English
Related papers

Related papers: DisCo-Layout: Disentangling and Coordinating Seman…

200 papers

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

Computation and Language · Computer Science 2024-06-26 Zihan Liao , Hang Yu , Jianguo Li , Jun Wang , Wei Zhang

Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep…

Machine Learning · Computer Science 2026-03-25 Tianyu Xiong , Skylar Wurster , Han-Wei Shen

Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Martin JJ. Bucher , Iro Armeni

In this work, we propose a disentangled latent optimization-based method for parameterizing grouped deforming 3D objects into shape and deformation factors in an unsupervised manner. Our approach involves the joint optimization of a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Mostofa Rafid Uddin , Jana Armouti , Umong Sain , Md Asib Rahman , Xingjian Li , Min Xu

Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Tianjiao Yu , Xinzhuo Li , Muntasir Wahed , Jerry Xiong , Yifan Shen , Ying Shen , Ismini Lourentzou

Realistic 3D indoor scene synthesis is vital for embodied AI and digital content creation. It can be naturally divided into two subtasks: object generation and layout generation. While recent generative models have significantly advanced…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Xingjian Ran , Yixuan Li , Linning Xu , Mulin Yu , Bo Dai

Disentangled representation learning offers useful properties such as dimension reduction and interpretability, which are essential to modern deep learning approaches. Although deep learning techniques have been widely applied to…

Machine Learning · Computer Science 2022-04-11 Sichen Zhao , Wei Shao , Jeffrey Chan , Flora D. Salim

Visual Floorplan Localization (FLoc) struggles with severe structural aliasing caused by repetitive minimalist layouts. This occurs because physically distant poses share highly similar visual-geometric features, which degrades spatial…

Robotics · Computer Science 2026-05-11 Ping Zhong , Shiyong Meng , Bolei Chen , Tao Zou , Chaoxu Mu , Jianxin Wang

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Machine Learning · Computer Science 2026-04-13 Taojie Zhu , Dongyang Xu , Ding Zou , Sen Zhao , Qiaobo Hao , Zhiguo Yang , Yonghong He

Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Yingrui Wu , Youkang Kong , Mingyang Zhao , Weize Quan , Dong-Ming Yan , Yang Liu

Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Henry Zheng , Hao Shi , Qihang Peng , Yong Xien Chng , Rui Huang , Yepeng Weng , Zhongchao Shi , Gao Huang

While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising…

Computation and Language · Computer Science 2025-06-06 Jiayi He , Hehai Lin , Qingyun Wang , Yi Fung , Heng Ji

Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Han Lin , Xichen Pan , Zun Wang , Yue Zhang , Chu Wang , Jaemin Cho , Mohit Bansal

Semantic communication systems introduce a new paradigm in wireless communications, focusing on transmitting the intended meaning rather than ensuring strict bit-level accuracy. These systems often rely on Deep Neural Networks (DNNs) to…

Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuchuan Wu , Minghan Zhuo , Teng Fu , Mengyang Zhao , Bin Li , Xiangyang Xue

Addressing the limitations of text as a source of accurate layout representation in text-conditional diffusion models, many works incorporate additional signals to condition certain attributes within a generated image. Although successful,…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Jonghyun Lee , Hansam Cho , Youngjoon Yoo , Seoung Bum Kim , Yonghyun Jeong

Modern recommender systems struggle to effectively utilize the rich, yet high-dimensional and noisy, multi-modal features generated by Large Language Models (LLMs). Treating these features as static inputs decouples them from the core…

Information Retrieval · Computer Science 2025-12-02 Jiahao Tian , Zhenkai Wang

Robotic manipulation requires precise spatial understanding to interact with objects in the real world. Point-based methods suffer from sparse sampling, leading to the loss of fine-grained semantics. Image-based methods typically feed RGB…

Robotics · Computer Science 2026-01-14 Hao Shi , Bin Xie , Yingfei Liu , Yang Yue , Tiancai Wang , Haoqiang Fan , Xiangyu Zhang , Gao Huang

Recently, advances in differential volumetric rendering enabled significant breakthroughs in the photo-realistic and fine-detailed reconstruction of complex 3D scenes, which is key for many virtual reality applications. However, in the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Sagie Benaim , Frederik Warburg , Peter Ebert Christensen , Serge Belongie

Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Boqiang Zhang , Hongtao Xie , Zuan Gao , Yuxin Wang