{"total":21,"rows":[{"id":"2404.14619","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","created":"2024-04-22","cited_by_count":75,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18,"area":null},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2405.14159","title":"Super Tiny Language Models","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2503.16423","title":"GAEA: A Geolocation Aware Conversational Assistant","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2406.06562","title":"Achieving Sparse Activation in Small Language Models","created":"2024-06-03","cited_by_count":4,"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":"2403.11026","title":"EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration","created":"2024-03-16","cited_by_count":3,"area":null},{"id":"2509.07324","title":"Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2503.10632","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2509.07994","title":"STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2608.11981","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2604.18655","title":"Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2405.05957","title":"OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning","created":"2024-05-09","cited_by_count":0,"area":null},{"id":"2410.06973","title":"Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2410.08388","title":"Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2507.10580","title":"An Offline Mobile Conversational Agent for Mental Health Support: Learning from Emotional Dialogues and Psychological Texts with Student-Centered Evaluation","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2604.06180","title":"MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis","created":"2026-02-05","cited_by_count":0,"area":null}],"next_cursor":null}