Let Skills Evolve Collectively with Agentic Evolver

AI 高考志愿顾问 — 会追问、会分析、敢说真话

Ideogram 4: Open image model at the forefront of design

Official code for the paper "Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models"

Official repo for "Let ViT Speak: Generative Language-Image Pre-training"

Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"

Repo for Qwen Image Finetune

[CVPR 2026 DataCV Workshop] 4KLSDB: A Large-Scale Native-4K Dataset and Benchmark for Image Restoration and Generation.

The first "ImageNet" 3D dataset.

A Foundation Model for Generalist Gaming Agents

[CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing

Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Tiny AutoEncoder for Hunyuan Video (and other video models)

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models

A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

The open source coding agent.

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images …

🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!

[ICML26 Spotlight] UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

[AAAI 2026] Official code release of our paper "Fine-grained Image Quality Assessment for Perceptual Image Restoration". 首个面向图像恢复的细粒度IQA数据集FGRestore+方法FGResQ

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

[CVPR 2026 Oral] VGGT Omega

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop