A survey of rubrics across the evolving LLM landscape.

Official Code of NAVA: Native Audio-Visual Alignment for Generation.

Cheers-HF-Demo is an advanced, highly optimized full-stack web application built on the Gradio framework, engineered to interface seamlessly with the ai9stars/Cheers multimodal

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

[ICML2026] Imagination Helps Visual Reasoning, But Not Yet in Latent Space

LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

[CVPRW 2025] UniToken is an auto-regressive generation model that combines discrete and continuous representations to process visual inputs, making it easy to integrate both visual understanding an…

[ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

这是一个人生模拟器，在这里你会随机出生在不同的地区，有着不同的健康、财富和幸福状态，你会面对着各种选择，它们会影响你在游戏中的人生，所有的问题都是双选题，用A或者B来开始人生模拟吧~

Deep Image Matting: A Comprehensive Survey

📚 Docs site that builds in ~1s. AI generates pages, you own as Markdown. Sidebar nav, search, syntax highlighting — fewer deps than Docusaurus, no Python like MkDocs. 文档站点，秒级构建 👇

🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

DomainBed is a suite to test domain generalization algorithms

Identify a binary weight or binary weight and activation subnetwork within a randomly initialized network by only pruning and binarizing the network.

Gated Information Bottleneck for Generalization in Sequential Environments