Skip to content

1/29 New papers #51

Closed
Closed

Activity

  1. claude commented on Jan 30, 2026

    @claude

    Claude finished @AmberLJC's task in 2m 22s —— View job


    Adding New Papers

    I'm unable to fetch paper details from arXiv because I don't have web access permissions.

    To complete this task, I have two options:

    Option 1 (Recommended): Grant me web access by allowing WebFetch or curl commands, then I can:

    • Automatically fetch all 6 paper titles and abstracts
    • Properly categorize them into the correct sections (Training/Serving/Multi-Modal/etc.)
    • Add properly formatted entries following the repository's style guide

    Option 2: You can provide the paper titles and categories here in a comment, and I'll immediately add them to README.md in the correct format.

    Papers waiting to be added:

    1. 2601.17654
    2. 2601.20309 (MLSys' 26)
    3. 2510.22101 (MLSys' 26)
    4. 2506.05871
    5. 2507.05411 (MLSys' 26)
    6. 2601.20408 (MLSys' 26)

    Let me know how you'd like to proceed!

  2. AmberLJC commented on Jan 30, 2026

    @AmberLJC
    OwnerAuthor

    @claude

    1. Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training — https://arxiv.org/abs/2601.17654 ([arXiv][1])

    2. SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips — https://arxiv.org/abs/2601.20309 ([arXiv][2])

    3. Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search — https://arxiv.org/pdf/2510.22101 ([arXiv][3])

    4. BestServe: Serving Strategies with Optimal Goodput in Collocation and Disaggregation Architectures — https://arxiv.org/html/2506.05871v1 ([arXiv][4])

    5. AXLearn: Modular Large Model Training on Heterogeneous Infrastructure — https://arxiv.org/pdf/2507.05411 ([arXiv][5])

    6. Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT — https://arxiv.org/pdf/2601.20408 ([arXiv][6])

  3. AmberLJC commented on Jan 30, 2026

    @AmberLJC
    OwnerAuthor
  4. claude commented on Jan 30, 2026

    @claude

    Claude finished @AmberLJC's task in 1m 43s —— View job • claude/issue-51-20260130-0722 • Create PR ➔


    Adding New Papers

    • Read README.md to understand current structure
    • Categorize papers into appropriate sections
    • Add Kareus paper (training energy optimization)
    • Add SuperInfer paper (LLM inference scheduling)
    • Add Scaling Up Small LMs paper (serving/deployment)
    • Add BestServe paper (serving strategies)
    • Add AXLearn paper (model training)
    • Add OptiKIT paper (enterprise LLM optimization)
    • Commit and push changes
    • Provide PR creation link

    Summary

    Successfully added all 6 papers to the README.md file:

    Training (Pre-training section):

    • Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training
    • AXLearn: Modular Large Model Training on Heterogeneous Infrastructure | MLSys' 26

    Serving (LLM serving section):

    • SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips | MLSys' 26
    • Scaling Up Efficient Small Language Models Serving: Serving and Deployment for Semantic Job Search | MLSys' 26
    • BestServe: Serving Strategies with Optimal Goodput in Collocation and Disaggregation Architectures
    • OptiKIT: Meeting SLOs, Slashing Hours - Automated Enterprise LLM Optimization | MLSys' 26

    All entries follow the repository's formatting guidelines with proper arXiv URLs and venue information.

    --- | Branch

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions