% Key papers for Transformer expressivity and circuits (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages. @inproceedings{iclr2019_universal_28995, title = {{Universal Transformers}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2019}, url = {https://iclr.cc/virtual/2019/poster/1068}, } @inproceedings{neurips2021_r_62684, title = {{R-Drop: Regularized Dropout for Neural Networks}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2021}, url = {https://nips.cc/virtual/2021/poster/27494}, } @inproceedings{aaai2021_compound_280, title = {{Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2021}, url = {https://aaai.org/papers/00178-compound-word-transformer-learning-to-compose-full-song-music-over-dynamic-directed-hypergraphs/}, } @inproceedings{cvpr2022_bridging_18394, title = {{Bridging Global Context Interactions for High-Fidelity Image Completion}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, } @inproceedings{iclr2017_structured_28272, title = {{Structured Attention Networks}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2017}, url = {https://openreview.net/forum?id=HkE0Nvqlg}, } @inproceedings{iclr2019_on_28957, title = {{On the Turing Completeness of Modern Neural Network Architectures}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2019}, url = {https://iclr.cc/virtual/2019/poster/707}, } @inproceedings{aaai2022_handwritten_2182, title = {{Handwritten Mathematical Expression Recognition via Attention Aggregation Based Bi-directional Mutual Learning}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2022}, url = {https://aaai.org/papers/00113-handwritten-mathematical-expression-recognition-via-attention-aggregation-based-bi-directional-mutual-learning/}, } @inproceedings{cvpr2023_masked_21535, title = {{Masked Image Modeling With Local Multi-Scale Reconstruction}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, url = {https://cvpr.thecvf.com/virtual/2023/poster/23258}, } @inproceedings{iclr2019_hyperbolic_29168, title = {{Hyperbolic Attention Networks}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2019}, url = {https://iclr.cc/virtual/2019/poster/805}, } @inproceedings{cvpr2022_neural_19435, title = {{Neural Inertial Localization}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, } @inproceedings{neurips2023_biot_68727, title = {{BIOT: Biosignal Transformer for Cross-data Learning in the Wild}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023}, url = {https://nips.cc/virtual/2023/poster/71117}, } @inproceedings{cvpr2024_sharingan_24813, title = {{Sharingan: A Transformer Architecture for Multi-Person Gaze Following}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, url = {https://cvpr.thecvf.com/virtual/2024/poster/29721}, } @inproceedings{aaai2025_robust_10579, title = {{Robust Tracking via Mamba-based Context-aware Token Learning}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/32943}, } @inproceedings{cvpr2022_collaborative_18482, title = {{Collaborative Transformers for Grounded Situation Recognition}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, } @inproceedings{aaai2025_miett_9852, title = {{MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/33748}, } @inproceedings{neurips2022_museformer_64438, title = {{Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022}, url = {https://nips.cc/virtual/2022/poster/54604}, } @inproceedings{aaai2021_transformer_1555, title = {{Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2021}, url = {https://aaai.org/papers/04546-transformer-style-relational-reasoning-with-dynamic-memory-updating-for-temporal-network-modeling/}, } @inproceedings{neurips2019_compositional_58016, title = {{Compositional De-Attention Networks}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2019}, url = {https://nips.cc/virtual/2019/poster/13730}, } @inproceedings{neurips2020_neural_60396, title = {{Neural Execution Engines: Learning to Execute Subroutines}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2020}, url = {https://nips.cc/virtual/2020/poster/18724}, } @inproceedings{aaai2023_fine_3699, title = {{Fine-Grained Position Helps Memorizing More, a Novel Music Compound Transformer Model with Feature Interaction Fusion}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2023}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/25650}, } @inproceedings{aaai2024_n_6733, title = {{N-gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/29461}, } @inproceedings{neurips2024_du_74322, title = {{Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/93238}, } @inproceedings{neurips2025_csbrain_78059, title = {{CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=agcXjEHmyW}, } @inproceedings{neurips2025_a_79984, title = {{A Generalist Intracortical Motor Decoder}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=utXSSdD9mt}, } @inproceedings{neurips2024_causal_70956, title = {{Causal Context Adjustment Loss for Learned Image Compression}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/96247}, } @inproceedings{iclr2025_cbramod_81904, title = {{CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025}, url = {https://iclr.cc/virtual/2025/poster/29880}, } @inproceedings{aaai2025_harnessing_9408, title = {{Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model Approach}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34138}, } @inproceedings{icml2024_decomposing_45502, title = {{Decomposing and Editing Predictions by Modeling Model Computation}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2024}, url = {https://icml.cc/virtual/2024/poster/32949}, } @inproceedings{aaai2025_breaking_8302, title = {{Breaking Information Isolation: Accelerating MRI via Inter-sequence Mapping and Progressive Masking}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/33147}, } @inproceedings{iclr2024_spatially_34528, title = {{Spatially-Aware Transformers for Embodied Agents}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/18546}, } @inproceedings{iclr2024_tree_34584, title = {{Tree Cross Attention}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/18490}, } @inproceedings{icml2026_thinking_51389, title = {{Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=LgFmen6sHP}, } @inproceedings{icml2026_quantifying_52304, title = {{Quantifying LLM Attention-Head Stability: Implications for Circuit Universality}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=UXzfLdXrBJ}, } @inproceedings{icml2026_emformer_53123, title = {{EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=cKztWFFGNE}, } @inproceedings{icml2026_language_54287, title = {{Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=nZy6lUWvhI}, } @inproceedings{icml2026_pianist_54455, title = {{Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=p6Ar2d4Cwr}, } @inproceedings{neurips2025_dynamic_75413, title = {{Dynamic Semantic-Aware Correlation Modeling for UAV Tracking}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=7lLnWh0otf}, }