Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Thomason, Jesse"'
Autor:
Hejabi, Parsa, Rahmati, Elnaz, Ziabari, Alireza S., Golazizian, Preni, Thomason, Jesse, Dehghani, Morteza
Large Language Models (LLMs) have shown impressive capabilities in complex tasks and interactive environments, yet their creativity remains underexplored. This paper introduces a simulation framework utilizing the game Balderdash to evaluate both the
Externí odkaz:
http://arxiv.org/abs/2411.10422
Language models for American Sign Language (ASL) could make language technologies substantially more accessible to those who sign. To train models on tasks such as isolated sign recognition (ISR) and ASL-to-English translation, datasets provide annot
Externí odkaz:
http://arxiv.org/abs/2411.03568
Navigating unfamiliar environments presents significant challenges for blind and low-vision (BLV) individuals. In this work, we construct a dataset of images and goals across different scenarios such as searching through kitchens or navigating outdoo
Externí odkaz:
http://arxiv.org/abs/2407.08219
Robot evaluations in language-guided, real world settings are time-consuming and often sample only a small space of potential instructions across complex scenes. In this work, we introduce contrast sets for robotics as an approach to make small, but
Externí odkaz:
http://arxiv.org/abs/2406.13636
This paper studies in-context learning by decomposing the output of large language models into the individual contributions of attention heads and MLPs (components). We observe curious components: good-performing ones that individually do well on a c
Externí odkaz:
http://arxiv.org/abs/2406.13131
Symbolic planners can discover a sequence of actions from initial to goal states given expert-defined, domain-specific logical action semantics. Large Language Models (LLMs) can directly generate such sequences, but limitations in reasoning and state
Externí odkaz:
http://arxiv.org/abs/2406.02791
Classical planning formulations like the Planning Domain Definition Language (PDDL) admit action sequences guaranteed to achieve a goal state given an initial state if any are possible. However, reasoning problems defined in PDDL do not capture tempo
Externí odkaz:
http://arxiv.org/abs/2403.17246
Publikováno v:
IEEE/RSJ International Conference on Intelligent Robots and Systems 2024
Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast, humans are abl
Externí odkaz:
http://arxiv.org/abs/2403.10940
Autor:
Srinivasan, Tejas, Hessel, Jack, Gupta, Tanmay, Lin, Bill Yuchen, Choi, Yejin, Thomason, Jesse, Chandu, Khyathi Raghavi
Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate predictions, selecti
Externí odkaz:
http://arxiv.org/abs/2402.15610
Humans perceive and comprehend different visual properties of an object based on specific contexts. For instance, we know that a banana turns brown ``when it becomes rotten,'' whereas it appears green ``when it is unripe.'' Previous studies on probin
Externí odkaz:
http://arxiv.org/abs/2402.13584