Official eval code for ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

Awesome-Paper-list: Visualization meets LLM

MotionStream: Real-Time Video Generation with Interactive Motion Controls

This is the official repository for the paper "MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning"

https://little-misfit.github.io/GRAG-Image-Editing/

Mastering Atari with Discrete World Models

Code and training scripts for FlexOlmo

Live evaluation of trading agents

Defeating the Training-Inference Mismatch via FP16

[arXiv 2025] Generative View Stitching

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

OmniNWM: Omniscient Navigation World Models for Autonomous Driving

Native Multimodal Models are World Learners

Official repo for: Epipolar Geometry Improves Video Generation Models

Official implementation of "Understanding multi-view transformers" (ICCV 2025 E2E3D Workshop)

The OpenEXR project provides the specification and reference implementation of the EXR file format, the professional-grade image storage format of the motion picture industry.

Minimal and annotated implementations of key ideas from modern deep learning research.

Devkit and documentation for the NVIDIA Physical AI Autonomous Vehicles Dataset

PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning

NOF0 - 开源的 AI 交易竞技场

Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

[NeurIPS 2025 Oral] Exploring Diffusion Transformer Designs via Grafting

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