collaborators

10 papers

q-bio.NC2026

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay

Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa +4

Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection of neuroscience a…

q-bio.NC2026

Task-conditioned probing of instruction-tuned multimodal LLMs: Region-specific brain alignment patterns under naturalistic stimuli

Subba Reddy Oota, Khushbu Pahwa, Prachi Jindal +5

Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain alignment compared to unimodal models.…

cs.LG2026

Supplement Generation Training for Enhancing Agentic Task Performance

Young Min Cho, Daniele Bonadiman, Divya Bhargavi +8

Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are…

cs.LG2026

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training

Anas Barakat, Souradip Chakraborty, Khushbu Pahwa +1

Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines succ…

q-bio.NC2026

Linguistic properties and model scale in brain encoding: from small to compressed language models

Subba Reddy Oota, Vijay Rowtula, Satya Sai Srinath Namburi +5

Recent work has shown that scaling large language models (LLMs) improves their alignment with human brain activity, yet it remains unclear what drives these gains and which represe…

cs.CL2025

Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection

Michelle Yuan, Khushbu Pahwa, Shuaichen Chang +5

Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods…