Lehigh AI Research Lab (LAIR) @ Lehigh University

university

https://openlair.github.io/

AI & ML interests

Trustworthy AI; Medical AI; Generative AI and LLMs; Federated Learning; Reinforcement Learning; AI agents for scientific research.

Recent Activity

songdj updated a Space 6 days ago

OpenLair/README

songdj published a Space 11 days ago

OpenLair/README

songdj authored a paper 22 days ago

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

View all activity

songdj

updated a Space 6 days ago

README

👀

songdj

published a Space 11 days ago

README

👀

songdj

authored 3 papers 22 days ago

submitted 2 papers to Daily Papers 22 days ago

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

Paper • 2610.21046 • Published 26 days ago • 22

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published 27 days ago • 72

songdj

authored a paper 2 months ago

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 37

songdj

submitted a paper to Daily Papers 2 months ago

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 37

songdj

authored a paper 5 months ago

OpenSkill: Open-World Self-Evolution for LLM Agents

Paper • 2606.06741 • Published Jun 4 • 30

songdj

authored a paper 6 months ago

AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery

Paper • 2605.23204 • Published May 22 • 29

songdj

authored 2 papers 7 months ago

Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math

Paper • 2603.24961 • Published Mar 26 • 3

Towards a Medical AI Scientist

Paper • 2603.28589 • Published Mar 30 • 91

songdj

submitted a paper to Daily Papers 8 months ago

Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math

Paper • 2603.24961 • Published Mar 26 • 3

songdj

authored 2 papers 9 months ago

LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation

Paper • 2602.10367 • Published Feb 10 • 13

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation

Paper • 2510.06231 • Published Oct 1, 2025

songdj

authored 4 papers over 1 year ago

Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents

Paper • 2505.23450 • Published May 29, 2025 • 9

SAMed-2: Selective Memory Enhanced Medical Segment Anything Model

Paper • 2507.03698 • Published Jul 4, 2025 • 12

A Survey on Post-training of Large Language Models

Paper • 2503.06072 • Published Mar 8, 2025 • 11

Aligning Multimodal LLM with Human Preference: A Survey

Paper • 2503.14504 • Published Mar 18, 2025 • 25

AI & ML interests

Recent Activity

Team members 2

OpenLair's activity

README

README