Flex3D features a two-stage process that generates high-quality 3D assets from a single image or text prompt. This technology represents the latest advancements in the field of 3D reconstruction, significantly improving the efficiency and quality of 3D content generation. Flex3D is developed with support from Meta, and the team has a strong background in 3D reconstruction and computer vision.

This GitHub repository contains training and inference code to replicate our winning solution in the AI Mathematics Olympic (AIMO) Progress Prize 1. Our solution consists of four main parts: a recipe for fine-tuning DeepSeekMath-Base 7B for use in solving math problems using Tool Integrated Reasoning (TIR); two high-quality datasets of about 10 million math questions and solutions; an algorithm for generating solution candidates with coding execution feedback (SC-TIR); and four carefully selected validation sets from AMC, AIME, and MATH to guide model selection and avoid overfitting the public leaderboard.

EgoGaussian is an advanced 3D scene reconstruction and dynamic object tracking technology. It can reconstruct 3D scenes and track the movement of objects dynamically using only RGB first-person perspective input. This technology leverages the unique discrete properties of Gaussian scattering to segment dynamic interactions from the background. Through a piece-wise online learning process, it utilizes the dynamic characteristics of human activities to reconstruct the evolution of the scene in chronological order and track the movement of rigid objects. EgoGaussian outperforms previous NeRF and dynamic Gaussian methods in wild video challenges and delivers exceptional quality in reconstructed models.

GaussianCube is an innovative 3D radiance representation method that significantly advances 3D generative modeling through its structured and explicit representation. This technology achieves high-precision fitting by utilizing a novel density-constrained Gaussian fitting algorithm and optimal transport methods, rearranging Gaussian functions onto a predefined voxel grid. Compared to traditional implicit feature decoders or spatially unstructured radiance representations, GaussianCube boasts fewer parameters and higher quality, making 3D generative modeling more accessible.

Developed by a team from Tsinghua University, Unique3D is a technology that can generate high-fidelity textured 3D mesh models from a single image. This technology has significant implications for image processing and 3D modeling, enabling users to quickly convert 2D images into 3D models, providing powerful technical support for game development, animation production, and virtual reality.

HippoRAG is a novel Retriever-Augmented Generation (RAG) framework inspired by human long-term memory, enabling Large Language Models (LLMs) to continuously integrate knowledge across external documents. Experiments demonstrate that HippoRAG can provide the capabilities of RAG systems, typically requiring expensive and high-latency iterative LLM pipelines, at a lower computational cost.

PhysDreamer is a method based on physics, which endows静态 3D objects with interactive dynamics by utilizing the object dynamics prior learned from video generation models. This approach allows for the simulation of realistic responses to novel interactions (such as external forces or agent operations) in the absence of real physical property data of objects. PhysDreamer promotes the development of more engaging and realistic virtual experiences through user studies to evaluate the realism of synthetic interactions.

Interactive3D is an advanced 3D generation model that provides users with precise control capabilities through interactive design. The model utilizes a two-stage cascading structure, employing different 3D representation methods, allowing users to modify and guide at any intermediate step of the generation process. Its significance lies in the ability to achieve fine control over the 3D model generation process, thereby creating high-quality 3D models that meet specific requirements.

MakerLab is an online platform offering a variety of 3D model design tools, including vase generators and sign customizers. Users can quickly and easily create personalized 3D models based on their own needs. The platform supports the use of templates for creation and provides an innovation playground where users can experiment with cutting-edge technologies like AI scanners. MakerLab is operated by BamBam Lab and aims to provide a space for users to freely create and share their ideas. Currently, the platform offers both free and paid services for users to choose according to their needs.

The Intel? Core? Ultra 200 series desktop processors are the first AI PC processors designed for the desktop platform, delivering exceptional gaming experiences and industry-leading computing performance while significantly reducing power consumption. These processors feature up to 8 next-generation performance cores (P-cores) and up to 16 next-generation efficiency cores (E-cores), resulting in up to a 14% performance improvement in multi-threaded workloads compared to the previous generation. They are also the first desktop processors equipped with a neural processing unit (NPU) for enthusiasts, and include built-in Xe GPU technology, supporting advanced media features.

Flex3D features a two-stage process that generates high-quality 3D assets from a single image or text prompt. This technology represents the latest advancements in the field of 3D reconstruction, significantly improving the efficiency and quality of 3D content generation. Flex3D is developed with support from Meta, and the team has a strong background in 3D reconstruction and computer vision.

The Intel? Gaudi? 3 AI Accelerator is a high-performance artificial intelligence accelerator launched by Intel, built on the efficient Intel? Gaudi? platform. It boasts outstanding MLPerf benchmark performance and is designed to handle demanding training and inference tasks. The accelerator supports AI applications such as large language models, multimodal models, and enterprise RAG in data centers or the cloud, operating on your existing Ethernet infrastructure. Whether you need a single accelerator or thousands, Intel Gaudi 3 can play a crucial role in your AI success.

This GitHub repository contains training and inference code to replicate our winning solution in the AI Mathematics Olympic (AIMO) Progress Prize 1. Our solution consists of four main parts: a recipe for fine-tuning DeepSeekMath-Base 7B for use in solving math problems using Tool Integrated Reasoning (TIR); two high-quality datasets of about 10 million math questions and solutions; an algorithm for generating solution candidates with coding execution feedback (SC-TIR); and four carefully selected validation sets from AMC, AIME, and MATH to guide model selection and avoid overfitting the public leaderboard.

EgoGaussian is an advanced 3D scene reconstruction and dynamic object tracking technology. It can reconstruct 3D scenes and track the movement of objects dynamically using only RGB first-person perspective input. This technology leverages the unique discrete properties of Gaussian scattering to segment dynamic interactions from the background. Through a piece-wise online learning process, it utilizes the dynamic characteristics of human activities to reconstruct the evolution of the scene in chronological order and track the movement of rigid objects. EgoGaussian outperforms previous NeRF and dynamic Gaussian methods in wild video challenges and delivers exceptional quality in reconstructed models.

GaussianCube is an innovative 3D radiance representation method that significantly advances 3D generative modeling through its structured and explicit representation. This technology achieves high-precision fitting by utilizing a novel density-constrained Gaussian fitting algorithm and optimal transport methods, rearranging Gaussian functions onto a predefined voxel grid. Compared to traditional implicit feature decoders or spatially unstructured radiance representations, GaussianCube boasts fewer parameters and higher quality, making 3D generative modeling more accessible.

Developed by a team from Tsinghua University, Unique3D is a technology that can generate high-fidelity textured 3D mesh models from a single image. This technology has significant implications for image processing and 3D modeling, enabling users to quickly convert 2D images into 3D models, providing powerful technical support for game development, animation production, and virtual reality.

HippoRAG is a novel Retriever-Augmented Generation (RAG) framework inspired by human long-term memory, enabling Large Language Models (LLMs) to continuously integrate knowledge across external documents. Experiments demonstrate that HippoRAG can provide the capabilities of RAG systems, typically requiring expensive and high-latency iterative LLM pipelines, at a lower computational cost.