Small on-device models

Trend over time

Evidence papers — 50 most recent of 722

• The Weight Is Over - Interactive Diffusion on Consumer GPUs
  Frieder Ganz, Maximilian Müller · Sep 2026 · arXiv
• Learned Parametric Emotion Editing: Real-Time Affective Filtering for On-Device Social Media Video
  Musa Rochi, Marcel Schubert, Christoph Gebhardt · Sep 2026 · arXiv
• Samsone: A Family of Open Small Audio Language Models for On-Device Inference
  Piotr Masztalski, Michał K. Grzeszczyk, Olaf Sikorski · Sep 2026 · arXiv
• TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching
  Zhihao Shu, Md Musfiqur Rahman Sanim, Jie Hu, Kun Yuan, Minghai Qin, Gagan Agrawal, Wei Niu · Sep 2026 · arXiv
• SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference
  Harish KB, Jagadeeswaran M, Pradheep P, Yuvanesh S, Sivakumar T · Sep 2026 · arXiv
• Opinion Dynamics-based Coalition Formation for Federated Learning in Heterogeneous IoT Systems
  Mohammed El Hanjri, Anas Abouaomar, Hamidou Tembine, Abdellatif Kobbane · Sep 2026 · arXiv
• QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training
  Davide Vitabile, N. Ranjan, Akshay Nambiar, Kamal K. Gupta, Amril Nazir · Sep 2026 · arXiv
• Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain
  Aakash Singh, Lakshmi Pedapudi, Chandrashekar M S, Sanyam Singh, Naga Ganesh, Vineet Singh · Sep 2026 · arXiv
• MOSAIC-SR: Transformer-Guided Symbolic Regression for Scientific Equation Recovery
  Peiyi Zheng, Yanming Kang, Hans De Sterck, Giang Tran · Sep 2026 · arXiv
• Federated Learning Framework for Privacy-Preserving Kidney Stone Detection
  Najiyya Younas, Omar Abdulkader, Yaser Ali Shah, Muhammad Jawad Ikram, Jebran Khan, Amaad Khalil · Sep 2026 · arXiv
• Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols
  Tariq Abdul-Quddoos, Xiangfang Li, Lijun Qian · Sep 2026 · arXiv
• VibeAvatar: Aligning Phonetic Kinematics and Human Aesthetics for High-Fidelity Talking Avatar Synthesis
  Qilin Wang, Mingyu Li, Hao Tang · Sep 2026 · arXiv
• Selection Is Retrieval, Abstention Is Not: On-Device Tool Routing over 70 Korean-English Actions
  Janghoon Lee · Sep 2026 · arXiv
• Geospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines
  Daniel Ebanks, Devika Jain · Sep 2026 · arXiv
• Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling
  Lixuan Wei, Wei Zhou, Jianwen Wu, Yipeng Shen, Meiling Wang, Haoran You · Sep 2026 · arXiv
• Affect-Prototype Guided Fusion for Open-Vocabulary Incomplete Multi-modal Emotion Recognition
  Yichi Zhang, Shenyue Wang, Jing Luo, Chunyang Yu, Xinyu Yang · Sep 2026 · arXiv
• Cross-Domain Inference for Human Localization: Applying Wi-Fi RSSI Data to CSI-Trained Models
  Ariel Duschanek-Myers, Thomas Welsh, Helmut Neukirchen · Sep 2026 · arXiv
• Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models
  Jinwoo Jeon, GyuYeop Do, Yubin Lim, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Byung-Jun Lee · Sep 2026 · arXiv
• Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators
  Yuyeong Shin · Sep 2026 · arXiv
• To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs
  Franck Signe, Hippolyte Pilchen, François Yvon, Édouard Grave · Sep 2026 · arXiv
• MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding
  Hongchang Shi, Jinpeng Hu, Ao Wang, Wenzheng Zhou, Hui Ma, Feng Li, Zenglin Shi · Sep 2026 · arXiv
• CapsuleMotion: A Lightweight Real-Time Visual Motion Predictor for Capsule Endoscopy
  Oliver Bause, Julia Werner, Oliver Bringmann · Sep 2026 · arXiv
• Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflows
  Baptiste Brument, Robin Bruneau, Benjamin Coupry, Vincent Demoulin, Jean Mélou, Antoine Laurent, Fabien Castan, Jean-Denis Durou, Lilian Calvet · Sep 2026 · arXiv
• Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models
  Inez Okulska, Bartosz Naskręcki, Jan Piotrowski, Tomasz Steifer · Sep 2026 · arXiv
• What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures with On-Device Measurements
  Takeshi Nishikawa · Sep 2026 · arXiv
• MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks
  Sokratis Nikolaidis, Stylianos I. Venieris, Leonidas Malachias, Iakovos S. Venieris · Sep 2026 · arXiv
• You Don't Need To Train: Agentic Heuristic Learning Studio for Executable Human Activity Recognition
  Siyu Yuan, He Zhang, Sizhen Bian, Bin Guo · Sep 2026 · arXiv
• Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference
  Tian Jin · Sep 2026 · arXiv
• World-Action Models for Robot Learning and Control: A Survey
  Zuxing Lu, Hongjia Zhai, Guanzhi Wang, Huajian Zeng, Jiaqi Yang, Jingyu Liu, Lei Cheng, Yuantai Zhang, Yuheng Qiu, Zezhou Cheng, Ivan Laptev, Danfei Xu, Benjamin Riviere, Giuseppe Loianno, Eric Xing, Xingxing Zuo · Sep 2026 · arXiv
• PC$^2$-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devices
  Yutong Gu, Yingxi Xie, Kejin Huang, Jian Ning, Hanzhe Liang, Linlin Shen, Jinbao Wang · Sep 2026 · arXiv
• URCHIN: A Horizontal Spiking Language Model for Data-Constrained Pretraining
  Po-Han Chiang · Sep 2026 · arXiv
• What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency
  Luoyang Sun, Guoyang Xia, Fengfa Li, Lei Ren, Xinyu Cui, Haifeng Zhang, Fangxiang Feng, Kaike Zhang, Kun Zhan, Yan Xie, Jun Wang, Cheng Deng · Sep 2026 · arXiv
• OrchSLM: Probing the Dynamics of Small Language Model Orchestration
  Chengxi Zhang, Yu Yao · Sep 2026 · arXiv
• Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems
  Reina Mun, Zishen Wan, Vijay Janapa Reddi · Sep 2026 · arXiv
• Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks
  Sebastiano Nordio, Michele Lotto · Sep 2026 · arXiv
• Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
  Lisa Bylinina · Sep 2026 · arXiv
• Predicting Train Delays in Finland Using Machine Learning and Weather Data
  Vinicius Pozzobon Borin, Jean Michel de Souza Sant'Ana, Nurul Huda Mahmood · Sep 2026 · arXiv
• LAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone Photos
  Achim von Stryk, Janis Keuper · Sep 2026 · arXiv
• Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs
  Joseph Kanichai, Tiziano De Matteis, Animesh Trivedi · Sep 2026 · arXiv
• Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling
  Tingshuo Fan, Hongtao Mu, Tianyu Zhou, Hansen Liu, Tao Ji · Sep 2026 · arXiv
• Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation
  Sudaksh Kalra, Dolly Sapra · Sep 2026 · arXiv
• PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling
  Weisi Yang, Stephen Xia · Sep 2026 · arXiv
• RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding
  Fang Li · Sep 2026 · arXiv
• From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora
  Christoph Wigbels, Ali Abusaleh, Markus T. Jansen, Alexander Mehler, Markus J. Hofmann · Sep 2026 · arXiv
• Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding
  Fengxiang Bie, Yuqing Jian, Yifan Yu, Zhongzhu Zhou, Zelei Shao, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu, Tianyi Zhang · Sep 2026 · arXiv
• A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware
  Maysam Khatib, Moysis Symeonides, Demetris Trihinas, George Pallis, Marios D. Dikaiakos · Sep 2026 · arXiv
• From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls
  Hamed Jafarzadeh Asl, Yuanhao Yu, Vahid Partovi Nia · Sep 2026 · arXiv
• Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling
  Haifeng Wen, Nicolò Michelusi, Osvaldo Simeone, Yang Yang, Hong Xing · Sep 2026 · arXiv
• Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning
  Jonathan Frank, David Richerby, Ansgar Scherp · Sep 2026 · arXiv
• ArmPoser: Real-Time, Calibration-Free Arm Pose Estimation from Smartwatch IMU
  Bishnu Dev, Vasco Xu, Xi-Aan Loh, Chenfeng Gao, Henry Hoffmann, Karan Ahuja · Sep 2026 · arXiv