中文
相关论文

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

200 篇论文

Autoregressive image and video generators are trained with teacher-forced histories but must sample from their own generated prefixes at inference time, making them vulnerable to exposure bias and prefix drift. Existing remedies either…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Xinyao Liao , Qiyuan He , Yicong Li , Jiayin Zhu , Xiaoye Qu , Wei Wei , Angela Yao

Training data plays an essential role in modern applications of machine learning. However, gathering labeled training data is time-consuming. Therefore, labeling is often outsourced to less experienced users, or completely automated. This…

计算机视觉与模式识别 · 计算机科学 2020-06-11 Alex Bäuerle , Heiko Neumann , Timo Ropinski

Natural language processing researchers have identified limitations of evaluation methodology for generation tasks, with new questions raised about the validity of automatic metrics and of crowdworker judgments. Meanwhile, efforts to…

Typical user-friendly renderings of knowledge graphs are visualisations and natural language text. Within the latter HCI solution approach, data-driven natural language generation systems receive increased attention, but they are often…

计算与语言 · 计算机科学 2021-06-29 Zola Mahlaza , C. Maria Keet , Jarryd Dunn , Matthew Poulter

Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predictions with lower accuracy compared to finetuning a model…

计算与语言 · 计算机科学 2024-08-13 Chenyang Zhao , Xueying Jia , Vijay Viswanathan , Tongshuang Wu , Graham Neubig

This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to…

系统与控制 · 计算机科学 2020-02-19 Brian Gaudet , Richard Linares , Roberto Furfaro

Vision and language navigation is a task that requires an agent to navigate according to a natural language instruction. Recent methods predict sub-goals on constructed topology map at each step to enable long-term action planning. However,…

计算机视觉与模式识别 · 计算机科学 2024-07-17 Renjie Lu , Jingke Meng , Wei-Shi Zheng

We propose SW-Guidance, a training-free approach for image generation conditioned on the color distribution of a reference image. While it is possible to generate an image with fixed colors by first creating an image from a text prompt and…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Alexander Lobashev , Maria Larchenko , Dmitry Guskov

Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in…

Embodied AI aims to develop robots that can \textit{understand} and execute human language instructions, as well as communicate in natural languages. On this front, we study the task of generating highly detailed navigational instructions…

计算与语言 · 计算机科学 2024-09-10 Muraleekrishna Gopinathan , Martin Masek , Jumana Abu-Khalaf , David Suter

By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer…

机器学习 · 计算机科学 2023-03-13 Yongchao Zhou , Andrei Ioan Muresanu , Ziwen Han , Keiran Paster , Silviu Pitis , Harris Chan , Jimmy Ba

This paper presents a framework for training an agent to actively request help in object-goal navigation tasks, with feedback indicating the location of the target object in its field of view. To make the agent more robust in scenarios…

机器学习 · 计算机科学 2023-03-29 Jenny Zhang , Samson Yu , Jiafei Duan , Cheston Tan

Reward models are central to aligning LLMs with human preferences, but they are costly to train, requiring large-scale human-labeled preference data and powerful pretrained LLM backbones. Meanwhile, the increasing availability of…

计算与语言 · 计算机科学 2025-10-27 Yapei Chang , Yekyung Kim , Michael Krumdick , Amir Zadeh , Chuan Li , Chris Tanner , Mohit Iyyer

Traditionally, Machine Translation (MT) Evaluation has been treated as a regression problem -- producing an absolute translation-quality score. This approach has two limitations: i) the scores lack interpretability, and human annotators…

计算与语言 · 计算机科学 2024-01-31 Ibraheem Muhammad Moosa , Rui Zhang , Wenpeng Yin

Language models will inevitably err in situations with which they are unfamiliar. However, by effectively communicating uncertainties, they can still guide humans toward making sound decisions in those contexts. We demonstrate this idea by…

人工智能 · 计算机科学 2024-10-08 Lingjun Zhao , Khanh Nguyen , Hal Daumé

Large language models (LLMs) can act as evaluators, a role studied by methods like LLM-as-a-Judge and fine-tuned judging LLMs. In the field of education, LLMs have been studied as assistant tools for students and teachers. Our research…

计算与语言 · 计算机科学 2025-09-26 Valeria Ramirez-Garcia , David de-Fitero-Dominguez , Antonio Garcia-Cabot , Eva Garcia-Lopez

The effectiveness of recommendation algorithms is typically assessed with evaluation metrics such as root mean square error, F1, or click through rates, calculated over entire datasets. The best algorithm is typically chosen based on these…

信息检索 · 计算机科学 2018-12-03 Andrew Collins , Dominika Tkaczyk , Joeran Beel

Guidance techniques are simple yet effective for improving conditional generation in diffusion models. Albeit their empirical success, the practical implementation of guidance diverges significantly from its theoretical motivation. In this…

计算机视觉与模式识别 · 计算机科学 2025-05-26 Zhengqi Gao , Kaiwen Zha , Tianyuan Zhang , Zihui Xue , Duane S. Boning

In this paper, we introduce the map-language navigation task where an agent executes natural language instructions and moves to the target position based only on a given 3D semantic map. To tackle the task, we design the instruction-aware…

人工智能 · 计算机科学 2022-09-27 Zehao Wang , Mingxiao Li , Minye Wu , Marie-Francine Moens , Tinne Tuytelaars

Little inquiry has explicitly addressed the role of action spaces in language-guided visual navigation -- either in terms of its effect on navigation success or the efficiency with which a robotic agent could execute the resulting…

计算机视觉与模式识别 · 计算机科学 2021-10-06 Jacob Krantz , Aaron Gokaslan , Dhruv Batra , Stefan Lee , Oleksandr Maksymets