laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
- 36k
- Python
- Apache-2.0
- 16 h ago
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.
ROS package to find a rigid-body transformation between a LiDAR and a camera for "LiDAR-Camera Calibration using 3D-3D Point correspondences"
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
A toolbox for target-less LiDAR-camera calibration [ROS1/ROS2]
[IROS2022] Robust Real-time LiDAR-inertial Initialization Method.
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
This repository is used for automatic calibration between high resolution LiDAR and camera in targetless scenes.
Full-color flat FDM printing with calibrated filament layer mixing. Reproduce image colors and tonal detail, fine-tune local recipes, and export slicer-ready 3MF files.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.
Awesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.
JevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.
Estimating pose using ArUCo Markers
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
Square-Root Robocentric Visual-Inertial Odometry with Online Spatiotemporal Calibration
🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.
[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
Read CO2 concentration from mh-z19 sensor on the Raspberry Pi & handle it. Detect Raspberry Pi model automatically and read the value from an appropriate serial device.
Reliability diagrams visualize whether a classifier model needs calibration
Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
Derivative-free parameter calibration and uncertainty quantification for expensive models using ensemble Kalman methods
Calibration procedure for the MPU9250's accelerometer, gyroscope, and magnetometer using Python and a Raspberry Pi Computer
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground
Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)
Text classification model, used with transformers.
Text classification model, used with strands-decider.
JEV & open-Jev answer verifiers, one identical test set
Runs in the browser on Hugging Face
Text classification model, used with strands-decider.
Text classification model, used with strands-decider.
Static JevBench snapshot for AI decision models
Runs in the browser on Hugging Face
Every forecast archived, every model graded
Runs in the browser on Hugging Face
One question, every public Strands decider, side by side
Runs in the browser on Hugging Face
Typed questions in, calibrated probabilities out
Runs in the browser on Hugging Face
Invert LLM hallucination into productive features
Runs in the browser on Hugging Face