Official repository for CVPR 2025 paper: OpenSDI: Spotting Diffusion-Generated Images in the Open World

Markdown editor with AI Assistant.

Code for paper "TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images"

Open-source unified multimodal model

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

Diffusion-based Image Manipulation Localization

[ICML'26] SICA & OpenMMSec

A unified foundation model for FIDL.

[ICML 2026] PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

[CVPR 2026] UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

implementation of the paper Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes

[CVPR 2026] The official PyTorch implementation of the "Vision Transformer Needs More Than Registers".

[NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

[AAAI 2025]Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

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

Codes for Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models

Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"

Contexts Optical Compression

[NeurIPS 2025] IEAP: Image Editing As Programs with Diffusion Models

Scan the Hallucination Citation of Academic papers. Convert second-hand citation to official version

[CVPR 26 Findings] Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

中国科研常用LaTeX模板集

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

Displays the China Computer Federation (CCF) recommended rank of international conferences and journals in the dblp, Google Scholar, Connected Papers and and Web of Science search results.