TSR · The desk
Science · 15 October 2026
Articles in this category in 15 October 2026.
TSR Desk · science · 15 October 2026, 01:00 UTC
Enabling Creative Exploration for Vibe Design AgentsTSR Desk · science · 15 October 2026, 01:00 UTC
Does a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory StudyTSR Desk · science · 15 October 2026, 01:00 UTC
InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly DetectionTSR Desk · science · 15 October 2026, 01:00 UTC
CTI2TTP: Evidence-Grounded TTP Extraction from Cyber Threat Intelligence viaTSR Desk · science · 15 October 2026, 01:00 UTC
Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized PuzzleTSR Desk · science · 15 October 2026, 01:00 UTC
MedHarnessBench: A Unified Benchmark for Healthcare Agent EvaluationTSR Desk · science · 15 October 2026, 01:00 UTC
HyWe: Unifying Search and Operation for Real-World Hybrid Web TasksTSR Desk · science · 15 October 2026, 01:00 UTC
Using Evidence-Centered Design to Guide Prompt Engineering in Measurement: An Illustration withTSR Desk · science · 15 October 2026, 01:00 UTC
ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-TunedTSR Desk · science · 15 October 2026, 01:00 UTC
ChemExplain: A Multimodal Benchmark for Explanatory Chemical ReasoningTSR Desk · science · 15 October 2026, 01:00 UTC
A Counterfactual Graph Approach to Oppositional Narrative AnalysisTSR Desk · science · 15 October 2026, 01:00 UTC
RadarGSOcc: Doppler-Aware 3D Semantic Occupancy Prediction Using 4D Radar Tensor withTSR Desk · science · 15 October 2026, 01:00 UTC
LoopArena: Benchmarking Models as Runtime Controllers for Loop EngineeringTSR Desk · science · 15 October 2026, 01:00 UTC
Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, andTSR Desk · science · 15 October 2026, 01:00 UTC
Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search AgentsTSR Desk · science · 15 October 2026, 01:00 UTC
Same Operation, Different Permission: Evaluating Whether Guardrails Honor AuthorizationTSR Desk · science · 15 October 2026, 01:00 UTC
ELECT: Settling Identity Before Rendering for Scalable Story VisualizationTSR Desk · science · 15 October 2026, 01:00 UTC
TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews