TSR · The desk
Science · 14 October 2026
Articles in this category in 14 October 2026.
TSR Desk · science · 14 October 2026, 07:00 UTC
CB-Agent: Concept-Based In-Context Learning for Sequential Action SelectionTSR Desk · science · 14 October 2026, 07:00 UTC
Interactive Navigation Beyond Reachability: Benchmark and Agentic FrameworkTSR Desk · science · 14 October 2026, 07:00 UTC
Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis viaTSR Desk · science · 14 October 2026, 07:00 UTC
Structural Baselines Matter for Agent Failure Detection and AttributionTSR Desk · science · 14 October 2026, 07:00 UTC
VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary InnovationTSR Desk · science · 14 October 2026, 07:00 UTC
Uncertainty Evaluation: Bridging Machine Learning and Measurement ScienceTSR Desk · science · 14 October 2026, 07:00 UTC
TRACE: Temporal Risk Assessment and Concept Editing for Safer Language GenerationTSR Desk · science · 14 October 2026, 07:00 UTC
RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication RecommendationTSR Desk · science · 14 October 2026, 07:00 UTC
Getting Space Right: Agentic Rewards for Image GenerationTSR Desk · science · 14 October 2026, 07:00 UTC
RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-GroundedTSR Desk · science · 14 October 2026, 07:00 UTC
Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent LoopsTSR Desk · science · 14 October 2026, 07:00 UTC
Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer VideosTSR Desk · science · 14 October 2026, 07:00 UTC
CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent CockpitsTSR Desk · science · 14 October 2026, 07:00 UTC
PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D ReconstructionTSR Desk · science · 14 October 2026, 07:00 UTC
Beyond Successful Play: Diagnosing Opponent Modeling in Large Language ModelsTSR Desk · science · 14 October 2026, 07:00 UTC
PatTransBench: an ipc-stratified, multi-dimensional benchmark for patent machine translation