% Key papers for Neural scaling laws (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_efficient_36174,
  title = {{Efficient softmax approximation for GPUs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/762},
}

@inproceedings{neurips2020_dynabert_59746,
  title = {{DynaBERT: Dynamic BERT with Adaptive Width and Depth}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18572},
}

@inproceedings{iclr2017_improving_28198,
  title = {{Improving Neural Language Models with a Continuous Cache}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=B184E5qee},
}

@inproceedings{neurips2022_beyond_65072,
  title = {{Beyond neural scaling laws: beating power law scaling via data pruning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53016},
}

@inproceedings{icml2018_efficient_36665,
  title = {{Efficient Neural Audio Synthesis}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2333},
}

@inproceedings{aaai2023_adatask_3067,
  title = {{AdaTask: A Task-Aware Adaptive Learning Rate Approach to Multi-Task Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26275},
}

@inproceedings{aaai2021_lrc_847,
  title = {{LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12830-lrc-bert-latent-representation-contrastive-knowledge-distillation-for-natural-language-understanding/},
}

@inproceedings{icml2023_flexgen_42270,
  title = {{FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25041},
}

@inproceedings{neurips2020_bert_59420,
  title = {{BERT Loses Patience: Fast and Robust Inference with Early Exit}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17145},
}

@inproceedings{cvpr2023_you_22587,
  title = {{You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21102},
}

@inproceedings{neurips2023_scaling_69180,
  title = {{Scaling Data-Constrained Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70706},
}

@inproceedings{cvpr2023_ffcv_20960,
  title = {{FFCV: Accelerating Training by Removing Data Bottlenecks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/20996},
}

@inproceedings{icml2023_cramming_41507,
  title = {{Cramming: Training a Language Model on a single GPU in one day.}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23926},
}

@inproceedings{aaai2023_scaling_4619,
  title = {{Scaling Law for Recommendation Models: Towards General-Purpose User Representations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25582},
}

@inproceedings{icml2022_unified_41314,
  title = {{Unified Scaling Laws for Routed Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17819},
}

@inproceedings{neurips2022_revisiting_65667,
  title = {{Revisiting Neural Scaling Laws in Language and Vision}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53499},
}

@inproceedings{iclr2022_scaling_31563,
  title = {{Scaling Laws for Neural Machine Translation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6721},
}

@inproceedings{neurips2024_training_74270,
  title = {{Training Compute-Optimal Protein Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93287},
}

@inproceedings{neurips2022_the_64584,
  title = {{The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53702},
}

@inproceedings{neurips2023_aging_67965,
  title = {{Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71809},
}

@inproceedings{cvpr2024_an_22761,
  title = {{An Empirical Study of Scaling Law for Scene Text Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30144},
}

@inproceedings{cvpr2025_scamo_27572,
  title = {{ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34928},
}

@inproceedings{neurips2025_a_79086,
  title = {{A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=lQYNmlTwtc},
}

@inproceedings{icml2024_actions_45768,
  title = {{Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32684},
}

@inproceedings{neurips2024_exploring_70564,
  title = {{Exploring Molecular Pretraining Model at Scale}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96550},
}

@inproceedings{icml2024_navigating_43382,
  title = {{Navigating Scaling Laws: Compute Optimality in Adaptive Model Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35070},
}

@inproceedings{icml2024_a_45336,
  title = {{A Dynamical Model of Neural Scaling Laws}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33116},
}

@inproceedings{iclr2025_strong_82898,
  title = {{Strong Model Collapse}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/32070},
}

@inproceedings{aaai2024_preparing_6983,
  title = {{Preparing Lessons for Progressive Training on Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29851},
}

@inproceedings{iclr2025_language_83119,
  title = {{Language models scale reliably with over-training and on downstream tasks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28688},
}

@inproceedings{cvpr2025_towards_27920,
  title = {{Towards Precise Scaling Laws for Video Diffusion Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34033},
}

@inproceedings{icml2026_tabiclv2_52126,
  title = {{TabICLv2: A Better, Faster, Scalable, and Open Tabular Foundation Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=SxsyLjIfWB},
}

@inproceedings{neurips2024_scaling_72653,
  title = {{Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94731},
}

@inproceedings{neurips2025_towards_76552,
  title = {{Towards Fully FP8 GEMM LLM Training at Scale}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=KYTFXxTJ12},
}

@inproceedings{iclr2025_cut_81349,
  title = {{Cut Your Losses in Large-Vocabulary Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30424},
}

@inproceedings{aaai2025_alrmr_7978,
  title = {{ALRMR-GEC: Adjusting Learning Rate Based on Memory Rate to Optimize the Edit Scorer for Grammatical Error Correction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35464},
}

@inproceedings{iclr2024_fast_33746,
  title = {{Fast-ELECTRA for Efficient Pre-training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19329},
}

@inproceedings{iclr2024_enhancing_34770,
  title = {{Enhancing Neural Training via a Correlated Dynamics Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18304},
}

@inproceedings{icml2024_wukong_43614,
  title = {{Wukong: Towards a Scaling Law for Large-Scale Recommendation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34838},
}