large language models

A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design

The design of reinforced concrete (RC) highway barriers is a safety-critical engineering task that requires strict compliance with regulatory provisions such as the AASHTO LRFD Bridge Design Specifications. Current engineering practice relies largely on manual, iterative, and experience-driven procedures to satisfy com...

MiniMaestro: Resource-Conscious Conversational Music Recommendation with a Single Open-Weight 8B Model

The RecSys Challenge 2026 Music-CRS (TalkPlay) task formalizes this as two coupled sub-problems: given dialogue history and user context, retrieve a ranked list of the top-20 tracks from the full, unrestricted catalog, and generate a response that justifies the recommendation while sustaining conversational coherence.

Overview and Analysis of the RecSys Challenge 2026: Conversational Music Recommendation

This paper presents the RecSys Challenge 2026 challenge task, dataset, evaluation protocol, and official results, and identifies limitations of the benchmark and evaluation protocol, including single-ground-truth relevance and teacher-forced evaluation of synthetic dialogues.

Talk Less, Rank Better: A Decoupled Pipeline for Conversational Music Recommendation

This paper describes the solution submitted by team Hallucinated to the ACM RecSys Challenge 2026, based on the TalkPlayData conversational music recommendation dataset, which addresses the ranking task with a classic multi-stage pipeline that combines a diverse pool of candidate generators, Reciprocal Rank Fusion, and...

Dialogue-Aware Conversational Music Recommendation via Multi-Modal Retrieval and Weighted RRF

The ACM-RecSys 2026 Music Conversational Recommendation Challenge (Music-CRS) bridges natural language processing and recommender systems, requiring systems to engage in multi-turn dialogues and recommend relevant tracks from a large catalog. In this paper, we present Team Sargam’s solution, a robust hybrid retrieval a...

Structured energy news sentiment extraction with Large Language Models for crude oil price forecasting

A Provider-Independent LLM Architecture for Adaptive Oracle SQL Tutoring: A Design Study

The design pairs cognitive adaptivity, realised as mastery-based task selection under configurable parameters, with motivational design grounded in Keller’s ARCS model, and a formalised adaptation logic linking learner states, adaptive responses, and conjectures.

Exploring the Genesis Platform Capabilities to Accelerate Scientific Discovery in OPAL

The plant phenotyping workflow of the Orchestrated Platform for Autonomous Laboratories is explored, which couples Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory with the Frontier supercomputer and replaces roughly twelve hours of manual analysis with interactive queries returning in seconds to m...

On AI’s role in training professionals in assisted reproductive technology

A comprehensive, AI-enhanced training framework designed to standardize and accelerate the education of clinicians, surgeons, and embryologists and integrate six core domains, including adaptive learning for theoretical knowledge, AI-driven simulations for clinical decision-making, virtual reality for surgical and embr...

Artificial Intelligence and Complementary Digital Health Technologies Across the Travel Medicine Continuum: A Narrative Review.

Artificial intelligence and complementary digital health technologies have the potential to improve travel healthcare throughout the travel continuum and current evidence remains largely retrospective, highlighting the need for prospective multicenter implementation studies evaluating clinically meaningful outcomes.

Language model-assisted label refinement for accurate sepsis detection from electronic health records

STRIDE, a machine-learning framework for sepsis detection across seven hospitals with a scalable approach to label quality, outperformed SOFA and Epic on discrimination and showed favorable calibration by Brier score, while retaining strong discrimination among SIRS-positive non-septic encounters.

Keep Evaluation Fair: Detecting Data Leakage in Code Generation Benchmarks via Membership Inference Attacks

Experiments on eight code generation benchmarks show that CGMIA outperforms eight existing membership inference methods in most cases, and effectively detects known leaked APPS samples in StarCoder-7B's training data.