VideoPainter is a video restoration and editing framework developed by institutions such as the Chinese University of Hong Kong, Tencent ARC Lab, the University of Tokyo, and the University of Macau. It is specifically designed for processing video content of any length. VideoPainter is based on a two-branch architecture...
TrajectoryCrafter, developed by Tencent PCG ARC Lab and the Chinese University of Hong Kong, is a camera trajectory redirection method for monocular video. It allows for free adjustment of the camera position and angle in post-production, easily altering the video's trajectory...
LanPaint is a high-quality image inpainting tool designed for Stable Diffusion models, achieving accurate image inpainting and replacement without additional training. LanPaint optimizes inpainting results through multi-round iterative inference, supporting seamless and...
START (Self-Taught Reasoner with Tools) is a new tool-enhanced reasoning model launched by Alibaba Group and the University of Science and Technology of China. It combines external tools (such as Python code executors) to improve the performance of large-scale reasoning systems...
SeedFoley is an end-to-end video audio generation model developed by ByteDance's Doubao Big Model Speech Team, providing intelligent audio generation services for video creation. By integrating spatiotemporal video features with a diffusion generation model, it achieves audio effects and...
R1-Omni is a multimodal language model based on reinforcement learning (RLVR) launched by Alibaba Tongyi, focusing on emotion recognition tasks. By combining visual and audio information, it can clearly explain the reasoning process of emotion recognition, demonstrating...
The DeepSeek Toolbox is an official DeepSeek GitHub project that demonstrates how to integrate the DeepSeek API into various popular software. The project lists a range of tools and applications that support DeepSeek, covering everything from...
Anus (Autonomous Networked Utility System) is an open-source autonomous intelligent agent project derived from Manus, replicating some of Manus's functionalities. Anus supports natural language command execution, multi-agent collaboration, network interaction, etc.
MeshPad is an interactive, artistic mesh generation and editing tool based on sketch input. It can quickly convert simple 2D sketches into high-quality 3D mesh models and supports real-time editing. Users can add or delete lines on the sketch...
PlanGEN is a multi-agent framework developed by Google Research that solves complex planning and reasoning problems through multi-agent collaboration, constraint guidance, and adaptive algorithmic selection. It comprises three key components: constrained agents, validation agents, and...
MV-MATH is a new benchmark dataset proposed by the Institute of Automation, Chinese Academy of Sciences, to evaluate the mathematical reasoning capabilities of multimodal large language models (MLLMs) in multi-visual scenes. The dataset contains 2009 high-quality mathematical problems, each...
MHA2MLA is a data-efficient fine-tuning method jointly developed by Fudan University, East China Normal University, Shanghai AI Lab, and other institutions. It optimizes any Transformer-based algorithm by incorporating DeepSeek's multi-head latent attention (MLA) mechanism...
GaussianAnything is a 3D generative framework developed by Nanyang Technological University's S-Lab in collaboration with the Shanghai AI Lab and other institutions. GaussianAnything is based on an interactive point cloud structured latent space and a cascaded flow matching model...
VACE (Video Creation and Editing) is a one-stop video generation and editing framework launched by Alibaba Tongyi Labs. It integrates various video tasks (such as reference video generation, video-to-video editing, masking, etc.)...
Seedream 2.0 is a native Chinese-English bilingual image generation model developed by ByteDance's Doubao Big Model team, addressing the shortcomings of existing models in text rendering and cultural understanding. The model utilizes a self-developed bilingual big language model (LL...
PP-DocBee is a multimodal large-scale model developed by the Baidu PaddlePaddle team, focusing on document image understanding. Based on the ViT+MLP+LLM architecture, it has powerful Chinese document parsing capabilities and can efficiently process text, tables, etc.
BEHAVIOR Robot Suite (BRS) is a framework developed by Fei-Fei Li's team at Stanford University for learning full-body motor skills to complete everyday household tasks. Based on the analysis of household activities, it identifies the key capabilities that robots need to possess, including...
MM-StoryAgent is an open-source, multimodal, multi-agent framework jointly developed by the X-LANCE Lab at Shanghai Jiao Tong University and Alibaba Group. It's used to generate immersive audio storybook videos. Based on a large-scale language model...
Deep Research Web UI is an open-source AI research assistant tool that helps users conduct in-depth research efficiently. Through AI-driven iterative search, it progressively delves into a specified topic, visualizing the research process in a tree structure...
Gemma 3 is Google's latest open-source artificial intelligence model, designed for developers to support AI application development across multiple devices. It supports over 35 languages and has the ability to analyze text, images, and short videos...
Reka Flash 3 is an open-source inference model from Reka AI, boasting 2.1 billion parameters. It supports multimodal input, including text, images, video, and audio, and can handle context lengths of up to 32k tokens, making it suitable for...
Ziyue Translation 2.0 is the latest large-scale translation model launched by NetEase Youdao. The model has undergone systematic upgrades in three key dimensions: data, algorithms, and evaluation, achieving a qualitative leap in translation quality, efficiency, and robustness. At the data level...
Motion Anything is a multimodal motion generation framework developed by institutions such as the Australian National University, the University of Sydney, Tencent, McGill University, and JD.com. It generates high-quality, controllable motion based on text, music, or a combination of both...
AI-Researcher is an open-source automated scientific research tool developed by the Data Science Lab at the University of Hong Kong. Based on a Large Language Model (LLM) agent, it automates the entire research process from idea to publication. AI-Researcher...