Latest Efficient ML Research Papers

The newest Efficient ML papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Efficient ML so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Edge AI for Energy-Efficient Smart IoT Systems: A Sustainable Computing Approach
  Prathamesh Uttam Patil · Zenodo (CERN European Organ... · Oct 31, 2026

  Abstract Artificial Intelligence of Things (AIoT) is transforming Internet of Things (IoT) systems by enabling data-driven decisions close to the point where data are generated. However, conventional cloud-centric architectures can introduc…

• Edge AI for Energy-Efficient Smart IoT Systems: A Sustainable Computing Approach
  Prathamesh Uttam Patil · Zenodo (CERN European Organ... · Oct 31, 2026

  Abstract Artificial Intelligence of Things (AIoT) is transforming Internet of Things (IoT) systems by enabling data-driven decisions close to the point where data are generated. However, conventional cloud-centric architectures can introduc…

• An ODE-based Sampler for Discrete Diffusion Models
  Samson Gourevitch, Yazid Janati, Eric Moulines, Eric P. Xing et al. · arXiv · Oct 29, 2026

  The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. I…

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• Soil Moisture Estimation in Precision Agriculture: A Knowledge Distillation Approach
  Mohammed Rakib, Vrinda Nagula, Arunkumar Bagavathi · arXiv · Oct 29, 2026

  Accurate soil moisture estimation is critical for precision agriculture, influencing irrigation, fertilization, and harvesting strategies. Traditional methods primarily rely on meteorological and soil property data, while recent approaches …

• Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
  Prakhar Kaushik, Soumava Paul, Alan Yuille · arXiv · Oct 27, 2026

  Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal su…

• EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning
  Sihan Yang, Weichen Bai, Ruichuan An, Yiming Cheng et al. · arXiv · Oct 27, 2026

  As executable environments for language agents scale, generating and verifying their rollouts becomes increasingly expensive. Under finite rollout budgets, this raises an important question: can data management at the environment level make…

• Orthogonal and Parametrized Multi-Attribute Steering of LLMs
  Remy Ogasawara, Cullen Anderson, Narmeen Fatimah Oozeer, Foad Namjoo et al. · arXiv · Oct 27, 2026

  Activation steering offers an effective and efficient way to modify an LLM's behavior at inference time. However, it remains unclear how to apply steering such that the signal is consistently strong and the steering strength has a universal…

• A note on data-efficient finetuning of vision foundation models
  Niclas Hergenröther, Antonio Orvieto · arXiv · Oct 27, 2026

  Adapting foundation models to a new task within or beyond the training domain is the de facto standard for building specialized machine learning models. Recently, Visual Prompting (VP) has emerged as a promising technique for efficient know…

• Keeping Inference in the Radio: Design and Measurement of a Spiking Accelerator for mmWave ISAC Activity Recognition
  Anthony Sánchez, Rafael Ruiz, José A. Belloch, Jesús O. Lacruz et al. · arXiv · Oct 27, 2026

  Integrated sensing and communication allows wireless networks to recognize human activity from the channel estimates that the receiver computes anyway. The inference, however, runs on the general-purpose processors of the base station, acce…

• CRISP: Co-designing Pruning and Scheduling for Efficient MoE Inference on Edge Servers
  Congwei Zhang, Youming Tao, Yifei Zou, Yu Yang et al. · arXiv · Oct 27, 2026

  Mixture-of-Experts (MoE) inference on memory-constrained edge platforms is often dominated by expert-weight movement rather than computation. Although each token activates only a small subset of experts, routing is input-dependent, so all e…

• Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization
  Shreya Meel, Sennur Ulukus, Itzhak Tamo · arXiv · Oct 26, 2026

  In federated learning (FL), secure aggregation enables a server to compute the sum of local model updates of $N$ clients, without revealing any information on the individual model updates to the server, beyond their sum. Different clients m…

• Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models
  Aidar Myrzakhan, Zhiqiang Shen · arXiv · Oct 26, 2026

  Diffusion large language models (dLLMs) can generate multiple tokens in parallel, but often require many decoding rounds to complete a response. Efficient generation depends not only on which tokens are easy to predict, but also on how comm…

• TRACE: Memory-Efficient Time Series Class-Incremental Learning via Temporal-Spectral Reconstruction
  Junhui Mao, Junru Zhang, Liming Ye, Cheng Peng et al. · arXiv · Oct 26, 2026

  Web-connected sensing applications continuously generate multivariate time series with evolving behavioral categories, making Time Series Class-Incremental Learning (TSCIL) essential for adapting to new classes without forgetting previously…

• Detecting bus delays and service anomalies in Niterói with autoencoder latent feature representations
  Matheus Germano, Claudio E. C. Campelo · arXiv · Oct 26, 2026

  Bus riders judge service by two failures: single trips that run late, and days on which the whole system misbehaves. We ask whether one unsupervised representation of raw GPS telemetry can serve both diagnoses on the NetMob 2026 Niterói bus…

• Provably Efficient Q-learning for Robust Reinforcement Learning
  Yuchen Jiao, Gen Li · arXiv · Oct 26, 2026

  Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robust RL algorithms based on robust MDPs (RMDPs) have been proposed, for …

• Neuromorphic Computing Architectures for Low-Power Edge Inference in IoT Applications
  Letahun Nemeon, P. Kharabi · Progress in Electronics and... · Oct 24, 2026

  The blistering advancements witnessed in the Internet of Things (IoT) ecosystem have led to the urgency of search outcomes that provide energy efficient, low latency, and smart processing support that manifests itself right at the edge. The…

• Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery
  Marek Masiak, Andrzej Szablewski, Nicola Cancedda, Constantin Venhoff · arXiv · Oct 23, 2026

  Fine-tuning on datasets of unknown origin can create a backdoor in the trained model when the data includes poisoned examples. Difficult to localise and remove, backdoors can persist through safety training. While parameter-efficient fine-t…

• Sustainability of TSFM Deployment and Pretraining: From Carbon Footprint Analysis to Mitigation via Pruning
  Cécile Luc, Nathanaël Lemonnier, Ievgen Redko · arXiv · Oct 23, 2026

  Time Series Foundation Models (TSFMs) offer strong zero-shot forecasting capabilities, but their high pretraining cost raises a practical sustainability question: does this upfront investment pay off over a full deployment lifecycle, compar…

• Singular Geometry of Low-Rank Adaptation
  Kamillo Ferry, Anthea Monod, Keisuke Yano · arXiv · Oct 23, 2026

  Low-rank adaptation (LoRA) is now a standard approach to parameter-efficient fine-tuning of large neural networks. Its low-rank factorization is inherently non-identifiable, making LoRA a singular statistical model whose learning complexity…

• On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
  Leon Sick, Lukas Hoyer, Yannick Strümpler, Christian Reisswig et al. · arXiv · Oct 23, 2026

  On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth question-answer pairs, human-curated problem sets, or other supervised sign…

• Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes
  August Arnstad, Geir Olve Storvik, Filippo Pagani, Leiv Rønneberg · arXiv · Oct 23, 2026

  There is growing evidence that the performance of a neural network depends largely on a small subset of its weights, which are typically identified by training a dense network and pruning it afterwards. Within a Bayesian framework, pruning …

• Optimal Accelerated Life Testing Sampling Plan Design With Piecewise Linear Function Based Modeling of Lifetime Characteristics
  Sandip Barui, Shovan Chowdhury · Quality and Reliability Eng... · Oct 23, 2026

  ABSTRACT Researchers have widely used accelerated life tests to determine an optimal inspection plan for lot acceptance. All such plans are proposed by assuming a known relationship between the lifetime characteristic(s) and the acceleratin…

• METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
  Ali Najar, Hosein Hasani, Amir Kooshan Fattah, Yasamin Rajabi et al. · arXiv · Oct 22, 2026

  Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long interaction histories. Classical recurrent agents compress experience into …

• Rethinking Sequence Compression with Test-time Regression
  Sihan Yang, Jie Huang, Hanxuan Li, Yifan Guo et al. · arXiv · Oct 22, 2026

  Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimodal models, and yet prevailing approaches based on pooling or learned projections remain underperforming. We revisit sequ…

• When to Follow the Teacher: Advantage-Based On-Policy Distillation
  Mahdi Sabbaghi, George Pappas, Hamed Hassani, Adel Javanmard · arXiv · Oct 22, 2026

  Online Policy Distillation (OPD) often outperforms offline methods such as Supervised Fine-Tuning (SFT) by training on trajectories sampled directly from the student. However, standard OPD trains the student to follow the teacher at every s…

• Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon
  Kyrylo Yemets, Andrii Yaroshevych, Victor Muryn, Ostap Khomenko et al. · arXiv · Oct 22, 2026

  Apple Silicon is among the most widely used platforms for local LLM inference, yet nearly all inference optimizations are designed and validated on server-class NVIDIA GPUs under batched serving workloads. Which optimizations retain their b…

• On Neighbourhood Cross Validation
  Simon N. Wood · Statistical Science · Oct 22, 2026

  Many varieties of cross validation would be statistically appealing for the estimation of smoothing and other penalized regression hyperparameters, were it not for the high cost of evaluating such criteria. Here it is shown how to efficient…

• Asymmetric On-Policy Distillation Learns In-Context Exploration
  Sriyash Poddar, Yanda Bao, Jacob Krantz, Matthew Chang et al. · arXiv · Oct 21, 2026

  Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such information-gathering behaviors tabula rasa via online reinf…

• CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents
  Wenhao Yu, Zhengcheng Wang, Jiahong Liu, Zexuan Qiu et al. · arXiv · Oct 21, 2026

  Joint reinforcement learning and self-distillation combines task rewards with dense teacher guidance for agent training, but their gradients can partly cancel. A mixing coefficient controls relative scale without selectively removing opposi…