% Key papers for Pruning and circuits in LLMs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2020_mixout_29501,
  title = {{Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HkgaETNtDB},
}

@inproceedings{cvpr2024_llms_23896,
  title = {{LLMs are Good Sign Language Translators}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30247},
}

@inproceedings{aaai2021_xl_1646,
  title = {{XL-WSD: An Extra-Large and Cross-Lingual Evaluation Framework for Word Sense Disambiguation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13648-xl-wsd-an-extra-large-and-cross-lingual-evaluation-framework-for-word-sense-disambiguation/},
}

@inproceedings{neurips2022_memorization_66249,
  title = {{Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54693},
}

@inproceedings{aaai2024_fluctuation_6031,
  title = {{Fluctuation-Based Adaptive Structured Pruning for Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28960},
}

@inproceedings{neurips2022_exploring_66505,
  title = {{Exploring Length Generalization in Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/52978},
}

@inproceedings{aaai2024_fairness_5966,
  title = {{Fairness-Aware Structured Pruning in Transformers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30256},
}

@inproceedings{aaai2017_on_101424,
  title = {{On the Transitivity of Hypernym-Hyponym Relations in Data-Driven Lexical Taxonomies}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10675},
}

@inproceedings{aaai2024_sparsity_7381,
  title = {{Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30160},
}

@inproceedings{aaai2022_vast_2931,
  title = {{VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/11477-vast-the-valence-assessing-semantics-test-for-contextualizing-language-models/},
}

@inproceedings{neurips2024_infllm_72931,
  title = {{InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94480},
}

@inproceedings{neurips2024_exploring_74650,
  title = {{Exploring Context Window of Large Language Models via Decomposed Positional Vectors}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92943},
}

@inproceedings{aaai2025_prompt_10375,
  title = {{Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34639},
}

@inproceedings{iclr2025_nv_83308,
  title = {{NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28505},
}

@inproceedings{iclr2024_the_35275,
  title = {{The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17798},
}

@inproceedings{iclr2024_in_35500,
  title = {{In-context Autoencoder for Context Compression in a Large Language Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17573},
}

@inproceedings{neurips2024_beacon_74000,
  title = {{BEACON: Benchmark for Comprehensive RNA Tasks and Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97501},
}

@inproceedings{aaai2024_what_7811,
  title = {{What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29765},
}

@inproceedings{iclr2023_unimax_33080,
  title = {{UniMax: Fairer and More Effective Language Sampling for Large-Scale Multilingual Pretraining}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10763},
}

@inproceedings{aaai2024_mid_6580,
  title = {{MID-FiLD: MIDI Dataset for Fine-Level Dynamics}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27774},
}

@inproceedings{icml2024_pruner_43324,
  title = {{Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35128},
}

@inproceedings{icml2026_mmbert_53744,
  title = {{mmBERT: A Modern Multilingual Encoder with Annealed Language Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=iJDJCO4mji},
}

@inproceedings{neurips2024_scaling_74146,
  title = {{Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93395},
}

@inproceedings{iclr2024_what_34448,
  title = {{What's In My Big Data?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18626},
}

@inproceedings{iclr2024_attention_34936,
  title = {{Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18138},
}

@inproceedings{aaai2024_machine_6593,
  title = {{Machine-Created Universal Language for Cross-Lingual Transfer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29824},
}

@inproceedings{aaai2025_3d_7867,
  title = {{3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34662},
}