Zobrazeno 1 - 10
of 252
pro vyhledávání: '"Hou, Yifan"'
Reasoning is a central capability of human intelligence. In recent years, with the advent of large-scale datasets, pretrained large language models have emerged with new capabilities, including reasoning. However, these models still struggle with lon
Externí odkaz:
http://arxiv.org/abs/2411.06655
Autor:
Hou, Yifan, Liu, Zeyi, Chi, Cheng, Cousineau, Eric, Kuppuswamy, Naveen, Feng, Siyuan, Burchfiel, Benjamin, Song, Shuran
Compliance plays a crucial role in manipulation, as it balances between the concurrent control of position and force under uncertainties. Yet compliance is often overlooked by today's visuomotor policies that solely focus on position control. This pa
Externí odkaz:
http://arxiv.org/abs/2410.09309
Visual language is a system of communication that conveys information through symbols, shapes, and spatial arrangements. Diagrams are a typical example of a visual language depicting complex concepts and their relationships in the form of an image. T
Externí odkaz:
http://arxiv.org/abs/2410.00193
Large language models (LLMs) exhibit an intriguing ability to learn a novel task from in-context examples presented in a demonstration, termed in-context learning (ICL). Understandably, a swath of research has been dedicated to uncovering the theorie
Externí odkaz:
http://arxiv.org/abs/2406.04216
Autor:
Hou, Yifan, Li, Jiaoda, Fei, Yu, Stolfo, Alessandro, Zhou, Wangchunshu, Zeng, Guangtao, Bosselut, Antoine, Sachan, Mrinmaya
Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a multi-step
Externí odkaz:
http://arxiv.org/abs/2310.14491
Autor:
Bauza, Maria, Bronars, Antonia, Hou, Yifan, Taylor, Ian, Chavan-Dafle, Nikhil, Rodriguez, Alberto
Existing robotic systems have a clear tension between generality and precision. Deployed solutions for robotic manipulation tend to fall into the paradigm of one robot solving a single task, lacking precise generalization, i.e., the ability to solve
Externí odkaz:
http://arxiv.org/abs/2307.13133
Various design settings for in-context learning (ICL), such as the choice and order of the in-context examples, can bias a model toward a particular prediction without being reflective of an understanding of the task. While many studies discuss these
Externí odkaz:
http://arxiv.org/abs/2305.19148
Autor:
Zhou, Wangchunshu, Jiang, Yuchen Eleanor, Cui, Peng, Wang, Tiannan, Xiao, Zhenxin, Hou, Yifan, Cotterell, Ryan, Sachan, Mrinmaya
The fixed-size context of Transformer makes GPT models incapable of generating arbitrarily long text. In this paper, we introduce RecurrentGPT, a language-based simulacrum of the recurrence mechanism in RNNs. RecurrentGPT is built upon a large langua
Externí odkaz:
http://arxiv.org/abs/2305.13304
Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models
Externí odkaz:
http://arxiv.org/abs/2210.13617
RGB-thermal salient object detection (RGB-T SOD) aims to locate the common prominent objects of an aligned visible and thermal infrared image pair and accurately segment all the pixels belonging to those objects. It is promising in challenging scenes
Externí odkaz:
http://arxiv.org/abs/2207.03558