中文
相关论文

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

200 篇论文

The field of multimodal robot navigation in indoor environments has garnered significant attention in recent years. However, as tasks and methods become more advanced, the action decision systems tend to become more complex and operate as…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Haru Kondoh , Asako Kanezaki

We propose an end-to-end model which generates captions for images embedded in news articles. News images present two key challenges: they rely on real-world knowledge, especially about named entities; and they typically have linguistically…

计算机视觉与模式识别 · 计算机科学 2020-06-16 Alasdair Tran , Alexander Mathews , Lexing Xie

A creative image-and-text generative AI system mimics humans' extraordinary abilities to provide users with diverse and comprehensive caption suggestions, as well as rich image creations. In this work, we demonstrate such an AI creation…

计算机视觉与模式识别 · 计算机科学 2021-10-20 Yupan Huang , Bei Liu , Jianlong Fu , Yutong Lu

Classical robotic systems typically rely on custom planners designed for constrained environments. While effective in restricted settings, these systems lack generalization capabilities, limiting the scalability of embodied AI and…

机器人学 · 计算机科学 2026-02-25 Guangming Wang , Qizhen Ying , Yixiong Jing , Olaf Wysocki , Brian Sheil

Natural language is perhaps the most flexible and intuitive way for humans to communicate tasks to a robot. Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often…

机器人学 · 计算机科学 2021-07-09 Corey Lynch , Pierre Sermanet

Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like generalization, interpretability, and inter-operability with human users. Inspired by the rich interactions…

机器学习 · 计算机科学 2026-02-05 Megha Srivastava , Cedric Colas , Dorsa Sadigh , Jacob Andreas

Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios within Reinforcement…

人工智能 · 计算机科学 2024-11-19 Yonggang Jin , Ge Zhang , Hao Zhao , Tianyu Zheng , Jarvi Guo , Liuyu Xiang , Shawn Yue , Stephen W. Huang , Zhaofeng He , Jie Fu

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

计算与语言 · 计算机科学 2021-10-15 Ian Palmer , Andrew Rouditchenko , Andrei Barbu , Boris Katz , James Glass

This paper discusses and demonstrates the outcomes from our experimentation on Image Captioning. Image captioning is a much more involved task than image recognition or classification, because of the additional challenge of recognizing the…

计算机视觉与模式识别 · 计算机科学 2018-05-24 Vikram Mullachery , Vishal Motwani

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has…

计算与语言 · 计算机科学 2022-03-24 Nathan Young , Qiming Bao , Joshua Bensemann , Michael Witbrock

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…

人工智能 · 计算机科学 2025-02-18 Jun Wang

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

人工智能 · 计算机科学 2026-02-03 Jian-Qiao Zhu , Hanbo Xie , Dilip Arumugam , Robert C. Wilson , Thomas L. Griffiths

Current Conversational AI systems employ different machine learning pipelines, as well as external knowledge sources and business logic to predict the next action. Maintaining various components in dialogue managers' pipeline adds…

计算与语言 · 计算机科学 2024-04-15 Amin Hosseiny Marani , Ulie Schnaithmann , Youngseo Son , Akil Iyer , Manas Paldhe , Arushi Raghuvanshi

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3)…

In this work, we explore techniques for augmenting interactive agents with information from symbolic modules, much like humans use tools like calculators and GPS systems to assist with arithmetic and navigation. We test our agent's…

计算与语言 · 计算机科学 2023-02-14 Ruoyao Wang , Peter Jansen , Marc-Alexandre Côté , Prithviraj Ammanabrolu

Time is a crucial factor in modelling dynamic behaviours of intelligent agents: activities have a determined temporal duration in a real-world environment, and previous actions influence agents' behaviour. In this paper, we propose a…

人工智能 · 计算机科学 2023-07-11 Stefano Bistarelli , Maria Chiara Meo , Carlo Taticchi

Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…

计算与语言 · 计算机科学 2021-09-15 Yao Qiu , Jinchao Zhang , Jie Zhou

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

计算与语言 · 计算机科学 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models…

机器学习 · 计算机科学 2026-02-04 Saurabh Anand , Shubham Malaviya , Manish Shukla , Sachin Lodha

Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based on all preceding ground truth tokens. However, this approach…

计算与语言 · 计算机科学 2024-10-28 Yongjing Yin , Junran Ding , Kai Song , Yue Zhang