[CVPR 2024] Data and benchmark code for the EgoExoLearn dataset

Official repository of FlowInOne: Unifying Multimodal Generation as Image-In Image-Out Flow Matching

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

The first open-domain closed-loop revisited benchmark for evaluating memory consistency and action control in world models.

Glance: Accelerating Diffusion Models with 1 Sample

Vision Bridge Transformer at Scale

[CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.

[ICLR 2026] The official repository for paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"

Computer-Use Agents as Judges for Generative UI

VCode: SVG as Symbolic Visual Representation

Native Multimodal Models are World Learners

[ACL-main-2026]We introduce Chart2Code, the first user-driven, hierarchical benchmark that systematically evaluates Large Multimodal Models on chart-to-code tasks of increasing difficulty.

PyTorch implementation of "UNIT: Unifying Image and Text Recognition in One Vision Encoder", NeurlPS 2024.

Contexts Optical Compression

[ICML 2026] Video generation via code

Automatic Video Generation from Scientific Papers

Code for Data Collection & Training in Sim+Real Envs: [RSS 2024] Natural Language Can Help Bridge the Sim2Real Gap

Official Repository for MolmoAct

Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).

📖 This is a repository for organizing papers, codes and other resources related to Visual Reinforcement Learning.

[ICCV 2025] Balanced Image Stylization with Style Matching Score

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT

[ECCV2024] This is an official inference code of the paper "Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering" and "Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Mu…

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

[ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

Janus-Series: Unified Multimodal Understanding and Generation Models

Unified layout planning and image generation, ICCV2025