27 papers
Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark
Alexander Apartsin, Yehudit Aperstein
Prospective clinical actions, the follow-ups, orders, referrals, and instructions that deter-mine what happens to a patient next, are annotated today in thin fragments across incom…
The Joule Point: an Energy-Optimal Operating Point for AI Inference
Alexander Apartsin, Yehudit Aperstein
Data centers serving AI inference strive to maximize GPU utilization, running their cards at full power by default: this maximizes throughput and holds latencies down, but it is en…
Three Generations of Healthcare IT: From the Digital Record to the Computable Care Process
Alexander Apartsin, Yehudit Aperstein
Objective. Healthcare IT is usually organized by the technologies it adopts. We instead organize it by the unit of information a system makes computable, and describe a computation…
Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems
Alexander Apartsin, Yehudit Aperstein
A cyber-physical system (CPS) can enter a faulty state that is individually normal on every sensor and reconstructs accurately, yet is improbable under normal joint operation. This…
Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies
Alexander Apartsin, Yehudit Aperstein
Much clinical value is conveyed not through structured records but through communication: exchanges in which patients describe symptoms, clinicians reason and give instructions, am…
Framing, Judging, Steering: An Assessable Competency Model for Teach-ing Students to Reason With Generative AI
Alexander Apartsin, Yehudit Aperstein
Generative AI makes answers easy and understanding hard, and uncritical use invites cognitive offloading. Schools still measure unaided performance, yet the real task is to produce…
CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks
Alexander Apartsin, Yehudit Aperstein
Selecting a pretrained language model, or evaluating a fine-tuned one, for a specific application is a high-value decision, yet the public benchmarks used to make it are poorly sui…
Reliable Extraction of Clinical Follow-Up Instructions: A Hybrid Neural-Symbolic Pipeline
Michal Laufer, Yehudit Aperstein, Alexander Apartsin
Objective. Outpatient notes carry follow-up instructions pairing actions with future times ("MRI brain in two weeks"). Extracting (action, date) pairs supports scheduling and audit…
Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models
Alexander Apartsin, Omri Sason, Yehudit Aperstein
Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language models could support such practice…
Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation
Alexander Apartsin, Yigal Meshulam, Yehudit Aperstein
Multi-robot task allocation usually assumes some combination of communication, known task models, or a coordinator. We study the opposite extreme, a regime common in practice but o…
A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis
Yehudit Aperstein, Alexander Apartsin
Educational aspect-based sentiment analysis (ABSA) can support course improvement, but public aspect-labeled student feedback remains scarce because educational reviews are private…
Domain-Gated Latent Diffusion: Generative Inverse Design of HMX-Class Energetic Materials with First-Principles Validation
Yehudit Aperstein, Alexander Apartsin
Energetic materials power mining, demolition, propulsion and airbags, yet today's compounds were designed decades ago. A successor must combine high energy release, low sensitivity…
IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences
Yehudit Aperstein, Eden Moran, Alexander Apartsin
When people recount personal memories, they often refer to people, places, and events indirectly, relying on con-textual cues rather than explicit names. Such implicit references a…
Mapping License Plate Recoverability Under Extreme Viewing Angles for Opportunistic Urban Sensing
Igor Adamenko, Orpaz Ben Aharon, Yehudit Aperstein +1
Urban environments contain many imaging sensors built for specific purposes, including ATM, body-worn, CCTV, and dashboard cameras. Under the opportunistic sensing paradigm, these…
SeaAlert: Robust Severity Classification and LLM-Based Information Extraction for Noisy Maritime Distress Communications
Tomer Atia, Yehudit Aperstein, Alexander Apartsin
Maritime distress communications transmitted over very high frequency (VHF) radio are safety-critical voice messages used to report emergencies at sea. Under the Global Maritime Di…
LLM-guided headline rewriting for clickability enhancement without clickbait
Yehudit Aperstein, Linoy Halifa, Sagiv Bar +1
Enhancing reader engagement while preserving informational fidelity is a central challenge in controllable text generation for news media. Optimizing news headlines for reader enga…
From Fuzzy Speech to Medical Insight: Benchmarking LLMs on Noisy Patient Narratives
Eden Mama, Liel Sheri, Yehudit Aperstein +1
The widespread adoption of large language models (LLMs) in healthcare raises critical questions about their ability to interpret patient-generated narratives, which are often infor…
When Curiosity Signals Danger: Predicting Health Crises Through Online Medication Inquiries
Dvora Goncharok, Arbel Shifman, Alexander Apartsin +1
Online medical forums are a rich and underutilized source of insight into patient concerns, especially regarding medication use. Some of the many questions users pose may signal co…
An Interpretable Benchmark for Clickbait Detection and Tactic Attribution
Lihi Nofar, Tomer Portal, Aviv Elbaz +2
The proliferation of clickbait headlines poses significant challenges to the credibility of information and user trust in digital media. While recent advances in machine learning h…
Multi-pathology Chest X-ray Classification with Rejection Mechanisms
Yehudit Aperstein, Amit Tzahar, Alon Gottlib +3
Overconfidence in deep learning models poses a significant risk in high-stakes medical imaging tasks, particularly in multi-label classification of chest X-rays, where multiple co-…
From Joy to Fear: A Benchmark of Emotion Estimation in Pop Song Lyrics
Shay Dahary, Avi Edana, Alexander Apartsin +1
The emotional content of song lyrics plays a pivotal role in shaping listener experiences and influencing musical preferences. This paper investigates the task of multi-label emoti…
Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
Inbal Bolshinsky, Shani Kupiec, Almog Sasson +2
In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent rec…
Code Review Without Borders: Evaluating Synthetic vs. Real Data for Review Recommendation
Yogev Cohen, Dudi Ohayon, Romy Somkin +2
Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new pro…
Stitching the Story: Creating Panoramic Incident Summaries from Body-Worn Footage
Dor Cohen, Inga Efrosman, Yehudit Aperstein +1
First responders widely adopt body-worn cameras to document incident scenes and support post-event analysis. However, reviewing lengthy video footage is impractical in time-critica…