Zobrazeno 1 - 10
of 25 426
pro vyhledávání: '"A. Ciara"'
Autor:
Rowles, Ciara
Diffusion models excel in image generation, but controlling them remains a challenge. We focus on the problem of style-conditioned image generation. Although example images work, they are cumbersome: srefs (style-reference codes) from MidJourney solv
Externí odkaz:
http://arxiv.org/abs/2411.12811
We study the cooperative stochastic $k$-armed bandit problem, where a network of $m$ agents collaborate to find the optimal action. In contrast to most prior work on this problem, which focuses on extending a specific algorithm to the multi-agent set
Externí odkaz:
http://arxiv.org/abs/2410.23867
Autor:
Bhardwaj, Eshta, Gujral, Harshit, Wu, Siyi, Zogheib, Ciara, Maharaj, Tegan, Becker, Christoph
Data curation is a field with origins in librarianship and archives, whose scholarship and thinking on data issues go back centuries, if not millennia. The field of machine learning is increasingly observing the importance of data curation to the adv
Externí odkaz:
http://arxiv.org/abs/2410.22473
Autor:
Vainer, Shimon, Kutsy, Konstantin, De Nigris, Dante, Rowles, Ciara, Elizarov, Slava, Donné, Simon
Multi-view consistency remains a challenge for image diffusion models. Even within the Text-to-Texture problem, where perfect geometric correspondences are known a priori, many methods fail to yield aligned predictions across views, necessitating non
Externí odkaz:
http://arxiv.org/abs/2410.06985
Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation
Generating high-quality 3D objects from textual descriptions remains a challenging problem due to computational cost, the scarcity of 3D data, and complex 3D representations. We introduce Geometry Image Diffusion (GIMDiffusion), a novel Text-to-3D mo
Externí odkaz:
http://arxiv.org/abs/2409.03718
Autor:
Rowles, Ciara, Vainer, Shimon, De Nigris, Dante, Elizarov, Slava, Kutsy, Konstantin, Donné, Simon
Diffusion models continuously push the boundary of state-of-the-art image generation, but the process is hard to control with any nuance: practice proves that textual prompts are inadequate for accurately describing image style or fine structural det
Externí odkaz:
http://arxiv.org/abs/2408.03209
Autor:
Tong, Zhishen, Deng, Zijian, Xu, Xiangkun, Newman, Ciara, Jia, Xun, Zhong, Yuncheng, Reinhart, Merle, Tsouchlos, Paul, Devling, Tim, Dehghani, Hamid, Iordachita, Iulian, Saha, Debabrata, Wong, John W., Wang, Ken Kang-Hsin
CBCT-guided small animal irradiators encounter challenges in localizing soft-tissue targets due to low imaging contrast. Bioluminescence tomography (BLT) offers a promising solution, but they have largely remained in laboratorial development, limitin
Externí odkaz:
http://arxiv.org/abs/2406.13078
Autor:
Bhardwaj, Eshta, Gujral, Harshit, Wu, Siyi, Zogheib, Ciara, Maharaj, Tegan, Becker, Christoph
Studies of dataset development in machine learning call for greater attention to the data practices that make model development possible and shape its outcomes. Many argue that the adoption of theory and practices from archives and data curation fiel
Externí odkaz:
http://arxiv.org/abs/2405.02703
Autor:
Vainer, Shimon, Boss, Mark, Parger, Mathias, Kutsy, Konstantin, De Nigris, Dante, Rowles, Ciara, Perony, Nicolas, Donné, Simon
Graphics pipelines require physically-based rendering (PBR) materials, yet current 3D content generation approaches are built on RGB models. We propose to model the PBR image distribution directly, avoiding photometric inaccuracies in RGB generation
Externí odkaz:
http://arxiv.org/abs/2402.05919
Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity
We theoretically explore the relationship between sample-efficiency and adaptivity in reinforcement learning. An algorithm is sample-efficient if it uses a number of queries $n$ to the environment that is polynomial in the dimension $d$ of the proble
Externí odkaz:
http://arxiv.org/abs/2310.01616