HART (Hybrid Autoregressive Transformer) is an autoregressive visual generative model developed by a research team at MIT. It can directly generate high-resolution images of 1024×1024 pixels, with quality comparable to diffusion models. H...
WebDreamer is a model-planning network agent developed by the Ohio State University and Orby AI research team. It utilizes large language models (LLMs), particularly GPT-4o, and serves as an interactive result on a world model prediction website...
Kandinsky-3 is a text-to-image (T2I) generation framework based on a latent diffusion model, standing out in the field of image synthesis for its high quality and realism. Kandinsky-3 can adapt to a variety of image generation tasks, including text-guided...
CAVIA is a multi-view video generation framework jointly developed by Apple, the University of Texas at Austin, and Google. It can transform a single input image into multiple spatiotemporally consistent video sequences. The framework is based on introducing viewpoint integrated attention...
Flex3D is an innovative two-stage 3D generation framework developed by Meta's GenAI team and a research team at Oxford University. It can generate high-quality 3D images from text, single images, or sparse view images based on any number of high-quality input views...
EvolveDirector is an innovative framework jointly launched by Alibaba and Nanyang Technological University. It trains a high-performance text-to-image generation model using publicly available resources and API interfaces for high-level models. The framework is based on existing high-level models...
MCP (Model Context Protocol) is an open protocol developed by Anthropic that enables seamless integration between large language model (LLM) applications and external data sources and tools. Based on...
LazyGraphRAG is a graph augmentation-generative augmented retrieval (RAG) framework developed by Microsoft Research, and is an iteration of GraphRAG. LazyGraphRAG significantly reduces data indexing costs, to 0.1% of GraphRAG, while also using...
LEOPARD is a visual language model developed by Tencent AI Lab in Seattle, specifically designed for understanding and processing multi-image tasks containing large amounts of text. LEOPARD is based on two main technological innovations: firstly, it incorporates approximately one million specially designed...
InternThinker, developed by the Shanghai Artificial Intelligence Laboratory, is a powerful reasoning model capable of autonomously generating high-intelligence-density data and meta-action thinking. Based on long-term thinking capabilities and self-reflection and correction mechanisms, it excels in mathematics, coding, and more...
Pangea is a multilingual, multimodal, large-scale language model (LLM) developed by a team at Carnegie Mellon University. It aims to improve the coverage of global language and cultural diversity. The model includes a diverse dataset of 6 million instructions and supports 39 languages...
MobA (Mobile Agent) is a novel mobile intelligent agent developed by a team at Shanghai Jiao Tong University. It enhances the automated task execution capabilities of mobile devices based on multimodal large language models (MLLMs). MobA employs a two-tier architecture: a high-level...
Frames is Runway's latest AI image generation model, achieving significant advancements in style control and visual fidelity. Frames maintains stylistic consistency, supports broad creative exploration, establishes a specific look for projects, and...
SlideChat, developed by the Shanghai AI Lab, Xiamen University, East China Normal University, and other institutions, is the first visual language assistant capable of understanding gigapixel-level full-slice images. SlideChat can generate detailed descriptions of full-slice images...
Fugatto is an audio synthesis and conversion model developed by NVIDIA, short for 'Foundational Generative Audio Transformer Opus 1'. The model can generate audio or video based on text prompts, receiving...
LongRAG is a robust retrieval enhancement generation (RAG) framework for long text question answering (LCQA), developed by a research team from Tsinghua University, the Chinese Academy of Sciences, and Zhipu. It is based on a hybrid retrieval system, an LLM-enhanced information extractor, and...
Illustrious is an open-source text-to-image animation generation model developed by Onoma AI Research. Based on key methods such as optimizing batch size, dropout control, training image resolution, and multi-level headings, it achieves high...
aisuite is an open-source Python library released by Andrew Ng, designed to provide a unified interface for calling multiple large language model (LLM) services. It supports services including OpenAI, Anthropic, and Azure...
XGrammar is an open-source software library developed by Tianqi Chen's team. It provides efficient, flexible, and portable structured data generation capabilities for large language models (LLMs). Based on context-free grammar (CFG) definition structures, it supports...
Edify 3D is an advanced 3D asset generation solution from NVIDIA that can quickly synthesize high-quality 3D models from text prompts or reference images. Edify 3D can generate models with detailed geometry, clear topology, etc., in just two minutes...
SongCreator is an AI music generation model developed by Tsinghua University Shenzhen International Graduate School, the Chinese University of Hong Kong, and other institutions. It can generate complete songs including vocals and accompaniment from lyrics.
Teacher2Task is a multi-teacher learning framework developed by Google that introduces teacher-specific input tags and reimagines the training process, eliminating the need for manually aggregating heuristics. The framework does not rely on aggregating tags; it directly aggregates training data...
DynaSaur is a large language model (LLM) agent framework from Adobe Research that breaks through the limitations of traditional LLM agent systems that are restricted by predefined action sets. The framework supports dynamic creation and composition of agent actions, based on generative...
Takin AudioLLM is a series of high-quality zero-shot speech generation models developed by the Everest team at Himalaya FM, including Takin TTS, Takin VC, and Takin Morphing. The models utilize state-of-the-art large-scale language modeling techniques...