📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

VLA-0: Building State-of-the-Art VLAs with Zero Modification

Depth Anything 3

Official implementation of "Understanding multi-view transformers" (ICCV 2025 E2E3D Workshop)

Official Implementation of Driv3R

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

PanSt3R: Multi-view Consistent Panoptic Segmentation (official code)

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

[NeurIPS 2025 Spotlight] Towards Understanding Camera Motions in Any Video

Rynn Robotics Context Protocol

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)

Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)

Tongyi Deep Research, the Leading Open-source Deep Research Agent

A unified inference and post-training framework for accelerated video generation.

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

🔥🔥🔥 ICLR 2025 Oral. Automating Agentic Workflow Generation.

OctoTools: An agentic framework with extensible tools for complex reasoning

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

not another coding agent, kode is agent cli for everything

[ICCV2025] Extrapolated Urban View Synthesis Benchmark

[T-PAMI 2025] DiffMVS & CasDiffMVS

XLeRobot: Practical Dual-Arm Mobile Home Robot for $660