Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

A feed-forward 3D foundation model for reconstructing scenes from streaming data

OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

SAM 3D Objects with Multi-view Images

Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

AI agents running research on single-GPU nanochat training automatically

[ICML'25] Official Implementation of "PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting"

Paper Survey for 3DGS SLAM

[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Self-reimplemented version of Long-LRM.

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

[CVPR2025] Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

G3Splat: Geometrically Consistent Generalizable Gaussian Splatting

[3DV 2026] Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

Multi-view Diffusion for 3D Generation

[NeurIPS 2024] Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images

Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]

[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

(IETIPR) Stroke-Seg: A Deep Learning-Based Framework for Chinese Stroke Segmentation

(MM 2025, Oral) GraphSplat: Sparse-View Generalizable 3D Gaussian Splatting is Worth Graph of Nodes

A GUI client for Windows, Linux and macOS, support Xray and sing-box and others

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)