activity
20242026
collaborators

6 papers

cs.CL2026

Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Models

Mahdiyeh Farajidizaji, Vatsal Raina

Instruction tuning is meant to make language models follow user requests, yet it is unclear whether small models comply when an instruction conflicts with their usual task behavior…

cs.CV2026

ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models

Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma +31

Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children or animals. Despite this, they a…

cs.IR2025

Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval

Eric He, Akash Gupta, Adian Liusie +4

Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarit…

cs.CL2025

Probing the Limits of Stylistic Alignment in Vision-Language Models

Asma Farajidizaji, Akash Gupta, Vatsal Raina

Vision-language models are increasingly used to generate image captions in specific styles, such as humor or romantic. However, these transformer-based models often struggle with t…

cs.CV2024

Structural-Based Uncertainty in Deep Learning Across Anatomical Scales: Analysis in White Matter Lesion Segmentation

Nataliia Molchanova, Vatsal Raina, Andrey Malinin +7

This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter lesion (WML) segment…

cs.CL2024

Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons

Adian Liusie, Vatsal Raina, Yassir Fathullah +1

LLM-as-a-judge approaches are a practical and effective way of assessing a range of text tasks. However, when using pairwise comparisons to rank a set of candidates, the computatio…