Automatic Extrinsic Calibration Method for LiDAR and Camera Sensor Setups. ROS Package.

Building a neural network and Transformer from scratch in C++, including tensors, backpropagation, optimization, attention, and language modeling.

Distributed LLM inference on Kubernetes with KubeRay and Ray Serve.

EN-Beta TTS evaluation, WER/DNSMOS preference data and LoRA DPO/GRPO alignment; based on VyvoTTS

B200 Attention from Scratch: understand one of the most complex GPU kernels on the latest hardware

Build, deploy, and scale a production-grade OCR pipeline using Rust, vLLM, Redis, KEDA, and Kubernetes.

PyTorch implementation of imitation learning policies for robotic manipulation: MLP, Transformer, Action Chunking, and Flow Matching — with pretrained checkpoints.

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

HKU-Dataset for Event-based VO/VIO/SLAM

A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.

LFM2.5 Audio inference with CUDA graphs and fast-mimi

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C infe…

[TRO 2022] Observability-Aware Intrinsic and Extrinsic Calibration of LiDAR-IMU Systems

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

GPS-denied drone navigation layer: optical flow + offline map geo-match + EKF → MAVLink (sim-validated).

Anthropic's original performance take-home, now open for you to try!

Code for "Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization"

[TRO 2025] AirVO upgrades to AirSLAM

A modular graph-based Retrieval-Augmented Generation (RAG) system

A RL framework for Crystal Structure Generation using GRPO

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

MLOps for DevOps Engineers - A hands-on, project-based guide to Machine Learning Operations

(ICCV2025) Learning-based Event-Inertial Odometry

If you want to become good at AI engineering & system design, join this newsletter 👇

Agent behavior clone for browser using, targeting general GUI using and distributed trajectory collecting.

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).