Multimedia Papers

What Would You Click? Personalized Video Thumbnail Generation with Preference-aware Highlight Retrieval Zhiyu He, Zecheng Zhao, Tong Chen, Zi Huang, Yiqun Liu, Min Zhang arxiv.org/abs/2607.12882 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙸𝚁]

GeoFovea-GS: Geometry-Aware Cross-Layer Gaussian Splatting for Wireless Aerial VR Zeyi Ren, Wencheng Yan, Jiawen Zhang, Jintao Yan, Sheng Zhou, Zhisheng Niu arxiv.org/abs/2607.12641 [𝚌𝚜.𝙼𝙼 𝚎𝚎𝚜𝚜.𝙸𝚅]

RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning Ruoxuan Zhang, Qiyun Zheng, Siyu Wu, Ling Zou, Hongxia Xie, Zhiyu Zhou, Jian-Yu Jiang-Lin, Zihan Li, Zhengguang Wang, Bin Wen, Ling Lo, Jianlong Fu, … arxiv.org/abs/2607.11044 [𝚌𝚜.𝙼𝙼]

Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space Thanh V. T. Tran, Ngoc-Son Nguyen, Luong Tran, Long-Khanh Pham, Paarth Neekhara, Shezheen Hussain, Van Nguyen arxiv.org/abs/2607.06405 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝚂𝙳] 💬Accepted to ECCV 2026

Multimodal Video-to-Music Recommendation via Semantic Retrieval and Temporal Reranking Seungheon Doh, Minhee Lee, Sangmoon Lee, Ben Sangbae Chon, … arxiv.org/abs/2607.05971 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝚂𝙳] 💬Accepted for publication at The Machine Learning for Audio workshop at ICML 2026

SleepBand: Single-Source Domain Generalization for Sleep Staging via Physiologically Structured Spectral Modeling Zhi Lu, Yang Hu, Yan Chen arxiv.org/abs/2607.04851 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙻𝙶]

Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption Nidhal Jegham, Boris Gamazaychikov, Sasha Luccioni arxiv.org/abs/2607.04553 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙰𝙸]

CellPrior-Net: Prior-Guided Nuclei Detection and Classification for H&E Whole-Slide Images Falah Jabar, Pasquale Lombardi, Aria Torkpour, Masoud Tafavvoghi, Per Niklas Benzler Waaler, … arxiv.org/abs/2607.00802 [𝚌𝚜.𝙼𝙼] 💬Submitted to Intelligence-Based Medicine Journal

Vertigo Vertigo: Reconstructing a Cinematic Ideal through its Predictive AI Double Adam Cole, Mick Grierson arxiv.org/abs/2607.00047 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙶𝚁]

Evidence Triangulation for Multimodal Fact-Checking in the Wild Stefanos-Iordanis Papadopoulos, Zacharias Chrysidis, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis arxiv.org/abs/2606.31367 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙲𝚅]

A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR Lin Chen, Jingping Fang, Hairui Liu, Chenyang Xu, Xiaorui Li, Weidong Cai, Xiaoming Chen arxiv.org/abs/2606.31225 [𝚌𝚜.𝙼𝙼] 💬Accepted to ECCV 2026

From Design Principles to Prototype: A Game for Students with ADHD and Learning Disabilities Transitioning to Post-Secondary Education Avery Keuben, Talaal Irtija, Joseph Tandyo, Stefanie Ng, Amy Wiebe, Samuel Gaudet, … arxiv.org/abs/2606.29482 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙲𝚈]

A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks Ishani Mondal, Aparna Garimella, Ananya Sai, Pannaga Shivaswamy, Jordan Boyd-Graber arxiv.org/abs/2606.28531 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙲𝙻]

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents Yiming Sun, Chen Chen, Zifan Zhou, Mi Zhang arxiv.org/abs/2606.27944 [𝚌𝚜.𝙼𝙼]

An Evaluation of Decentralized Group Formation Techniques for Flying Light Specks Hamed Alimohammadzadeh, Heather Culbertson, Shahram Ghandeharizadeh arxiv.org/abs/2606.26645 [𝚌𝚜.𝙼𝙼]

UI-LIC: A Unified Framework for Evaluating Learned Image Compression Models Nicholas J. Nolen, Luc Trudeau, Andrew C. Freeman arxiv.org/abs/2606.23545 [𝚌𝚜.𝙼𝙼]

Composition: Building Community with Arts, Math, and Code (Experience Report) Isidore Mohr, Claire Wang arxiv.org/abs/2606.23526 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝚂𝙴]

OlfactProfile: Profile-Conditioned Odor Prediction from Audiovisual Content Zhengyu Lou, Bosheng Qin, Yanan Wang, Duanduan Yin, Wentao Ye, Yu Xin arxiv.org/abs/2606.17921 [𝚌𝚜.𝙼𝙼]

DiffPC: Diffusion-Based Projector Photometric Compensation Yuxi Wang, Haibin Ling, Bingyao Huang arxiv.org/abs/2606.17521 [𝚌𝚜.𝙼𝙼]

Effective and Low-cost Lane-based Map Localization for Vehicle-Centric Route Generation Hong-Shiang Lin, Jung-Hsin Chen, Yu-Luen Tzeng, Wei-Hao Chen, Yi-Chen Lee, Li-Jhe Chen, Peng-Yuan Chen arxiv.org/abs/2606.16101 [𝚌𝚜.𝙼𝙼 𝚌𝚜.𝙲𝚅]