text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

MathEval is a benchmark dedicated to the holistic evaluation on mathematical capacities of LLMs.

A curated list of awesome Multimodal studies.

Official implementation of AnimateDiff.

AnimateDiff for AUTOMATIC1111 Stable Diffusion WebUI

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

Here we will track the latest AI Multimodal Models, including Multimodal Foundation Models, LLM, Agent, Audio, Image, Video, Music and 3D content. 🔥

Next-Token Prediction is All You Need

Offical Repo for "Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale"

Handwritten Text Recognition and Character Detection

A reading list of video generation

The related works and background techniques about Openai o1

The successful integration of Qwen2-VL-Instruct into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image queries, an…

Recaption large (Web)Datasets with vllm and save the artifacts.

This project is a collection of fine-tuning scripts to help researchers fine-tune Qwen 2 VL on HuggingFace datasets.

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

Material for gpu-mode lectures

An ML Systems Onboarding list

GPU programming related news and material links

Efficient Triton Kernels for LLM Training

OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM

code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"

[ICML'2024] Can AI Assistants Know What They Don't Know?

An open-source RAG-based tool for chatting with your documents.

NLP Zero to Hero in just 10 Kernels