中文
相关论文

相关论文: BLOCK: An Open-Source Bi-Stage MLLM Character-to-S…

200 篇论文

Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combination of modalities, their number of parameters grows…

计算机视觉与模式识别 · 计算机科学 2019-02-13 Hedi Ben-younes , Rémi Cadene , Nicolas Thome , Matthieu Cord

Game UI implementation requires translating stylized mockups into interactive engine entities. However, current "Screenshot-to-Code" tools often struggle with the irregular geometries and deep visual hierarchies typical of game interfaces.…

人机交互 · 计算机科学 2026-04-22 Yunshu Bai , RuiHao Li , Hao Zhang , Chien Her Lim , Ming Yan , Mengtian Li

Block-based programming environments such as Scratch are increasingly popular in programming education, in particular for young learners. While the use of blocks helps prevent syntax errors, semantic bugs remain common and difficult to…

软件工程 · 计算机科学 2025-09-16 Yuan Si , Daming Li , Hanyuan Shi , Jialu Zhang

Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scenes efficiently by dynamically scanning and…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Yuchen Feng , Zhenyu Zhang , Naibin Gu , Yilong Chen , Peng Fu , Zheng Lin , Shuohuan Wang , Yu Sun , Hua Wu , Weiping Wang , Haifeng Wang

World modeling is a crucial task for enabling intelligent agents to effectively interact with humans and operate in dynamic environments. In this work, we propose MineWorld, a real-time interactive world model on Minecraft, an open-ended…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Junliang Guo , Yang Ye , Tianyu He , Haoyu Wu , Yushu Jiang , Tim Pearce , Jiang Bian

We present Blocks2World, a novel method for 3D scene rendering and editing that leverages a two-step process: convex decomposition of images and conditioned synthesis. Our technique begins by extracting 3D parallelepipeds from various…

计算机视觉与模式识别 · 计算机科学 2023-07-14 Vaibhav Vavilala , Seemandhar Jain , Rahul Vasanth , Anand Bhattad , David Forsyth

Large Language Models (LLMs) have emerged as a promising approach for binary decompilation. However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program's source-level structure with its…

软件工程 · 计算机科学 2025-09-29 Hanzhuo Tan , Weihao Li , Xiaolong Tian , Siyi Wang , Jiaming Liu , Jing Li , Yuqun Zhang

This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to…

机器学习 · 计算机科学 2021-06-21 Maren Awiszus , Frederik Schubert , Bodo Rosenhahn

Despite recent advances in deep generative modeling, skin lesion classification systems remain constrained by the limited availability of large, diverse, and well-annotated clinical datasets, resulting in class imbalance between benign and…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Stathis Galanakis , Alexandros Koliousis , Stefanos Zafeiriou

In this paper, we first present the character texture generation system \textit{Minecraft-ify}, specified to Minecraft video game toward in-game application. Ours can generate face-focused image for texture mapping tailored to 3D virtual…

计算机视觉与模式识别 · 计算机科学 2024-03-05 Bumsoo Kim , Sanghyun Byun , Yonghoon Jung , Wonseop Shin , Sareer UI Amin , Sanghyun Seo

We present Word2Minecraft, a system that leverages large language models to generate playable game levels in Minecraft based on structured stories. The system transforms narrative elements-such as protagonist goals, antagonist challenges,…

计算与语言 · 计算机科学 2025-03-24 Shuo Huang , Muhammad Umair Nasir , Steven James , Julian Togelius

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

计算与语言 · 计算机科学 2022-03-31 Wenliang Dai , Lu Hou , Lifeng Shang , Xin Jiang , Qun Liu , Pascale Fung

Automating the transformation of user interface (UI) designs into front-end code holds significant promise for accelerating software development and democratizing design workflows. While multimodal large language models (MLLMs) can…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Yilei Jiang , Yaozhi Zheng , Yuxuan Wan , Jiaming Han , Qunzhong Wang , Michael R. Lyu , Xiangyu Yue

Clothing virtual characters is a time-consuming and often manual process. Outfits can be composed of multiple garments, and each garment must be fitted to the unique shape of a character. Since characters can vary widely in size and shape,…

图形学 · 计算机科学 2025-04-25 Jonathan Leaf , David Sebastian Minor , Gilles Daviet , Nuttapong Chentanez , Greg Klar , Ed Quigley

Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs). To further validate the capabilities of…

人工智能 · 计算机科学 2024-06-14 Shiying Hu , Zengrong Huang , Chengpeng Hu , Jialin Liu

Recent advances in large language models (LLMs) enable compelling story generation, but connecting narrative text to playable visual environments remains an open challenge in procedural content generation (PCG). We present a lightweight…

图形学 · 计算机科学 2026-01-05 Yi-Chun Chen , Arnav Jhala

Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. The general idea is to first generate class-agnostic region proposals and then feed the cropped proposal regions to CLIP to utilize its…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Ziqin Zhou , Bowen Zhang , Yinjie Lei , Lingqiao Liu , Yifan Liu

Model parameter synchronization across GPUs introduces high overheads for data-parallel training at scale. Existing parameter synchronization protocols cannot effectively leverage available network resources in the face of ever increasing…

分布式、并行与集群计算 · 计算机科学 2019-10-14 Guanhua Wang , Shivaram Venkataraman , Amar Phanishayee , Jorgen Thelin , Nikhil Devanur , Ion Stoica

The main challenges hindering the adoption of deep learning-based systems in clinical settings are the scarcity of annotated data and the lack of interpretability and trust in these systems. Concept Bottleneck Models (CBMs) offer inherent…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Cristiano Patrício , Luís F. Teixeira , João C. Neves

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

计算机视觉与模式识别 · 计算机科学 2025-02-20 Hong-You Chen , Zhengfeng Lai , Haotian Zhang , Xinze Wang , Marcin Eichner , Keen You , Meng Cao , Bowen Zhang , Yinfei Yang , Zhe Gan
‹ 上一页 1 2 3 10 下一页 ›