Zobrazeno 1 - 10
of 1 151
pro vyhledávání: '"Matusik P"'
Tactile sensors present a powerful means of capturing, analyzing, and augmenting human-environment interactions. Accelerated by advancements in design and manufacturing, resistive matrix-based sensing has emerged as a promising method for developing
Externí odkaz:
http://arxiv.org/abs/2412.00247
Autor:
Wijaya, Kevin Tirta, Guo, Minghao, Sun, Michael, Seidel, Hans-Peter, Matusik, Wojciech, Babaei, Vahid
Accurate property prediction is crucial for accelerating the discovery of new molecules. Although deep learning models have achieved remarkable success, their performance often relies on large amounts of labeled data that are expensive and time-consu
Externí odkaz:
http://arxiv.org/abs/2411.03537
Visual Question-Answering, a technology that generates textual responses from an image and natural language question, has progressed significantly. Notably, it can aid in tracking and inquiring about daily activities, crucial in healthcare monitoring
Externí odkaz:
http://arxiv.org/abs/2410.20034
While large language models (LLMs) have integrated images, adapting them to graphs remains challenging, limiting their applications in materials and drug design. This difficulty stems from the need for coherent autoregressive generation across texts
Externí odkaz:
http://arxiv.org/abs/2410.04223
Autor:
Chen, Peter Yichen, Liu, Chao, Ma, Pingchuan, Eastman, John, Rus, Daniela, Randle, Dylan, Ivanov, Yuri, Matusik, Wojciech
Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates object pro
Externí odkaz:
http://arxiv.org/abs/2410.03920
Autor:
Sun, Michael, Lo, Alston, Gao, Wenhao, Guo, Minghao, Thost, Veronika, Chen, Jie, Coley, Connor, Matusik, Wojciech
Designing synthetically accessible molecules and recommending analogs to unsynthesizable molecules are important problems for accelerating molecular discovery. We reconceptualize both problems using ideas from program synthesis. Drawing inspiration f
Externí odkaz:
http://arxiv.org/abs/2409.05873
A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold N
Externí odkaz:
http://arxiv.org/abs/2408.10205
Autor:
Rao, Pramod, Fox, Gereon, Meka, Abhimitra, R, Mallikarjun B, Zhan, Fangneng, Weyrich, Tim, Bickel, Bernd, Pfister, Hanspeter, Matusik, Wojciech, Elgharib, Mohamed, Theobalt, Christian
Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency,
Externí odkaz:
http://arxiv.org/abs/2407.10487
Autor:
Li, Sizhe Lester, Zhang, Annan, Chen, Boyuan, Matusik, Hanna, Liu, Chao, Rus, Daniela, Sitzmann, Vincent
Mirroring the complex structures and diverse functions of natural organisms is a long-standing challenge in robotics. Modern fabrication techniques have dramatically expanded feasible hardware, yet deploying these systems requires control software to
Externí odkaz:
http://arxiv.org/abs/2407.08722
Autor:
Guo, Minghao, Wang, Bohan, Ma, Pingchuan, Zhang, Tianyuan, Owens, Crystal Elaine, Gan, Chuang, Tenenbaum, Joshua B., He, Kaiming, Matusik, Wojciech
We present a computational framework that transforms single images into 3D physical objects. The visual geometry of a physical object in an image is determined by three orthogonal attributes: mechanical properties, external forces, and rest-shape geo
Externí odkaz:
http://arxiv.org/abs/2405.20510