Ivy-VL is a lightweight multimodal AI model developed by AI Safeguard in collaboration with Carnegie Mellon University and Stanford University, specifically designed for mobile and edge devices. The model boasts 3 billion parameters, significantly reducing the size compared to other large multimodal models...
ColorFlow is an image sequence colorization model jointly developed by Tsinghua University and Tencent ARC Labs. It can colorize images while preserving the individual identities within the sequence with fine precision. It is based on retrieval enhancement, context learning, and super-resolution techniques...
NodeTool is an open-source AI workflow visualization builder. NodeTool integrates a wide range of AI tools and models, and its simple, visual interface allows users to quickly prototype and test without coding. NodeTool supports...
VMB (Visuals Music Bridge) is a multimodal music generation framework developed by the Institute of Information Engineering, Chinese Academy of Sciences, the School of Cyberspace Security, University of Chinese Academy of Sciences, Shanghai Artificial Intelligence Laboratory, Shanghai Jiao Tong University, and other institutions...
Doubao's Visual Understanding Model is an advanced AI model developed by Doubao, possessing visual recognition and reasoning capabilities. It boasts powerful visual localization capabilities, supporting bounding box localization for multiple targets, small targets, and general targets...
Doubao 3D Generated Models are 3D generated models launched by Doubao, belonging to the Doubao large model family. The models are based on the 3D-DiT architecture and can generate high-quality 3D modules. When used in conjunction with the Volcano Engine digital twin platform veOmniverse,...
MV-Adapter is a multi-view consistent image generation model developed by research teams from Beijing University of Aeronautics and Astronautics, VAST, and Shanghai Jiao Tong University. MV-Adapter can convert pre-trained text-to-image diffusion models into multi-view consistent images...
FACTS Grounding is a benchmark developed by Google DeepMind to evaluate the capabilities of large language models (LLMs). It measures the model's ability to generate factually accurate text without fabricated information based on a given context. FACTS Grounding...
MarkItDown is a versatile open-source document processing tool from Microsoft that can convert various file formats, including PDF, PPT, Word, Excel, images, audio, and HTML, into Markdown format. It supports OCR text recognition, speech-to-text conversion, and more.
EMMA-X is an embodied multimodal action model with 7 billion parameters developed by the Singapore University of Technology and Design. It was created by fine-tuning OpenVLA on evidenced chain-of-thought (CoT) inference data. EMMA-X incorporates hierarchical embodied datasets...
WeaveFox is an AI-powered front-end intelligent development platform launched by Ant Group, providing developers and creators with brand-new productivity tools. Its core function is to quickly convert design drafts into high-quality front-end code, supporting various design documents...
What is UniReal? UniReal is a framework jointly developed by the University of Hong Kong and Adobe Research, focusing on enabling various image generation and editing tasks. Based on simulating real-world dynamics, the framework can handle image processing within a single model...
X-AnyLabeling is an image annotation software that integrates multiple deep learning algorithms, focusing on improving annotation efficiency and accuracy. X-AnyLabeling supports diverse annotation styles for images and videos, adapts to various AI training scenarios, and provides...
Explorer is a generative world model developed by Odyssey that can transform any image into a detailed 3D world. The Explorer model excels at generating realistic worlds and supports dynamic effects. Explorer is based on Gaussian splashing...
Gemini 2.0 Flash Thinking is Google's latest reasoning-enhanced AI model, designed for efficient reasoning and interpretability in complex problems. It has achieved outstanding performance on the Chatbot Arena leaderboard, surpassing its predecessor...
Genesis is an open-source generative physics engine jointly developed by research institutions such as Carnegie Mellon University, the University of Maryland, Stanford University, and MIT. It can simulate everything in the world. Genesis can be described in simple language and is fast...
AniDoc is a simplified 2D animation coloring AI model jointly developed by the Hong Kong University of Science and Technology, Ant Group, Nanjing University, Zhejiang University, and the University of Hong Kong. Based on a video diffusion model, it automatically converts sketch sequences into color animations, following a reference...
ElevenLabs Flash is a low-latency speech synthesis model from ElevenLabs, designed for fast conversational AI. ElevenLabs Flash comes in two versions: Flash v2 only supports English, while Flash v2.5 supports 32 languages...
OpenAI's o3 model is a next-generation inference model following o1. It's OpenAI's first model to integrate image reasoning into thought processes, allowing users to directly consider images within their thought processes. Users can upload blurry, inverted, or low-quality images...
StyleStudio is a text-driven style transfer model jointly developed by Westlake University AI Lab, Fudan University, Nanyang Technological University, and Hong Kong University of Science and Technology (Guangzhou). It can integrate the style of a reference image with the content of text prompts...
RWKV-7 is the latest large-scale model architecture version in the RWKV series, surpassing traditional attention and linear attention paradigms. It boasts more flexible state evolution capabilities and can solve problems that attention cannot address with the same computational power...
PromptWizard is an automated suggestion optimization framework from Microsoft that improves the performance of large language models (LLMs) on specific tasks. Based on self-evolution and self-adaptation mechanisms, PromptWizard uses feedback-driven criticism and...
INFP is an audio-driven head generation framework designed specifically for two-person dialogue interaction. It automatically switches roles guided by the dialogue audio, eliminating the need for manual role assignment and switching. INFP consists of two phases: action-based head generation...
VisionFM is a multimodal, multi-task vision foundational model designed specifically for general ophthalmic artificial intelligence. It was pre-trained on 3.4 million ophthalmic images from 560,457 individuals, covering a wide range of ophthalmic diseases...