Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Du, Yingjun"'
Autor:
Liu, Jie, Zhou, Pan, Du, Yingjun, Tan, Ah-Hwee, Snoek, Cees G. M., Sonke, Jan-Jakob, Gavves, Efstratios
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term
Externí odkaz:
http://arxiv.org/abs/2411.04679
Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional shifts that negatively impact generalizability to unseen samples. This
Externí odkaz:
http://arxiv.org/abs/2410.20164
Pre-trained vision-language models like CLIP have remarkably adapted to various downstream tasks. Nonetheless, their performance heavily depends on the specificity of the input text prompts, which requires skillful prompt template engineering. Instea
Externí odkaz:
http://arxiv.org/abs/2410.15397
Recent advancements in open vocabulary models, like CLIP, have notably advanced zero-shot classification and segmentation by utilizing natural language for class-specific embeddings. However, most research has focused on improving model accuracy thro
Externí odkaz:
http://arxiv.org/abs/2404.00701
Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile process.
Externí odkaz:
http://arxiv.org/abs/2306.14770
This paper investigates the problem of scene graph generation in videos with the aim of capturing semantic relations between subjects and objects in the form of $\langle$subject, predicate, object$\rangle$ triplets. Recognizing the predicate between
Externí odkaz:
http://arxiv.org/abs/2306.10122
Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is inspired
Externí odkaz:
http://arxiv.org/abs/2306.05189
Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for few-shot learnin
Externí odkaz:
http://arxiv.org/abs/2305.10309
Modern image classifiers perform well on populated classes, while degrading considerably on tail classes with only a few instances. Humans, by contrast, effortlessly handle the long-tailed recognition challenge, since they can learn the tail represen
Externí odkaz:
http://arxiv.org/abs/2304.00101
Publikováno v:
ICLR 2022
Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and test distrib
Externí odkaz:
http://arxiv.org/abs/2112.08181