implementing minimal versions of joint-embedding predictive architecture (JEPA)

Official implementation of "StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues", CVPR 2026.

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

AI agents running research on single-GPU nanochat training automatically

[ICLR 2026 🔥 ] Official implementation of "UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing"

A course on aligning smol models.

Pytorch Lightning Implement of Generative Recommenders

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

(ICLR 2023) Official PyTorch implementation of "What Do Self-Supervised Vision Transformers Learn?"

The best ChatGPT that $100 can buy.

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

simple pytorch pipeline for pretraining/finetuning vision models on imagenet-1k

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

DeepConf: Deep Think with Confidence

A list of works on evaluation of visual generation models, including evaluation metrics, models, and systems

Official Implementation of Paper Transfer between Modalities with MetaQueries

FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

[TACL/EMNLP'24] Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"

A curated list of awesome papers on Embodied AI and related research/industry-driven resources.

👋 Overcomplete is a Vision-based SAE Toolbox

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Open-source implementation of AlphaEvolve

A final sanity checklist to help your CS paper get accepted, not desk rejected.

The simplest, fastest repository for training/finetuning small-sized VLMs.

Implementing DeepSeek R1's GRPO algorithm from scratch