AutoTrain (AutoTrain Advanced) is an open-source, no-code platform from Hugging Face that simplifies the training process for state-of-the-art models. It allows users to create, fine-tune, and deploy their own AI models without writing code...
CAMPHOR is a small language model (SLM) multi-agent framework developed by Apple, designed to improve privacy and responsiveness on mobile devices. The framework is based on processing multiple user inputs locally on the device and performing personalized contextual inference...
ACE (All-round Creator and Editor) is an all-around image generation and editing model based on diffusion transform, developed by Tongyi Lab of Alibaba Group. ACE introduces Long Context Conditional Units (LCUs) and a unified conditional grid...
ViewExtrapolator is a novel perspective extrapolation method jointly developed by research teams from Nanyang Technological University and UCAS. Based on the generation prior of Stable Video Diffusion (SVD), it synthesizes views far beyond the training view...
OpenScholar is a retrieval-enhanced language model (LM) jointly developed by the University of Washington and the Allen Institute for AI. It helps scientists answer questions by retrieving and synthesizing relevant papers from scientific literature. The system uses large-scale scientific...
SmolVLM is a lightweight visual language model from Hugging Face, designed specifically for on-device inference. With 2 billion parameters, it achieves high memory efficiency and fast processing speed. SmolVLM offers three versions to meet different needs...
OneDiffusion, a multi-functional large-scale diffusion model launched by AI2, seamlessly supports bidirectional image synthesis and understanding, covering various tasks such as text-to-image generation, conditional image generation, and image understanding. It is based on combining all conditions and objectives...
LongAlign is an improved text-to-image (T2I) diffusion model developed by a research team at the University of Hong Kong, which enhances the alignment accuracy of long text inputs. LongAlign uses segment-level coding techniques to segment long texts, adapting to different encoding methods...
ebook2audiobookXTTS is an open-source AI tool that converts ebooks into audiobooks. It supports various ebook formats, such as epub, pdf, and mobi, and uses Coqui XTTS technology to achieve high-quality audio...
Optima is a framework developed by Tsinghua University for optimizing multi-agent systems (MAS) based on large language models (LLMs). Based on an iterative generation, ranking, selection, and training paradigm, it significantly improves communication efficiency and task performance...
MuCodec is an ultra-low bitrate music codec jointly developed by researchers from Tsinghua University Shenzhen International Graduate School, Tencent AI Lab, and the Chinese University of Hong Kong. It enables efficient music compression and high-fidelity reconstruction. MuCodec...
Find3D is a 3D part segmentation model developed by Caltech, capable of segmenting any part of any object based on any text query. Find3D uses a powerful data engine to automatically generate training data from 3D assets on the internet...
Sketch2Lineart is an AI-powered drawing tool that transforms simple hand-drawn sketches into clear line drawings. It automatically generates sketch descriptions and draws line drawings based on them, supporting adjustments to details to suit different styles. Users...
Fancy123 is a 3D mesh generation technology developed by Huazhong University of Science and Technology and South China University of Technology. It generates high-quality 3D meshes from single images based on plug-and-play deformation technology. The method includes two enhancement modules and a back-projection operation...
Mooncake is a large-scale model inference architecture jointly open-sourced by Kimi from the Dark Side of the Moon, Tsinghua University, and other institutions. It employs a distributed architecture centered around KVCache, fully utilizing the unfilled space in the GPU cluster by separating the pre-filling and decoding clusters...
QwQ-32B-Preview (QwQ-32B) is an open-source AI inference model launched by Alibaba, demonstrating outstanding performance in mathematics and programming. QwQ-32B-Preview contains 32.5 billion parameters and can process hints of up to 32,000 tokens. In multiple...
InfiMM-WebMath-40B is a massively multimodal dataset jointly open-sourced by ByteDance and the Chinese Academy of Sciences. It aims to improve the mixed text and image reasoning capabilities of multimodal models in the field of mathematics. The dataset is sourced from Common Crawl...
SAM 2.1 (Segment Anything Model 2.1) is an advanced visual segmentation model developed by Meta (Facebook's parent company) for image and video processing. It is based on a simple Transformer architecture and streaming memory design...
Qwen2VL-Flux is a multimodal image generation model that combines Qwen2VL's visual language understanding with the FLUX framework to generate high-quality images based on text prompts and image references. The model supports multiple generation modes, including variant generation, ...
ShowUI is a visual-language-action model jointly developed by the Show Lab at the National University of Singapore and Microsoft, designed to improve the efficiency of graphical user interface (GUI) assistants. The model reduces computational costs based on UI-guided visual token selection...
NVLM is a cutting-edge multimodal large-scale language model (LLM) from NVIDIA, achieving performance comparable to top-tier proprietary models (such as GPT-4o) and open-access models (such as Llama 3-V 405B and InternVL 2) on vision-language tasks...
Promptriever is a novel retrieval model jointly developed by Johns Hopkins University and Samaya AI. It can accept natural language prompts like a language model, responding to users' search needs in an intuitive way. Promptriever...
LongLLaVA is a multimodal large-scale language model (MLLM) based on a hybrid architecture combining Mamba and Transformer modules. It can efficiently process large amounts of images, and is particularly adept at video understanding and high-resolution image analysis. LongLLaVA...
Devika is an open-source AI programming assistant that can understand and break down complex instructions. It gathers information using integrated AI search and web browsing capabilities, and then writes code to achieve its goals. Devika supports various AI models and possesses advanced planning and reasoning abilities...