SPRIGHT (SPatially RIGHT) is a large-scale visual-language dataset focusing on spatial relationships, jointly developed by Arizona State University, Intel Labs, Hugging Face, the University of Washington, and other institutions. It can solve...
LIGER is a hybrid retrieval model developed by Meta AI and other institutions, combining the advantages of generative retrieval and dense retrieval. LIGER uses a generative retrieval module to generate a finite set of candidate items, and then uses dense retrieval to rank and...
SeedVR is a diffusion transformer model developed by Nanyang Technological University and ByteDance, capable of achieving high-quality general-purpose video restoration. SeedVR is based on an introduced shift-window attention mechanism, employing a large (64×64) window and attention at the boundaries...
AutoDroid-V2 is a mobile GUI automation script agent developed by the Tsinghua University Artificial Intelligence Industry Research Institute. Based on Small Language Models (SLM), it improves the performance of GUI agents on devices through code generation technology. AutoDroid...
EnerVerse is the first 4D world model for robots developed by the Zhiyuan Robotics team. It guides robots to complete complex tasks by generating a future embodied space. The model employs an autoregressive diffusion model combined with a sparse memory mechanism (Spars...
Seer is an end-to-end operation model jointly developed by the Shanghai AI Lab, the School of Computer Science and Technology at Peking University, and the School of Software and Microelectronics at Peking University, achieving a high degree of coordination between robot vision prediction and action execution...
ArtCrafter is a text-to-image style transfer framework jointly developed by Tsinghua University, Pengcheng Laboratory, and Lenovo Research. Based on a diffusion model, it addresses the limitations of traditional methods in terms of style expression, content consistency, and output diversity...
Ingredients is a powerful framework based on combining multiple identity (ID) photos with a video diffusion Transformer for custom video creation. Ingredients enables highly customized video creation based on three core modules...
MultiBooth is a multi-concept image generation method developed by Tsinghua University Shenzhen International Graduate School, Meta, Hong Kong University of Science and Technology, and other institutions. It can generate images containing multiple user-specified concepts from text. MultiBooth will generate...
Aria-UI is a large-scale multimodal model designed for graphical user interface (GUI) localization tasks, jointly developed by the University of Hong Kong and Rhymes AI. Based on a purely visual approach, it does not rely on auxiliary inputs such as HTML or AXTree, and utilizes large-scale...
TransPixar is an advanced text-to-video generation method jointly open-sourced by the Chinese University of Hong Kong, Adobe Research, the Hong Kong University of Science and Technology, and SmartMoore. It extends pre-trained RGB video models to generate RGBA videos that include transparency information...
STAR is an innovative real-world video super-resolution (VSR) framework jointly developed by Nanjing University, ByteDance, and Southwest University. It can generate high-resolution (HR) videos from low-resolution (LR) videos while preserving detail...
Wanxiang 2.1 is an upgraded version of Tongyi Wanxiang launched by Alibaba. Based on its self-developed high-efficiency VAE and DiT architecture, it enhances spatiotemporal context modeling capabilities, supports efficient encoding and decoding of unlimited-length 1080P videos, and for the first time achieves Chinese text-to-video generation...
Spark Minutes is an audio and video processing platform launched by iFlytek, integrating transcription, summarization, translation, and analysis. It is widely used in general meetings, interviews, sales meetings, training sessions, and other scenarios. It helps individuals efficiently summarize key meeting content...
Hallo3, jointly developed by Fudan University and Baidu, is a portrait image animation technology based on Diffusion Transformer Networks (DTNs) that can generate highly dynamic and realistic videos. Hallo3 is based on...
rStar-Math is an innovative research project launched by Microsoft Research Asia. Based on Monte Carlo Tree Search (MCTS) driven deep thinking, it enables small language models (SLMs) to reach or even surpass OpenAI's large-scale mathematical reasoning capabilities...
SPAR3D, developed by Stability AI and the University of Illinois at Urbana-Champaign, is an advanced method for generating 3D models from a single image. It efficiently reconstructs high-quality 3D objects from a single image. SPAR3D is based on a two-stage design, the first stage...
Search-o1 is an innovative framework developed by Renmin University of China and Tsinghua University to enhance the reasoning capabilities of large-scale reasoning models (LRMs) when facing complex problems. It is based on the Integrated Agent Retrieval Enhanced Generation (RAG) mechanism and Reason...
ConceptMaster is an innovative framework for multi-concept video customization. It generates high-quality, concept-consistent custom videos on a diffusion Transformer model without requiring tuning during testing. The framework learns decoupled...
SenseNova, a multimodal large-scale model, was officially launched by SenseTime on January 10, 2025. The model achieves native fusion modality, significantly improving both deep reasoning and multimodal information processing capabilities...
Agent Laboratory, a collaborative research framework developed by AMD and Johns Hopkins University, is based on Large Language Models (LLMs) and aims to accelerate scientific discovery, reduce costs, and improve research quality. Agent Laboratory accepts...
XinYanYiMa is a company specializing in AI programming application development, founded by Ming Chaoping, founder of Noisee, an overseas product of the company "The Dark Side of the Moon". The company's full name is Shenzhen XinYanYiMa Technology Co., Ltd., established on September 23, 2024, and located in Shenzhen, Guangdong Province...
PPTAgent is an innovative framework developed by the Chinese Information Processing Laboratory of the Institute of Software, Chinese Academy of Sciences. Based on a two-stage editing method that mimics human workflows, it automatically generates high-quality presentations from documents. PPTAgent analyzes...
HoloDrive is a holistic 2D-3D multimodal street scene generation framework for autonomous driving, proposed by SenseTime and the Shanghai Artificial Intelligence Laboratory, among other institutions. The framework jointly generates camera images and LiDAR point clouds, filling gaps in 2D scene generation for autonomous driving...