browser-inference

Lightweight interactive medical image segmentation via in-context learning. Single dense 2D prompt + interactions → full 3D mask. Runs in-browser.

Convert any ML model (ONNX, GGUF, TFLite) into a standalone browser project with hand-written WGSL compute shaders. Zero dependencies, zero frameworks.

How small can English get? 8 tiny language models (fp16 vs ternary) trained from scratch on TinyStories, judged by a frozen LLM judge, and running live in your browser.

qwen3-asr.cpp compiled to WebAssembly for browser-side speech recognition.

Boundary Detection for Web Applications: A Lightweight Browser-Based Approach

Browser-side proof of qwen3-asr.wasm and deltanet.wasm. Runs locally in the browser as a voice round-trip.

纯浏览器端实时 CV 推理与可视化：人脸检测/478点关键点、姿态33点、物体检测、图像分类、人脸识别 1:N，全部在浏览器内推理

A JavaScript-based web application demonstrating real-time AI inference in the browser using TensorFlow.js.

Fashion-MNIST training, distillation and deployment experiments on PYNQ-Z1, with ONNX checkpoints and a browser demo.

Needle 2 running on pure Javascript, without the need of WebAssembly.

Run AI models in your browser — transformers.js on WebGPU/WASM. Free, unlimited, private: no API keys, no server, no rate limits.

llama.cpp compiled to WebAssembly for browser-side LLM inference. DeltaNet/SSM enabled.

基于 ONNX Runtime Web 的 PaddleDetection 浏览器目标检测 SDK，支持图片、摄像头和视频帧

End-to-end ML web app that predicts student performance with a Python-trained Linear Regression model exported to JavaScript and used directly in Vue