Tootfinder

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
FaQiang Qian, WeiKun Zhang, Ziliang Wang, Kang An, Xuhui Zheng, Liangjian Wen, Mengya Gao, Yong Dai, Yichao Wu
https://arxiv.org/abs/2509.25148

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
Shaping powerful LLMs to be beneficial and safe is central to AI alignment. We argue that post-training alignment is fundamentally a unified Preference Learning problem, involving two modalities: demonstrated preferences (e.g., Supervised Fine-Tuning, SFT) and comparative preferences (e.g., Reinforcement Learning, RL).The standard sequential pipeline-SFT followed by RL-is flawed due to a critical distributional mismatch: SFT uses static expert data, but as the policy evolves, its generation dis…

Sim2Field: End-to-End Development of AI RANs for 6G
Russell Ford, Hao Chen, Pranav Madadi, Mandar Kulkarni, Xiaochuan Ma, Daoud Burghal, Guanbo Chen, Yeqing Hu, Chance Tarver, Panagiotis Skrimponis, Vitali Loseu, Yu Zhang, Yan Xin, Yang Li, Jianzhong Zhang, Shubham Khunteta, Yeswanth Guddeti Reddy, Ashok Kumar Reddy Chavva, Mahantesh Kothiwale, Davide Villa
htt…

Sim2Field: End-to-End Development of AI RANs for 6G
Following state-of-the-art research results, which showed the potential for significant performance gains by applying AI/ML techniques in the cellular Radio Access Network (RAN), the wireless industry is now broadly pushing for the adoption of AI in 5G and future 6G technology. Despite this enthusiasm, AI-based wireless systems still remain largely untested in the field. Common simulation methods for generating datasets for AI model training suffer from "reality gap" and, as a result, the perfo…

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Arthur Bizzi, Matias Grynberg, Vitor Matias, Daniel Perazzo, Jo\~ao Paulo Lima, Luiz Velho, Nuno Gon\c{c}alves, Jo\~ao Pereira, Guilherme Schardong, Tiago Novello
https://arxiv.org/abs/2510.09537

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit neural representations (INRs) for modeling such deformations, due to their meshlessness and differentiability; however, extracting coherent and accurate morphings from standard MLPs typically relies on costly regularizations, which often lead to unstable traini…

A CSP approach to Graph Sandwich Problems
Manuel Bodirsky, Santiago Guzm\'an-Pro
https://arxiv.org/abs/2510.09128 https://arxiv.org/pdf/2510.09128

A CSP approach to Graph Sandwich Problems
The \emph{Sandwich Problem} (SP) for a graph class $\calC$ is the following computational problem. The input is a pair of graphs $(V,E_1)$ and $(V,E_2)$ where $E_1\subseteq E_2$, and the task is to decide whether there is an edge set $E$ where $E_1\subseteq E \subseteq E_2$ such that the graph $(V,E)$ belongs to $\calC$. In this paper we show that many SPs correspond to the constraint satisfaction problem (CSP) of an infinite $2$-edge-coloured graph $H$. We then notice that several known comple…

Surface-Localized Magnetic Order in RuO2 Thin Films Revealed by Low-Energy Muon Probes
Akashdeep Akashdeep, Sachin Krishnia, Jae-Hyun Ha, Siyeon An, Maik Gaerner, Thomas Prokscha, Andreas Suter, Gianluca Janka, G\"unter Reiss, Timo Kuschel, Dong-Soo Han, Angelo Di Bernardo, Zaher Salman, Gerhard Jakob, Mathias Kl\"aui
https://arx…

Surface-Localized Magnetic Order in RuO2 Thin Films Revealed by Low-Energy Muon Probes
Ruthenium dioxide (RuO2) has recently emerged as a candidate altermagnet, yet its intrinsic magnetic ground state, particularly in thin films, remains debated. This study aims to clarify the nature and spatial extent of the magnetic order in RuO2 thin films grown under different conditions. Thin films of RuO2 with thicknesses of 30 nm and 33 nm are fabricated by pulsed laser deposition and sputtering onto TiO2(110) and Al2O3(1-102) substrates, respectively. Low-energy muon spin rotation/relaxat…

No Sign of a Magnetar Remnant Following the Kilonova-Producing Long GRB 211211A $\sim 1.7~$Years Later
Genevieve Schroeder (Cornell), Ben Margalit, Brian D. Metzger, Wen-fai Fong, Benjamin P. Gompertz, Kate D. Alexander, Edo Berger, Tanmoy Laskar, Gavin P. Lamb, Andrew Levan, Charles D. Kilpatrick, Jillian C. Rastinejad
https://arxiv.org/a…

No Sign of a Magnetar Remnant Following the Kilonova-Producing Long GRB 211211A $\sim 1.7~$Years Later
In addition to a $γ$-ray burst (GRB), the merger of two neutron stars may produce a temporarily or indefinitely stable neutron star remnant with a strong magnetic field (a "magnetar"). As this magnetar remnant spins down, it can deposit its rotational energy into the surrounding kilonova ejecta, producing synchrotron emission that peaks in the radio bands $\sim$months-years after the merger ("boosted kilonova"). The nearby ($z=0.0763$) long-duration GRB 211211A, which has an apparent kilonova …

Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Rongzhi Zhang, Liqin Ye, Yuzhao Heng, Xiang Chen, Tong Yu, Lingkai Kong, Sudheer Chava, Chao Zhang
https://arxiv.org/abs/2510.12121

Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse user expectations. Current LLM alignment methods, however, typically provide only directional or open-ended guidance, failing to reliably achieve exact attribute intensities. We address this limitation with three key designs: (1) reformulating precise attribute intensity control as a target-reaching problem, rather t…

WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask Generation
Runting Li, Shijie Lian, Hua Li, Yutong Li, Wenhui Wu, Sam Kwong
https://arxiv.org/abs/2510.12605

WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask Generation
Underwater Salient Object Detection (USOD) faces significant challenges, including underwater image quality degradation and domain gaps. Existing methods tend to ignore the physical principles of underwater imaging or simply treat degradation phenomena in underwater images as interference factors that must be eliminated, failing to fully exploit the valuable information they contain. We propose WaterFlow, a rectified flow-based framework for underwater salient object detection that innovatively…

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
Gangwei Xu, Haotong Lin, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Sida Peng, Xin Yang
https://arxiv.org/abs/2510.07316

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
This paper presents Pixel-Perfect Depth, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds from estimated depth maps. Current generative depth estimation models fine-tune Stable Diffusion and achieve impressive performance. However, they require a VAE to compress depth maps into latent space, which inevitably introduces \textit{flying pixels} at edges and details. Our model addresses this challenge by directly…

ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training
Leonard Bruns, Axel Barroso-Laguna, Tommaso Cavallari, \'Aron Monszpart, Sowmya Munukutla, Victor Adrian Prisacariu, Eric Brachmann
https://arxiv.org/abs/2510.11605

ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training
Scene coordinate regression (SCR) has established itself as a promising learning-based approach to visual relocalization. After mere minutes of scene-specific training, SCR models estimate camera poses of query images with high accuracy. Still, SCR methods fall short of the generalization capabilities of more classical feature-matching approaches. When imaging conditions of query images, such as lighting or viewpoint, are too different from the training views, SCR models fail. Failing to genera…