Stars
Application of modeling of transcranial ultrasound for neuromodulation applications
A modelling and optimisation framework for medical ultrasound
A Python interface to k-Wave GPU accelerated binaries
A JAX-based research framework for differentiable and parallelizable acoustic simulations, on CPU, GPUs and TPUs
MUG500+: Database of 500 high-resolution healthy human skulls and 29 craniotomy skulls and implants
Official implementation of paper "Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments"
The PyTorch-based audio source separation toolkit for researchers
Official Implementation of TSELM: Target speaker extraction using discrete tokens and language models
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
as FreeEEG32 plus alpha1.5 test passed, FreeEEG32 project changed to beta version
Official Repo for Paper: "Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios"
Files related to the ultracortex, the OpenBCI 3D-printable EEG headset currently under development
A viewer for OCP based Code-CAD (CadQuery, build123d) integrated into VS Code
🚀 Text2Grad: Converting natural language feedback into gradient signals for precise model optimization. Revolutionizing RLHF with span-level rewards and targeted improvements across code generation…
A Reproduction of GDM's Nested Learning Paper
Diagram tensors from torch, jax, tensorflow, numpy, etc., for understanding and debugging
A deep learning framework built on an autograd engine with high level abstractions and low level control.
A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine …
A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explor…
🚀 Efficient implementations of state-of-the-art linear attention models
slime is an LLM post-training framework for RL Scaling.