VOW employs VOPRF for privacy-preserving, verifiable watermark detection in short texts, enhancing security and trustworthiness.

Xiaokun Luan, Yihao Zhang, Pengcheng Su et al.

SQuadGen generates simple quad layouts using Chart Distance Fields, improving editability and artist-friendliness.

Youkang Kong, Yang Liu, Yue Dong et al.

SafeTune combines GNN and semantic analysis to filter poisoned RTL data, enhancing LLM fine-tuning security.

Mahshid Rezakhani, Nowfel Mashnoor, Kimia Azar et al.

Proposes a distributional alignment game framework for answer-level fine-tuning, utilizing GRPO for efficient training, achieving significant performance gains.

Mehryar Mohri, Jon Schneider, Yifan Wu

Proposed event-driven step-level cascade framework improves efficiency, achieving 58.2% success rate.

Jinbiao Wei, Kangqi Ni, Yilun Zhao et al.

The EVOREC framework combines model editing and FA-based constrained decoding for adaptive service recommendation, achieving 25.9% improvement in Recall@5.

Guodong Fan, Cuiyun Gao, Chun Yong Chong et al.

Proposed a disagreement-guided strategy routing method, improving mathematical reasoning accuracy by 3%-7%.

Zhimin Lin, Yixin Ji, Jinpeng Li et al.

PAINT integrates adaptive partial solution masking and sparse energy interpolation, boosting self-distilled reasoning performance.

Zhiquan Tan, Yinrong Hong

Introduces 'Embodied Multimedia' with a four-layer architecture to enhance task performance in embodied intelligence.

Yang Liu, Wei Zuo, Guanwei Zhao et al.

TimeMM employs time-conditioned spectral filtering with adaptive modal routing to model non-stationary user preferences in multimodal recommendation, outperforming SOTA.

Wei Yang, Rui Zhong, Zihan Lin et al.

HLTM framework improves LinkedIn Hiring Assistant's answer accuracy by over 5% and retrieval F1 by over 10%.

Zhentao Xu, Shangjin Zhang, Emir Poyraz et al.

Proposed uxWeb dataset and uxCUA model achieve 25% improvement in automated GUI usability assessment accuracy, enabling scalable, data-driven evaluation.

Alice Gao, Weixi Tong, Rishab Vempati et al.

SymphonyGen uses a 3D hierarchical framework for controllable orchestral generation, enhancing music quality.

Xuzheng He, Nan Nan, Zhilin Wang et al.

Proposes DynamicGUIBench and DynamicUI, leveraging video-based perception to address partial observability in high-dynamic GUI environments, achieving 20% performance gains.

Enqi Liu, Liyuan Pan, Zhi Gao et al.

PhyloSDF generates 3D skull morphology via residual flow matching, achieving a Pearson correlation of 0.993.

Kaikwan Lau, Gary P. T. Choi

Designed four value-sensitive AI systems to explore AI's impact on prayer, emphasizing user agency.

Soonho Kwon, Dong Whi Yoo, Shaowen Bardzell et al.

VibeToken is a resolution-agnostic 1D Transformer image tokenizer enabling efficient AR image synthesis at arbitrary resolutions.

Maitreya Patel, Jingtao Li, Weiming Zhuang et al.

Demonstrates nontrivial tree-level amplitudes in self-dual (higher-spin) theories within Kleinian and complex Minkowski spaces, advancing celestial holography and AdS/CFT duality frameworks.

Mattia Serrani, Evgeny Skvortsov

Sentiment and emotion classification of Indonesian e-commerce reviews using Multi-Task BiLSTM and AutoML, achieving high accuracy.

Hermawan Manurung, Ibrahim Al-Kahfi, Ahmad Rizqi et al.

Proposes HDET method to improve optimization quality and generalization of large models via automatic learning rate exploration.

Hailing Cheng, Tao Huang, Chen Zhu et al.