cs.PF

Papers

• TinyD\'ej\`aVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams (2026)
  Zhaolan Huang et al.
  0.00
• SHARP: An Adaptable, Energy-Efficient Accelerator for Recurrent Neural Network (2023)
  Reza Yazdani et al.
  —
• Conformer-Based Speech Recognition On Extreme Edge-Computing Devices (2024)
  Mingbin Xu et al.
  —
• TorchFX: A modern approach to Audio DSP with PyTorch and GPU acceleration (2025)
  Matteo Spanio et al.
  —
• Implementing Keyword Spotting on the MCUX947 Microcontroller with Integrated NPU (2025)
  Petar Jaku\v{s} et al.
  —
• Regression Language Models for Code (2026)
  Yash Akhauri et al.
  —
• DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures (2026)
  Peiming Yang et al.
  —
• Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers (2026)
  Zhaolan Huang et al.
  —
• An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum (2026)
  Suvi De Silva et al.
  —
• KPI2KVI: A Multi Agent Workflow for Calculating Key Value Indicators from Service Descriptions (2026)
  Masoud Shokrnezhad et al.
  —
• Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation (2026)
  Ji-Won Park et al.
  —
• Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems (2026)
  Deepak Panigrahy et al.
  —
• ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU (2026)
  Aman Sunesh et al.
  —
• Cost-Effective Model Evaluation with Meta-Learning (2026)
  Trinh Pham et al.
  —
• The Model Parking Tax: Quantifying the Hidden Energy Cost of Always-On GPU Model Deployment (2026)
  Sai Sathvik Vadari
  —
• The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution (2026)
  Deepak Panigrahy et al.
  —
• A Methodology to Assess Power Modeling in Energy-Aware Federated Learning on Heterogeneous Mobile Devices (2026)
  Chaimae Jallouli et al.
  —
• MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference (2026)
  Kexin Chu et al.
  —