generalized Visual CAPTCHA Solving with Agentic Vision Language Model

AnyAccomp: Generalizable accompaniment generation for vocals and solo instruments, powered by a quantized melodic bottleneck.

Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Retrieval and Retrieval-augmented LLMs

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

[ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

This is the official repository for Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models.

[COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting

Noise15 , Noisex-92 and Nonspeech

Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging (TIFS2024)

A Framework for Speech, Language, Audio, Music Processing with Large Language Model

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

A Self-Consistent Robust Error (ICML 2022)