GaussianCity is an efficient, borderless 3D city generation framework developed by the S-Lab team at Nanyang Technological University, based on 3D Gaussian rendering (3D-GS) technology. It introduces a compact BEV-Point representation method, minimizing the scene's video memory (VRAM)...
Asyncflow v1.0 is an AI text-to-speech model launched by the podcast platform Podcastle. It supports over 450 voice options and can generate high-quality speech readings for text content, suitable for multiple languages and styles.
ART (Anonymous Region Transformer) is a novel multi-layer transparent image generation technology that can directly generate multiple independent transparent layers (supporting RGBA format) based on global text prompts and anonymous region layouts.
NextGenAI is a global alliance launched by OpenAI to advance education and research based on AI technology. NextGenAI unites 15 top universities and institutions, including Harvard University, MIT, and Oxford University, and OpenAI...
NotaGen is a music generation model developed by institutions such as the Central Conservatory of Music, Beijing University of Aeronautics and Astronautics, and Tsinghua University. It generates high-quality classical music scores based on a training paradigm that mimics Large Language Models (LLM). NotaGen is based on...
DiffRhythm is an end-to-end music generation tool jointly developed by Northwestern Polytechnical University and the Chinese University of Hong Kong, Shenzhen. Based on latent diffusion technology, it can quickly generate music...
OmniAlign-V is a high-quality dataset jointly developed by Shanghai Jiao Tong University, Shanghai AI Lab, Nanjing University, Fudan University, and Zhejiang University. It is specifically designed to improve the alignment between multimodal large language models (MLLMs) and human preferences...
TrendPublish is an AI-powered trend discovery and content publishing system. It gathers information from multiple sources, including Twitter/X and websites, and uses AI services such as DeepseekAI and Qianwen for intelligent summarization and trend analysis...
Proxy Lite is an open-source, lightweight visual language model (VLM) with 3 bytes of parameters, supporting automated web page tasks. Proxy Lite can operate a browser like a human, performing tasks such as web page interaction, data scraping, and form filling.
WeGen is a unified multimodal generative model developed by the University of Science and Technology of China in collaboration with Shanghai Jiao Tong University, the WeChat team, the Chinese Academy of Sciences, and other institutions. It enables diverse visual generation tasks based on natural dialogue. WeGen combines multimodal...
DiffBrush is an image generation and editing framework developed by Beijing University of Posts and Telecommunications, Tsinghua University, China Telecom Artificial Intelligence Research Institute, and Northwestern Polytechnical University. It requires no training and allows users to intuitively control image generation based on hand-drawn sketches...
Liquid is a minimalist unified multimodal generation framework jointly developed by Huazhong University of Science and Technology, ByteDance, and the University of Hong Kong. Based on VQGAN, it encodes images into discrete visual tokens, sharing the same vocabulary space as text tokens, enabling large-scale...
X-Dancer is a music-driven human dance video generation framework jointly developed by ByteDance, researchers from UC San Diego, and USC. It supports the generation of diverse and realistic full-body dance videos from single still images...
AVD2 (Accident Video Diffusion for Accident Video Description) is a technology jointly developed by Tsinghua University, Hong Kong University of Science and Technology, Jilin University, Nanjing University of Science and Technology, Beijing Institute of Technology, Fudan University, and other institutions...
Kiss3DGen is an innovative 3D asset generation framework that efficiently generates, edits, and enhances 3D objects by refactoring a pre-trained 2D image diffusion model. Its core function is to generate a "3D Bundle Image," which combines multi-view images and their corresponding...
Archon is an open-source project focused on building and optimizing AI agents. It demonstrates the core concepts of modern AI development by autonomously generating code and optimizing agent performance. Archon's core features include rapid agent construction...
PodAgent is a podcast generation framework jointly developed by the Chinese University of Hong Kong, Microsoft, and Xiaohongshu. Based on simulating real-life talk show scenarios, it automatically generates rich and engaging podcasts using a multi-agent collaborative system (including host, guests, and writers)...
Chat2SVG is an innovative text-to-vector graphics (SVG) generation framework that automates the creation of high-quality SVG graphics by combining Large Language Models (LLMs) and image diffusion models. Through a multi-stage workflow, it first...
QwQ-32B is a new inference model open-sourced by Alibaba, with 32 billion parameters. Trained using large-scale reinforcement learning (RL), it performs exceptionally well in tasks such as mathematical reasoning and programming, rivaling the performance of DeepSense with 671 billion parameters...
Light-R1 is an open-source AI model from 360 AI, focusing on long-chain reasoning in mathematics, specifically Light-R1-32B. The model is based on Qwen2.5-32B-Instruct, using 70,000 mathematical data points and a two-stage learning process (SF...
SpatialVLA is a novel spatial embodied general manipulation model jointly developed by the Shanghai AI Lab, the China Telecom Artificial Intelligence Research Institute, and ShanghaiTech University. Based on pre-training with millions of real data points, it endows robots with general 3D...
TheoremExplainAgent (TEA) is an open-source multimodal agent system developed by the University of Waterloo, Votee AI, and other institutions. It generates long-form animated videos to help people better understand mathematical and scientific theorems. TheoremExplainAgent...
Aya Vision, developed by Cohere, is a multimodal, multilingual vision model that enhances multilingual and multimodal communication capabilities globally. It supports 23 languages and can perform image description generation, visual question answering, text translation, and more.
BGE-VL is a multimodal vector model developed by the Beijing Academy of Artificial Intelligence in collaboration with several universities. It is trained on the large-scale synthetic dataset MegaPairs. BGE-VL focuses on multimodal retrieval tasks, such as text-to-image retrieval and combined image retrieval...