DM2 Lab

Meng Jiang

Hi! I am an Associate Professor and Frank M. Freimann Collegiate Professor of Computer Science and Engineering at the University of Notre Dame. I'm appointed as a Lucy Family Institute Fellow as well as the Program Chair of ND-IBM Tech Ethics Lab. My research fields are AI and Data Science. I'm interested in developing Strong, Controllable, Multimodal AI for applications such as Sciences (e.g., material discovery, math reasoning) and Engineering (e.g., physical systems, recommender systems), as well as education and mental health. Typical approaches are:

Tuning multimodal AI to gain knowledge and skills, and precisely follow complex instructions;
Generalizing multimodal AI capabilities with multi-objective reinforcement learning;
Controlling multimodal AI to act under moral, ethical, or rational guidelines;
Adapting multimodal AI efficiently for personalized service and scientific discovery.

I am directing the Data Mining towards Decision Making (DM2) Lab as well as the Foundation Models and Applications (FAML) Lab at Lucy Family Institute. DM2 Lab is looking for multiple RAs to work on (1) foundation models and agentic systems for chemistry and material sciences, (2) machine learning theories and techniques for foundation model safety and steerability, and (3) foundation models and agentic systems for open-sourcing physical intelligence. Drop me an e-mail if you are interested!

What's New

October 2026: Gave a talk at UChicago AI in Science Seminar.
September 2026: Gave talks at NEC Lab Europe and SciML workshop.
August 2026: Keynote speeh at RelKD workshop in KDD.
June 2026: Gang Liu has successfully passed his dissertation defense and will join the City University of Hong Kong as an assistant professor. Congratulations, Dr. Liu! He is looking for PhD students - if you are interested in the PhD program at CityU, please contact Dr. Liu.
May 2026: Mengxia Yu has successfully passed her dissertation defense and will join Apple. Congratulations, Dr. Yu!
April 2026: Welcome Jinduo Guo and Chuhan Wang to join our lab and the CSE PhD Program in Fall 2026!
January 2026: Jim and I are organizing the Physical AI Working Group supported by the Data, AI, and Computing (DAC) Initiative at the University of Notre Dame. Let us know if you are interested in the group activities!
January 2026: Scientific AI Winter School at the University of Puerto Rico was successful! We presented the work of learning and reasoning for molecular inverse design.
December 2025: Welcome Weijiang (Vicky) Li to join our lab and the CSE PhD Program in January 2026! Gang Liu, with great work on AI for Science, is on the academic job market!
October 2025: We're proud to announce that Coefficient Giving is supporting our work on AI safety - Probing-Guided Robust Unlearning!

Latest Publications

Controllable Molecular Generative Foundation Models, NeurIPS, 2026.
Bridging Textual Profiles and Latent User Embeddings for Personalization, NeurIPS, 2026.
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions, NeurIPS, 2026.
Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents, EMNLP, 2026. (Demo)
KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning, EMNLP, 2026.
Safety-Aware Contrastive Decoding for Contextual Safety in Multimodal Large Language Models, EMNLP, 2026.
Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness, Findings of EMNLP, 2026.
ADRD-Bench: An LLM Benchmark for Alzheimer’s Disease and Related Dementias, Findings of EMNLP, 2026.
ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents, Findings of EMNLP, 2026.
ReplicatorBench: Benchmarking LLM Agents on Replicability Studies in Social and Behavioral Sciences, KDD, 2026. (AI4Sciences)
SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression, KDD, 2026. (AI4Sciences)
Composing Policy Gradients and Prompt Optimization for Language Model Programs, CAIS, 2026.
Dossier: Deep Research via Ledger-Driven Branching Search and Query Encoding Learning, CAIS, 2026.
MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring, ACL, 2026.
Instant Personalized Large Language Model Adaptation via Hypernetwork, ACL, 2026.
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards, ACL, 2026.
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning, Findings of ACL, 2026.
Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs, Findings of ACL, 2026.
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues, Findings of ACL, 2026.
Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning, Findings of ACL, 2026.
Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation, Findings of ACL, 2026.
Crepe: A Mobile Screen Data Collector Using Graph Query, CHI, 2026.
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting, TACL, 2026.
Graph Diffusion Transformers are In-Context Molecular Designers, ICLR, 2026.
Dual-Space Smoothness for Robust and Balanced LLM Unlearning, ICLR, 2026.
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning, ICLR, 2026.
Context Selection and Rewriting for Video-based Educational Question Generation, EAAI, 2026.

Advised PhD Dissertations

Last updated on October 19, 2026.