PPaperPicks
← All conferences
Editions202620252024

MLSys 2025

N

Conference on Machine Learning and Systems

Official site ↗
61
accepted papers
61
authors
May 13-16, 2025
dates
USA
location

61 / 61 papers

  1. 1
    A Bring-Your-Own-Model Approach for ML-Driven Storage Placement in Warehouse-Scale Computers
    Chenxi Yang
    DBLP profile ↗ORCID search ↗
  2. 2
    AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine
    Carlo Siebenschuh
    DBLP profile ↗ORCID search ↗
  3. 3
    AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution
    Zhiqiang Xie
    DBLP profile ↗ORCID search ↗
  4. 4
    AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
    Yinfang Chen
    DBLP profile ↗ORCID search ↗
  5. 5
    APOLLO: SGD-like Memory, AdamW-level Performance
    Hanqing Zhu
    DBLP profile ↗ORCID search ↗
  6. 6
    Balancing Pipeline Parallelism with Vocabulary Parallelism
    Man Tsung Yeung
    DBLP profile ↗ORCID search ↗
  7. 7
    COMET: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
    Shulai Zhang
    DBLP profile ↗ORCID search ↗
  8. 8
    Context Parallelism for Scalable Million-Token Inference
    Amy Yang
    DBLP profile ↗ORCID search ↗
  9. 9
    DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling
    Sohaib Ahmad
    DBLP profile ↗ORCID search ↗
  10. 10
    Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking
    Marco Federici
    DBLP profile ↗ORCID search ↗
  11. 11
    Efficient On-Device Machine Learning with a Biologically-Plausible Forward-Only Algorithm
    Baichuan Huang
    DBLP profile ↗ORCID search ↗
  12. 12
    Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators
    Geonhwa Jeong
    DBLP profile ↗ORCID search ↗
  13. 13
    FastTree: Optimizing Attention Kernel and Runtime for Tree-Structured LLM Inference
    Zaifeng Pan
    DBLP profile ↗ORCID search ↗
  14. 14
    FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning
    Minxue Tang
    DBLP profile ↗ORCID search ↗
  15. 15
    FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving
    Zihao Ye
    DBLP profile ↗ORCID search ↗
  16. 16
    FlexAttention: A Programming Model for Generating Fused Attention Variants
    Juechu Dong
    DBLP profile ↗ORCID search ↗
  17. 17
    FlexInfer: Flexible LLM Inference with CPU Computations
    Seonjin Na
    DBLP profile ↗ORCID search ↗
  18. 18
    FLStore: Efficient Federated Learning Storage for non-training workloads
    Ahmad Faraz Khan
    DBLP profile ↗ORCID search ↗
  19. 19
    Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs
    Zichao Yue
    DBLP profile ↗ORCID search ↗
  20. 20
    HyC-LoRA: Memory Efficient LoRA Fine-tuning with Hybrid Activation Compression
    Yujin Wang
    DBLP profile ↗ORCID search ↗
  21. 21
    Interference-aware Edge Runtime Prediction with Conformal Matrix Completion
    Tianshu Huang
    DBLP profile ↗ORCID search ↗
  22. 22
    Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
    Neel P. Bhatt
    DBLP profile ↗ORCID search ↗
  23. 23
    LAVA: Lifetime-Aware VM Allocation with Learned Distributions and Adaptation to Mispredictions
    Jianheng Ling
    DBLP profile ↗ORCID search ↗
  24. 24
    LeanAttention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers
    Rya Sanovar
    DBLP profile ↗ORCID search ↗
  25. 25
    Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers
    Francesco Daghero
    DBLP profile ↗ORCID search ↗
  26. 26
    LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
    Shang Yang
    DBLP profile ↗ORCID search ↗
  27. 27
    Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training
    Mingyu Liang
    DBLP profile ↗ORCID search ↗
  28. 28
    Marconi: Prefix Caching for the Era of Hybrid LLMs
    Rui Pan
    DBLP profile ↗ORCID search ↗
  29. 29
    Mas-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-constrained Edge Devices
    Mohammadali Shakerdargah
    DBLP profile ↗ORCID search ↗
  30. 30
    MEADOW: Memory-efficient Dataflow and Data Packing for Low Power Edge LLMs
    Abhishek Moitra
    DBLP profile ↗ORCID search ↗
  31. 31
    MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators
    Beichen Huang
    DBLP profile ↗ORCID search ↗
  32. 32
    NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference
    Xuanlin Jiang
    DBLP profile ↗ORCID search ↗
  33. 33
    On Distributed Larger-Than-Memory Subset Selection With Pairwise Submodular Functions
    Maximilian Böther
    DBLP profile ↗ORCID search ↗
  34. 34
    Optimizing LLM Queries in Relational Data Analytics Workloads
    Shu Liu
    DBLP profile ↗ORCID search ↗
  35. 35
    Photon: Federated LLM Pre-Training
    Lorenzo Sani
    DBLP profile ↗ORCID search ↗
  36. 36
    PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
    Daiyaan Arfeen
    DBLP profile ↗ORCID search ↗
  37. 37
    ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In the Cloud
    Lu Wang
    DBLP profile ↗ORCID 0000-0002-7305-1496 ↗
  38. 38
    QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
    Yujun Lin
    DBLP profile ↗ORCID search ↗
  39. 39
    Radius: Range-based Gradient Sparsity for Large Foundation Model Pre-training
    Mingkai Zheng
    DBLP profile ↗ORCID search ↗
  40. 40
    ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation
    Zhiyu Mei
    DBLP profile ↗ORCID search ↗
  41. 41
    Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
    Wei Gao
    DBLP profile ↗ORCID search ↗
  42. 42
    Rubick: Exploiting Job Reconfigurability for Deep Learning Cluster Scheduling
    Xinyi Zhang
    DBLP profile ↗ORCID search ↗
  43. 43
    SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
    Qianchao Zhu
    DBLP profile ↗ORCID search ↗
  44. 44
    ScaleFusion: Scalable Inference of Spatial-Temporal Diffusion Transformers for High-Resolution Long Video Generation
    Jiacheng Yang
    DBLP profile ↗ORCID search ↗
  45. 45
    Scaling Deep Learning Training with MPMD Pipeline Parallelism
    Anxhelo Xhebraj
    DBLP profile ↗ORCID search ↗
  46. 46
    Seesaw: High-throughput LLM Inference via Model Re-sharding
    Qidong Su
    DBLP profile ↗ORCID search ↗
  47. 47
    Self-Data Distillation for Recovering Quality in Pruned Large Language Models
    Vithursan Thangarasa
    DBLP profile ↗ORCID search ↗
  48. 48
    SOLA: Optimizing SLO Attainment for Large Language Model Serving with State-Aware Scheduling
    Ke Hong
    DBLP profile ↗ORCID search ↗
  49. 49
    Spa: Scaling Graph Neural Network Training on Large graphs via Probabilistic splitting
    Sandeep Polisetty
    DBLP profile ↗ORCID search ↗
  50. 50
    SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix Operations
    Md. Saidul Hoque Anik
    DBLP profile ↗ORCID search ↗