{"list":"other","total":65,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2408.00724","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","created":"2024-08-01","cited_by_count":290},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113},{"id":"2304.03208","title":"Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster","created":"2023-04-06","cited_by_count":109},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88},{"id":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"2404.10102","title":"Chinchilla Scaling: A replication attempt","created":"2024-04-15","cited_by_count":72},{"id":"2405.15074","title":"4+3 Phases of Compute-Optimal Neural Scaling Laws","created":"2024-05-23","cited_by_count":68},{"id":"2501.12370","title":"Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models","created":"2025-01-21","cited_by_count":50},{"id":"1907.10121","title":"SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python","created":"2019-07-23","cited_by_count":49},{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44},{"id":"2403.14606","title":"The Elements of Differentiable Programming","created":"2024-03-21","cited_by_count":43},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39},{"id":"2308.01814","title":"Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit","created":"2023-08-03","cited_by_count":38},{"id":"2411.06646","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","created":"2024-11-11","cited_by_count":30},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29},{"id":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27},{"id":"2407.21075","title":"Apple Intelligence Foundation Language Models","created":"2024-07-29","cited_by_count":24},{"id":"2410.18837","title":"High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws","created":"2024-10-24","cited_by_count":22},{"id":"2005.10419","title":"Why distillation helps: a statistical perspective","created":"2020-05-21","cited_by_count":21},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18},{"id":"2407.04600","title":"Understanding the Gains from Repeated Self-Distillation","created":"2024-07-05","cited_by_count":15},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15},{"id":"2408.16947","title":"An Empirical Study of Scaling Laws for Transfer","created":"2024-08-30","cited_by_count":9},{"id":"2212.12965","title":"BD-KD: Balancing the Divergences for Online Knowledge Distillation","created":"2022-12-25","cited_by_count":7},{"id":"2411.14478","title":"Why you don't overfit, and don't need Bayes if you only train for one epoch","created":"2024-11-19","cited_by_count":2}],"next_cursor":null}