AI
No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation
Researchers have developed a method to create and validate unknown person names for use in evaluatin...
AI
Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness
Researchers have developed a new method for filling in gaps in physiological time-series data, such ...
AI
Specification Portability Across LLM Development Agents: Cross-Agent Compatibility in Specification-Driven Software Migration
Researchers investigated how easily specifications written for one Large Language Model (LLM) can be...
AI
Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking
Researchers have discovered a vulnerability in AI systems that can be exploited to make them produce...
AI
Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation
Researchers have proposed AdaptedKG, a method for improving sequential recommend...
AI
EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
Researchers have developed EnSI-RAG, a framework for long-document question answ...
AI
Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
Researchers have developed a new method for improving image captioning called Re...
AI
TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
Researchers have developed a new framework called TurboBias 2.0 for improving th...