Energy-Efficient ML

ML: Machine Learning

Energy-efficient machine learning studies how to reduce the resources required to train and run models, especially on edge devices and at large serving scale. Common approaches include pruning, quantization, distillation, sparse and early-exit models, efficient scheduling and routing, and hardware-software co-design for GPUs, accelerators, and neuromorphic chips. Researchers increasingly measure energy on real hardware and assess carbon and other environmental impacts across the model life cycle, since proxies such as FLOPs do not reliably predict deployment costs. The central challenge is balancing energy, accuracy, latency, and memory while determining whether efficiency gains translate into lower total impact as usage grows.

Latest papers

257 papers17 papers in the last four weeks, down 23% on the four weeks before. 0.1% of all new papers.

SLICE-CiM: Selective Layer-wise Inference Control Engine with Confidence-Based Early Exit for SRAM based Digital Compute-in-Memory
Oct 27, 2026Pratham Sharma, Mohd Faisal Khan, Santosh Kumar VishvakarmaEfficient Neural Network Inference Energy-Efficient ML
Department of Electrical Engineering, Indian Institute of Technology Indore, Indore, India
Sustainability of TSFM Deployment and Pretraining: From Carbon Footprint Analysis to Mitigation via Pruning
Oct 23, 2026Cécile Luc, Nathanaël Lemonnier, Ievgen RedkoTime-Series Foundation Models Energy-Efficient ML
Strategy & Innovation, AI Hub, Schneider Electric, Rueil-Malmaison, France · Strategy & Innovation, AI Hub, Schneider Electric, Grenoble, France
ENCL: Enabling Efficient Neuromorphic Continual Learning with Local Learning Rule and Sub-Network Freezing Strategy
Oct 22, 2026Rachmad Vidya Wicaksana Putra, Shuochen Zhou, Hassan Raza +1Energy-Efficient ML Local Learning
eBRAIN Lab, New York University (NYU) Abu Dhabi, United Arab Emirates
Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures
Oct 22, 2026Jinsong Wu, Yixin Xiao, Haowei Bi +1Responsible AI Energy-Efficient ML
School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China · Department of Electrical Engineering, University of Chile, Santiago, Chile
Energy and Latency First: How Deployment Constraints Reverse Time-Series Model Selection
Oct 22, 2026Shruti Bothe, Illyyne Saffar, Ayush K. VarshneyModel Selection Energy-Efficient ML
Ericsson Research, Santa Clara, USA · Ericsson Research, Massy, France · Ericsson Research, Kista, Sweden
Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy?
Oct 22, 2026Amirreza Zeinali, Jon Saad-Falcon, Avanika Narayan +5AI and Labor Energy-Aware LLM Inference
Stanford University · University of California, Berkeley · The University of Texas at Austin
A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC
Oct 21, 2026Masood Jan, Wafa Njima, Xun Zhang +1Wireless Localization Transfer Learning
Doctoral School of Computer Science, Telecommunications and Electronics (EDITE), Sorbonne University, Paris, France · LISITE Laboratory, Institut Supérieur d’Électronique de Paris, Paris, France · Université Paris-Saclay, LISV Laboratory, France +1
The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
Oct 15, 2026Ruichen Ma, Yicai Chen, Pujun Zhou +5Spiking Neural Networks Energy-Efficient ML
University of Electronic Science and Technology of China (UESTC) · Shenzhen Institute for Advanced Study, UESTC
LocalTrain: Integer-Only Local Learning for Energy-Efficient CNN Training on Edge FPGAs
Oct 12, 2026Shiqi Ding, Xuanyu Liang, Xinyang Liu +4On-Device Training Energy-Efficient ML
University of Cambridge · University College London · University of Bristol
Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
Oct 9, 2026Zeyu Yang, Wes ArmourEnergy-Aware LLM Inference LLM Inference Efficiency
Department of Engineering Science, University of Oxford
Fault-tolerant foundation models
Oct 7, 2026Trevor McCourt, Ila R. Fiete, Isaac L. ChuangLLM Training Language Model Scaling Laws
Department of Electrical Engineering and Computer Science, MIT · Department of Brain and Cognitive Sciences, McGovern Institute, MIT · Department of Physics, MIT
ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference
Oct 6, 2026Zou Qingyun, Bin Gao, Wenju Zhao +3Energy-Efficient ML VLM Quantization
National University of Singapore · Huazhong University of Science and Technology
Choosing an energy-efficient software architecture for building system diagnostic support
Oct 5, 2026Roxane Koitz-Hristov, Franz WotawaEnergy-Efficient ML Building Energy Management
Graz University of Technology Institute of Software Engineering and Artificial Intelligence Inffeldgasse 16b/2, A-8010 Graz, Austria
Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows
Oct 2, 2026Merve Astekin, Yan Naing Tun, Arda Goknil +5Software Engineering Agents LLM Agent Evaluation
SINTEF, Oslo, Norway · Singapore Management University, Singapore, Singapore · Ozyegin University, Istanbul, Turkiye
Exposing the Cost of Deep Learning Audio Development
Oct 1, 2026Constance Douwes, Paul Magron, Romain SerizelEnergy-Efficient ML
Universit´e de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France
Beyond State-of-the-Art: Standardising Environmental Impact Metrics for AI Research
Oct 1, 2026Lachlan McGinness, Dan Pagendam, Robert OffnerLLM Inference Efficiency Energy-Efficient ML
School of Computing, Australian National University · Commonwealth Scientific and Industrial Research Organisation
Energy Variation in Training Modern Computer Vision Architectures
Sep 29, 2026David Cortes, Carlos Juiz, Belen BermejoEnergy-Efficient ML Vision Transformer
University of the Balearic Islands (Spain)
Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisions
Sep 28, 2026Tianyao Shi, Xipeng Shen, Yi DingLLM Inference Efficiency LLM Serving
Elmore Family School of Electrical and Computer Engineering, Purdue University, USA
From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring?
Sep 27, 2026Daisy R. Bradley, Nathan A. Hinchliffe, Daniel J. Pitchforth +2Energy-Efficient ML Physics-Informed ML
Dynamics Research Group, University of Sheffield, Sheffield, UK
Logic Gate Networks and Lookup Table Networks as Lightweight Hardware Classifiers for Inter-patient ECG Arrhythmia Classification
Sep 26, 2026Wout Mommen, Lars Keuninckx, Siddharth Patil +3Differentiable Logic Gate Networks Electrocardiogram Classification
Interuniversity Microelectronics Centre (IMEC), Kapeldreef 75, Leuven, 3001, Belgium · Vrije Universiteit Brussel, Pleinlaan 2, Elsene, 1050, Belgium · imec Holst Centre, High Tech Campus 31, Eindhoven, 5656 AE, the Netherlands
The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models
Sep 25, 2026Christoph Walser, Mauricio Fadel Argerich, Jonathan FürstDocument Information Extraction Energy-Efficient ML
Zurich University of Applied Sciences, Switzerland · Universidad Politécnica de Madrid, Spain
Energy-efficient operation of neural operators for virtual sensing
Sep 24, 2026Jason Yoo, Samrendra Roy, Souvik Chakraborty +1Energy-Efficient ML Efficient Neural Network Inference
Nuclear, Plasma & Radiological Engineering Department, Grainger College of Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA · Department of Applied Mechanics, Indian Institute of Technology Delhi, New Delhi, India · Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, New Delhi, India +1
A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model
Sep 22, 2026Imad Lakim, Ebtesam Almazrouei, Ibrahim Abu Alhaol +2Arabic Language Models Energy-Efficient ML
TII, Abu Dhabi · LightOn, Paris
A principled approach for energy-efficient training via phase-aware GPU frequency tuning
Sep 21, 2026Miguel Braga, Júlio Pinto, Rahma Nouaji +5Energy-Efficient ML
INESC TEC & U. Minho · McGill University
Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving
Sep 19, 2026Muhammad Abdur Rab Siddiqui, Daniela Rojas, Chen Yang +3Energy-Aware LLM Inference LLM Routing
University of Alberta Edmonton, Alberta, Canada · University of California San Diego La Jolla, California, USA · Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China +1
Investigating the Performance and Energy Costs of Replicating Band-Split RNN for Music Source Separation
Sep 18, 2026Paul Magron, Romain Serizel, Constance DouwesAudio Source Separation ML Reproducibility
Université de Lorraine, CNRS Inria, LORIA, F-54000 Nancy, France · Centrale Med, Aix Marseille Univ CNRS, LIS, Marseille, France
RISC-V and machine learning: a survey
Sep 17, 2026Shriman Keshri, Apparna Singh, Chinmaya Kumar Palo +2Energy-Efficient ML Neural Network Hardware Acceleration
National Institute of Science Education and Research, Bhubaneswar, Odisha, India · Work conducted at NISER · Sri Sri University, Cuttack, Odisha, India +2
Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum
Sep 16, 2026Carolina Fortuna, Vid Hanžel, Tim Strnad +1LLM Inference Efficiency Energy-Efficient ML
Department of Communication Systems, Jožef Stefan Institute, Jamova cesta 39, 1000 Ljubljana, Slovenia
A Game-Theoretic Framework for Incentive-Compatible AI training Under Renewable-Energy Constraints
Sep 14, 2026Konstantinos Varsos, Ramin Khalili, Adamantia Stamou +2Mechanism Design Energy-Efficient ML
Athens University of Economics and Business, Greece · Independent researcher, Munich Germany
One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training
Sep 14, 2026Erik Schultheis, Maximilian Kleinegger, Dan AlistarhEnergy-Efficient ML GPU Acceleration
ISTA · TU Wien · RedHat AI

Oct 27, 2026J/K move · Enter open · S save

SLICE-CiM: Selective Layer-wise Inference Control Engine with Confidence-Based Early Exit for SRAM based Digital Compute-in-Memory

Pratham Sharma, Mohd Faisal Khan, Santosh Kumar Vishvakarma

Department of Electrical Engineering, Indian Institute of Technology Indore, Indore, India

Efficient Neural Network Inference Energy-Efficient ML Compute-in-Memory

Open paper AskPDF arXiv

Digital SRAM compute-in-memory (CIM) macros enable energy-efficient CNN inference by eliminating off-chip weight transfers; however, peripheral control logic introduces three inefficiencies: bit- slice over-activation at reduced precision (L1), unnecessary accumula- tion depth (L2), and idle precision-transition stalls (L3). To address these, we present four synthesizable peripheral blocks: a Flush-Merge Enable (FME) controller, a Confidence-Based Early-Exit (EE) module, a Precision Register with Decoder (PR/PD), and a Bit-Serial Cycle Controller (CC), co-designed to minimize switching activity, wordline overhead, and leakage. Implemented in TSMC 65-nm CMOS at 335 MHz, the peripheral framework occupies 1769.760 μm2 post-synthesis and 1982.131 μm2 post-PnR. Gate-level VCD analysis reports 6.0706 μW leakage and 288.2902 μW (post-synthesis) / 322.8850 μW (post-PnR) dynamic power, totaling 328.9556 μW (0.2402% of system power). The EE module dominates dynamic power (58.2%), while WLG dominates area (58.1%). System evaluation on MobileNetV2 (CIFAR-100) shows efficiency scaling from 31.35 TOPS/W (8b/8b, 1.2 V) to 454.91 TOPS/W (2b/8b, 0.8 V), achieving 13.33x improvement without bitcell modification or retraining. The framework targets CNN workloads exploiting sparsity, with Transformer extension as future work.