中文
相关论文

相关论文: On the Evaluation of Vision-and-Language Navigatio…

200 篇论文

Recent research in behaviour understanding through language grounding has shown it is possible to automatically generate behaviour models from textual instructions. These models usually have goal-oriented structure and are modelled with…

人工智能 · 计算机科学 2020-01-14 Debajyoti Paul Chowdhury , Arghya Biswas , Tomasz Sosnowski , Kristina Yordanova

Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete…

We present a method for training reference-guided, perceptive reinforcement learning locomotion policies for humanoid robots in which reference trajectories are modulated in training to be consistent with terrain geometry. Aiming to deploy…

机器人学 · 计算机科学 2026-05-18 William D. Compton , Zachary Olkin , Aaron D. Ames

Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified. In this paper, we present a novel training…

计算与语言 · 计算机科学 2020-03-11 Qiaolin Xia , Xiujun Li , Chunyuan Li , Yonatan Bisk , Zhifang Sui , Jianfeng Gao , Yejin Choi , Noah A. Smith

The ability of large language models (LLMs) to follow user instructions is central to their reliability, safety, and usefulness. While prior studies assess instruction adherence in the model's main responses, we argue that it is also…

机器学习 · 计算机科学 2025-10-20 Yongchan Kwon , Shang Zhu , Federico Bianchi , Kaitlyn Zhou , James Zou

The academic field of learning instruction-guided visual navigation can be generally categorized into high-level category-specific search and low-level language-guided navigation, depending on the granularity of language instruction, in…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Gengze Zhou , Yicong Hong , Zun Wang , Chongyang Zhao , Mohit Bansal , Qi Wu

Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language modality for scene descriptions or reasoning and lack the…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Sicheng Zuo , Yuxuan Li , Wenzhao Zheng , Zheng Zhu , Jie Zhou , Jiwen Lu

Visual Language Navigation (VLN) powered robots have the potential to guide blind people by understanding route instructions provided by sighted passersby. This capability allows robots to operate in environments often unknown a prior.…

机器人学 · 计算机科学 2026-01-29 Masaki Kuribayashi , Kohei Uehara , Allan Wang , Daisuke Sato , Simon Chu , Shigeo Morishima

Goal-oriented vision-language navigation requires robust exploration capabilities for agents to navigate to specified goals in unknown environments without step-by-step instructions. Existing methods tend to exclusively utilize…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Songze Li , Zun Wang , Gengze Zhou , Jialu Li , Xiangyu Zeng , Ziyang Gong , Limin Wang , Yu Qiao , Qi Wu , Mohit Bansal , Yi Wang

Classifier-Free Guidance (CFG) has been a default technique in various visual generative models, yet it requires inference from both conditional and unconditional models during sampling. We propose to build visual models that are free from…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Huayu Chen , Kai Jiang , Kaiwen Zheng , Jianfei Chen , Hang Su , Jun Zhu

In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing…

机器学习 · 计算机科学 2026-05-21 Jerry Y. Huang , Justin Lin , Sheel Shah , Kartik Nair , Nicholas M. Boffi

Finding an object of a specific class in an unseen environment remains an unsolved navigation problem. Hence, we propose a hierarchical learning-based method for object navigation. The top-level is capable of high-level planning, and…

人工智能 · 计算机科学 2022-11-17 Matthias Hutsebaut-Buysse , Kevin Mets , Tom De Schepper , Steven Latré

Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the expense of generation diversity, limiting the utility of these…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Nicola Dall'Asen , Xiaofeng Zhang , Reyhane Askari Hemmat , Melissa Hall , Jakob Verbeek , Adriana Romero-Soriano , Michal Drozdzal

Work on instruction-tuned Large Language Models (LLMs) has used automatic methods based on text overlap and LLM judgments as cost-effective alternatives to human evaluation. In this paper, we perform a meta-evaluation of such methods and…

计算与语言 · 计算机科学 2024-10-03 Ehsan Doostmohammadi , Oskar Holmström , Marco Kuhlmann

This work presents a mapless global navigation approach for outdoor applications. It combines the exploratory capacity of conditional variational autoencoders (CVAEs) to generate trajectories and the semantic segmentation capabilities of a…

机器人学 · 计算机科学 2026-02-03 Gonzalo Olguin , Javier Ruiz-del-Solar

Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods update a visual projector to translate visual information for…

计算机视觉与模式识别 · 计算机科学 2025-08-04 Hyundong Jin , Hyung Jin Chang , Eunwoo Kim

Textual explanations have proved to help improve user satisfaction on machine-made recommendations. However, current mainstream solutions loosely connect the learning of explanation with the learning of recommendation: for example, they are…

信息检索 · 计算机科学 2021-01-26 Aobo Yang , Nan Wang , Hongbo Deng , Hongning Wang

Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents. Large…

计算与语言 · 计算机科学 2024-03-06 Hitesh Golchha , Sahil Yerawar , Dhruvesh Patel , Soham Dan , Keerthiram Murugesan

Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance methods have emerged with improved generation quality and human preference. However, can…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Dian Xie , Shitong Shao , Lichen Bai , Zikai Zhou , Bojun Cheng , Shuo Yang , Jun Wu , Zeke Xie

Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of images using text-to-image models without considering the…

机器学习 · 计算机科学 2025-04-08 Yucheng Suo , Fan Ma , Kaixin Shen , Linchao Zhu , Yi Yang