{"total":57,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63,"area":"distill"},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57,"area":null},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2410.24159","title":"GPT or BERT: why not both?","created":"2024-10-31","cited_by_count":27,"area":null},{"id":"2407.16154","title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","created":"2024-07-23","cited_by_count":26,"area":"distill"},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2410.22906","title":"From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes","created":"2024-10-30","cited_by_count":11,"area":null},{"id":"2510.04764","title":"Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models","created":"2025-10-06","cited_by_count":11,"area":null},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2410.03613","title":"Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2506.15681","title":"GenRecal: Generation after Recalibration from Large to Small Vision-Language Models","created":"2025-06-18","cited_by_count":10,"area":"mllm"},{"id":"2510.20411","title":"Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction","created":"2025-10-23","cited_by_count":9,"area":null},{"id":"2412.03275","title":"AntLM: Bridging Causal and Masked Language Models","created":"2024-12-04","cited_by_count":8,"area":null},{"id":"2404.02204","title":"Emergent Abilities in Reduced-Scale Generative Language Models","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2505.24181","title":"SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought","created":"2025-05-30","cited_by_count":7,"area":"lr"},{"id":"2512.22238","title":"Masking Teacher and Reinforcing Student for Distilling Vision-Language Models","created":"2025-12-23","cited_by_count":6,"area":"mllm"},{"id":"2409.17312","title":"BabyLlama-2: Ensemble-Distilled Models Consistently Outperform Teachers With Limited Data","created":"2024-09-25","cited_by_count":5,"area":"distill"},{"id":"2410.01487","title":"Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2406.04523","title":"Proofread: Fixes All Errors with One Tap","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2411.06672","title":"What Should Baby Models Read? Exploring Sample-Efficient Data Composition on Model Performance","created":"2024-11-11","cited_by_count":4,"area":null},{"id":"2411.13045","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","created":"2024-11-20","cited_by_count":4,"area":"distill"},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2505.12313","title":"ExpertSteer: Intervening in LLMs through Expert Knowledge","created":"2025-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.02823","title":"The Curious Case of In-Training Compression of State Space Models","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2406.19227","title":"Aligning Teacher with Student Preferences for Tailored Training Data Generation","created":"2024-06-27","cited_by_count":3,"area":"distill"},{"id":"2410.15365","title":"BERTtime Stories: Investigating the Role of Synthetic Story Data in Language Pre-training","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2501.11006","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2503.00245","title":"CoSMoEs: Compact Sparse Mixture of Experts","created":"2025-02-28","cited_by_count":3,"area":"moe"},{"id":"2507.05617","title":"Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching","created":"2025-07-08","cited_by_count":3,"area":"distill"},{"id":"2508.15475","title":"Influence-driven Curriculum Learning for Pre-training on Limited Data","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.08470","title":"Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling","created":"2025-10-09","cited_by_count":2,"area":"mllm"},{"id":"2511.20652","title":"When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2502.15616","title":"Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2504.02521","title":"UNDO: Understanding Distillation as Optimization","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2504.09620","title":"Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference","created":"2025-04-13","cited_by_count":1,"area":"mllm"},{"id":"2505.11837","title":"On Membership Inference Attacks in Knowledge Distillation","created":"2025-05-17","cited_by_count":1,"area":"safety"},{"id":"2506.07424","title":"Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2603.24518","title":"TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models","created":"2026-03-25","cited_by_count":1,"area":"distill"},{"id":"2604.18963","title":"Distillation Traps and Guards: A Calibration Knob for LLM Distillability","created":"2026-04-21","cited_by_count":1,"area":"distill"},{"id":"2408.10729","title":"Towards Efficient Large Language Models for Scientific Text: A Review","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2410.22081","title":"Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2411.16487","title":"When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets?","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2412.15978","title":"BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2505.19529","title":"Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation","created":"2025-05-26","cited_by_count":0,"area":null}],"next_cursor":null}