Stars
code for eccv 2026: Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning
Socio-Foundation project website: generalizable individual behavior simulation via hierarchical capability distillation.
面向长期陪伴的生成式 AI 角色研究原型:角色拥有独立作息、日程与信息边界,人格倾向随长期经历演化。Live2D 立绘 + 现实时间同步 + 大模型驱动对话,浏览器端可运行。
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
[WWW 2025] Official PyTorch Code for "CTR-Driven Advertising Image Generation with Multimodal Large Language Models"
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm
A ultra-low-cost social simulation engine based on OASIS, powered by TypeSafe Jev.
VENEER: how much of an LLM judge's verdict is formatting, not substance? Same claims, nine renderings, 972 pairwise judgments.
LynnReal-Omni brings text-to-video, image-to-video, human- and hand-pose guided generation, structural control, omni-reference generation, style transfer, video editing, degraded-video restoration …
Scan the Hallucination Citation of Academic papers. Convert second-hand citation to official version
(AAAI 2026) SoMe: A Realistic Benchmark for LLM-based Social Media Agents
Official implementation of Uni-EmoAgent: A Unified Multi-Agent Framework for Emotional Understanding and Generation.
[ICML2026] Attend to Anything: Foundation Model for Unified Human Attention Modeling (Saliency Prediction; Video saliency)
Virality scoring for short videos via Meta's TRIBE v2 fMRI model (Visual, Audio and Text Brain Mapping Model).
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
Real-time visual performance and projection mapping in your browser. VJ tool with quad warping, video playback, custom GLSL shaders, AI-assisted generation, and generative graphics. Built with Reac…
Audio-reactive visualizer project with Rust core and TypeScript frontend
This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction
DeepSeek Harness: Everything is a Plugin.
[Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation
Dreamatic - An Open Harness for Design Agents