{"list":"other","total":107,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"2105.10056","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","created":"2021-05-20","cited_by_count":383},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2105.00243","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","created":"2021-05-01","cited_by_count":352},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"1810.06060","title":"Distributed learning of deep neural network over multiple agents","created":"2018-10-14","cited_by_count":279},{"id":"2305.18292","title":"Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models","created":"2023-05-29","cited_by_count":261},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"id":"2010.08678","title":"TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems","created":"2020-10-17","cited_by_count":165},{"id":"1802.07876","title":"Federated Meta-Learning with Fast Convergence and Efficient Communication","created":"2018-02-22","cited_by_count":155},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"2209.10083","title":"Federated Learning from Pre-Trained Models: A Contrastive Learning Approach","created":"2022-09-21","cited_by_count":142},{"id":"2003.08082","title":"Federated Visual Classification with Real-World Data Distribution","created":"2020-03-18","cited_by_count":128},{"id":"1709.01921","title":"Distributed Deep Neural Networks over the Cloud, the Edge and End Devices","created":"2017-09-06","cited_by_count":120},{"id":"2401.06432","title":"Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models","created":"2024-01-12","cited_by_count":116},{"id":"2008.06402","title":"SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud","created":"2020-08-14","cited_by_count":112},{"id":"2203.05797","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","created":"2022-03-11","cited_by_count":108},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102},{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78},{"id":"1901.09672","title":"Personalized Dialogue Generation with Diversified Traits","created":"2019-01-28","cited_by_count":74},{"id":"2006.06954","title":"Towards Flexible Device Participation in Federated Learning","created":"2020-06-12","cited_by_count":65},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61},{"id":"1703.02091","title":"Optimized Cost per Click in Taobao Display Advertising","created":"2017-02-27","cited_by_count":57},{"id":"1904.10631","title":"Low-Memory Neural Network Training: A Technical Report","created":"2019-04-24","cited_by_count":57},{"id":"2306.09486","title":"FedMultimodal: A Benchmark For Multimodal Federated Learning","created":"2023-06-15","cited_by_count":51},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48},{"id":"2402.11890","title":"Revisiting Knowledge Distillation for Autoregressive Language Models","created":"2024-02-19","cited_by_count":42},{"id":"1905.13536","title":"Scaling Video Analytics on Constrained Edge Nodes","created":"2019-05-24","cited_by_count":36},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35},{"id":"2104.06624","title":"Device-Cloud Collaborative Learning for Recommendation","created":"2021-04-14","cited_by_count":34},{"id":"2403.03129","title":"CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following","created":"2024-03-05","cited_by_count":33},{"id":"2405.19262","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","created":"2024-05-29","cited_by_count":32},{"id":"2005.08416","title":"EdgeRec: Recommender System on Edge in Mobile Taobao","created":"2020-05-18","cited_by_count":29},{"id":"2402.15505","title":"Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts","created":"2024-02-23","cited_by_count":28},{"id":"2306.08401","title":"LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming","created":"2023-06-14","cited_by_count":27},{"id":"2205.14833","title":"Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning","created":"2022-05-30","cited_by_count":23},{"id":"2208.09577","title":"Real-time Short Video Recommendation on Mobile Devices","created":"2022-08-20","cited_by_count":21},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17},{"id":"2501.05647","title":"Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation","created":"2025-01-10","cited_by_count":15},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13},{"id":"2201.10382","title":"On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systems","created":"2022-01-24","cited_by_count":6}],"next_cursor":"100"}