This is the official repository of the paper "Towards Physically Executable 3D Gaussian for Embodied Navigation".

InteriorGS: 3D Gaussian Splatting Dataset of Semantically Labeled Indoor Scenes

[RSS 2026] Official code & data for "OmniNavBench: Beyond Isolation — A Unified Benchmark for General-Purpose Navigation"

NavSR: A Multi-Modal Navigation Dataset for Service Robot with Comprehensive Ground Truth

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

Tactile Sensing • Data Collection • IL/RL/VLA/WM • Manipulation • Simulation • Open Source

Masked Depth Modeling for Spatial Perception

The official implementation of InfiniteVGGT

Official implementation of [AstraNav-World: World Model for Foresight Control and Consistency]

[CVPR2025] Prior Does Matter: Visual Navigation via Denoising Diffusion Brdige Models

[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[ICRA 2026] Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"

[ICCV2025] LONG3R: Long Sequence Streaming 3D Reconstruction

[RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

gradslam is an open source differentiable dense SLAM library for PyTorch

Gemini is a modern LaTex beamerposter theme 🖼

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Nano vLLM

[ICLR 2026] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces

[CVPR 2026] Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Official Implementation for Inference-time Scaling of Diffusion Models through Classical Search

Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching