% Key papers for Distributed LLM inference systems (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2018_deep_28623,
  title = {{Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/68},
}

@inproceedings{cvpr2021_checkerboard_16700,
  title = {{Checkerboard Context Model for Efficient Learned Image Compression}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{icml2017_resource_36367,
  title = {{Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/696},
}

@inproceedings{icml2018_coded_36576,
  title = {{Coded Sparse Matrix Multiplication}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1924},
}

@inproceedings{iclr2018_a_28541,
  title = {{A Hierarchical Model for Device Placement}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/140},
}

@inproceedings{neurips2018_pipe_57508,
  title = {{Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11771},
}

@inproceedings{icml2019_ithemal_37458,
  title = {{Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4057},
}

@inproceedings{aaai2023_ahpa_3041,
  title = {{AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26852},
}

@inproceedings{cvpr2018_efficient_13055,
  title = {{Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Efficient_Large-Scale_Approximate_CVPR_2018_paper.html},
}

@inproceedings{aaai2023_ising_3933,
  title = {{Ising-Traffic: Using Ising Machine Learning to Predict Traffic Congestion under Uncertainty}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26121},
}

@inproceedings{neurips2023_xtrimogene_69038,
  title = {{xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70837},
}

@inproceedings{aaai2022_etinynet_2056,
  title = {{EtinyNet: Extremely Tiny Network for TinyML}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/04628-etinynet-extremely-tiny-network-for-tinyml/},
}

@inproceedings{neurips2020_hm_59983,
  title = {{HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16906},
}

@inproceedings{icml2021_massively_39594,
  title = {{Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10157},
}

@inproceedings{neurips2023_scissorhands_67701,
  title = {{Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72050},
}

@inproceedings{icml2023_bibench_41494,
  title = {{BiBench: Benchmarking and Analyzing Network Binarization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25256},
}

@inproceedings{aaai2023_drop_3503,
  title = {{Drop Clause: Enhancing Performance, Robustness and Pattern Recognition Capabilities of the Tsetlin Machine}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26588},
}

@inproceedings{aaai2021_a_15,
  title = {{A Flexible Framework for Communication-Efficient Machine Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08101-a-flexible-framework-for-communication-efficient-machine-learning/},
}

@inproceedings{neurips2022_understanding_64106,
  title = {{Understanding Hyperdimensional Computing for Parallel Single-Pass Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53876},
}

@inproceedings{neurips2020_autosync_59407,
  title = {{AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18220},
}

@inproceedings{aaai2025_light_9791,
  title = {{Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33062},
}

@inproceedings{neurips2024_pipeline_72495,
  title = {{Pipeline Parallelism with Controllable Memory}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94868},
}

@inproceedings{aaai2024_disjoint_5716,
  title = {{Disjoint Partial Enumeration without Blocking Clauses}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28652},
}

@inproceedings{aaai2024_harnessing_6192,
  title = {{Harnessing Manycore Processors with Distributed Memory for Accelerated Training of Sparse and Recurrent Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29087},
}

@inproceedings{aaai2025_l3tc_9660,
  title = {{L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33446},
}

@inproceedings{aaai2024_incorporating_6313,
  title = {{Incorporating Serverless Computing into P2P Networks for ML Training: In-Database Tasks and Their Scalability Implications (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30419},
}

@inproceedings{aaai2025_tinyfoa_11007,
  title = {{TinyFoA: Memory Efficient Forward-Only Algorithm for On-Device Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33910},
}

@inproceedings{neurips2024_privcirnet_72457,
  title = {{PrivCirNet: Efficient Private Inference via Block Circulant Transformation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94901},
}

@inproceedings{aaai2025_massively_9914,
  title = {{Massively Parallel Continuous Local Search for Hybrid SAT Solving on GPUs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33211},
}

@inproceedings{neurips2024_scalable_70547,
  title = {{Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96566},
}

@inproceedings{neurips2025_dynapipe_75880,
  title = {{DynaPipe: Dynamic Layer Redistribution for Efficient Serving of LLMs with Pipeline Parallelism}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=D6w7wIN360},
}

@inproceedings{neurips2025_towards_78846,
  title = {{Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=isil4sVqSQ},
}

@inproceedings{aaai2026_closertome_107427,
  title = {{CloserToMe: A Unified Framework for Accurate and Transferable Latency Prediction Across Heterogeneous Devices}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39779},
}

@inproceedings{aaai2025_csr_8365,
  title = {{CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34779},
}

@inproceedings{aaai2025_compression_8479,
  title = {{Compression-Aware Computing for Scalable and Sustainable AI}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35126},
}

@inproceedings{cvpr2025_uniap_27995,
  title = {{UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34343},
}

@inproceedings{iclr2024_co2_34675,
  title = {{CO2: Efficient Distributed Training with Full Communication-Computation Overlap}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18399},
}

@inproceedings{icml2024_towards_44632,
  title = {{Towards a Better Theoretical Understanding of Independent Subnetwork Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33820},
}

@inproceedings{icml2024_get_45639,
  title = {{Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32813},
}

@inproceedings{icml2025_efficiently_48499,
  title = {{Efficiently Serving Large Multimodal Models Using EPD Disaggregation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44120},
}