Code for the Fractured Entangled Representation Hypothesis position paper!

Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.

Code for the deep neural network modeling of a large-scale fMRI dataset.

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Sparse Linear Concept Embeddings

Pretrained decoders for intracortical BCI.

Large Concept Models: Language modeling in a sentence representation space

Brain Imaging Analysis Kit

High-Resolution Image Synthesis with Latent Diffusion Models

Starter code for the BOLDMoments fMRI video dataset

PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.

Make-An-Audio-3: Transforming Text/Video into Audio via Flow-based Large Diffusion Transformers

Decode Neural signal as Speech

Language Generation from Brain Recordings

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

Simple image captioning model

Code behind Arxiv Papers

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model

Inference code for Llama models