Tootfinder

CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs
Yangshu Yuan, Heng Chen, Xinyi Jiang, Christian Ng, Kexin Qiu
https://arxiv.org/abs/2507.22074

CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs
The rapid advancement of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) has enhanced our ability to process and generate human language and visual information. However, these models often struggle with complex, multi-step multi-modal instructions that require logical reasoning, dynamic feedback integration, and iterative self-correction. To address this, we propose CIMR: Contextualized Iterative Multimodal Reasoning, a novel framework that introduces a context-aware itera…

Thermodynamically driven tilt grain boundaries of monolayer crystals using catalytic liquid alloys
Min-Yeong Choi, Chang-Won Choi, Dong-Yeong Kim, Moon-Ho Jo, Yong-Sung Kim, Si-Young Choi, Cheol-Joo Kim
https://arxiv.org/abs/2507.22689

Thermodynamically driven tilt grain boundaries of monolayer crystals using catalytic liquid alloys
We report a method to precisely control the atomic defects at grain boundaries (GBs) of monolayer MoS2 by vapor-liquid-solid (VLS) growth using sodium molybdate liquid alloys, which serve as growth catalysts to guide the formations of the thermodynamically most stable GB structure. The Mo-rich chemical environment of the alloys results in Mo-polar 5|7 defects with a yield exceeding 95%. The photoluminescence (PL) intensity of VLS-grown polycrystalline MoS2 films markedly exceeds that of th…

IFEvalCode: Controlled Code Generation
Jian Yang, Wei Zhang, Shukai Liu, Linzheng Chai, Yingshui Tan, Jiaheng Liu, Ge Zhang, Wangchunshu Zhou, Guanglin Niu, Zhoujun Li, Binyuan Hui, Junyang Lin
https://arxiv.org/abs/2507.22462

IFEvalCode: Controlled Code Generation
Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed requirements such as coding style, line count, and structural constraints, beyond mere correctness. To address this, the paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs in controlled code ge…

I couldn’t sleep. My brain kept spinning: I brush my teeth at night. Then I don’t eat, I don’t drink, I just sleep. Nothing goes in my mouth. So why, when I wake up, do I brush my teeth again? I already did it! Nothing changed. It’s like someone decided mornings need a repeat, but my mouth is just as clean as before.
Sometimes I wonder, who decided this? Why do we all just do it, like it’s written in the sky or something? I like the feeling of brushing but not the taste of toothpaste, …

Trump says Epstein poached young women from Mar-a-Lago. That raises new questions about what he knew.
https://www.cnn.com/2025/07/29/politics/epstein-trump-falling-out-analysis?cid=ios_app

RecGPT Technical Report
Chao Yi, Dian Chen, Gaoyang Guo, Jiakai Tang, Jian Wu, Jing Yu, Sunhao Dai, Wen Chen, Wenjun Yang, Yuning Jiang, Zhujin Gao, Bo Zheng, Chi Li, Dimin Wang, Dixuan Wang, Fan Li, Fan Zhang, Haibin Chen, Haozhuang Liu, Jialin Zhu, Jiamang Wang, Jiawei Wu, Jin Cui, Ju Huang, Kai Zhang, Kan Liu, Lang Tian, Liang Rao, Longbin Li, Lulu Zhao, Mao Zhang, Na He, Peiyang Wang, Qiqi Huang, Tao Luo, Wenbo Su, Xiaoxiao He, Xin Tong, Xu Chen, Xunke Xi, Yang Li, Yaxuan Wu, Yeqiu…

RecGPT Technical Report
Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evo…

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
Siqi Luo, Haoran Yang, Yi Xin, Mingyang Yi, Guangyang Wu, Guangtao Zhai, Xiaohong Liu
https://arxiv.org/abs/2507.22872

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a subset of parameters; however, most existing approaches are task-agnostic, failing to fully exploit task-specific adaptations, which leads to suboptimal efficiency and performance. To address this limitation, we propose Task-Relevant Parameter and Token Select…

AeroLite-MDNet: Lightweight Multi-task Deviation Detection Network for UAV Landing
Haiping Yang, Huaxing Liu, Wei Wu, Zuohui Chen, Ning Wu
https://arxiv.org/abs/2506.21635

AeroLite-MDNet: Lightweight Multi-task Deviation Detection Network for UAV Landing
Unmanned aerial vehicles (UAVs) are increasingly employed in diverse applications such as land surveying, material transport, and environmental monitoring. Following missions like data collection or inspection, UAVs must land safely at docking stations for storage or recharging, which is an essential requirement for ensuring operational continuity. However, accurate landing remains challenging due to factors like GPS signal interference. To address this issue, we propose a deviation warning sys…

Wafer-scale Programmed Assembly of One-atom-thick Crystals
Seong-Jun Yang, Ju-Hyun Jung, Eunsook Lee, Edmund Han, Min-Yeong Choi, Daesung Jung, Shinyoung Choi, Jun-Ho Park, Dongseok Oh, Siwoo Noh, Ki-Jeong Kim, Pinshane Y. Huang, Chan-Cuk Hwang, Cheol-Joo Kim
https://arxiv.org/abs/2507.22677

Wafer-scale Programmed Assembly of One-atom-thick Crystals
Crystalline films offer various physical properties based on the modulation of their thicknesses and atomic structures. The layer-by-layer assembly of atomically thin crystals provides powerful means to arbitrarily design films at the atomic-level, which are unattainable with existing growth technologies. However, atomically-clean assembly of the materials with high scalability and reproducibility remains challenging. We report programmed crystal assembly (PCA) of graphene and monolayer hexagon…

Magnetization switching by current in an elemental ferromagnetic single layer
Yanyan Yang, Weiwei Lin
https://arxiv.org/abs/2507.22016 https://arxiv.org/pd…

Magnetization switching by current in an elemental ferromagnetic single layer
Current-induced magnetization switching, a fundamental phenomenon related to spin-transport of electrons, enables non-voltaic and fast information write, facilitating applications in low-power memory and logic devices. However, magnetization switching by spin-orbit torques is usually attributed to current flowing in the nonmagnetic metal layer of multilayers or in magnetic alloys with heavy elements. Here, we report perpendicular magnetization switching induced by current flowing in an elementa…