Results 111 to 120 of about 28,763 (261)

Explain and interpret few-shot learning [PDF]

, 2023
Recent advancements in Artificial Intelligence have been fueled by vast datasets, powerful computing resources, and sophisticated algorithms. However, traditional Machine Learning models face limitations in handling scarce data. Few-Shot Learning (FSL) offers a promising solution by training models on a small number of examples per class.
openaire   +2 more sources

Durability of Soft Pneumatic Actuators: A Review and Benchmarking Protocol

Advanced Robotics Research, EarlyView.
Lack of durability is a key challenge hindering the broad scale adoption of soft pneumatic actuators (SPAs) in automation industries. This review provides a comprehensive overview of existing research on SPA durability, introduces a standardized durability benchmarking protocol to consolidate the testing of SPAs, and outlines promising directions for ...
Dickson Chiu Yu Wong, Yucheng Luo, Rob Bernardus Nicolaas Scharff   +2 more
wiley   +1 more source

Few-shot Calligraphy Style Learning

CoRR
We introduced "Presidifussion," a novel approach to learning and replicating the unique style of calligraphy of President Xu, using a pretrained diffusion model adapted through a two-stage training process. Initially, our model is pretrained on a diverse dataset containing works from various calligraphers.
Fangda Chen, Jiacheng Nie, Lichuan Jiang, Zhuoer Zeng   +3 more
openaire   +2 more sources

Multimodal Human–Robot Interaction Using Human Pose Estimation and Local Large Language Models

Advanced Robotics Research, EarlyView.
A multimodal human–robot interaction framework integrates human pose estimation (HPE) and a large language model (LLM) for gesture‐ and voice‐based robot control. Speech‐to‐text (STT) enables voice command interpretation, while a safety‐aware arbitration mechanism prioritizes gesture input for rapid intervention.
Nasiru Aboki, Ilche Georgievski, Marco Aiello   +2 more
wiley   +1 more source

Prompt-based learning for few-shot class-incremental learning

Alexandria Engineering Journal
Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to incrementally learn new tasks from a limited number of labeled samples, while retaining knowledge of previously learned tasks, mimicking the way humans learn.
Jicheng Yuan, Hang Chen, Songsong Tian, Wenfa Li, Lusi Li, Enhao Ning, Yugui Zhang   +6 more
doaj   +1 more source

LLM‐Integrated Human–Robot Interaction System for Microrobots

Advanced Robotics Research, EarlyView.
This paper proposes an LLM‐based control framework for guiding microrobots using human natural language. This framework can convert the natural human speech into safe and executable command sets for reliable navigation in complex environments. The experimental results show high accuracy and robustness in task performance, demonstrating the potential of
Bairong Zhu, Amar Salehi, Tingting Yu
wiley   +1 more source

Intelligent Sky Guardians (InSkyGuard): An Aerial Robotic Swarm for Autonomous Detection and Entrapment of Rogue Multirotors

Advanced Robotics Research, EarlyView.
Intelligent Sky Guardians (InSkyGuard) is introduced as a four‐drone swarm that autonomously detects, tracks, and safely captures rogue drones using a coordinated net system. Computer vision and leader–follower control architecture enable synchronized enclosure, while integrated failsafes enhance system reliability. Validated through closed‐environment
Joshua Hastings, Levanya Dewanarayana, Iline Shaju, Haider Al‐Wizni, Sampson Marquis, Weicheng Huang, Pooya Sareh   +6 more
wiley   +1 more source

VL-Few: Vision Language Alignment for Multimodal Few-Shot Meta Learning

Applied Sciences
Complex tasks in the real world involve different modal models, such as visual question answering (VQA). However, traditional multimodal learning requires a large amount of aligned data, such as image text pairs, and constructing a large amount of ...
Han Ma, Baoyu Fan, Benjamin K. Ng, Chan-Tong Lam   +3 more
doaj   +1 more source

Synthesizing DSLs for Few-Shot Learning

Proceedings of the ACM on Programming Languages
We study the problem of synthesizing domain-specific languages (DSLs) for few-shot learning in symbolic domains. Given a base language and instances of few-shot learning problems, where each instance is split into training and testing samples, the DSL synthesis problem asks for a grammar over the base language that guarantees that small ...
Paul Krogmeier, P. Madhusudan
openaire   +2 more sources

Mesenchymal Stromal Cell‐Mediated Intercellular Communication: Mapping the Interactome for Skeletal Muscle Homeostasis and Regeneration

Advanced Science, EarlyView.
Liu et al. define a systems‐level interactome of fibroadipogenic progenitor (FAP)‐mediated signaling in skeletal muscle by integrating single‐cell transcriptomics with FAP depletion‐based perturbation analysis. Functional interrogation using a conditioned media bioassay links predicted signaling to multicellular outcomes, establishing a framework to ...
Xingyu Liu, Edgar E. Perez Carbajal, Yih‐Chii Hwang, Sahil A. Mapkar, Benjamin W. Gilman, Sarah A. Bliss, Lam B. Tran, Kalgi T. Mehta, Jacob O. Banyasz, Ming Yu, Reynold R. Liu, Matthew N. Ly, Christapher S. Morrissey, Michael N. Wosczyna   +13 more
wiley   +1 more source