Download

Featured

Codebases

DreamEngine

LMM for image generation.

SAMURAI

Visual object tracking.

Aurora

Efficient LMMs for video understanding.

LMMs-Eval

(Contributor) Evaluation Suite of LMMs.

MovieChat

LMMs for long-form video understanding.

StableVideo

Diffusion-based video editing.

Featured

Datasets

Video-MMLU

A massive benchmark designed to evaluate the capabilities of LMMs in understanding Multi-Discipline Lectures.

TEMPURA

1M reasoning about causal event relationships and generate fine-grained, timestamped descriptions of untrimmed videos.

RISE

The first benchmark for evaluating reasoning-informed visual editing, focusing on four key reasoning types: Temporal, Causal, Spatial, and Logical Reasoning

Science T2I @ CVPR 2025

We collect over 20k image pairs, enabling the training of a language-guided reward model for text-to-image alignment with scientific knowledge.

VDC @ ICLR 2025

The first benchmark for detailed video captioning, featuring over one thousand videos with significantly longer and more detailed captions.

EMMOE

Explore environments and perform various open-vocabulary mobile manipulation tasks based solely on instructions and sensor observations for robots.

RT-Pose @ ECCV 2024

A human pose estimation (HPE) dataset, consisting of calibrated radar ADC data, 4D radar tensors, stereo RGB images, and LiDAR point clouds.

CityCraft

Including 2D semantic layouts of urban areas, corresponding satellite images, and high-quality 3D building assets.

MovieChat @ CVPR 2024

A manually labeled long video QA and caption dataset, contains 1,000 video, for each longer than ten thousands frames.

VFD-2000

A video fight detection dataset collected from YouTube, contains 2,000 video clips in diverse scenarios.

Featured

Surveys

An Empirical Study of GPT-4o Image Generation Capabilities

Technical Report (91 pages)

A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision

IEEE Transactions on Visualization and Computer Graphics (TVCG)

Deep Learning Methods for Small Molecule Drug Discovery: A Survey

IEEE Transactions on Artificial Intelligence (TAI)

Awesome-list: Vector Quantized Variational Autoencoder (VQ-VAE)

GitHub Repo

Deep vision multimodal learning: Methodology, benchmark, and trend

Applied Science

Featured

Templates

arXiv Template

Overleaf

Download

Poster Template

Overleaf

Download

Curriculum Vitae (CV) Template

Overleaf

Download

Project Page Template

Github

Download

CVPR/ICCV Rebuttal Template

Overleaf

Download

Download

Featured

Codebases

DreamEngine

SAMURAI

Aurora

LMMs-Eval

MovieChat

StableVideo

Featured

Datasets

Video-MMLU

TEMPURA

RISE

Science T2I @ CVPR 2025

VDC @ ICLR 2025

EMMOE

RT-Pose @ ECCV 2024

CityCraft

MovieChat @ CVPR 2024

VFD-2000

Featured

Surveys

An Empirical Study of GPT-4o Image Generation Capabilities

A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision

Deep Learning Methods for Small Molecule Drug Discovery: A Survey

Awesome-list: Vector Quantized Variational Autoencoder (VQ-VAE)

Deep vision multimodal learning: Methodology, benchmark, and trend

Featured

Templates

arXiv Template

Poster Template

Curriculum Vitae (CV) Template

Project Page Template

CVPR/ICCV Rebuttal Template

Featured

Posters