{"total":111,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204,"area":null},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204,"area":null},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2402.07871","title":"Scaling Laws for Fine-Grained Mixture of Experts","created":"2024-02-12","cited_by_count":173,"area":"moe"},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"area":null},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132,"area":null},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2406.00899","title":"YODAS: Youtube-Oriented Dataset for Audio and Speech","created":"2024-06-02","cited_by_count":60,"area":null},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44,"area":null},{"id":"2208.04347","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","created":"2022-08-08","cited_by_count":43,"area":null},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2301.13442","title":"Scaling laws for single-agent reinforcement learning","created":"2023-01-31","cited_by_count":41,"area":null},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"area":null},{"id":"2505.14738","title":"R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science","created":"2025-05-20","cited_by_count":41,"area":"agents"},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2404.06393","title":"MuPT: A Generative Symbolic Music Pretrained Transformer","created":"2024-04-09","cited_by_count":33,"area":null},{"id":"2406.15720","title":"Scaling Laws for Fact Memorization of Large Language Models","created":"2024-06-22","cited_by_count":33,"area":null},{"id":"2410.12360","title":"Towards Neural Scaling Laws for Time Series Foundation Models","created":"2024-10-16","cited_by_count":33,"area":null},{"id":"2302.09650","title":"Scaling Laws for Multilingual Neural Machine Translation","created":"2023-02-19","cited_by_count":27,"area":null},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2110.05448","title":"Unsupervised Neural Machine Translation with Generative Language Models Only","created":"2021-10-11","cited_by_count":24,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2202.06387","title":"Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments","created":"2022-02-13","cited_by_count":23,"area":null},{"id":"2212.07530","title":"Causes and Cures for Interference in Multilingual Translation","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2410.12883","title":"Scaling Laws for Multilingual Language Models","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2506.08228","title":"Scaling Laws of Motion Forecasting and Planning -- Technical Report","created":"2025-06-09","cited_by_count":19,"area":null},{"id":"2301.10309","title":"Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interaction","created":"2023-01-24","cited_by_count":16,"area":null},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2309.01826","title":"One Wide Feedforward is All You Need","created":"2023-09-04","cited_by_count":15,"area":null},{"id":"2412.07942","title":"Neural Scaling Laws Rooted in the Data Distribution","created":"2024-12-10","cited_by_count":15,"area":null},{"id":"2203.02094","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","created":"2022-03-04","cited_by_count":14,"area":null},{"id":"2209.13435","title":"Scaling Laws For Deep Learning Based Image Reconstruction","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2210.13447","title":"Precision Machine Learning","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2505.03793","title":"LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2402.02054","title":"Towards Neural Scaling Laws on Graphs","created":"2024-02-03","cited_by_count":13,"area":null},{"id":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2405.04912","title":"GP-MoLFormer: A Foundation Model For Molecular Generation","created":"2024-04-04","cited_by_count":11,"area":null},{"id":"2205.11747","title":"BabyBear: Cheap inference triage for expensive language models","created":"2022-05-24","cited_by_count":10,"area":null},{"id":"2306.11475","title":"Delegated Classification","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2502.07503","title":"Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2407.01300","title":"Collaborative Performance Prediction for Large Language Models","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2304.03216","title":"On the Pareto Front of Multilingual Neural Machine Translation","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2502.05074","title":"Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2308.16561","title":"MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis","created":"2023-08-31","cited_by_count":6,"area":"distill"},{"id":"2510.08565","title":"NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints","created":"2025-10-09","cited_by_count":6,"area":"lr"},{"id":"2310.13913","title":"Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2509.24012","title":"Pretraining Scaling Laws for Generative Evaluations of Language Models","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2510.03313","title":"Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2210.14593","title":"Scaling Laws Beyond Backpropagation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2303.17183","title":"The Nordic Pile: A 1.2TB Nordic Dataset for Language Modeling","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2305.12057","title":"Accurate Knowledge Distillation with n-best Reranking","created":"2023-05-20","cited_by_count":4,"area":"distill"},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2403.09832","title":"Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks","created":"2024-03-14","cited_by_count":4,"area":"safety"},{"id":"2408.11243","title":"Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2409.15051","title":"Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.02657","title":"Less LLM, More Documents: Searching for Improved RAG","created":"2025-10-03","cited_by_count":4,"area":"rag"},{"id":"2504.03635","title":"Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models","created":"2025-04-04","cited_by_count":3,"area":"lr"},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2204.09259","title":"DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2305.14124","title":"When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2402.02084","title":"Revisiting the Markov Property for Machine Translation","created":"2024-02-03","cited_by_count":2,"area":null},{"id":"2501.12486","title":"The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2507.10613","title":"Sub-Scaling Laws: On the Role of Data Density and Training Strategies in LLMs","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2604.12911","title":"Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2605.08296","title":"BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2112.08570","title":"Can Multilinguality benefit Non-autoregressive Machine Translation?","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2305.06155","title":"Leveraging Synthetic Targets for Machine Translation","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2307.08426","title":"Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts","created":"2023-07-17","cited_by_count":1,"area":"distill"},{"id":"2505.23032","title":"Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.12932","title":"Complexity Scaling Laws for Neural Models using Combinatorial Optimization","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2509.18353","title":"MolPILE -- large-scale, diverse dataset for molecular representation learning","created":"2025-09-22","cited_by_count":1,"area":null}],"next_cursor":"100"}