中文
相关论文

相关论文: Think Before You Act: Unified Policy for Interleav…

200 篇论文

Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture…

计算机视觉与模式识别 · 计算机科学 2023-07-10 Clayton Fields , Casey Kennington

Simultaneous machine translation (SiMT) starts its translation before reading the whole source sentence and employs either fixed or adaptive policy to generate the target sentence. Compared to the fixed policy, the adaptive policy achieves…

计算与语言 · 计算机科学 2022-10-24 Shoutao Guo , Shaolei Zhang , Yang Feng

Image captioning creates informative text from an input image by creating a relationship between the words and the actual content of an image. Recently, deep learning models that utilize transformers have been the most successful in…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Israa Al Badarneh , Bassam Hammo , Omar Al-Kadi

Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the…

计算机视觉与模式识别 · 计算机科学 2019-03-18 Dheeraj Peri , Shagan Sah , Raymond Ptucha

Task-oriented dialogue is difficult in part because it involves understanding user intent, collecting information from the user, executing API calls, and generating helpful and fluent responses. However, for complex tasks one must also…

计算与语言 · 计算机科学 2023-06-05 Stefania Raimondo , Christopher Pal , Xiaotian Liu , David Vazquez , Hector Palacios

To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents…

计算与语言 · 计算机科学 2024-06-03 Jessy Lin , Yuqing Du , Olivia Watkins , Danijar Hafner , Pieter Abbeel , Dan Klein , Anca Dragan

Deep reinforcement learning agents often struggle when tasks require understanding both vision and language. Conventional architectures typically isolate perception (for example, CNN-based visual encoders) from decision-making (policy…

机器学习 · 计算机科学 2025-10-28 Aryan Mathur , Asaduddin Ahmed

Image captioning is a challenging problem owing to the complexity in understanding the image content and diverse ways of describing it in natural language. Recent advances in deep neural networks have substantially improved the performance…

计算机视觉与模式识别 · 计算机科学 2017-04-14 Zhou Ren , Xiaoyu Wang , Ning Zhang , Xutao Lv , Li-Jia Li

Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…

人工智能 · 计算机科学 2025-10-22 Zhenyu Bi , Meng Lu , Yang Li , Swastik Roy , Weijie Guan , Morteza Ziyadi , Xuan Wang

Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…

计算与语言 · 计算机科学 2022-10-24 Mitja Nikolaus , Emmanuelle Salin , Stephane Ayache , Abdellah Fourtassi , Benoit Favre

Such human-assisting systems as robots need to correctly understand the surrounding situation based on observations and output the required support actions for humans. Language is one of the important channels to communicate with humans,…

机器人学 · 计算机科学 2022-10-07 Taiki Nakamura , Seiya Kawano , Akishige Yuguchi , Yasutomo Kawanishi , Koichiro Yoshino

In high-stakes domains such as healthcare and finance, effective decision-making demands not just accurate outcomes but transparent and explainable reasoning. However, current language models often lack the structured deliberation needed…

计算与语言 · 计算机科学 2025-08-26 Xiusi Chen , Shanyong Wang , Cheng Qian , Hongru Wang , Peixuan Han , Heng Ji

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…

计算与语言 · 计算机科学 2025-10-14 Sabrina McCallum , Amit Parekh , Alessandro Suglia

Recommender systems often use text-side information to improve their predictions, especially in cold-start or zero-shot recommendation scenarios, where traditional collaborative filtering approaches cannot be used. Many approaches to…

信息检索 · 计算机科学 2024-10-10 Vojtěch Vančura , Pavel Kordík , Milan Straka

In multi-turn dialog, utterances do not always take the full form of sentences \cite{Carbonell1983DiscoursePA}, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog…

计算与语言 · 计算机科学 2020-12-15 Xiuying Chen , Zhi Cui , Jiayi Zhang , Chen Wei , Jianwei Cui , Bin Wang , Dongyan Zhao , Rui Yan

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making,…

Attention-based architectures trained on internet-scale language data have demonstrated state of the art reasoning ability for various language-based tasks, such as logic problems and textual reasoning. Additionally, these Large Language…

机器人学 · 计算机科学 2025-08-22 Mark Van der Merwe , Devesh Jha

Cognitive planning is the structural decomposition of complex tasks into a sequence of future behaviors. In the computational setting, performing cognitive planning entails grounding plans and concepts in one or more modalities in order to…

人工智能 · 计算机科学 2022-10-11 Maria Attarian , Advaya Gupta , Ziyi Zhou , Wei Yu , Igor Gilitschenski , Animesh Garg

There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their abilities to reason about the histories of their actions and…