VideoPriorSD: Generating High-Resolution Images via Video-based Priors

This is the official PyTorch implementation of "ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality"

Official repository for CoMM Dataset

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

A banchmark list for evaluation of large language models.

LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

OLMoE: Open Mixture-of-Experts Language Models

Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"

[NeurIPS 2024] Repository for the paper "OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking".

Official code base for paper EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance

a collection of awesome autoregressive visual generation models

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

A paper list of some recent works about Token Compress for Vit and VLM

ElasticTok: Adaptive Tokenization for Image and Video

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Diff-DGMN: A Diffusion-based Dual Graph Multi-attention Network for POI Recommendation

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

Official PyTorch Implementation of "Scalable Autoregressive Image Generation with Mamba"

🌋👵🏻 Yo'LLaVA: Your Personalized Language and Vision Assistant

A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

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

Official Implementation for "MyVLM: Personalizing VLMs for User-Specific Queries" (ECCV 2024)