Search Results

Refine Results
  1. Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  2. Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  3. Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  4. A Scalable Digital Twin Framework for Energy Optimization in Data Centers

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  5. EdgeServing: Deadline-Aware Multi-DNN Serving at the Edge

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  6. OpenG2G: A Simulation Platform for AI Datacenter-Grid Runtime Coordination

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  7. Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism

    Published in ArXiv cs.DC Recent Papers (2026)
    Get full text
    Online Article RSS Article
  8. Low-Latency Out-of-Core ANN Search in High-Dimensional Space

    Published in ArXiv cs.DB Recent Papers (2026)
    Get full text
    Online Article RSS Article
  9. Bayes Meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes

    Get full text
    Online Article RSS Article
  10. An Extensible and Verifiable Language for Query Rewrite Rules

    Published in ArXiv cs.DB Recent Papers (2026)
    Get full text
    Online Article RSS Article
  11. Anatomy of a Query: W5H Dimensions and FAR Patterns for Text-to-SQL Evaluation

    Published in ArXiv cs.DB Recent Papers (2026)
    Get full text
    Online Article RSS Article
  12. Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  13. FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  14. On the Security of Research Artifacts

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  15. PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  16. Privacy by Postprocessing the Discrete Laplace Mechanism

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  17. Autonomous Adversary: Red-Teaming in the age of LLM

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  18. Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  19. Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation

    Published in ArXiv cs.CR Recent Papers (2026)
    Get full text
    Online Article RSS Article
  20. Efficiently Escaping Saddle Points in Bilevel Optimization

    Get full text
    Online Article RSS Article