Results 111 to 120 of about 29,104 (263)

Tibetan Few‐Shot Learning Model With Deep Contextualised Two‐Level Word Embeddings

CAAI Transactions on Intelligence Technology
Few‐shot learning is the task of identifying new text categories from a limited set of training examples. The two key challenges in few‐shot learning are insufficient understanding of new samples and imperfect modelling.
Ziyue Zhang, Yongbin Yu, Xiangxiang Wang, Xiao Feng, Yuze Li, Jiarun Shen, Dorje Tashi, Jin Zhang, Lobsang Yeshi, Lei Li, Nyima Tashi, Jingye Cai   +11 more
doaj   +1 more source

Spheroid‐On‐A‐Drop: A Modular Droplet Microfluidics Platform

Advanced Materials Technologies, EarlyView.
The proposed Spheroid‐on‐a‐Drop platform represents a reproducible and tunable platform for the fabrication of biocompatible GelMA‐based microgels, able to support controlled 3D tumor spheroid culture. Its precise control over droplet dynamics and cell distribution paves the way for advanced applications in tissue modeling, drug screening, and ...
A. Fergola, V. Vighetto, G. Mesiano, A. Cosola, S. L. Marasso, M. Cocuzza, C. F. Pirri, L. Napione, F. Frascella   +8 more
wiley   +1 more source

Scalable Task Planning via Large Language Models and Structured World Representations

Advanced Robotics Research, EarlyView.
This work efficiently combines graph‐based world representations with the commonsense knowledge in Large Language Models to enhance planning techniques for the large‐scale environments that modern robots will need to face. Planning methods often struggle with computational intractability when solving task‐level problems in large‐scale environments ...
Rodrigo Pérez‐Dattari, Zhaoting Li, Robert Babuška, Jens Kober, Cosimo Della Santina   +4 more
wiley   +1 more source

The Future of Research in Cognitive Robotics: Foundation Models or Developmental Cognitive Models?

Advanced Robotics Research, EarlyView.
Research in cognitive robotics founded on principles of developmental psychology and enactive cognitive science would yield what we seek in autonomous robots: the ability to perceive its environment, learn from experience, anticipate the outcome of events, act to pursue goals, and adapt to changing circumstances without resorting to training with ...
David Vernon
wiley   +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

Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback

Advanced Robotics Research, EarlyView.
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami   +4 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

3D Printing of Soft Robotic Systems: Advances in Fabrication Strategies and Future Trends

Advanced Robotics Research, EarlyView.
Collectively, this review systematically examines 3D‐printed soft robotics, encompassing material selections, function integration, and manufacturing methodologies. Meanwhile, fabrication strategies are analyzed in order of increasing complexity, highlighting persistent challenges with proposed solutions.
Changjiang Liu, Bin Cui, Xumin Huang, Xiaoyu (Rayne) Zheng, T. Thang Vo‐Doan, Ruirui Qiao   +5 more
wiley   +1 more source

Identifying Physical Interactions in Contact‐Based Robot Manipulation for Learning from Demonstration

Advanced Robotics Research, EarlyView.
Robots can learn manipulation tasks from human demonstrations. This work proposes a versatile method to identify the physical interactions that occur in a demonstration, such as sequences of different contacts and interactions with mechanical constraints.
Alex Harm Gert‐Jan Overbeek, Herman van der Kooij, Douwe Dresscher, Mark Vlutters   +3 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