8 papers
SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models
Aafiya Hussain, Gaurav Srivastava, Alvi Ishmam +2
Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulati…
Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
Chris Latimer, Nicoló Boschi, Andrew Neeser +4
Agent memory has been touted as a dimension of growth for LLM-based applications, enabling agents that can accumulate experience, adapt across sessions, and move beyond single-shot…
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Meng Lu, Ran Xu, Yi Fang +14
While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, rem…
JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation
Zhenyu Bi, Gaurav Srivastava, Yang Li +4
While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language model…
BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
Gaurav Srivastava, Aafiya Hussain, Zhenyu Bi +5
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce…
Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
Gaurav Srivastava, Aafiya Hussain, Sriram Srinivasan +1
Large language models (LLMs) achieve impressive performance on complex mathematical benchmarks yet sometimes fail on basic math reasoning while generating unnecessarily verbose res…