4 papers
Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
Farooq Ahmad Wani, Maria Sofia Bucarelli, Mujtaba Hussain Mirza +5
Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs substantia…
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
Wai-Chung Kwan, Aryo Pradipta Gema, Joshua Ong Jun Leang +1
Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or…
Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
Matteo Attimonelli, Alessandro De Bellis, Aryo Pradipta Gema +8
Composed Image Retrieval (CIR) is a multimodal retrieval task where a query consists of a reference image and a textual modification, and the goal is to retrieve a target image sat…
Same Answer, Different Representations: Hidden instability in VLMs
Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena +6
The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processi…