TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

Janus-Series: Unified Multimodal Understanding and Generation Models

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

This repo contains the code for 1D tokenizer and generator

LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

Schedule-Free Optimization in PyTorch

Annotated version of the Mamba paper

VideoSys: An easy and efficient system for video generation

A curated list of recent diffusion models for video generation, editing, and various other applications.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

Recent LLM-based CV and related works. Welcome to comment/contribute!

Official code for the NeurIPS 2023 paper "Switching Temporary Teachers for Semi-Supervised Semantic Segmentation"

✨✨Latest Advances on Multimodal Large Language Models

The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams

[ICCV-2023]-Universal Video Segmentaion For VSS, VPS and VIS

[ICCV2023] DETR Doesn’t Need Multi-Scale or Locality Design