Zobrazeno 1 - 10
of 293
pro vyhledávání: '"Tian Yingtao"'
Undeniably, Large Language Models (LLMs) have stirred an extraordinary wave of innovation in the machine learning research domain, resulting in substantial impact across diverse fields such as reinforcement learning, robotics, and computer vision. Th
Externí odkaz:
http://arxiv.org/abs/2405.03547
Generative AI tools are becoming more prevalent in 3D modeling, enabling users to manipulate or create new models with text or images as inputs. This makes it easier for users to rapidly customize and iterate on their 3D designs and explore new creat
Externí odkaz:
http://arxiv.org/abs/2404.10142
Autor:
Tian, Yingtao
Chinese, Japanese, and Korean (CJK), with a vast number of native speakers, have profound influence on society and culture. The typesetting of CJK languages carries a wide range of requirements due to the complexity of their scripts and unique litera
Externí odkaz:
http://arxiv.org/abs/2404.05212
Evolutionary optimization algorithms are often derived from loose biological analogies and struggle to leverage information obtained during the sequential course of optimization. An alternative promising approach is to leverage data and directly disc
Externí odkaz:
http://arxiv.org/abs/2403.02985
Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms. These include gradient descent, classification, sequence completion, transformation, and improvement. In this work, we investigate whether la
Externí odkaz:
http://arxiv.org/abs/2402.18381
Autor:
Kitamoto, Asanobu, Hwang, Jared, Vuillod, Bastien, Gautier, Lucas, Tian, Yingtao, Clanuwat, Tarin
This paper presents the official release of the Digital Typhoon dataset, the longest typhoon satellite image dataset for 40+ years aimed at benchmarking machine learning models for long-term spatio-temporal data. To build the dataset, we developed a
Externí odkaz:
http://arxiv.org/abs/2311.02665
Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e.g. meta-learning through long inner loop unrolls or optimizing non-differentiable operators. One core re
Externí odkaz:
http://arxiv.org/abs/2311.02394
Autor:
Tian, Yingtao
Computational creativity has contributed heavily to abstract art in modern era, allowing artists to create high quality, abstract two dimension (2D) arts with a high level of controllability and expressibility. However, even with computational approa
Externí odkaz:
http://arxiv.org/abs/2304.12932
DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards
Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have shown the effectiveness of encour
Externí odkaz:
http://arxiv.org/abs/2304.10770
Recent advances in deep learning, such as powerful generative models and joint text-image embeddings, have provided the computational creativity community with new tools, opening new perspectives for artistic pursuits. Text-to-image synthesis approac
Externí odkaz:
http://arxiv.org/abs/2204.08472