中文
相关论文

相关论文: CoCoG-2: Controllable generation of visual stimuli…

200 篇论文

Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Yize Zhang , Meiqi Chen , Sirui Chen , Bo Peng , Yanxi Zhang , Tianyu Li , Chaochao Lu

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities but often grapple with reliability challenges like hallucinations. While Knowledge Graphs (KGs) offer explicit grounding, existing paradigms of KG-augmented…

计算与语言 · 计算机科学 2026-04-15 Yuanxiang Liu , Songze Li , Xiaoke Guo , Zhaoyan Gong , Qifei Zhang , Huajun Chen , Wen Zhang

A growing number of approaches exist to generate explanations for image classification. However, few of these approaches are subjected to human-subject evaluations, partly because it is challenging to design controlled experiments with…

人工智能 · 计算机科学 2021-05-07 Martin Schuessler , Philipp Weiß , Leon Sixt

Current research on visual analytics systems largely follows the research paradigm of interactive system design in the field of Human-Computer Interaction (HCI), and includes key methodologies including design requirement development based…

人机交互 · 计算机科学 2026-03-02 Xiaolong Zhang

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Yusuf Dalva , Guocheng Gordon Qian , Maya Goldenberg , Tsai-Shien Chen , Kfir Aberman , Sergey Tulyakov , Pinar Yanardag , Kuan-Chieh Jackson Wang

In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Yi Zhang , Ke Yu , Siqi Wu , Zhihai He

Most previous studies integrate cognitive language processing signals (e.g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring…

计算与语言 · 计算机科学 2023-11-15 Yuqi Ren , Deyi Xiong

Generative models have achieved success in producing semantically plausible 2D images, but it remains challenging in 3D generation due to the absence of spatial geometry constraints. Typically, existing methods utilize geometric features as…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Haonan Wang , Hanyu Zhou , Haoyue Liu , Tao Gu , Luxin Yan

Systems with both language comprehension and generation capabilities can benefit from the tight connection between the two. This work studies coupling comprehension and generation with focus on continually learning from interaction with…

计算与语言 · 计算机科学 2024-08-29 Mustafa Omer Gul , Yoav Artzi

Beyond conveying semantic information, images also possess cognitive properties that elicit specific psychological responses from viewers, such as memory encoding or emotional reactions. Although modern text-to-image (T2I) models generate…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Shengqi Dang , Yi He , Jiaying Lei , Ziqing Qian , Nan Cao

Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e.,…

计算与语言 · 计算机科学 2022-01-25 Zhiting Hu , Li Erran Li

The past decades have witnessed the rapid development of image and video coding techniques in the era of big data. However, the signal fidelity-driven coding pipeline design limits the capability of the existing image/video coding…

计算机视觉与模式识别 · 计算机科学 2020-01-13 Yueyu Hu , Shuai Yang , Wenhan Yang , Ling-Yu Duan , Jiaying Liu

Recent advances in Generative Adversarial Networks GANs applications continue to attract the attention of researchers in different fields. In such a framework, two neural networks compete adversely to generate new visual contents…

人工智能 · 计算机科学 2023-11-27 Mohammad Lataifeh , Xavier A Carrascoa , Ashraf M Elnagara , Naveed Ahmeda , Imran Junejo

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

计算机视觉与模式识别 · 计算机科学 2022-04-26 Haiyang Huang , Zhi Chen , Cynthia Rudin

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider…

计算与语言 · 计算机科学 2020-06-03 Lifu Tu , Xiaoan Ding , Dong Yu , Kevin Gimpel

Developers of text generation models rely on automated evaluation metrics as a stand-in for slow and expensive manual evaluations. However, image captioning metrics have struggled to give accurate learned estimates of the semantic and…

计算与语言 · 计算机科学 2022-03-21 Mert İnan , Piyush Sharma , Baber Khalid , Radu Soricut , Matthew Stone , Malihe Alikhani

Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Chengqi Duan , Rongyao Fang , Yuqing Wang , Kun Wang , Linjiang Huang , Xingyu Zeng , Hongsheng Li , Xihui Liu

Open vocabulary image segmentation tackles the challenge of recognizing dynamically adjustable, predefined novel categories at inference time by leveraging vision-language alignment. However, existing paradigms typically perform…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Jianghang Lin , Yue Hu , Jiangtao Shen , Yunhang Shen , Liujuan Cao , Shengchuan Zhang , Rongrong Ji

This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and…

人工智能 · 计算机科学 2025-05-12 Jiayuan Mao , Joshua B. Tenenbaum , Jiajun Wu

A remarkable ability of human beings resides in compositional reasoning, i.e., the capacity to make "infinite use of finite means". However, current large vision-language foundation models (VLMs) fall short of such compositional abilities…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Junyan Li , Delin Chen , Yining Hong , Zhenfang Chen , Peihao Chen , Yikang Shen , Chuang Gan