linzhiqiu

Cosmos

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

mochi

The best OSS video generation models, created by Genmo

lmms-eval

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

Awesome-LLM-Post-training

Awesome Reasoning LLM Tutorial/Survey/Guide

ml-aim

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

pasa

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholarly queries.

Sa2VA

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

mega-sam

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

VideoLLaMA3

Frontier Multimodal Foundation Models for Image and Video Understanding

LanguageBind

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

tarsier

Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

LongVU

[ICML 2025] Official PyTorch implementation of LongVU

PerspectiveFields

[CVPR 2023 Highlight] Perspective Fields for Single Image Camera Calibration

superclass

[NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training

NaturalBench

🚀 [NeurIPS24] Make Vision Matter in Visual-Question-Answering (VQA)! Introducing NaturalBench, a vision-centric VQA benchmark (NeurIPS'24) that challenges vision-language models with simple questions about natural imagery.

MAmmoTH-VL

(ACL 2025) MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

viddiff

[ICLR 2025] Video Action Differencing

MotionBench

Official code for MotionBench (CVPR 2025)

VidComposition

[CVPR 2025] VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

wyd-benchmark

GPS2Pix

[CVPR 2025] GPS as a Control Signal for Image Generation

SAVs

Official Codebase for "Generative Multimodal Model Features Are Discriminative Vision-Language Classifiers"

llava-score

VidCapBench

AKiRa

DGPref

EvoGen

T2I-Probology

Experimental results + resources for probing compositional structure in generative text-to-image (T2I) models

cece-vlm

Code for Natural Language Inference Improves Compositionality in Vision-Language Models

t2v_metrics

Evaluating text-to-image/video/3D models with VQAScore