papers

Publications (10)

cs.AI2026

BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models

Thierry Blankenstein, Jialin Yu, Zixuan Li +6

Agents backed by large language models (LLMs) increasingly rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raise…

cs.CY2026

Permission Manifests for Web Agents

Samuele Marro, Alan Chan, Xinxing Ren +12

The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conven…

cs.AI2026

Benchmarking at the Edge of Comprehension

Samuele Marro, Jialin Yu, Emanuele La Malfa +8

As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improv…

cs.CR2025

ToolTweak: An Attack on Tool Selection in LLM-based Agents

Jonathan Sneh, Ruomei Yan, Jialin Yu +6

As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tool…

cs.CV2022

Adaptive Token Sampling For Efficient Vision Transformers

Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari +5

While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs…

cs.CV2025

DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding

Tanveer Hannan, Dimitrios Mallios, Parth Pathak +5

Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impra…

cs.CV2021

Relighting Images in the Wild with a Self-Supervised Siamese Auto-Encoder

Yang Liu, Alexandros Neophytou, Sunando Sengupta +1

We propose a self-supervised method for image relighting of single view images in the wild. The method is based on an auto-encoder which deconstructs an image into two separate enc…

cs.CV2026

STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering

Emad Bahrami, Olga Zatsarynna, Parth Pathak +3

We introduce STRIVE (SpatioTemporal Reinforcement with Importance-aware Variant Exploration), a structured reinforcement learning framework for video question answering. While grou…

cs.SD2021

Cross-modal Spectrum Transformation Network For Acoustic Scene classification

Yang Liu, Alexandros Neophytou, Sunando Sengupta +1

Convolutional neural networks (CNNs) with log-mel spectrum features have shown promising results for acoustic scene classification tasks. However, the performance of these CNN base…

cs.CV2024

Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI

Carolina Lopez Olmos, Alexandros Neophytou, Sunando Sengupta +1

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for traini…