AI
BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM Unlearning
Researchers propose BLADE, a new method for unlearning large language models (LLMs). Unlearning refe...
AI
Hybrid Panels: Toward Human-AI Collaboration in Survey Research
Researchers propose the concept of 'hybrid panels' as a way to improve survey research by combining ...
AI
Clinical Graph-JEPA: Predictive Patient-State Knowledge Graphs for Cognitive Decision Support
Researchers have developed a framework for creating and refining clinical knowledge graphs. These gr...
AI
Vision-Language Models for Occupational Physical Exposure Assessment: Estimating External Hand Forces in Manual Material Handling Tasks from RGB Video
Researchers have developed a system to estimate external hand forces in manual material handling tas...
AI
AI-based worker guidance in assembly and disassembly operations using multimodal ego/exo-centric data capture and structured task knowledge
Researchers have developed an AI system that guides workers in assembly and disa...
AI
Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains
Researchers have developed a dataset called ICU-REACT to teach large language mo...
AI
GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering
Researchers have developed a framework called GeoRisk-RAG to improve the reliabi...
AI
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
Researchers propose a solution to the problem of copy-pasting model-generated co...