Tootfinder

Evaluating Phylogenetic Comparative Methods under Reticulate Evolutionary Scenarios
Lydia Morley, Emma Lehmberg, Sungsik Kong
https://arxiv.org/abs/2603.25986 https://arxiv.org/pdf/2603.25986 https://arxiv.org/html/2603.25986
arXiv:2603.25986v1 Announce Type: new
Abstract: Phylogenetic comparative methods (PCMs) are widely used to study trait evolution. However, many evolutionary histories involve reticulate evolutionary scenarios, such as hybridization, that violate core assumptions of these methods. In this study, we evaluate how such violations affect the performance of PCMs. In particular, we focus on the ancestral character estimation, evolutionary rate estimation, and model selection. We simulate continuous trait evolution on various phylogenetic network topologies and assess the performance of PCMs that assume a bifurcating tree (i.e., major tree of the network) as the underlying model of evolution. We found that the performance of the tested PCMs was suboptimal. Using random forest, generalized linear models, and model-based clustering, we identified key factors contributing to these inaccuracies. Our results show that frequent and/or recent hybridization accompanied by one ore more transgressive events and rapidly evolving traits (i.e., high evolutionary rate) lead to significant estimation error, especially with respect to rate estimation and model choice. These factors substantially shift trait values away from tree-based model expectations, leading to overall increased error in parameter estimates. Our study demonstrates cases in which PCMs that rely on trees are likely to misinterpret biological histories and offers recommendations for researchers studying systems with complex evolutionary histories.
toXiv_bot_toot

Autotuning T-PaiNN: Enabling Data-Efficient GNN Interatomic Potential Development via Classical-to-Quantum Transfer Learning
Vivienne Pelletier, Vedant Bhat, Daniel J. Rivera, Steven A. Wilson, Christopher L. Muhich
https://arxiv.org/abs/2603.24752 https://arxiv.org/pdf/2603.24752 https://arxiv.org/html/2603.24752
arXiv:2603.24752v1 Announce Type: new
Abstract: Machine-learned interatomic potentials (MLIPs), particularly graph neural network (GNN)-based models, offer a promising route to achieving near-density functional theory (DFT) accuracy at significantly reduced computational cost. However, their practical deployment is often limited by the large volumes of expensive quantum mechanical training data required. In this work, we introduce a transfer learning framework, Transfer-PaiNN (T-PaiNN), that substantially improves the data efficiency of GNN-MLIPs by leveraging inexpensive classical force field data. The approach consists of pretraining a PaiNN MLIP architecture on large-scale datasets generated from classical molecular simulations, followed by fine-tuning (dubbed autotuning) using a comparatively small DFT dataset. We demonstrate the effectiveness of autotuning T-PaiNN on both gas-phase molecular systems (QM9 dataset) and condensed-phase liquid water. Across all cases, T-PaiNN significantly outperforms models trained solely on DFT data, achieving order-of-magnitude reductions in mean absolute error while accelerating training convergence. For example, using the QM9 data set, error reductions of up to 25 times are observed in low-data regimes, while liquid water simulations show improved predictions of energies, forces, and experimentally relevant properties such as density and diffusion. These gains arise from the model's ability to learn general features of the potential energy surface from extensive classical sampling, which are subsequently refined to quantum accuracy. Overall, this work establishes transfer learning from classical force fields as a practical and computationally efficient strategy for developing high-accuracy, data-efficient GNN interatomic potentials, enabling broader application of MLIPs to complex chemical systems.
toXiv_bot_toot

Nice!
Urban Science Beyond Samples: Up-to-Date Street Network Models and Indicators for Every Urban Area in the World
https://arxiv.org/abs/2605.00108

Urban Science Beyond Samples: Up-to-Date Street Network Models and Indicators for Every Urban Area in the World
Urban planners need up-to-date, global, and consistent street network models and indicators to measure resilience and performance, model accessibility, and target local quality-of-life interventions. This article presents up-to-date street network models and indicators for every urban area in the world. It uses 2025 urban area boundaries from the Global Human Settlement Layer, allowing users to join these data to hundreds of other urban attributes. Its workflow ingests 180 million OpenStreetMap…

Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates
Toshifumi Mori, Kei-ichi Okazaki, Kang Kim, Nobuyuki Matubayasi
https://arxiv.org/abs/2603.25237 https://arxiv.org/pdf/2603.25237 https://arxiv.org/html/2603.25237
arXiv:2603.25237v1 Announce Type: new
Abstract: In complex molecular systems, the reaction coordinate (RC) that characterizes transition pathways is essential to understand underlying molecular mechanisms. This review surveys a framework for identifying the RC by applying deep learning to the committor, which provides the most reliable measure of the progress along a transition path. The inputs to the neural network are collective variables (CVs) expressed as functions of atomic coordinates of the system, and the corresponding RC is predicted as the output by training the network on the committor as the learning target. Because deep learning models typically operate in a black-box manner, it is difficult to determine which input variables govern the predictions. The incorporation of eXplainable Artificial Intelligence (XAI) techniques enables quantitative assessment of the contributions of individual input variables to the predictions. This approach allows the identification of CVs that play dominant roles and demonstrates that the committor distribution on the surface using important CVs is separated by well-defined boundaries. The framework provides an explainable deep learning strategy for assigning a molecular mechanism from the RC and is applicable to a wide range of complex molecular systems.
toXiv_bot_toot

Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
Bong Gyun Shin, Chan Sik Lee, Hyesun Suh
https://arxiv.org/abs/2605.21507 https://arxiv.org/pdf/2605.21507 https://arxiv.org/html/2605.21507
arXiv:2605.21507v1 Announce Type: new
Abstract: Atmospheric visibility is a critical variable for transportation safety and air quality management, however, accurate prediction remains challenging due to the complex interactions between meteorological conditions and air pollutants, as well as the rarity of low-visibility events. This study introduces a machine learning framework to nowcast visibility in six major South Korean cities. To handle the imbalance in the 2018-2020 training data, we applied the Synthetic Minority Over-sampling Technique with Nominal and Continuous (SMOTENC) and Conditional Tabular Generative Adversarial Network (CTGAN). An ensemble approach combining machine learning and deep learning models was then used and evaluated on a 2021 test dataset. The results revealed a marked decline in predictive performance in the test set compared to the cross-validation phase. This degradation was attributed to a distributional shift between training and testing periods, which was quantitatively confirmed by measuring the Wasserstein distance of the most influential feature identified by SHAP analysis. In general, this study presents a methodology that aims to simultaneously address the dual challenges of data imbalance and temporal distributional shifts, and emphasizes the necessity of accounting for evolving external environmental factors when implementing nowcasting models on time-series data.
toXiv_bot_toot

Replaced article(s) found for physics.flu-dyn. https://arxiv.org/list/physics.flu-dyn/new
[1/1]:
- On the stability of an in-line formation of hydrodynamically interacting flapping plates
Monika Nitsche, Anand U. Oza, Michael Siegel
https://arxiv.org/abs/2410.04626 https://mastoxiv.page/@arXiv_physicsfludyn_bot/113270998236203403
- Side-wall wetting and linear stability of falling films
Hammam Mohamed, J\"orn Sesterhenn
https://arxiv.org/abs/2504.13300 https://mastoxiv.page/@arXiv_physicsfludyn_bot/114374794050144417
- An Omni-Temporal Theory for Hydrodynamic Dispersion and Reaction in Porous Media
Md Abdul Hamid, Kyle C. Smith
https://arxiv.org/abs/2505.06063 https://mastoxiv.page/@arXiv_physicsfludyn_bot/114493702701690116
- Confirming Wave Turbulence Predictions in Rotating Turbulence
Omri Shaltiel, Omri Gat, Eran Sharon
https://arxiv.org/abs/2510.25446 https://mastoxiv.page/@arXiv_physicsfludyn_bot/115462467154250733
- Using Physics Informed Neural Network (PINN) and Neural Network (NN) to Improve a $k-\omega$ Turb...
Lars Davidson
https://arxiv.org/abs/2511.12493 https://mastoxiv.page/@arXiv_physicsfludyn_bot/115570134553603649
- Oscillating Detonation of Liquid Ammonia
Wenhao Wang, Zongmin Hu, Peng Zhang
https://arxiv.org/abs/2511.14167 https://mastoxiv.page/@arXiv_physicsfludyn_bot/115575358542454196
- On the Poisson-Source Basis of Logarithmic Wall-Pressure-Variance Growth
Jonathan M. O. Massey, Joseph C. Klewicki, Beverley J. McKeon
https://arxiv.org/abs/2511.16776 https://mastoxiv.page/@arXiv_physicsfludyn_bot/115603689363840109
- Convolutional causal learning for aerodynamic flows
Ryo Koshikawa, Ryo Araki, Qiong Liu, Kai Fukami
https://arxiv.org/abs/2601.19104 https://mastoxiv.page/@arXiv_physicsfludyn_bot/115971839485449464
- Assessing engineering wake models against operational data: insights from the Lillgrund wind farm...
Siguenza-Alvarado, Harrison, Mohammadi, Vishwakarma, Bossanyi, Landberg, Bastankhah
https://arxiv.org/abs/2601.21035 https://mastoxiv.page/@arXiv_physicsfludyn_bot/115983015393462612
- Neural equilibria for long-term prediction of nonlinear conservation laws
Benitez, Hegazy, Guo, Dokmani\'c, Mahoney, de Hoop
https://arxiv.org/abs/2501.06933 https://mastoxiv.page/@arXiv_csLG_bot/113825452743912532
- Self-similar rupture of thin films of power-law fluid
Michael C Dallaston, Steven A Kedda, Scott W McCue
https://arxiv.org/abs/2509.05383 https://mastoxiv.page/@arXiv_condmatsoft_bot/115173629129170202
- Instability and self-propulsion of flexible autophoretic filaments
Ursy Makanga, Akhil Varma, Panayiota Katsamba
https://arxiv.org/abs/2509.10153 https://mastoxiv.page/@arXiv_condmatsoft_bot/115207443699020835
- Analytical response functions for a compressible thin fluid layer with odd viscosity
Abdallah Daddi-Moussa-Ider, Yuto Hosaka, Shigeyuki Komura
https://arxiv.org/abs/2602.18136 https://mastoxiv.page/@arXiv_condmatsoft_bot/116119064615788127
toXiv_bot_toot

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/5]:
- Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic D...
Lakshan Cooray, Deshan Sumanathilaka, Pattigadapa Venkatesh Raju
https://arxiv.org/abs/2602.00665 https://mastoxiv.page/@arXiv_csCL_bot/116006686092324902
- SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
Dai, Gao, Zhang, Wang, Luo, Wang, Wang, Wu, Wang
https://arxiv.org/abs/2602.03548
- OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering
Yifan Zhu, Xinyu Mu, Tao Feng, Zhonghong Ou, Yuning Gong, Haoran Luo
https://arxiv.org/abs/2602.03707
- GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek
Zhang, Konomi, Xypolopoulos, Divriotis, Skianis, Nikolentzos, Stamou, Shang, Vazirgiannis
https://arxiv.org/abs/2602.05150
- Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems
Zhangqi Duan, Arnav Kankaria, Dhruv Kartik, Andrew Lan
https://arxiv.org/abs/2602.17542 https://mastoxiv.page/@arXiv_csCL_bot/116102514058414603
- MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models
Kejing Xia, Mingzhe Li, Lixuan Wei, Zhenbang Du, Xiangchi Yuan, Dachuan Shi, Qirui Jin, Wenke Lee
https://arxiv.org/abs/2603.01331 https://mastoxiv.page/@arXiv_csCL_bot/116165314672421581
- A Browser-based Open Source Assistant for Multimodal Content Verification
Milner, Foster, Karmakharm, Razuvayevskaya, Roberts, Porcellini, Teyssou, Bontcheva
https://arxiv.org/abs/2603.02842 https://mastoxiv.page/@arXiv_csCL_bot/116170368271004704
- Nw\=ach\=a Mun\=a: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
Sharma, Shrestha, Poudel, Tiwari, Shrestha, Ghimire, Bal
https://arxiv.org/abs/2603.07554 https://mastoxiv.page/@arXiv_csCL_bot/116204797995674104
- Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
Mingyang Song, Mao Zheng
https://arxiv.org/abs/2603.09938 https://mastoxiv.page/@arXiv_csCL_bot/116210189810004206
- AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Ag...
Zekun Wu, Adriano Koshiyama, Sahan Bulathwela, Maria Perez-Ortiz
https://arxiv.org/abs/2603.12564 https://mastoxiv.page/@arXiv_csCL_bot/116237800898328349
- GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages
Gyamfi, Azunre, Moore, Budu, Asare, Owusu, Asiamah
https://arxiv.org/abs/2603.13793 https://mastoxiv.page/@arXiv_csCL_bot/116243544688031749
- sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Not...
Ibrahim Ebrar Yurt, Fabian Karl, Tejaswi Choppa, Florian Matthes
https://arxiv.org/abs/2603.13962 https://mastoxiv.page/@arXiv_csCL_bot/116243646346563497
- ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation
Yuzhe Shang, Pengzhi Gao, Yazheng Yang, Jiayao Ma, Wei Liu, Jian Luan, Jinsong Su
https://arxiv.org/abs/2603.14903 https://mastoxiv.page/@arXiv_csCL_bot/116243711232778054
- BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Ba...
Tanvir Ahmed Sijan, S. M Golam Rifat, Pankaj Chowdhury Partha, Md. Tanjeed Islam, Md. Musfique Anwar
https://arxiv.org/abs/2603.15949 https://mastoxiv.page/@arXiv_csCL_bot/116249122231759766
- EngGPT2: Sovereign, Efficient and Open Intelligence
G. Ciarfaglia, et al.
https://arxiv.org/abs/2603.16430 https://mastoxiv.page/@arXiv_csCL_bot/116249228411487178
- HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning
Bartosz Trojan, Filip G\k{e}bala
https://arxiv.org/abs/2603.19278 https://mastoxiv.page/@arXiv_csCL_bot/116277612915482857
- Automatic Analysis of Collaboration Through Human Conversational Data Resources: A Review
Yi Yu, Maria Boritchev, Chlo\'e Clavel
https://arxiv.org/abs/2603.19292 https://mastoxiv.page/@arXiv_csCL_bot/116277620779254916
- Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Langu...
Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg, Tuhin Chakrabarty
https://arxiv.org/abs/2603.20957 https://mastoxiv.page/@arXiv_csCL_bot/116283538317671552
- KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning
Shuai Wang, Yinan Yu
https://arxiv.org/abs/2603.21440 https://mastoxiv.page/@arXiv_csCL_bot/116283595007808076
toXiv_bot_toot

Nice!
Urban Science Beyond Samples: Up-to-Date Street Network Models and Indicators for Every Urban Area in the World
https://arxiv.org/abs/2605.00108