Baihan Lin (doerlbh)

doerlbh

Geek Repo

Company:Columbia University

Location:New York, NY

Home Page:https://www.baihan.org

Twitter:@doerlbh

Github PK Tool:Github PK Tool


Organizations
Cell-3
datacomma
doer3Dprint
doerbeta
doerblog
doercalendar
doerlife
KnowledgeAI
kriegeskorte-lab
linlab
neuroinference
rsagroup
scienceontheway
xneuro

Baihan Lin's starred repositories

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Language:PythonLicense:MITStargazers:64669Issues:537Issues:0

llama_index

LlamaIndex is a data framework for your LLM applications

Language:PythonLicense:MITStargazers:33627Issues:239Issues:4440

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonLicense:Apache-2.0Stargazers:20698Issues:177Issues:375

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookLicense:MITStargazers:18229Issues:117Issues:503

gpt4-pdf-chatbot-langchain

GPT4 & LangChain Chatbot for large PDF docs

chat-ui

Open source codebase powering the HuggingChat app

Language:TypeScriptLicense:Apache-2.0Stargazers:6816Issues:77Issues:501

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Language:PythonLicense:MITStargazers:6364Issues:60Issues:78

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Language:PythonLicense:MITStargazers:4222Issues:31Issues:103

LLaVA-Med

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Language:PythonLicense:NOASSERTIONStargazers:1299Issues:25Issues:72

rag-demystified

An LLM-powered advanced RAG pipeline built from scratch

Language:PythonLicense:Apache-2.0Stargazers:760Issues:5Issues:6

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

Language:Jupyter NotebookLicense:MITStargazers:639Issues:29Issues:35

AlignLLMHumanSurvey

Aligning Large Language Models with Human: A Survey

llama4micro

A "large" language model running on a microcontroller

Language:C++License:MITStargazers:461Issues:6Issues:7

machine-learning-for-the-web

Repository for the "Machine Learning for the Web" class at ITP, NYU

Language:JavaScriptLicense:MITStargazers:404Issues:19Issues:4

brainmagick

Training and evaluation pipeline for MEG and EEG brain signal encoding and decoding using deep learning. Code for our paper "Decoding speech perception from non-invasive brain recordings" published in Nature Machine Intelligence, 2023.

Language:PythonLicense:NOASSERTIONStargazers:388Issues:15Issues:4

tree-diffusion

Diffusion on syntax trees for program synthesis

Language:PythonLicense:MITStargazers:388Issues:4Issues:7

awesome-ml-demos

Curated list of interactive ML demos

LLaVA-Interactive-Demo

LLaVA-Interactive-Demo

Language:PythonLicense:Apache-2.0Stargazers:332Issues:15Issues:8

fMRI-reconstruction-NSD

fMRI-to-image reconstruction on the NSD dataset.

Language:Jupyter NotebookLicense:MITStargazers:273Issues:4Issues:36

world-models

Extracting spatial and temporal world models from LLMs

Language:Jupyter NotebookLicense:MITStargazers:228Issues:6Issues:4

SCAN

Simple language-driven navigation tasks for studying compositional learning

Language:Jupyter NotebookStargazers:155Issues:7Issues:11

clin-summ

Clinical text summarization by adapting large language models

Language:PythonLicense:MITStargazers:57Issues:4Issues:4

PsychoBench

Benchmarking LLMs' Psychological Portrayal

Language:PythonLicense:GPL-3.0Stargazers:50Issues:5Issues:2

deep-fMRI-dataset

Code accompanying data release of natural language listening fMRI data (LeBel et al.)

Language:PythonLicense:MITStargazers:46Issues:5Issues:9

collective_motion_actinf

Code for simulating collective motion from groups of continuous-time and -space active inference agents.

luminate

Denoising longitudinal microbiome data.

Language:PythonStargazers:7Issues:0Issues:0
Language:PythonStargazers:1Issues:1Issues:0