{"list":"other","total":52,"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"2403.17919","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","created":"2024-03-26","cited_by_count":89},{"id":"2405.03917","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","created":"2024-05-07","cited_by_count":76},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54},{"id":"2402.05445","title":"Accurate LoRA-Finetuning Quantization of LLMs via Information Retention","created":"2024-02-08","cited_by_count":41},{"id":"2402.10193","title":"BitDelta: Your Fine-Tune May Only Be Worth One Bit","created":"2024-02-15","cited_by_count":39},{"id":"2401.16405","title":"Scaling Sparse Fine-Tuning to Large Language Models","created":"2024-01-29","cited_by_count":26},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22},{"id":"1406.5986","title":"A Statistical Perspective on Randomized Sketching for Ordinary Least-Squares","created":"2014-06-23","cited_by_count":21},{"id":"2403.01273","title":"NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention","created":"2024-03-02","cited_by_count":12},{"id":"1911.11177","title":"Structured Multi-Hashing for Model Compression","created":"2019-11-25","cited_by_count":10},{"id":"2405.15525","title":"Sparse Matrix in Large Language Model Fine-tuning","created":"2024-05-24","cited_by_count":8},{"id":"2309.16119","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","created":"2023-09-28","cited_by_count":6},{"id":"1901.11261","title":"Higher-order Count Sketch: Dimensionality Reduction That Retains Efficient Tensor Operations","created":"2019-01-31","cited_by_count":5},{"id":"2310.11611","title":"In defense of parameter sharing for model-compression","created":"2023-10-17","cited_by_count":5},{"id":"1710.07850","title":"Deep Neural Network Approximation using Tensor Sketching","created":"2017-10-21","cited_by_count":3},{"id":"1604.05753","title":"Sketching and Neural Networks","created":"2016-04-19","cited_by_count":1}],"next_cursor":null}