Tootfinder

Dual-View Disentangled Multi-Intent Learning for Enhanced Collaborative Filtering
Shanfan Zhang, Yongyi Lin, Yuan Rao, Chenlong Zhang
https://arxiv.org/abs/2506.11538

Dual-View Disentangled Multi-Intent Learning for Enhanced Collaborative Filtering
Disentangling user intentions from implicit feedback has become a promising strategy to enhance recommendation accuracy and interpretability. Prior methods often model intentions independently and lack explicit supervision, thus failing to capture the joint semantics that drive user-item interactions. To address these limitations, we propose DMICF, a unified framework that explicitly models interaction-level intent alignment while leveraging structural signals from both user and item perspectiv…

Bipedal Balance Control with Whole-body Musculoskeletal Standing and Falling Simulations
Chengtian Ma, Yunyue Wei, Chenhui Zuo, Chen Zhang, Yanan Sui
https://arxiv.org/abs/2506.09383

Bipedal Balance Control with Whole-body Musculoskeletal Standing and Falling Simulations
Balance control is important for human and bipedal robotic systems. While dynamic balance during locomotion has received considerable attention, quantitative understanding of static balance and falling remains limited. This work presents a hierarchical control pipeline for simulating human balance via a comprehensive whole-body musculoskeletal system. We identified spatiotemporal dynamics of balancing during stable standing, revealed the impact of muscle injury on balancing behavior, and genera…

Coercive Field Reduction in Ultra-thin Al1-XScXN via Interfacial Engineering with a Scandium Electrode
Yinuo Zhang, Rajeev Kumar Rai, Giovanni Esteves, Yubo Wang, Deep M. Jariwala, Eric A. Stach, Roy H. Olsson III
https://arxiv.org/abs/2506.10169

Coercive Field Reduction in Ultra-thin Al1-XScXN via Interfacial Engineering with a Scandium Electrode
Aluminum scandium nitride (AlScN) ferroelectrics are promising for next-generation non-volatile memory applications due to their high remnant polarization as well as fast switching and scalability to nanometer thicknesses. As device dimensions shrink, the coercive field in ultra-thin ferroelectric films increases, which challenges low-voltage operation. We demonstrate that interfacial engineering through bottom electrode selection and strain management reduces this coercive field increase and i…

One-dimensional interacting Su-Schrieffer-Heeger model at quarter filling: An exact diagonalization study
Yan-Xiao Wang, Yin Zhong
https://arxiv.org/abs/2506.06148

One-dimensional interacting Su-Schrieffer-Heeger model at quarter filling: An exact diagonalization study
This study explores the ground-state phase diagram and topological properties of the spinless 1D Su-Schrieffer-Heeger (SSH) model with nearest-neighbor (NN) interactions at quarter filling. We analyze key physical quantities such as the local electron density distribution, correlation functions for bond-order-wave (BOW) and charge-density-wave (CDW) -- by integrating twisted boundary conditions with the Lanczos technique and employing high-precision numerical diagonalization methods, complement…

Near-Field Sensing Enabled Predictive Beamforming: Fundamentals, Framework, and Opportunities
Hao Jiang, Zhaolin Wang, Yue Liu, Hyundong Shin, Arumugam Nallanathan, Yuanwei Liu
https://arxiv.org/abs/2506.09225

Near-Field Sensing Enabled Predictive Beamforming: Fundamentals, Framework, and Opportunities
The article proposes a novel near-field predictive beamforming framework for high-mobility wireless networks. Specifically, due to the spherical waves and non-uniform Doppler frequencies brought by the near-field region, the new ability of full-dimensional location and velocity sensing is characterized. Building on this foundation, the near-field predictive beamforming framework is proposed to proactively design beamformers for mobility users following arbitrary trajectories. Compared to the co…

Precise control of the phase-transition temperature of VO2 from 70 to -35 {\deg}C for tunable optics
Jin-Woo Cho, Jonathan L. King, Martin Hafermann, Karla Paz, Shenwei Yin, Tanuj Kumar, Hongyan Mei, Joseph A. Andrade, Dung. T. Quach, Colin Hessel, Chenghao Wan, Carsten Ronning, David Woolf, Mikhail A. Kats
https://arxiv.org/abs…

Precise control of the phase-transition temperature of VO2 from 70 to -35 °C for tunable optics
We demonstrate the combination of metal doping and ion bombardment as a hybrid technique to precisely engineer the insulator-to-metal transition (IMT) properties of vanadium dioxide (VO$_2$) films. This approach enables (i) setting the phase-transition temperature ($T_c$) from $-35$ to $70$ °C, (ii) near-zero hysteresis in highly doped and irradiated films, and (iii) robust optical contrast across a broad range of doping and irradiation conditions, down to $T_c = -35$ °C. While previous work …

RationalVLA: A Rational Vision-Language-Action Model with Dual System
Wenxuan Song, Jiayi Chen, Wenxue Li, Xu He, Han Zhao, Pengxiang Ding Shiyan Su, Feilong Tang, Xuelian Cheng, Donglin Wang, Zongyuan Ge, Xinhu Zheng, Zhe Liu, Hesheng Wang, Yunhui Liu, Haoang Li
https://arxiv.org/abs/2506.10826

RationalVLA: A Rational Vision-Language-Action Model with Dual System
A fundamental requirement for real-world robotic deployment is the ability to understand and respond to natural language instructions. Existing language-conditioned manipulation tasks typically assume that instructions are perfectly aligned with the environment. This assumption limits robustness and generalization in realistic scenarios where instructions may be ambiguous, irrelevant, or infeasible. To address this problem, we introduce RAtional MAnipulation (RAMA), a new benchmark that challen…

Conversational Search: From Fundamentals to Frontiers in the LLM Era
Fengran Mo, Chuan Meng, Mohammad Aliannejadi, Jian-Yun Nie
https://arxiv.org/abs/2506.10635

Conversational Search: From Fundamentals to Frontiers in the LLM Era
Conversational search enables multi-turn interactions between users and systems to fulfill users' complex information needs. During this interaction, the system should understand the users' search intent within the conversational context and then return the relevant information through a flexible, dialogue-based interface. The recent powerful large language models (LLMs) with capacities of instruction following, content generation, and reasoning, attract significant attention and advancements, …

Principal Context-aware Diffusion Guided Data Augmentation for Fault Localization
Shihao Fu, Yan Lei
https://arxiv.org/abs/2505.24079 https://

Principal Context-aware Diffusion Guided Data Augmentation for Fault Localization
Test cases are indispensable for conducting effective fault localization (FL). However, test cases in practice are severely class imbalanced, i.e. the number of failing test cases (i.e. minority class) is much less than that of passing ones (i.e. majority class). The severe class imbalance between failing and passing test cases have hindered the FL effectiveness. To address this issue, we propose PCD-DAug: a Principal Context-aware Diffusion guided Data Augmentation approach that generate syn…

Topotactic oxidation of Ruddlesden-Popper nickelates reveals new structural family: oxygen-intercalated layered perovskites
Dan Ferenc Segedin, Jinkwon Kim, Harrison LaBollita, Nicole K. Taylor, Kyeong-Yoon Baek, Suk Hyun Sung, Ari B. Turkiewicz, Grace A. Pan, Abigail Y. Jiang, Maria Bambrick-Santoyo, Tobias Schwaigert, Casey K. Kim, Anirudh Tenneti, Alexander J. Grutter, Shin Muramoto, Alpha T. N'Diaye, Ismail El Baggari, Donald A. Walko, Hua Zhou, Charles M. Brooks, Antia S. Bota…

Topotactic oxidation of Ruddlesden-Popper nickelates reveals new structural family: oxygen-intercalated layered perovskites
Layered perovskites such as the Dion-Jacobson, Ruddlesden-Popper, and Aurivillius families host a wide range of correlated electron phenomena, from high-temperature superconductivity to multiferroicity. Here we report a new family of layered perovskites, realized through topotactic oxygen intercalation of La_{n+1}Ni_{n}O_{3n+1} (n=1-4) Ruddlesden-Popper nickelate thin films grown by ozone-assisted molecular-beam epitaxy. Post-growth ozone annealing induces a large c-axis expansion - 17.8% for L…