Multi-modal conversational AI (xRx) system

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Code implementation of RP3D-Diag

The related works and background techniques about Openai o1

"QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs" Empirical Methods in Natural Language Processing (EMNLP) 2024, Findings, Accepted.

[Under Review] Official PyTorch implementation code for realizing the technical part of Phantom of Latent representing equipped with enlarged hidden dimension to build super frontier vision languag…

Electronic Health Record Analysis with Python.

PubMedQA: A Dataset for Biomedical Research Question Answering

Efficiently Fine-Tune 100 LLMs in WebUI (ACL 2024)

LLM Tuning with PEFT (SFT RM PPO DPO with LoRA)

Chain-of-Spot: Interactive Reasoning Improves Large Vision-language Models

Paper Reproduction Google SCoRE(Training Language Models to Self-Correct via Reinforcement Learning)

[ECAI 2024 Oral] CoQAH : Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model

[MIDL 2024] PLURAL : Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-ray

large population models

A Large ECG-Language Model for Cardiac Disease Diagnosis

MCPL: Multi-modal Collaborative Prompt Learning for Medical Vision-Language Model (Initial Version)

[ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"

[ECCV'2024] HERGen: Elevating Radiology Report Generation with Longitudinal Data

Elo algorithm implementation in Python

[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

Evaluating LLMs' multi-round chatting capability via assessing conversations generated by two LLM instances.

Exploring limitations of LLM-as-a-judge

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

The repo of ASGMVLP