{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1808.03314","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","created":"2018-08-09","cited_by_count":420},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264},{"id":"2404.02258","title":"Mixture-of-Depths: Dynamically allocating compute in transformer-based language models","created":"2024-04-02","cited_by_count":258},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2301.13196","title":"Looped Transformers as Programmable Computers","created":"2023-01-30","cited_by_count":237},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2211.15841","title":"MegaBlocks: Efficient Sparse Training with Mixture-of-Experts","created":"2022-11-29","cited_by_count":209},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172},{"id":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152},{"id":"2311.12424","title":"Looped Transformers are Better at Learning Learning Algorithms","created":"2023-11-21","cited_by_count":149},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144},{"id":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102},{"id":"2409.15647","title":"Looped Transformers for Length Generalization","created":"2024-09-24","cited_by_count":99},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"2307.02628","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","created":"2023-07-05","cited_by_count":89},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83},{"id":"2310.05424","title":"Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding","created":"2023-10-09","cited_by_count":80},{"id":"2104.08803","title":"Consistent Accelerated Inference via Confident Adaptive Transformers","created":"2021-04-18","cited_by_count":74},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70},{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69},{"id":"2410.08292","title":"Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?","created":"2024-10-10","cited_by_count":65},{"id":"2405.16039","title":"MoEUT: Mixture-of-Experts Universal Transformers","created":"2024-05-25","cited_by_count":59},{"id":"2404.18911","title":"Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting","created":"2024-04-29","cited_by_count":58},{"id":"1807.05353","title":"Recurrent Stacking of Layers for Compact Neural Machine Translation Models","created":"2018-07-14","cited_by_count":38},{"id":"2403.03432","title":"Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models","created":"2024-03-06","cited_by_count":38},{"id":"2202.05826","title":"End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking","created":"2022-02-11","cited_by_count":33},{"id":"1902.09701","title":"Learning Implicitly Recurrent CNNs Through Parameter Sharing","created":"2019-02-26","cited_by_count":27},{"id":"2111.05297","title":"Sliced Recursive Transformer","created":"2021-11-09","cited_by_count":26},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19},{"id":"2409.19044","title":"On the Inductive Bias of Stacking Towards Improving Reasoning","created":"2024-09-27","cited_by_count":19},{"id":"1312.1847","title":"Understanding Deep Architectures using a Recursive Convolutional Network","created":"2013-12-06","cited_by_count":11},{"id":"2312.03248","title":"Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning","created":"2023-12-06","cited_by_count":8},{"id":"2305.19585","title":"LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction","created":"2023-05-31","cited_by_count":7},{"id":"2311.08623","title":"DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models","created":"2023-11-15","cited_by_count":7}],"next_cursor":null}