14 citations · 40 across the 31 of their papers we have counts for
33 papers
Benchmarking the Quantum Leap: Auditing LLM Evaluation for Quantum Code Generation
Ethan Seefried, Romit Ghosh, Sharmin Afrose +4
Large language models (LLMs) can generate quantum programs, but reliable evaluation remains difficult because benchmarks differ in task composition, scoring, and failure handling.…
Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models
Vanessa Lama, Sanjay Das, Emily Herron +5
Domain-specialized language models are widely used for scientific question answering, but stronger general-purpose systems raise a sharper question: when does domain-specific fine-…
Decoupled I/O-Dominant Pipelines for Large-Scale Whole-Slide Image Embedding Extraction
Mayanka Chandrashekar, Xi Zhang, Ethan Seefried +3
Whole-slide images (WSIs) are central to computational pathology but are prohibitively large, making patch-based processing the practical unit for foundation model inference. At sc…
Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking
Swati Rajwal, Sanjay Das, Tirthankar Ghosal
Large language models (LLMs) are increasingly used for scientific hypothesis generation. However, evaluating generated hypotheses remains a challenge for trustworthy AI-enabled sci…
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
Xuehang Guo, Pengyuan Li, Tom Hope +3
As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding across these modalities poses fun…
Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation
Shashwat Sourav, Subhadeep Pal, Markus J. Buehler +4
AI co-scientists can generate fluent materials-science hypotheses, but fluency does not show that an answer preserves a scientifically meaningful mechanism. We present a graph-to-a…
Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap
Rafael Ferreira da Silva, Milad Abolhasani, Peter Beaucage +25
One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The fi…
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Subhadeep Pal, Shashwat Sourav, Tirthankar Ghosal +1
Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models…
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
Sanjay Das, Ran Elgedawy, Ethan Seefried +2
Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification. While large language m…
Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams
Abhishek Kumar, Isha Motiyani, Tilak Kasturi +3
Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through dense spatial layouts, domain…
Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research
Shashwat Sourav, Tanjin. He, Maria K. Y. Chan +2
AI co-scientists are increasingly used for scientific discovery, but current evaluations still do not test them on a key task: moving from a concrete scientific or technological pr…
The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
Shashwat Sourav, Viktoriia Baibakova, Sanjay Das +4
Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generated hypotheses. We study KG-g…
BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents
Ethan Seefried, Ran Eldegaway, Sanjay Das +2
Decades of engineering drawings and technical records remain locked in legacy archives with inconsistent or missing metadata, making retrieval difficult and often manual. We presen…
Predicting New Concept-Object Associations in Astronomy by Mining the Literature
Jinchu Li, Yuan-Sen Ting, Alberto Accomazzi +2
We construct a concept-object knowledge graph from the full astro-ph corpus through July 2025. Using an automated pipeline, we extract named astrophysical objects from OCR-processe…
Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams
Ethan Seefried, Prahitha Movva, Naga Harshita Marupaka +2
We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By ca…
AstroMLab 5: Structured Summaries and Concept Extraction for 400,000 Astrophysics Papers
Yuan-Sen Ting, Alberto Accomazzi, Tirthankar Ghosal +4
We present a dataset of 408,590 astrophysics papers from arXiv (astro-ph), spanning 1992 through July 2025. Each paper has been processed through a multi-stage pipeline to produce:…
HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments
Ran Elgedawy, Sanjay Das, Ethan Seefried +7
Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and E…
ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property
Maria Mahbub, Vanessa Lama, Sanjay Das +6
High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must trac…
Findings of the Third Automatic Minuting (AutoMin) Challenge
Kartik Shinde, Laurent Besacier, Ondrej Bojar +2
This paper presents the third edition of AutoMin, a shared task on automatic meeting summarization into minutes. In 2025, AutoMin featured the main task of minuting, the creation o…
Intelligent Manufacturing Support: Specialized LLMs for Composite Material Processing and Equipment Operation
Gunnika Kapoor, Komal Chawla, Tirthankar Ghosal +6
Engineering educational curriculum and standards cover many material and manufacturing options. However, engineers and designers are often unfamiliar with certain composite materia…
EPIC: Generative AI Platform for Accelerating HPC Operational Data Analytics
Ahmad Maroof Karimi, Woong Shin, Jesse Hines +3
We present EPIC, an AI-driven platform designed to augment operational data analytics. EPIC employs a hierarchical multi-agent architecture where a top-level large language model p…
PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
Renan Souza, Amal Gueroudji, Stephen DeWitt +5
Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and pee…
A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
Agada Joseph Oche, Ademola Glory Folashade, Tirthankar Ghosal +1
Retrieval-Augmented Generation (RAG) represents a major advancement in natural language processing (NLP), combining large language models (LLMs) with information retrieval systems…
AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model
Tijmen de Haan, Yuan-Sen Ting, Tirthankar Ghosal +7
General-purpose large language models (LLMs), despite their broad capabilities, often struggle with specialized domain knowledge. This gap hinders their deployment as reliable rese…