{"total":98,"rows":[{"id":"2509.20354","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","created":"2025-09-24","cited_by_count":139,"area":null},{"id":"2511.21689","title":"ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration","created":"2025-11-26","cited_by_count":47,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2603.10055","title":"Training Language Models via Neural Cellular Automata","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2507.19364","title":"From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation","created":"2025-07-25","cited_by_count":10,"area":null},{"id":"2510.07248","title":"Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2508.03332","title":"Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2508.16703","title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2508.20186","title":"AI Propaganda factories with language models","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2510.14113","title":"Toward Cybersecurity-Expert Small Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2511.22334","title":"Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2507.03152","title":"MedVAL: Toward Expert-Level Medical Text Validation with Language Models","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2507.10880","title":"Domain-Adaptive Small Language Models for Structured Tax Code Prediction","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2508.19580","title":"ArgCMV: An Argument Summarization Benchmark for the LLM-era","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2510.05846","title":"Luth: Efficient French Specialization for Small Language Models and Cross-Lingual Transfer","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2511.13703","title":"Generalist Foundation Models Are Not Clinical Enough for Hospital Operations","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2512.02716","title":"Menta: A Small Language Model for On-Device Mental Health Prediction","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2601.13922","title":"Automatic Prompt Optimization for Dataset-Level Feature Discovery","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2603.06958","title":"Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2510.09780","title":"SVTime: Small Time Series Forecasting Models Informed by \"Physics\" of Large Vision Model Forecasters","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2511.03370","title":"EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2511.23271","title":"Learning a Single Token to Replace Long System Prompts in LLMs","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2602.00166","title":"Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.14591","title":"FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2604.07385","title":"Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2506.23273","title":"FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysis","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2507.13835","title":"Conformal Data Contamination Tests for In-distribution Data Acquisition","created":"2025-07-18","cited_by_count":1,"area":null},{"id":"2508.06753","title":"Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2510.06349","title":"Flexible Swarm Learning May Outpace Foundation Models in Essential Tasks","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2511.02895","title":"A Criminology of Machines","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.03610","title":"A systematic review of relation extraction task since the emergence of Transformers","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2511.06441","title":"Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2512.06660","title":"Effective and Efficient Threat Hunting with Small Language Models","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2512.10110","title":"Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2601.01320","title":"Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2603.01869","title":"Sovereign AI-based Public Services are Viable and Affordable","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.06173","title":"Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2604.19394","title":"Can Continual Pre-training Bridge the Performance Gap between General-purpose and Specialized Language Models in the Medical Domain?","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.03301","title":"SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2606.21619","title":"The Alignment Problem in Constrained Code Generation","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2607.02512","title":"Program-as-Weights: A Programming Paradigm for Fuzzy Functions","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.11997","title":"Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.18256","title":"PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.20216","title":"Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.11242","title":"Lost in Context Compaction: When LLM Systems Drop Side Constraints","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2609.16338","title":"Breaking the 1.58-bit Barrier for Ternary LLMs","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2507.11687","title":"MetaLint: Easy-to-Hard Generalization for Code Linting","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2507.22921","title":"Fast and Accurate Contextual Knowledge Extraction Using Cascading Language Model Chains and Candidate Answers","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2508.05199","title":"EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.06477","title":"Intuition emerges in Maximum Caliber models at criticality","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.15617","title":"Trained Miniatures: Low cost, High Efficacy SLMs for Sales & Marketing","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2510.01427","title":"A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.01671","title":"A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.06263","title":"Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2511.12823","title":"Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2512.03053","title":"Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.06001","title":"Small Language Models Reshape Higher Education: Courses, Textbooks, and Teaching","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.13154","title":"MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.23862","title":"Probing the Limits of Compressive Memory: A Study of Infini-Attention in Small-Scale Pretraining","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2601.07121","title":"ReMIND: Orchestrating Modular Large Language Models for Controllable Serendipity A REM-Inspired System Design for Emergent Creative Ideation","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.07961","title":"Language Markers of Emotion Flexibility Predict Depression and Anxiety Treatment Outcomes","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.08844","title":"Emissions and Performance Trade-off Between Small and Large Language Models","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2601.23206","title":"High-quality generation of dynamic game content via small language models: A proof of concept","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00871","title":"Beyond Output Critique: Self-Correction via Task Distillation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.12005","title":"LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.14050","title":"Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2602.21374","title":"Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2602.24174","title":"Task-Centric Acceleration of Small-Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.19975","title":"Promoting Critical Thinking With Domain-Specific Generative AI Provocations","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.26510","title":"Clinical named entity recognition in the Portuguese language: a benchmark of modern BERT models and LLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.04692","title":"Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.20795","title":"Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.00964","title":"Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.16767","title":"Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.25394","title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.25949","title":"Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.31136","title":"Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.08043","title":"Aleena: Alignment Agent for Research Software Engineering Collaborations","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.10878","title":"LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.19847","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.22854","title":"Coordinated Networking for On-Device Agent-Augmented Real-Time Communication","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.04488","title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.17034","title":"Agents unlock new capabilities through Switching LoRA Adapters as a Tool (SLAaaT)","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.18033","title":"Where A Small Language Model Helps in Invoice Categorisation, Understood Through Embedding Geometry","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.20918","title":"UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30021","title":"Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.21666","title":"Samsone: A Family of Open Small Audio Language Models for On-Device Inference","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.28765","title":"Reinforcement Learning with Verifiable Rewards for Small Search Agents","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30219","title":"Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.00025","title":"Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.02001","title":"Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.14209","title":"Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14576","title":"Iterate on an LLM, Serve on an SLM","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}