PPaperPicks
← All conferences
Editions202620252024

MLSys 2024

N

Conference on Machine Learning and Systems

Official site ↗
39
accepted papers
39
authors
May 12-16, 2024
dates
USA
location

39 / 39 papers

  1. 1
    Accelerating ReLU for MPC-Based Private Inference with a Communication-Efficient Sign Estimation
    Kiwan Maeng
    DBLP profile ↗ORCID search ↗
  2. 2
    Accurate Low-Degree Polynomial Approximation of Non-Polynomial Operators for Fast Private Inference in Homomorphic Encryption
    Jingtian Dang
    DBLP profile ↗ORCID search ↗
  3. 3
    ACROBAT: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time
    Pratik Fegade
    DBLP profile ↗ORCID search ↗
  4. 4
    Atom: Low-Bit Quantization for Efficient and Accurate LLM Serving
    Yilong Zhao
    DBLP profile ↗ORCID search ↗
  5. 5
    AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration
    Ji Lin
    DBLP profile ↗ORCID search ↗
  6. 6
    CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation
    Yifei Xu
    DBLP profile ↗ORCID search ↗
  7. 7
    COMET: Neural Cost Model Explanation Framework
    Isha Chaudhary
    DBLP profile ↗ORCID search ↗
  8. 8
    DiffusionPipe: Training Large Diffusion Models with Efficient Pipelines
    Ye Tian
    DBLP profile ↗ORCID search ↗
  9. 9
    Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large Scale Recommendation
    Liang Luo
    DBLP profile ↗ORCID search ↗
  10. 10
    Distributed Matrix-Based Sampling for Graph Neural Network Training
    Alok Tripathy
    DBLP profile ↗ORCID search ↗
  11. 11
    Does Compressing Activations Help Model Parallel Training?
    Song Bian
    DBLP profile ↗ORCID search ↗
  12. 12
    Efficient Post-training Quantization with FP8 Formats
    Haihao Shen
    DBLP profile ↗ORCID search ↗
  13. 13
    FedTrans: Efficient Federated Learning via Multi-Model Transformation
    Yuxuan Zhu
    DBLP profile ↗ORCID search ↗
  14. 14
    Fine-Tuning Language Models Using Formal Methods Feedback: A Use Case in Autonomous Systems
    Yunhao Yang
    DBLP profile ↗ORCID search ↗
  15. 15
    FLASH: Fast Model Adaptation in ML-Centric Cloud Platforms
    Haoran Qiu
    DBLP profile ↗ORCID search ↗
  16. 16
    FlashDecoding++: Faster Large Language Model Inference with Asynchronization, Flat GEMM Optimization, and Heuristics
    Ke Hong
    DBLP profile ↗ORCID search ↗
  17. 17
    HeteGen: Efficient Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices
    Xuanlei Zhao
    DBLP profile ↗ORCID search ↗
  18. 18
    HeteroSwitch: Characterizing and Taming System-Induced Data Heterogeneity in Federated Learning
    Gyudong Kim
    DBLP profile ↗ORCID search ↗
  19. 19
    JIT-Q: Just-in-time Quantization with Processing-In-Memory for Efficient ML Training
    Mohamed Assem Ibrahim
    DBLP profile ↗ORCID search ↗
  20. 20
    Keyformer: KV Cache reduction through key tokens selection for Efficient Generative Inference
    Muhammad Adnan
    DBLP profile ↗ORCID search ↗
  21. 21
    L-GreCo: Layerwise-adaptive Gradient Compression For Efficient Data-parallel Deep Learning
    Ilia Markov
    DBLP profile ↗ORCID search ↗
  22. 22
    Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping
    Chenyu Jiang
    DBLP profile ↗ORCID search ↗
  23. 23
    LIFL: A Lightweight, Event-driven Serverless Platform for Federated Learning
    Shixiong Qi
    DBLP profile ↗ORCID search ↗
  24. 24
    On Latency Predictors for Neural Architecture Search
    Yash Akhauri
    DBLP profile ↗ORCID search ↗
  25. 25
    Proceedings of the Eighth Conference on Machine Learning and Systems, MLSys 2025, Santa Clara, CA, USA, May 12-15, 2025
    Matei Zaharia
    DBLP profile ↗ORCID 0000-0002-7547-7204 ↗
  26. 26
    Proceedings of the Seventh Annual Conference on Machine Learning and Systems, MLSys 2024, Santa Clara, CA, USA, May 13-16, 2024
    Phillip B. Gibbons
    DBLP profile ↗ORCID search ↗
  27. 27
    Prompt Cache: Modular Attention Reuse for Low-Latency Inference
    In Gim
    DBLP profile ↗ORCID search ↗
  28. 28
    Proteus: Preserving Model Confidentiality during Graph Optimizations
    Yubo Gao
    DBLP profile ↗ORCID search ↗
  29. 29
    Punica: Multi-Tenant LoRA Serving
    Lequn Chen
    DBLP profile ↗ORCID search ↗
  30. 30
    Q-Hitter: A Better Token Oracle for Efficient LLM Inference via Sparse-Quantized KV Cache
    Zhenyu Zhang
    DBLP profile ↗ORCID search ↗
  31. 31
    QMoE: Sub-1-Bit Compression of Trillion Parameter Models
    Elias Frantar
    DBLP profile ↗ORCID search ↗
  32. 32
    Schrodinger's FP Training Neural Networks with Dynamic Floating-Point Containers
    Milos Nikolic
    DBLP profile ↗ORCID search ↗
  33. 33
    SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
    Zhixu Du
    DBLP profile ↗ORCID search ↗
  34. 34
    SLoRA: Scalable Serving of Thousands of LoRA Adapters
    Ying Sheng
    DBLP profile ↗ORCID search ↗
  35. 35
    Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design
    Jian Meng
    DBLP profile ↗ORCID search ↗
  36. 36
    UniDM: A Unified Framework for Data Manipulation with Large Language Models
    Yichen Qian
    DBLP profile ↗ORCID search ↗
  37. 37
    VIDUR: A Large-Scale Simulation Framework for LLM Inference
    Amey Agrawal
    DBLP profile ↗ORCID search ↗
  38. 38
    vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUs
    Size Zheng
    DBLP profile ↗ORCID search ↗
  39. 39
    VQPy: An Object-Oriented Approach to Modern Video Analytics
    Shan Yu
    DBLP profile ↗ORCID search ↗