Capacity

Follow this topic Ask about this topic

Recent momentum

-25%

9 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

4 new papers

A weekly snapshot of new work published in Capacity.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Capacity.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Capacity.

79 papers

Latest in Capacity

Open your feed →

COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads
Sep 16, 2026Yukai Zhou, Hongfan WuInference Workloads Semantic Fragmentation
Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory
Sep 15, 2026Yuto Sakurai, Takeaki Shimokawa, Kazunori Iwata +1Dense Associative Memory Hopfield Networks
Scaling Laws for Physics-Aware ACOPF Surrogate Learning
Sep 14, 2026Yijiang Li, Emon Dey, Stefano Fenu +3Ac Optimal Power Flow Scaling Laws
What an odour descriptor corpus can and cannot measure: valence, attenuation, and the ceiling of the public record
Sep 14, 2026Stylianos Kampakis, Fabio RovaiOlfactory Perception Inter-Rater Variability
AI for AI: Optimizing Additional Infrastructure Build-out to Power Artificial Intelligence Data Centers
Sep 8, 2026Alexander Crosier, Kyle Onghai, Ronnie SircarArtificial Intelligence Data Centers Data Centers
Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation
Sep 8, 2026Jiaming Yang, Chenwei Tang, Liangli Zhen +2Key-Value Cache Eviction Quadratic Attention
MINERVA: How Small Can a Manipulation Policy Be and Still Solve LIBERO?
Sep 3, 2026Kohei Sendai, Tatsuya Matsushima, Yusuke IwasawaVision-Language-Action Models Manipulation
Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
Aug 31, 2026Zhanbo Zhang, Ming Liu, Qing WangMemorization Topological Data Analysis
Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss
Aug 28, 2026Niccolò Ajroldi, Diana Alexandra Onutu, Haider Al-Tahan +4Learning Rates Batch Size
TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures
Aug 13, 2026Orkun Irsoy, Leman Akoglu, Osman YaganNetworked Systems Capacity
Adaptive Semantic Capacity Allocation for Parallel Generative Recommendation
Aug 10, 2026Chenxi Li, Yuchen Lu, Xu YangLarge-Scale Recommendation Systems Beam Search
ASPaeroFlow: Decomposition Heuristics for Joint Air Traffic Flow & Capacity Management
Aug 10, 2026Alexander Beiser, Markus Hecher, Nysret Musliu +2Air Traffic Control Capacity
Signature-Guided Capacity Occupancy for Dense Expert Merging
Aug 10, 2026Lingching Tung, Chi-Jui Kim, Beicheng Xu +2Model Merging Mixture-of-Experts Models
Adaptive Two-Level Allocation of a Conserved Capacity Budget Across Locations and Service Classes
Aug 7, 2026Simone Mainardi, Kaushal Bansal, Prabhat SinghBandwidth Constraints Capacity
Complete, Scalable, and Robust Prioritized Planning for Multi-Robot Ordered Storage and Retrieval at Maximum Capacity
Aug 7, 2026William Zhang, Tzvika Geft, Jingjin Yu +1Multi-Robot Motion Planning Warehouse Automation
Skaling: Chinchilla's Exponents Meet Kaplan's Coupling
Aug 7, 2026Mathurin Videau, Badr Youbi-Idrissi, David Lopez-Paz +1Scaling Laws Exponents
Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning
Aug 7, 2026Alireza Moayedikia, Alicia Troncoso LoraFederated Learning Finite-Sample Coverage Guarantees
Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints
Aug 7, 2026Paul-Peter ArslanLarge Language Model Bias Triage
Differentiating Through Dual Prices: End-to-End Policy Learning Under Capacity Constraints
Aug 5, 2026Mohammadsaeed Haghi, Mahdi Salmani, Nima KelidariStochastic Delays Prices
ACA-GS: Adaptive-Capacity Anchored Gaussian Splatting for Compact Dynamic Radiance Fields
Aug 5, 2026Seunghyeon Song, Joo Chan Lee, Chanung Park +4Gaussian Splatting Wireless Radiance Field
Quantum-Inspired Evolutionary Neighborhood Search for Arrival-Departure Track Utilization Adjustment under Short-Term Disturbances
Jul 27, 2026Xiaobin Li, Wuming Lei, Yanbin Gao +1Transit Network Design Quantum Approximate Optimization Algorithm
How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning
Jul 23, 2026Kaizhen Tan, Heqing Du, Yang FengLow-Rank Adaptation Adapters Parameter-Efficient Fine-Tuning
Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models
Jul 22, 2026Niraj Gadhe, Kirti Bhardwaj, Moulik Jain +2Networked Systems Capacity
Locality-Aware Density Control for Efficient Gaussian-based Image Representation
Jul 20, 2026Jiacong Chen, Qingyu Mao, Xiandong Meng +5Gaussian Splatting Capacity
Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones
Jul 19, 2026Ayoub Ghriss, Sourav ChakrabortyQuadratic Attention Dense Associative Memory
Capacity and Redundancy Trade-offs in Multi-Task Learning
Jul 17, 2026Asif KhanMulti--Task Learning Redundancy
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities
Jul 15, 2026Eunna Lee, Jungpyo Nam, Sunjun HwangLarge Language Model Safety Hallucinations
Constraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination
Jul 14, 2026Usman Haider, Karl MasonFederated Reinforcement Learning Smart Grids
Random Label Prediction Heads for Studying Memorization in Deep Neural Networks
Jul 13, 2026Marlon Becker, Jonas Konrad, Luis Garcia Rodriguez +1Memorization Neural Network
ML in a Box: Analyzing Containerization Practices in Open Source ML Projects
Jul 11, 2026Faten Jebari, Emna Ksontini, Amine Barrak +1Machine Learning Capacity
MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning
Jul 9, 2026Harrison Rush, Vincent Davis, Simone Antonelli +3Flow-Based Policy Proximal Policy Optimization
Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
Jul 8, 2026Qinnan Cai, Yibo Zhao, Xiang LiSearch Agents Capacity
LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs
Jul 4, 2026Xiaoyue Liu, Zheng DongLast Mile Large Language Model Routing
Two AI Metrics Diverged: Will it Make All the Difference?
Jul 1, 2026Alex Fogelson, Zachary A. Brown, Hans Gundlach +2Artificial Intelligence Benchmarks Frontier Models
Joint Air Traffic Flow and Capacity Management via Answer Set Programming
Jun 22, 2026Alexander Beiser, Markus Hecher, Nysret Musliu +1Air Traffic Control Mixed-Integer Programming
Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity
Jun 19, 2026Xuan Qi, Yi Wei, Fanqi Yu +1Affine Model Complexity
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 Data Centers Data Centers
Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
Jun 16, 2026Hao Liang, Cheng Tang, Yunzong XuStochastic Delays Optimal Scheduling
Small Initialization Matters for Large Language Models
Jun 16, 2026Liangkai Hang, Junjie Yao, Zhiyu Li +3Capacity
Qualified Educational Capacity Planning under Heterogeneous Student Support Needs: A Synthetic Benchmark and Decision-Support Framework
Jun 15, 2026Carlos Eduardo Sanoja, Oscar Enrique Moreno MayzEducation Capacity
Architectural Wisdom: A Framework for Governing Optimization in AI Systems
Jun 15, 2026Edward Y. ChangArtificial Intelligence Governance Artificial Intelligence Systems
Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models
Jun 12, 2026Chenyu Zhou, Qiliang Jiang, Boguang PanLow-Rank Adaptation Visual Grounding
Capacity, Not Format: Rethinking Structured Reasoning Failures
Jun 8, 2026Hengxin FanReasoning Failures Capacity
Unified Energy for Invariant and Independent Decoding in Diffusion Language Models
Jun 8, 2026Yuchen Yan, Minkai Xu, Zaiquan Yang +1Diffusion Language Models Invariance
How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap
Jun 7, 2026Jasmeet Singh Bindra, Siddharth PanwarBrain-Computer Interface Capacity
Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models
Jun 7, 2026Arya Shah, Himanshu Beniwal, Mayank Singh +1Multilingual Safety Cross-Lingual Alignment
The Capacity of Information-Theoretic Secure Aggregation in Federated Learning
Jun 5, 2026Lanxin Yi, Jinbao Zhu, Kai Wan +1Federated Learning Diffie-Hellman
Shortcomings and capacities of real-constrained neural networks in complex spaces
Jun 3, 2026Andrew GracykNeural-Network Approximation Neural Network
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
Jun 1, 2026Jiebin Zhang, Zhenghan Yu, Song Liu +9Speculative Decoding LLM Inference Efficiency
Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
May 29, 2026Konstantin Nikolaou, Jonas Scheunemann, Sven Krippendorf +2Scaling Laws Neural Tangent Kernel
A Dual-Path Architecture for Scaling Compute and Capacity in LLMs
May 28, 2026Markus Frey, Behzad Shomali, Joachim Koehler +1Transformer Layers Large Models
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
May 28, 2026Jing Huang, Daniel Wurgaft, Rachit Bansal +6Large Behavior Model Capacity
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
May 25, 2026Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li +2Large-Scale Image Generation Multimodal Generation
Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
May 25, 2026Martin Marek, Dongkyu Cho, Shikai Qiu +3Catastrophic Forgetting Forgetting
Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks
May 23, 2026Aakash Kumar, Anatoly Khina, Frederik Mallmann-Trenn +1Hopfield Networks Attractors
Characterizing the Representational Capacity of Neural Processes
May 22, 2026Robin YoungNeural Architectures Representational Capacity
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
May 22, 2026Xu Ouyang, Deyi Liu, Yuhang Cai +5Large Models Scaling Laws
Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws
May 20, 2026Nandan Kumar Jha, Brandon ReagenOptimizer Design Scaling Laws
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
May 20, 2026Alexi Canesse, Benoît Goupil, Jesse Read +1Multi-Agent Reinforcement Learning Bandwidth Constraints
Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
May 18, 2026Matthew L. Smith, Jonathan P. Shock, Samuel T. Segun +2Large Language Model Performance Factual Recall

Sep 16, 2026 · cs.DCJ/K move · Enter open · S save

COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads

Yukai Zhou, Hongfan Wu

With the rapid advancement of deep learning technology, shared GPU clusters receive an increasing number of deep learning training (DLT) jobs. Yet resource fragmentation make such clusters underutilized and forces the DLT jobs running on them to endure long turnaround times. Extensive research has been devoted to quantifying fragmentation and developing scheduling algorithms that alleviate its impact. However, existing fragmentation measures break down in the absence of workload distribution information, while current schedulers cannot continuously maintain resource fragmentation at a low level. To tackle these problems, we first introduce Scheduler-Induced Fragmentation (SIF), a metric built on the notion of partial-nodes that is independent of historical workload knowledge. We then propose COMPASS-ABS, which employs the COMPact-ASSured (COMPASS) algorithm to confine the cluster state within a tight Anchor-Based Space (ABS), whose construction fully leverages the topological alignment between dominant workload size and node capacity. Moreover. We also prove that it ensures SIF is bounded by

\frac{2}{N}

under a workload composition condition that matches both theory and production. Evaluations implemented on a physical cluster and a simulated cluster demonstrate COMPASS-ABS effectiveness at improving resource utilization, reducing DLT job completion time by reducing fragmentation.

Inference Workloads Semantic Fragmentation Capacity Compass Deep Learning

Open paper Ask about it PDF