Stars
Official PyTorch implementation of "Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models"
TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Align Anything: Training All-modality Model with Feedback
[ICLR 2024] Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
[ACL Main 2025] I0T: Embedding Standardization Method Towards Zero Modality Gap
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Shortest solutions for CS231n 2021-2025
Code / solutions for Mathematics for Machine Learning (MML Book)
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Famous Vision Language Models and Their Architectures
[ICLR 2025] VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
RewardBench: the first evaluation tool for reward models.
A Pytorch implementation of "Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings"
Forward-Looking Active REtrieval-augmented generation (FLARE)
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
This repository contains a collection of papers and resources on Reasoning in Large Language Models.
LLM (Large Language Model) FineTuning
A plugin for reading and annotating PDFs and EPUBs in obsidian.
Making large AI models cheaper, faster and more accessible
Learning embeddings for classification, retrieval and ranking.
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)