About
Research & Development
New Benchmark Reveals Large Language Models’ Challenges in Advanced Physics
TLDR: CMPhysBench is a new benchmark with over 520 graduate-level calculation problems in Condensed Matter Physics designed to evaluate Large Language Models (LLMs). It...
Research & Development
Improving Product Search in Multi-Turn Conversations with Dynamic Reranking
TLDR: The paper introduces a novel framework for multimodal conversational product search that uses a generative retriever combined with a Test-Time Reranking (TTR) mechanism....
Research & Development
Diagnosing Realism in AI-Generated Contact Center Dialogues
TLDR: This research introduces a diagnostic framework with 18 metrics to evaluate the realism of AI-generated synthetic dialogues for contact centers. It benchmarks four...
Research & Development
Enhancing IoT Network Localization with Deep Learning and Matrix Completion in the Face of Outliers
TLDR: This research introduces E-MDNL, a novel deep learning and matrix completion-aided technique for robust IoT network localization. It effectively handles outlier-contaminated Euclidean distance...
Research & Development
Precision and Clarity: Rule-Based Stuttering Detection in Clinical Settings
TLDR: This research paper introduces an enhanced rule-based framework for stuttering detection that prioritizes interpretability and transparency, crucial for clinical applications. It achieves competitive...
Research & Development
Unlocking Math Success: How AI Reveals Key Drivers of Student Achievement Across Nations
TLDR: A cross-national study by Liu Liu and Dai Rui utilized Explainable AI (XAI) on PISA 2018 data from ten countries to predict and...