{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"2010.07611","title":"Layer-adaptive sparsity for the Magnitude-based Pruning","created":"2020-10-15","cited_by_count":126},{"id":"2304.13960","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","created":"2023-04-27","cited_by_count":114},{"id":"2312.11983","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","created":"2023-12-19","cited_by_count":111},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"2110.04869","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","created":"2021-10-10","cited_by_count":70},{"id":"2404.14047","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","created":"2024-04-22","cited_by_count":64},{"id":"2311.09755","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","created":"2023-11-16","cited_by_count":58},{"id":"2402.15173","title":"Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer","created":"2024-02-23","cited_by_count":53},{"id":"2412.06538","title":"Understanding Factual Recall in Transformers via Associative Memories","created":"2024-12-09","cited_by_count":51},{"id":"2409.17481","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","created":"2024-09-26","cited_by_count":50},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46},{"id":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25},{"id":"2410.21520","title":"LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation","created":"2024-10-28","cited_by_count":25},{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21},{"id":"2402.06126","title":"Learn To be Efficient: Build Structured Sparsity in Large Language Models","created":"2024-02-09","cited_by_count":20},{"id":"2410.07461","title":"Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning","created":"2024-10-09","cited_by_count":20},{"id":"2504.01346","title":"RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking","created":"2025-04-02","cited_by_count":18},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14},{"id":"2506.09034","title":"FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed","created":"2025-06-10","cited_by_count":14},{"id":"2407.02211","title":"PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning","created":"2024-07-02","cited_by_count":13},{"id":"2412.17336","title":"APEX$^2$: Adaptive and Extreme Summarization for Personalized Knowledge Graphs","created":"2024-12-23","cited_by_count":13},{"id":"2310.10191","title":"VIBE: Topic-Driven Temporal Adaptation for Twitter Classification","created":"2023-10-16","cited_by_count":12},{"id":"2410.04870","title":"On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent","created":"2024-10-07","cited_by_count":12},{"id":"2503.06881","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","created":"2025-03-10","cited_by_count":12},{"id":"2508.10026","title":"SABER: Switchable and Balanced Training for Efficient LLM Reasoning","created":"2025-08-08","cited_by_count":12},{"id":"2502.04350","title":"CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance","created":"2025-02-04","cited_by_count":11},{"id":"2406.01820","title":"Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning","created":"2024-06-03","cited_by_count":10},{"id":"2307.08941","title":"MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models","created":"2023-07-18","cited_by_count":6},{"id":"2402.05830","title":"Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting","created":"2024-02-08","cited_by_count":6},{"id":"2502.03460","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","created":"2025-02-05","cited_by_count":6},{"id":"2306.08325","title":"GCformer: An Efficient Framework for Accurate and Scalable Long-Term Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":5},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","cited_by_count":3},{"id":"2405.20710","title":"i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation","created":"2024-05-31","cited_by_count":2},{"id":"1912.00200","title":"Pruning at a Glance: Global Neural Pruning for Model Compression","created":"2019-11-30","cited_by_count":1}],"next_cursor":null}