HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
Supercharge your command line with LLMs and get shell scripting assistance in Fish. 💪
TorchANI 2.0 is an open-source library that supports training, development, and research of ANI-style neural network interatomic potentials. It was originally developed and is currently maintained by the Roitberg group.
Skills and eval rubrics for K-12 teachers, co-developed with Learning Commons
Our inference and training framework to run on the Cosmos Models
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
Efficient and easy multi-instance LLM serving
Deliver safe & effective language models
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
A Comprehensive Framework for Visual SLAM Systems and Datasets
Computational Pathology Toolbox developed by TIA Centre, University of Warwick.
[ICLR 2026] LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
A deterministic text-based fishing mini-game for AI to play — single file, zero dependencies, let your AI companion go fishing.
Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️
Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).
Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.
Module for statistical learning, with a particular emphasis on time-dependent modelling
[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.