Tootfinder

LTA-thinker: Latent Thought-Augmented Training Framework for Large Language Models on Complex Reasoning
Jiaqi Wang, Binquan Ji, Haibo Luo, Yiyang Qi, Ruiting Li, Huiyan Wang, Yuantao Han, Cangyi Yang, jiaxu Zhang, Feiliang Ren
https://arxiv.org/abs/2509.12875

LTA-thinker: Latent Thought-Augmented Training Framework for Large Language Models on Complex Reasoning
Complex Reasoning in Large Language Models can be dynamically optimized using Test-Time Scaling (TTS) to mitigate Overthinking. Methods such as Coconut, SoftCoT and its variant are effective in continuous latent space inference, the core bottleneck still lies in the efficient generation and utilization of high-quality Latent Thought. Drawing from the theory of SoftCoT++ that a larger variance in the generated Latent Thought distribution more closely approximates the golden truth distribution, w…

Cryogenic magnetization dynamics in tensile-strained ultrathin yttrium iron garnets with tunable magnetic anisotropy
Jihyung Kim, Dongchang Kim, Seung-Gi Lee, Yung-Cheng Li, Jae-Chun Jeon, Jiho Yoon, Sachio Komori, Ryotaro Arkakwa, Tomoyasu Taniyama, Stuart S. P. Parkin, Kun-Rok Jeon
https://arxiv.org/abs/2507.12776

Cryogenic magnetization dynamics in tensile-strained ultrathin yttrium iron garnets with tunable magnetic anisotropy
We report a significant reduction of low-temperature damping losses in tensile-strained, ultrathin Y3Fe5O12 (YIG) films grown by pulsed laser deposition, exhibiting ultralow damping constants and tunable magnetic anisotropy. Comparative broadband FMR measurements show that tensile-strained YIG films on Gd3Sc2Ga3O12 (GSGG) retain low damping even at nanometer thicknesses and cryogenic temperatures, outperforming relaxed films on Gd3Ga5O12. Based on static magnetometry measurements and microstruc…

ConvergeWriter: Data-Driven Bottom-Up Article Construction
Binquan Ji, Jiaqi Wang, Ruiting Li, Xingchen Han, Yiyang Qi, Shichao Wang, Yifei Lu, Yuantao Han, Feiliang Ren
https://arxiv.org/abs/2509.12811

ConvergeWriter: Data-Driven Bottom-Up Article Construction
Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive external knowledge bases remains a significant challenge. Existing "top-down" methods, which first generate a hypothesis or outline and then retrieve evidence, often suffer from a disconnect between the model's plan and the available knowledge, leading to content fragmentation and factual inaccuracies. To address these limitations, we propose a novel "b…

Thyme: Think Beyond Images
Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, Wei Chen, Xiao Hu, Bin Wen, Kaiyu Jiang, Changyi Liu, Tianke Zhang, Haonan Fan, Kaibing Chen, Jiankang Chen, Haojie Ding, Kaiyu Tang, Zhang Zhang, Liang Wang, Fan Yang, Tingting Gao, Guorui Zhou
https://arxiv.org/abs/2508.11630

Thyme: Think Beyond Images
Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make…

MultiPark: Multimodal Parking Transformer with Next-Segment Prediction
Han Zheng, Zikang Zhou, Guli Zhang, Zhepei Wang, Kaixuan Wang, Peiliang Li, Shaojie Shen, Ming Yang, Tong Qin
https://arxiv.org/abs/2508.11537

MultiPark: Multimodal Parking Transformer with Next-Segment Prediction
Parking accurately and safely in highly constrained spaces remains a critical challenge. Unlike structured driving environments, parking requires executing complex maneuvers such as frequent gear shifts and steering saturation. Recent attempts to employ imitation learning (IL) for parking have achieved promising results. However, existing works ignore the multimodal nature of parking behavior in lane-free open space, failing to derive multiple plausible solutions under the same situation. Notab…

A Survey of Reinforcement Learning for Software Engineering
Dong Wang, Hanmo You, Lingwei Zhu, Kaiwei Lin, Zheng Chen, Chen Yang, Junji Yu, Zan Wang, Junjie Chen
https://arxiv.org/abs/2507.12483

A Survey of Reinforcement Learning for Software Engineering
Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent systems. In the field of software engineering (SE), the increasing complexity of systems and the ris…

Transversal packings in families of percolated hypergraphs
Jie Han, Jie Hu, Shunan Wei, Donglei Yang
https://arxiv.org/abs/2507.12740 https://

Transversal packings in families of percolated hypergraphs
Let $F$ be a strictly $1$-balanced $k$-graph on $s$ vertices with $t$ edges and $δ_{F,d}^T$ be the infimum of $δ>0$ such that for every $α>0$ and sufficiently large $n\in \mathbb{N}$, every $k$-graph system $\mathbf H=\{H_{1}, H_{2}, \dots ,H_{tn}\}$ on the same $sn$ vertices with $δ_d(H_i)\ge (δ+α)\binom{sn-d}{k-d}$, $i\in [tn]$ contains a transversal $F$-factor, that is, an $F$-factor consisting of exactly one edge from each $H_i$. In this paper we prove the following result. Let $\math…

On the logarithmic correction of transition fronts in shifting environments
King-Yeung Lam, Chang-Hong Wu
https://arxiv.org/abs/2509.11521 https://arxiv.or…

On the logarithmic correction of transition fronts in shifting environments
In this paper, we investigate the location of the spreading front and convergence to traveling wave profile of solutions to the Fisher-KPP equation in the following two cases: (i) in unbounded domains with an expanding boundary; (ii) on the real line where the environment function has a shifting jump discontinuity. Our approach is based on extending ideas in Bramson's seminal work in 1983, and applying gluing technique to construct super/subsolutions.

Enhanced anomalous Hall conductivity via Ga doping in Mn\textsubscript{3}Sn and Mn\textsubscript{3}Ge
Chenyue Wen, Danrong Xiong, Chengyi Yang, Dapeng Zhu, Weisheng Zhao
https://arxiv.org/abs/2508.11321

Enhanced anomalous Hall conductivity via Ga doping in Mn\textsubscript{3}Sn and Mn\textsubscript{3}Ge
This study examines the anomalous Hall effect (AHE) in the Heusler series \ce{Mn3Z} (Z=Ga, Ge, Sn), with a particular emphasis on the manipulation of non-collinear antiferromagnetic structures to enhance AHE. By employing density-functional theory and first-principles calculations, we demonstrate that the anomalous Hall conductivity is markedly responsive to electron filling. By strategically doping Ga into \ce{Mn3Sn} and \ce{Mn3Ge} in order to modulate the electron density, a significant incre…

Geometric Analysis of Magnetic Labyrinthine Stripe Evolution via U-Net Segmentation
Vin\'icius Yu Okubo, Kotaro Shimizu, B. S. Shivaran, Gia-Wei Chern, Hae Yong Kim
https://arxiv.org/abs/2509.11485

Geometric Analysis of Magnetic Labyrinthine Stripe Evolution via U-Net Segmentation
Labyrinthine stripe patterns are common in many physical systems, yet their lack of long-range order makes quantitative characterization challenging. We investigate the evolution of such patterns in bismuth-doped yttrium iron garnet (Bi:YIG) films subjected to a magnetic field annealing protocol. A U-Net deep learning model, trained with synthetic degradations including additive white Gaussian and Simplex noise, enables robust segmentation of experimental magneto-optical images despite noise an…