Tootfinder

mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity
Elvis Nava, Victoriano Montesinos, Erik Bauer, Benedek Forrai, Jonas Pai, Stefan Weirich, Stephan-Daniel Gravert, Philipp Wand, Stephan Polinski, Benjamin F. Grewe, Robert K. Katzschmann
https://arxiv.org/abs/2506.11916…

mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity
We present a diffusion-based model recipe for real-world control of a highly dexterous humanoid robotic hand, designed for sample-efficient learning and smooth fine-motor action inference. Our system features a newly designed 16-DoF tendon-driven hand, equipped with wide angle wrist cameras and mounted on a Franka Emika Panda arm. We develop a versatile teleoperation pipeline and data collection protocol using both glove-based and VR interfaces, enabling high-quality data collection across dive…

Centralized Copy-Paste: Enhanced Data Augmentation Strategy for Wildland Fire Semantic Segmentation
Joon Tai Kim, Tianle Chen, Ziyu Dong, Nishanth Kunchala, Alexander Guller, Daniel Ospina Acero, Roger Williams, Mrinal Kumar
https://arxiv.org/abs/2507.06321

Centralized Copy-Paste: Enhanced Data Augmentation Strategy for Wildland Fire Semantic Segmentation
Collecting and annotating images for the purpose of training segmentation models is often cost prohibitive. In the domain of wildland fire science, this challenge is further compounded by the scarcity of reliable public datasets with labeled ground truth. This paper presents the Centralized Copy-Paste Data Augmentation (CCPDA) method, for the purpose of assisting with the training of deep-learning multiclass segmentation models, with special focus on improving segmentation outcomes for the fire…

crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023
Navodini Wijethilake, Reuben Dorent, Marina Ivory, Aaron Kujawa, Stefan Cornelissen, Patrick Langenhuizen, Mohamed Okasha, Anna Oviedova, Hexin Dong, Bogyeong Kang, Guillaume Sall\'e, Luyi Han, Ziyuan Zhao, Han Liu, Tao Yang, Shahad Hardan, Hussain Alasmawi, Santosh Sanjeev, Yuzhou Zhuang, Satoshi Kondo, Maria Baldeon Calisto, Shaikh Muh…

crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023
The cross-Modality Domain Adaptation (crossMoDA) challenge series, initiated in 2021 in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), focuses on unsupervised cross-modality segmentation, learning from contrast-enhanced T1 (ceT1) and transferring to T2 MRI. The task is an extreme example of domain shift chosen to serve as a meaningful and illustrative benchmark. From a clinical application perspective, it aims to automate Ve…

Last year, we bought a collection of 17 Georgia paintings by 19th- and 20th-century artists, many of whom are lesser known. Even the ones who are better known, like #NellChoateJones, aren't exactly _well_ known. We're excited to start studying these works and learning about the Georgia scenes many of them show.

Machine Learning for Evolutionary Graph Theory
Guoli Yang, Matteo Cavaliere, Mingtao Zhang, Giovanni Masala, Adam Miles, Mengzhu Wang
https://arxiv.org/abs/2507.08363

Machine Learning for Evolutionary Graph Theory
The stability of communities - whether biological, social, economic, technological or ecological depends on the balance between cooperation and cheating. While cooperation strengthens communities, selfish individuals, or "cheaters," exploit collective benefits without contributing. If cheaters become too prevalent, they can trigger the collapse of cooperation and of the community, often in an abrupt manner. A key challenge is determining whether the risk of such a collapse can be detected in ad…

Correcting for Position Bias in Learning to Rank: A Control Function Approach
Md Aminul Islam, Kathryn Vasilaky, Elena Zheleva
https://arxiv.org/abs/2506.06989

Correcting for Position Bias in Learning to Rank: A Control Function Approach
Implicit feedback data, such as user clicks, is commonly used in learning-to-rank (LTR) systems because it is easy to collect and it often reflects user preferences. However, this data is prone to various biases, and training an LTR system directly on biased data can result in suboptimal ranking performance. One of the most prominent and well-studied biases in implicit feedback data is position bias, which occurs because users are more likely to interact with higher-ranked documents regardless …

Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
Simon Matrenok, Skander Moalla, Caglar Gulcehre
https://arxiv.org/abs/2507.08068 https://arxiv.org/pdf/2507.08068 https://arxiv.org/html/2507.08068
arXiv:2507.08068v1 Announce Type: new
Abstract: Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage offline or off-policy data, such as DPO and REBEL, are limited to learning from preference pairs or relative signals. To bridge this gap, we introduce \emph{Quantile Reward Policy Optimization} (QRPO), which learns from pointwise absolute rewards while preserving the simplicity and offline applicability of DPO-like methods. QRPO uses quantile rewards to enable regression to the closed-form solution of the KL-regularized RL objective. This reward yields an analytically tractable partition function, removing the need for relative signals to cancel this term. Moreover, QRPO scales with increased compute to estimate quantile rewards, opening a new dimension for pre-computation scaling. Empirically, QRPO consistently achieves top performance on chat and coding evaluations -- reward model scores, AlpacaEval 2, and LeetCode -- compared to DPO, REBEL, and SimPO across diverse datasets and 8B-scale models. Finally, we find that training with robust rewards instead of converting them to preferences induces less length bias.
toXiv_bot_toot

Fast Bilateral Teleoperation and Imitation Learning Using Sensorless Force Control via Accurate Dynamics Model
Koki Yamane, Yunhan Li, Masashi Konosu, Koki Inami, Junji Oaki, Sho Sakaino, Toshiaki Tsuji
https://arxiv.org/abs/2507.06174

Fast Bilateral Teleoperation and Imitation Learning Using Sensorless Force Control via Accurate Dynamics Model
In recent years, the advancement of imitation learning has led to increased interest in teleoperating low-cost manipulators to collect demonstration data. However, most existing systems rely on unilateral control, which only transmits target position values. While this approach is easy to implement and suitable for slow, non-contact tasks, it struggles with fast or contact-rich operations due to the absence of force feedback. This work demonstrates that fast teleoperation with force feedback is…

Physics-Guided Dual Implicit Neural Representations for Source Separation
Yuan Ni, Zhantao Chen, Alexander N. Petsch, Edmund Xu, Cheng Peng, Alexander I. Kolesnikov, Sugata Chowdhury, Arun Bansil, Jana B. Thayer, Joshua J. Turner
https://arxiv.org/abs/2507.05249

Physics-Guided Dual Implicit Neural Representations for Source Separation
Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions--such as background and signal distortions--that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for app…

Learning to Explore: An In-Context Learning Approach for Pure Exploration
Alessio Russo, Ryan Welch, Aldo Pacchiano
https://arxiv.org/abs/2506.01876 https:…

Learning to Explore: An In-Context Learning Approach for Pure Exploration
In this work, we study the active sequential hypothesis testing problem, also known as pure exploration, where the goal is to actively control a data collection process to efficiently identify the correct hypothesis underlying a decision problem. While relevant across multiple domains, devising adaptive exploration strategies remains challenging, particularly due to difficulties in encoding appropriate inductive biases. Existing Reinforcement Learning (RL)-based methods often underperform when …