Stars
A curated list of LLM/MLLM guardrails, safety benchmarks, guard models, jailbreak attacks, moderation datasets, and evaluation tools.
A bilingual awesome list for VLM/MLLM knowledge injection research: benchmarks, papers, tools, resources, and ecosystem updates.
A bilingual awesome list for refusal suppression research: benchmarks, papers, tools, models, and ecosystem updates.
A collection of the latest research and resources on Fine-Grained Multimodal Perception
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
A Model Context Protocol server for searching and analyzing arXiv papers
Awesome LLM security tools, research, and documents
[CVPR 2026] LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models
A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation
[NeurIPS 2025] An official source code for paper "GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning".
Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.
Vero: An Open RL Recipe for General Visual Reasoning
Fully Open Framework for Democratized Multimodal Reinforcement Learning.
Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”
Official implementation of Seeing with You: Perception-Reasoning Co-evolution for Multimodal Reasoning.
Official repository of "Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning".
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Self-evolving vision language models from zero data
A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".
PaperBanana: Automating Academic Illustration For AI Scientists
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks