{"total":42,"rows":[{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2602.18182","title":"Capabilities Ain't All You Need: Measuring Propensities in AI","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2603.13768","title":"Causal Tracing of Audio-Text Fusion in Large Audio Language Models","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2605.04970","title":"Skill Neologisms: Towards Skill-based Continual Learning","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.03869","title":"On Adaptivity in Zeroth-Order Optimization","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.27904","title":"Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.04525","title":"Language Models Represent and Transform Concepts with Shared Geometry","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2602.04604","title":"Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.00777","title":"DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2603.10827","title":"Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.26557","title":"MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2605.18607","title":"Forecasting Downstream Performance of LLMs With Proxy Metrics","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.06211","title":"FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.14743","title":"Quantifying the Generation Modality Gap in Speech-Text Language Models","created":"2026-09-13","cited_by_count":1,"area":null},{"id":"2604.27618","title":"Math Education Digital Shadows for Investigating Learning with GenAI: Mathematics Performance, Anxiety, and Confidence in LLMs","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.11608","title":"PRISM: A Geometric Risk Bound for Decomposing Drift into Scale, Shape, and Head","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.18163","title":"TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.21076","title":"GradeLegal: Automated Grading for German Legal Cases","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.15735","title":"EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.19096","title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19100","title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.02118","title":"Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.03207","title":"S-DiverSe: Spanish Diverse Speech","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.14661","title":"SmartRAG: Native Graph-Based RAG for Mobile Device","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.16214","title":"What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.27955","title":"SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.09109","title":"Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.36920","title":"Benchmarking Automatic Speech Recognition Tools for Iberian Languages","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39929","title":"RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01093","title":"OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06345","title":"Breaking Bureaucracy: Evaluating open-source LLMs for legal document review","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07109","title":"JudgeMoE: Distributional Aggregation for LLM-as-a-Judge","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08162","title":"The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08778","title":"Sherpa: Teaching LLMs to Teach Adaptively","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09976","title":"EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10536","title":"Decoupling Exploration from Optimization in RLVR","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12338","title":"VFold: Symmetry-Aware Cross-Layer Value Cache Compression","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13145","title":"VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}