Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    [2609.39632] Towards Better Exploration in Sequential Test-Time Scaling

    November 21, 2026

    A Sparse Low-Rank Biclique Decomposition for Graphs

    November 21, 2026

    Hours after Anthropic claims a Claude proof of the Riemann hypothesis, Stanford releases an all-human competing draft

    November 21, 2026
    Facebook X (Twitter) Instagram
    Trending
    • [2609.39632] Towards Better Exploration in Sequential Test-Time Scaling
    • A Sparse Low-Rank Biclique Decomposition for Graphs
    • Hours after Anthropic claims a Claude proof of the Riemann hypothesis, Stanford releases an all-human competing draft
    • [2609.37351] Clause-Factored Bilateral State Grounding and Scoped Passivity for Counterfactual Open-World Deductive Reasoning
    • Best Laptops for Travel (2026): Which to Take on the Road
    • [2611.25796] How Reliable Are Explanations of Language Models That Detect Insider Threats?
    • Lifting Classifier Training with Latent Gaussian Mixture Models
    • New open model Inkling 2 Mini thinks in loops to solve problems with fewer words and still runs on a laptop
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Saturday, November 21
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
    Machine Learning

    Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment

    adminBy adminNovember 19, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 26 Jun 2026 (v1), last revised 18 Nov 2026 (this version, v2)]

    View a PDF of the paper titled FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment, by Fan Mo and 4 other authors

    View PDF

    Abstract:Mixture-of-Experts (MoE) language models scale model capacity through sparse expert activation, yet deployment still requires storing and serving all experts. Moreover, deployment budgets can vary substantially across devices, users, and workloads. Existing MoE compression methods typically optimize a separate compressed model for each target budget. We introduce FlexMoE, a post-training one-for-all framework that converts a large pretrained MoE model into a multi-budget family of smaller deployable subnetworks. FlexMoE first ranks expert FFN channels by importance to construct a sliceable weight space shared across budgets, and then learns expert-wise discrete retention actions under gradually increasing cost pressure, allowing a single action-training run to produce reliable pruning masks across budgets. Moreover, only a single mid-budget fine-tune can further recover degraded performance and yields a shared recovered model that transfers to other unseen budgets, avoiding repeated per-budget recovery and separated checkpoint storage. Across tested MoE LLMs with diverse architectures and scales, FlexMoE consistently outperforms strong MoE compression baselines. In particular, on Qwen2-57B-A14B, it retains ~99.8% of base performance while pruning 50% of routed-expert parameters even without recovery fine-tuning. For deployment, pruned subnetworks deliver real memory reduction and end-to-end throughput gains, while our kernel co-design enables runtime budget switching without checkpoint reloading and delivers substantial inference acceleration.

    Submission history

    From: Fan Mo [view email]
    [v1]
    Fri, 26 Jun 2026 09:08:03 UTC (4,381 KB)
    [v2]
    Wed, 18 Nov 2026 17:03:50 UTC (4,181 KB)

    Deployment Expert Flexible learning MoE MultiBudget OneforAll Pruning
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    [2609.39632] Towards Better Exploration in Sequential Test-Time Scaling

    November 21, 2026

    A Sparse Low-Rank Biclique Decomposition for Graphs

    November 21, 2026

    [2609.37351] Clause-Factored Bilateral State Grounding and Scoped Passivity for Counterfactual Open-World Deductive Reasoning

    November 21, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Machine Learning

    [2609.39632] Towards Better Exploration in Sequential Test-Time Scaling

    By adminNovember 21, 20260

    [Submitted on 30 Sep 2026 (v1), last revised 19 Nov 2026 (this version, v3)] View…

    A Sparse Low-Rank Biclique Decomposition for Graphs

    November 21, 2026

    Hours after Anthropic claims a Claude proof of the Riemann hypothesis, Stanford releases an all-human competing draft

    November 21, 2026

    [2609.37351] Clause-Factored Bilateral State Grounding and Scoped Passivity for Counterfactual Open-World Deductive Reasoning

    November 21, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    [2609.39632] Towards Better Exploration in Sequential Test-Time Scaling

    November 21, 2026

    A Sparse Low-Rank Biclique Decomposition for Graphs

    November 21, 2026

    Hours after Anthropic claims a Claude proof of the Riemann hypothesis, Stanford releases an all-human competing draft

    November 21, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.