ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

The official implementation of "DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos"

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

4D Radar Object Detection for Autonomous Driving in Various Weather Conditions

[CVPR2026] Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction

[CVPR 2026] This repository is the official implementation of MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

[CVPR 2026] OccAny: Generalized Unconstrained Urban 3D Occupancy. The first Unified Framework for Generalized 3D Occupancy Prediction. Supports SAM2/SAM3, MUSt3R & Depth Anything 3.

[CVPR 2026 Oral] VGGT Omega

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

[CVPR 2026] Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments

[ECCV 2026] OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

[CVPR'2026, Oral] FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)^N Diffusion Refinement

One click installation of Minkowski Engine, suitable for 50 series graphics cards, CUDA 12.8 version

[TRO 2026] Code for "Scalable Unseen Object 6-DoF Absolute Pose Estimation with Robotic Integration".

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

[CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

[NeurIPS'24 Spotlight] Is Your LiDAR Placement Optimized for 3D Scene Understanding?

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

[ICML'26] Official repository of Utonia: Toward One Encoder for All Point Clouds

[AAAI 2026] Official implementation of the paper ”SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features“

[CVPR2026] Zoo3D: Zero-Shot 3D Object Detection at Scene Level

Official repository for "AM-RADIO: Reduce All Domains Into One"

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

[WACV'24] TD3D: Top-Down Beats Bottom-Up in 3D Instance Segmentation

Depth Anything 3