Institution profile

University of Haifa

Academic institutioneurope · il
Official website
Research library189linked papers
Opportunities0open roles
Selected work

Representative Papers

See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection

Jan 15, 2026

This work addresses the limited out-of-distribution (OOD) generalization of end-to-end autonomous driving policies, which stems from the high redundancy in patch-level features extracted by foundation models, leading policies to overfit spurious correlations. For the first time, this study identifies and quantifies such redundancy and introduces Stochastic Patch Selection (SPS), a mechanism that randomly masks a subset of image patch features per frame while preserving spatial layout, thereby compelling the policy to learn invariant decision cues from diverse yet complete scene views. Leveraging features from foundation models such as BLIP2, combined with PCA and cross-patch similarity analysis, SPS improves OOD performance by 6.2% on average—and up to 20.4%—in closed-loop simulation, accelerates inference by 2.4×, and enables deployment on real vehicles without fine-tuning, outperforming existing state-of-the-art methods in eight out of nine ablation settings.

1 citationsRead paper

Making Absence Visible: The Roles of Reference and Prompting in Recognizing Missing Information

Jan 12, 2026

Interactive visualization systems often suffer from presence bias, overlooking information absent from the display that users nonetheless expect to see, thereby hindering the formation of a complete mental model of the data. This study investigates how reference frames—global baselines versus concrete exemplars—and prompting strategies influence users’ ability to identify missing categories across three domains: energy, wealth, and political regimes. Through controlled experiments integrating methods from cognitive psychology and interactive visualization techniques, the research demonstrates that reference frames grounded in concrete exemplars are significantly more effective than global baselines in facilitating the detection of missing information. Furthermore, active prompting mechanisms markedly enhance users’ awareness of such omissions. These findings offer empirical support and practical guidance for designing expectation-driven visualizations that better align with users’ cognitive processes.

1 citationsRead paper

DiSCo: Making Absence Visible in Intelligent Summarization Interfaces

Jan 12, 2026

This work addresses a critical limitation in current abstractive summarization systems: their susceptibility to "presence bias," which causes them to reflect only explicitly mentioned content while overlooking crucial missing information, potentially misleading user decisions. To mitigate this, the authors propose DiSCo, a novel method that introduces an expectation-driven contrastive mechanism grounded in domain-typical topic reference distributions. By comparing the entity-specific content against expected domain-level discourse patterns, DiSCo automatically identifies and integrates anomalously overemphasized or omitted aspects into the generated summary. User studies across three domains—ski resorts, beaches, and downtown accommodations—demonstrate that summaries produced by DiSCo are consistently rated as more informative and decision-relevant, significantly enhancing both system transparency and practical utility for end users.

1 citationsRead paper
Recent publications

Latest Papers

Tactile Search: Enhancing Targeting in 3D Space

Sep 05, 2026

Visual search is crucial in daily life, from scanning for relevant information to spotting signs of danger. When sensory channels are overloaded or degraded, cognitive tasks can be supported by crossmodal information representations through vibrotactile cues. We introduce Tactile Search, an approach that uses modulation of frequency and amplitude of vibrations to the hands, for guiding attention to the location of objects in 3D space. We evaluated this approach in a competitive VR game where participants searched for targets using both vision and touch. Across two studies -- an in-the-wild demonstration (n=55) and a controlled laboratory experiment (n=28) -- we found that vibrotactile feedback significantly improved performance and increased user confidence. In the combined haptic condition, performance did not differ across target heights. We further analyzed participants'subjective experiences and search strategies highlighting the benefits of the tactile cues. Our findings suggest that Tactile Search can enhance interaction and provide design considerations for integrating haptic search into interactive systems.

0 citationsRead paper