·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Creative Integration: A Decidable Criterion of Creativity18m◆SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series18m◆QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction18m◆Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy18m◆DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs18m◆MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models18m◆Codifying the Judge: Scalable Evaluation via Program Distillation18m◆SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent18m◆Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents18m◆Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits18m◆DSTFView: Multi-View Cloud-Edge Workload Forecasting with Dual-Input Spatio-Temporal-Frequency Modeling18m◆MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models18m◆Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting18m◆Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines18m◆Reference Feature Atlases for Mechanistic Auditing of Language Models18m◆SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs18m◆Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL18m◆PhononBench-MP40: a spectrum-resolved benchmark dataset for phonon stability18m◆Too much evidence, too little time: From text to actionable recommendations through multi-objective evidence reasoning18m◆Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models18m◆Creative Integration: A Decidable Criterion of Creativity18m◆SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series18m◆QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction18m◆Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy18m◆DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs18m◆MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models18m◆Codifying the Judge: Scalable Evaluation via Program Distillation18m◆SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent18m◆Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents18m◆Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits18m◆DSTFView: Multi-View Cloud-Edge Workload Forecasting with Dual-Input Spatio-Temporal-Frequency Modeling18m◆MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models18m◆Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting18m◆Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines18m◆Reference Feature Atlases for Mechanistic Auditing of Language Models18m◆SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs18m◆Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL18m◆PhononBench-MP40: a spectrum-resolved benchmark dataset for phonon stability18m◆Too much evidence, too little time: From text to actionable recommendations through multi-objective evidence reasoning18m◆Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models18m◆
News/Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits
arxiv
PublishedJuly 28, 2026 at 4:00 AM
—neutral

Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2607.22564v1 Announce Type: new Abstract: Convolutional neural networks often contain redundant feature maps that increase storage and inference cost. This paper presents a loss-aware feature-map pruning framework using multi-armed bandits. Feature-map pruning is structured because it removes

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivCreative Integration: A Decidable Criterion of Creativity18marxivSeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series18marxivQFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction18marxivSame Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy18m
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews