{"total":112,"rows":[{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184,"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":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"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":"2409.09359","title":"Symbolic Regression with a Learned Concept Library","created":"2024-09-14","cited_by_count":83,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2311.17241","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","created":"2023-11-28","cited_by_count":47,"area":null},{"id":"2305.17564","title":"Federated Conformal Predictors for Distributed Uncertainty Quantification","created":"2023-05-27","cited_by_count":46,"area":null},{"id":"2309.04255","title":"LLMCad: Fast and Scalable On-device Large Language Model Inference","created":"2023-09-08","cited_by_count":45,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","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":"2401.04757","title":"How predictable is language model benchmark performance?","created":"2024-01-09","cited_by_count":37,"area":null},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2403.04547","title":"CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?","created":"2024-03-07","cited_by_count":35,"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":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2407.11095","title":"DeepGate3: Towards Scalable Circuit Representation Learning","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2412.15321","title":"Next Patch Prediction for Autoregressive Visual Generation","created":"2024-12-19","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":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"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":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20,"area":null},{"id":"2307.02460","title":"Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources","created":"2023-07-05","cited_by_count":16,"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":"2310.16621","title":"ArTST: Arabic Text and Speech Transformer","created":"2023-10-25","cited_by_count":14,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"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":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2306.14975","title":"The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2502.17262","title":"Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2502.19320","title":"Shh, don't say that! Domain Certification in LLMs","created":"2025-02-26","cited_by_count":7,"area":null},{"id":"2509.06467","title":"Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2209.14969","title":"Transfer Learning with Pretrained Remote Sensing Transformers","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2406.02052","title":"PETRA: Parallel End-to-end Training with Reversible Architectures","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2305.15248","title":"Delving Deeper into Data Scaling in Masked Image Modeling","created":"2023-05-24","cited_by_count":5,"area":null},{"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":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","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":"2509.12818","title":"Data Scaling Laws for Radiology Foundation Models","created":"2025-09-16","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":"2303.01598","title":"A Meta-Learning Approach to Predicting Performance and Data Requirements","created":"2023-03-02","cited_by_count":4,"area":null},{"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":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2410.12119","title":"Scaling Laws for Post Training Quantized Large Language Models","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2502.04066","title":"Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training","created":"2025-02-06","cited_by_count":4,"area":null},{"id":"2507.11690","title":"The Impact of Coreset Selection on Spurious Correlations and Group Robustness","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2510.09768","title":"Scaling Laws and Symmetry, Evidence from Neural Force Fields","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2305.10210","title":"Object Re-Identification from Point Clouds","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2406.16988","title":"MD tree: a model-diagnostic tree grown on loss landscape","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2407.17120","title":"Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2412.05313","title":"{\\lambda}: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2306.00693","title":"GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2306.07215","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2311.01358","title":"The Universal Statistical Structure and Scaling Laws of Chaos and Turbulence","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2501.15001","title":"What if Eye...? Computationally Recreating Vision Evolution","created":"2025-01-25","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":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2605.26248","title":"Unified Neural Scaling Laws","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2311.13583","title":"Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2402.05675","title":"Is Adversarial Training with Compressed Datasets Effective?","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.06311","title":"How much data do you need? Part 2: Predicting DL class specific training dataset sizes","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2409.10142","title":"AALF: Almost Always Linear Forecasting","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2503.10686","title":"MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2505.15657","title":"LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.19990","title":"Progressive Scaling Visual Object Tracking","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2505.21813","title":"Optimizing Data Augmentation through Bayesian Model Selection","created":"2025-05-27","cited_by_count":1,"area":null},{"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":"2506.00398","title":"Position: Olfaction Standardization is Essential for the Advancement of Embodied Artificial Intelligence","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2506.02882","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","created":"2025-06-03","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":"2509.10000","title":"Neural Scaling Laws for Deep Regression","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.18120","title":"A Coopetitive-Compatible Data Generation Framework for Cross-silo Federated Learning","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2509.26397","title":"Are neural scaling laws leading quantum chemistry astray?","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2511.13078","title":"A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learning","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.23903","title":"Scaling Remote Sensing Foundation Models: Data Domain Tradeoffs at the Peta-Scale","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2604.19089","title":"Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2406.08149","title":"Universal Scale Laws for Colors and Patterns in Imagery","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2407.17954","title":"Scaling Training Data with Lossy Image Compression","created":"2024-07-25","cited_by_count":0,"area":null},{"id":"2409.19104","title":"Responsible AI in Open Ecosystems: Reconciling Innovation with Risk Assessment and Disclosure","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2410.19810","title":"Training Compute-Optimal Vision Transformers for Brain Encoding","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2411.05225","title":"Breaking The Ice: Video Segmentation for Close-Range Ice-Covered Waters","created":"2024-11-07","cited_by_count":0,"area":null},{"id":"2503.18979","title":"Threshold Crossings as Tail Events for Catastrophic AI Risk","created":"2025-03-23","cited_by_count":0,"area":null}],"next_cursor":"100"}