Tanwi Mallick

Researcher, MCS, Argonne National Laboratory

Joined

May 2024

Names

Tanwi Mallick (Preferred)

Emails

****@anl.gov (Confirmed)

Personal Links

Career & Education History

Researcher

MCS, Argonne National Laboratory (anl.gov)

2018 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Pretraining and Fine-tuning

Present

Scientific machine learning

2018 – Present

Graph neural network

2018 – Present

Uncertainty quantification

2018 – Present

Publications

Toward Reliable, Safe, and Secure LLMs for Scientific Applications
Saket Sanjeev Chaturvedi, Joshua Bergersona, Tanwi Mallick
- ICLR 2026 AIWILD
- Readers: Everyone
PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training
Seth Ockerman, Amal Gueroudji, Tanwi Mallick, Yixuan He, Line Pouchard, Robert Ross, Shivaram Venkataraman
- Crossref
- Readers: Everyone
Analyzing a Lifetime of Failures on a Cray XC40 Supercomputer
Kevin A. Brown, Tanwi Mallick, Zhiling Lan, Robert B. Ross, Christopher D. Carothers
- Crossref
- Readers: Everyone
Beyond End-to-End: Understanding the Limits of LLMs in Scientific Problem Solving
Youyuan Liu, Sheng Di, Neil Getty, Tanwi Mallick, Robert Underwood, Sian Jin
- Crossref
- Readers: Everyone
LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
Samuel Yeh, Sharon Li, Tanwi Mallick
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
Chih-Hsuan Yang, Tanwi Mallick, Le Chen, Krishnan Raghavan, Azton Wells, Amal Gueroudji, Ian Foster, Rajeev Thakur
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
Samuel Yeh, Sharon Li, Tanwi Mallick
- ICLR 2026 Poster
- Readers: Everyone
Statistical Early Stopping for Reasoning Models
Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Weijie J Su, Edgar Dobriban
- NeurIPS 2025 ER Workshop
- Readers: Everyone
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Post-Training for Multi-LLM Agents
Chih-Hsuan Yang, Tanwi Mallick, Ian Foster, Amal Gueroudji, Rajeev Thakur
- LAW
- Readers: Everyone
GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?
Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Jiashu He, John K Hutchison, Camillo Jose Taylor, Tanwi Mallick
- SpaVLE Poster
- Readers: Everyone

View all 19 publications

Co-Authors

View all 58 co-authors