collaborators

9 papers

cs.LG2026

MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding

Sai Munikoti, Ian Stewart, Chengping Chai +4

The application of generalist multimodal models (GMMs) to specialized scientific domains remains limited due to the scarcity of comprehensive domain-specific datasets that integrat…

cs.AI2026

Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models

Sameera Horawalavithana, Lauren Phillips, Ian Stewart +2

Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge…

cs.CV2026

SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions

Sameera Horawalavithana, Sai Munikoti, Ian Stewart +2

Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less explored in improving LLMs to align e…

cs.LG2026

Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models

Souradeep Chattopadhyay, Brendan Kennedy, Sai Munikoti +2

In the critical task of making generative models trustworthy and robust, methods for Uncertainty Quantification (UQ) have begun to show encouraging potential. However, many of thes…

cs.CL2025

Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models

Ian Stewart, Sameera Horawalavithana, Brendan Kennedy +2

Multimodal foundation models (MFMs) such as OFASys show the potential to unlock analysis of complex data such as images, videos, and audio data via text prompts alone. However, the…

cs.CL2025

Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing

Reilly Raab, Mike Parker, Dan Nally +4

The advent of language models (LMs) has the potential to dramatically accelerate tasks that may be cast to text-processing; however, real-world adoption is hindered by concerns reg…