Workload

Ask about this topic

Momentum

3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 69

All topics
CardsList

  1. AgBench: Agentic AI Benchmarks for Personal AI Devices

    Sep 29, 2026Yizhou Han, Di Wu, Dhananjay Saikumar +1Agentic BenchmarksArtificial Intelligence Systems

    University of St Andrews, UK · Zhejiang University of Technology, China

  2. When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse

    Sep 24, 2026Yiyu Liu, Minlan Yu, Juncheng YangEvictionCache

    Harvard University

  3. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

    Sep 17, 2026DeepSeek-AI, :, Anyi Xu +590Key-Value Cache CompressionKey-Value Cache

  4. Artificial Intelligence for Energy Optimization in Data Centers

    Sep 3, 2026Mohammed Basharath Ullah, Summaiya Unnisa Begum, Mohammed Nadeem UllahEnergy-EfficientEnergy Resources

    Hyderabad, India

  5. Workload Identification with Physical Side Channels for AI Governance

    Aug 31, 2026Simone Gargiulo, Gabriel KulpGraphics Processing Unit ResourcesWorkload

    Pivotal Research · Intelligence Security Laboratories

  6. Intelligent Edge Computing

    Aug 31, 2026Kalgi Gandhi, Minal BhiseIntelligent EdgeWorkload

    Pandit Deendayal Energy University, Gandhinagar, Gujarat, India · Distributed Databases Group, Dhirubhai Ambani University, Gandhinagar, Gujarat, India

  7. KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models

    Aug 10, 2026Chen Qiu, Ziwu Liu, Chao Fei +2Key-Value Cache CompressionDiagnostic Benchmark

    KAUST Thuwal, Saudi Arabia

  8. LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm

    Aug 6, 2026Anjali Gangadhar Katageria, Shobha Rani, Raghu Nandan SenguptaWorkloadQueue Control

    Department of Mathematics, Indian Institute of Technology Dharwad, Dharwad, Karnataka, India · Department of Management Sciences, Indian Institute of Technology Kanpur, Kanpur, Uttar Pradesh, India

  9. OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality

    Aug 5, 2026Yidian Chen, Yingzi Gu, Natan Vidra +2Multi-Agent OrchestrationOrchestration

    Anote

  10. DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization

    Aug 3, 2026Minnan Pei, Gang Li, Zeyu Zhu +7Dynamic 3D Gaussian SplattingScalability

    Institute of Automation, Chinese Academy of Sciences, C2DL, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Shanghai Jiao Tong University, Shanghai, China

  11. Understanding Online Failure Prediction in Linux Through Complementary Multi-View Explainability

    Aug 1, 2026Diogo Dória, João R. CamposEarly Failure PredictionWorkload

    University of Coimbra, CISUC/LASI Department of Informatics Engineering Coimbra, Portugal

  12. Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces

    Aug 1, 2026Liming Liu, Chao Hu, Mingfei Lu +7Large Language Model ServingWorkload

    Central South University, Changsha, China · University of Technology Sydney, Sydney, Australia · Chongqing Normal University, Chongqing, China +2

  13. Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale

    Jul 30, 2026Banruo Liu, Haoran Qiu, Íñigo Goiri +3Coding AgentsCopilot

    UIUC · Microsoft Azure Research · Microsoft Azure

  14. Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet

    Jul 27, 2026Eliseo CurcioLarge Language Model TrainingOptimal Power Shutoff

    Advanced Department of Artificial Intelligence and Energy – New York

  15. WISERouter: LLM Routing with Workload Budget Constraint

    Jul 26, 2026Yifei Li, Zihui Gao, Laks V. S. LakshmananLarge Language Model RoutingWorkload

    The University of British Columbia

  16. Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection

    Jul 17, 2026Anshu Singh, Alejandro SeifHazardVideo Dataset

    Government Technology Agency of Singapore

  17. ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM

    Jul 16, 2026Hyunwoo Oh, Suyeon Jang, Hanning Chen +3Matrix MultiplicationIn-Memory Computing

    University of California, Irvine

  18. Workload-Driven Optimization for On-Device Real-Time Subtitle Translation

    Jul 10, 2026Tsz-To WongTranslation QualitySmall Large Language Models

    National Yang Ming Chiao Tung University, Hsinchu, Taiwan

  19. Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration

    Jul 9, 2026Amir Asiaee, Kaveh AryanCausal InferencesSynthetic Data

    Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA · Department of Informatics, King’s College London, London, UK

  20. Optimizing ML Workload Partitioning between CPUs and CIM Accelerators for Heterogeneous Computing

    Jul 6, 2026Joel Klein, Rebecca Pelke, Roberto Laudani +2Inference WorkloadsIn-Memory Computing

    Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Germany

  21. ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators

    Jul 2, 2026Xinxin Chen, Haoran Qiao, Yiming Guo +3Field-Programmable Gate ArraysFault Tolerance

    Department of Computer Science University of Chinese Academy of Sciences

  22. Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets

    Jun 29, 2026Ali Ramlaoui, Daniel T. Speckhard, Sagar Pal +3Molecular DynamicsModel Training

    Entalpic, Paris, France · Universit´e Paris-Saclay, CentraleSup´elec, Inria, Gif-sur-Yvette, France

  23. Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure

    Jun 24, 2026Maxwell Twelftree, David Lemphers, An-chi He +1WorkloadArtificial Intelligence Infrastructure

    Maincode, Melbourne, Australia

  24. Managing Task Execution for Unknown Workloads in Batteryless IoT: A Hardware-Agnostic Evaluation

    Jun 23, 2026Samer Nasser, Henrique Duarte Moura, Ritesh Kumar Singh +2WorkloadResource-Constrained Edge Devices

    University of Antwerp - imec, IDLab Research Group, Antwerp, Belgium

  25. Recency/Frequency Adaptive KV Caching for Large Language Model Serving

    Jun 19, 2026Yang Shen, Meghana Madhyastha, Robert Underwood +2Key-Value CacheLLM Inference Optimization

    Department of Computer Science, Johns Hopkins University, Baltimore, USA

  26. Learning Burst-Aware Early Warning Models for Capacity Stress under AI Workload Surges in Hyperscale Data Centers

    Jun 19, 2026Zihan Yu, Xianling Zeng, Zhiming Xue +2Artificial Intelligence InfrastructureWorkload

    College of Professional Studies Northeastern University Boston, USA · College of Engineering Northeastern University Boston, USA · Khoury College of Computer Sciences Northeastern University Boston, USA

  27. Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents

    Jun 17, 2026Emmanuel Aboah Boateng, Kyle MacDonald, Amardeep Kumar +2Large Language Model AgentsDecoupling

    DoorDash, Inc.

  28. OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization

    Jun 16, 2026Longlong Zhu, Jiashuo Yu, Zedi Chen +12Bringing Network CodingOptimization Modeling

    Zhejiang University Hangzhou, Zhejiang, China · College of Computer and Data Science Fuzhou University Fuzhou, Fujian, China · Yangzhou University Yangzhou, Jiangsu, China +1

  29. AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems

    Jun 14, 2026Yajie Zhou, Ao Li, Ashwin Silla +2Self-Evolving AgentsSelf-Evolution

    University of Maryland, College Park · Carnegie Mellon University

  30. Service-Induced Congestion in Memory-Constrained LLM Serving

    Jun 14, 2026Ruicheng Ao, Jing Dong, Gan Luo +1Large Language Model ServingLarge Language Model Memory

    Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, MA 02139 · Columbia Business School, Columbia University, New York, NY 10027 · School of Mathematical Sciences, Peking University, Beijing, China

  31. Multimodal Physiological Assessment of Contact-Rich Physical Human-Robot Interaction Under Varying Environmental Conditions

    Jun 12, 2026Yanyi Chen, Xi Wang, Min DengPhysiological DataPhysiological Signals

    Department of Civil, Environmental, and Construction Engineering, Texas Tech University, Lubbock, TX 79409, USA · Department of Construction Science, Texas A&M University, College Station, TX 77843, USA · Department of Civil and Environmental Engineering, University of Tennessee, Knoxville, TN 37996, USA

  32. ros2probe: Non-intrusive, Kernel-selective Observability for Robot Operating System 2 Middleware

    Jun 9, 2026Jisang Yu, Sanghoon Lee, Yeonwoo Choi +1Robot Operating SystemPartial Observability

    DGIST Daegu, Republic of Korea

  33. Complexity-Balanced Diffusion Splitting

    Jun 4, 2026Noam Issachar, Dani Lischinski, Raanan FattalGenerative ModelsWorkload

    The Hebrew University of Jerusalem

  34. Multi-Camera AR Guidance System for Surgical Instrument Handling and Assembly: Investigating Workload and Efficiency

    Jun 3, 2026Shiyu Li, Julian Kreimeier, Hannah Schieber +4Surgical RobotsAugmented Reality

    Technical University of Munich, Human-Centered-Computing and Extended Reality Lab · TUM University Hospital, Orthopedics and Sports Orthopedics · Munich Institute of Robotics and Machine Intelligence (MIRMI) +2

  35. Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack

    Jun 2, 2026Yang Yang, Kevin Wang, Yuanhai Luo +4On-Chain AttestationsKubernetes

    OPPO · Phala

  36. MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency

    Jun 2, 2026Saptarshi Mitra, Yifan Zhang, Rachid Karami +5Mixture-Of-Expert InferenceWorkload

    University of California, Irvine, USA · University of Southern California, Los Angeles, USA · Intel, USA

  37. DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference

    Jun 2, 2026Kathiravan PalaniappanSchedulersWorkload

    Independent Researcher (University of Colorado Colorado Springs Alumni)

  38. ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving

    May 30, 2026Seokjin Go, Marko Scrbak, Ephrem Wu +2Mixture-Of-Expert InferenceInference Workloads

    Georgia Institute of Technology Atlanta, GA, USA · Advanced Micro Devices, Inc. Austin, TX, USA · Advanced Micro Devices, Inc. Santa Clara, CA, USA +1

  39. SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition

    May 29, 2026Yunkai Lou, Longbin Lai, Shunyang Li +2Large DatabasesWorkload

    Alibaba Group Hangzhou, China · Zhejiang GongshangYing ZhangUniversity Hangzhou, China

  40. An Empirical Audit of k-NAF Budget Accounting for Anchored Decoding

    May 27, 2026J. VijayavallabhToken Budget AllocationModel Auditing

    Indian Institute of Technology Madras Chennai, India

  41. A Policy-Driven Runtime Layer for Agentic LLM Serving

    May 26, 2026Rui Zhang, Chaeeun Kim, Liting HuMulti-Llm AgentsProduction Agentic Systems

    University of California, Santa Cruz

  42. LearnedCache: An eBPF-Integrated Perceptron-Based Eviction Policy for the Linux Page Cache

    May 25, 2026Zejia QiEvictionCache

  43. AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational Memory

    May 24, 2026Aojie Yuan, Haiyue Zhang, Shahin NazarianConversational MemoryWorkload

    University of Southern California Los Angeles, CA, USA

  44. Accelerating Divisible Load Processing Through Machine Learning: A Practical Framework for Large-Scale Workloads

    May 22, 2026Bharadwaj VeeravalliInference WorkloadsWorkload

    Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore

  45. Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption

    May 19, 2026Mert Yildiz, Pietro Spadaccino, Alexey Rolich +2PreemptionOffloading

    Sapienza University of Rome, Rome, Italy

  46. TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks

    May 16, 2026Hanzhang Shen, Haoran Wu, Yiren Zhao +1Key-Value Cache QuantizationAgentic Inference

    University of Cambridge · Imperial College London

  47. Driving Through the Network: Performance and Workload Under Latency and Video Impairment

    May 15, 2026Ines Trautmannsheimer, Ahmed Azab, Frank DiermeyerVideo QualityTeleoperation

    Technical University of Munich, School of Engineering and Design, Institute of Automotive Technology and Munich Institute of Robotics and Machine Intelligence (MIRMI), 85748 Munich, Germany

  48. APWA: A Distributed Architecture for Parallelizable Agentic Workflows

    May 14, 2026Evan Rose, Tushin Mallick, Matthew D. Laws +2Multi-Agent WorkflowsAgentic Workflows

    Northeastern University

  49. BlitzGS: City-Scale Gaussian Splatting at Lightning Speed

    May 13, 2026Zhongtao Wang, Huishan Au, Yilong Li +6Gaussian PrimitivesSpeeds

    Peking University, China

  50. Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

    May 11, 2026Prathamesh Vasudeo Naik, Naresh Dintakurthi, Yue WangLarge Language Model WorkflowsAnti-Money Laundering

  51. ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload

    May 11, 2026Ziyue Liu, Zhengyang Wang, Ruijie Zhang +7Large Language Model TrainingFault Tolerance

    University of California at Santa Barbara · Argonne National Laboratory

  52. Agent-X: Full Pipeline Acceleration of On-device AI Agents

    May 11, 2026Jinha Chung, Byeongjun Shin, Jiin Kim +1Workload

    KAIST Republic of Korea, Daejeon

  53. From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs

    May 10, 2026Daemyung Kang, Eunjin Hwang, Hanjeong Lee +11NvidiaWorkload

    Lablup Inc.∗

  54. Regulating Branch Parallelism in LLM Serving

    May 7, 2026Swapnil Gandhi, Siva Hari, William J. Dally +1Large Language Model ServingWorkload

    1Stanford University · 2NVIDIA

  55. Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management

    May 7, 2026Haoyu Zheng, Fangcheng Fu, Jia Wu +6Kv-Cache ManagementWorkload

    Wuhan University · Shanghai Jiao Tong University · Macquarie University +2

  56. Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

    May 3, 2026Nikita Agrawal, Ruben MayerKey-Value Cache CompressionLarge Language Model Serving

    University of Bayreuth

  57. Human-Less LLM Serving: Quantifying the Human Tax on Throughput

    May 3, 2026Jianhui Lian, Li Chen, Dan Li +1Large Language Model ServingTime-To-First-Token

    Tsinghua SIGS · Beijing Zhongguancun Laboratory · Tsinghua University

  58. MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving

    May 3, 2026Zhaoyuan Su, Olatunji Ruwase, Karthik Ganesan +5Mixture-Of-Expert InferencePrefill

    University of Virginia · 2Snowflake AI Research · 3Harvard University

  59. Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving

    Apr 28, 2026Shan Yu, Junyi Shu, Yuanjiang Ni +14WorkloadCache

    UCLA · Alibaba Cloud Computing · Alibaba Group +6

  60. Scalable Inference Architectures for Compound AI Systems: A Production Deployment Study

    Apr 28, 2026Srikanta Prasad S, Utkarsh AroraAgentic InferenceArtificial Intelligence Deployment

    Agentforce AI Platform, Salesforce India Pvt Ltd Bangalore, Karnataka, India