[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Repository Index
132,241 visible repositories in the index
1–24 of 27 · Most stars
A general fine-tuning kit geared toward image/video/audio diffusion models.
- diffusers
- diffusion-models
- fine-tuning
- flux-dev
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- large-multimodal-models
- multimodal-large-language-models
- omni-language-model
- omni-modal-video-understanding
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
- diffusion-models
- generative-model
- rlhf
- human-preferences
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
- agent
- large-language-models
- llm
- post-training
AgentEvolver: Towards Efficient Self-Evolving Agent System
- agent
- llm
- reinforcement-learning
- self-evolving
Recipes to train reward model for RLHF.
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
- artificial-intelligence
- deep-learning
- transformers
- beyond-human-data
把英文论文读成舒服的中文:本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.
- academic
- arxiv
- chinese
- claude-code
Medical o1, Towards medical complex reasoning with LLMs
HuatuoGPT, Towards Taming Language Models To Be a Doctor. (An Open Medical GPT)
[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
Dromedary: towards helpful, ethical and reliable LLMs.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
- alignment
- reward
- reward-model
- rlhf
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
- foundation-models
- multimodal
- representation-learning
- vision-language
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
- alignment
- large-language-models
- preference-alignment
- rlhf
轻量级 LLM Post-training 框架,支持 SFT、RLVR、On-Policy KD、Guide KD 及混合训练;实现单轮/多轮 Guide 蒸馏、多教师蒸馏、Reward 混合训练与自动化数据分流👩🎓👨🎓
Official implementation for "Towards a Unified Self-Distillation Framework for Large Language Models" (https://arxiv.org/abs/2605.06597).
data-to-paper: Backward-traceable AI-driven scientific research
- agents
- ai
- autonomous-agents
- interactive-machine-learning
EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://aclanthology.org/2026.emnlp-main.878/))