Tootfinder

Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
Masoumeh Sharafi, Soufiane Belharbi, Houssem Ben Salem, Ali Etemad, Alessandro Lameiras Koerich, Marco Pedersoli, Simon Bacon, Eric Granger
https://arxiv.org/abs/2508.09202

Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
Facial expression recognition (FER) models are employed in many video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting their performance in real-world applications. To improve their performance, source-free domain adaptation (SFDA) methods have been proposed to personalize a pretrained source model using only unlabeled target domain da…

The Othello AI Arena: Evaluating Intelligent Systems Through Limited-Time Adaptation to Unseen Boards
Sundong Kim
https://arxiv.org/abs/2508.09292 https://…

The Othello AI Arena: Evaluating Intelligent Systems Through Limited-Time Adaptation to Unseen Boards
The ability to rapidly adapt to novel and unforeseen environmental changes is a cornerstone of artificial general intelligence (AGI), yet it remains a critical blind spot in most existing AI benchmarks. Traditional evaluation largely focuses on optimizing performance within fixed environments, failing to assess systems' flexibility and generalization capabilities when faced with even subtle rule or structural modifications. Addressing this gap, I introduce the Othello AI Arena, a novel benchmar…

Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
Zezhen Xiang, Jingzhi Gong, Tao Chen
https://arxiv.org/abs/2507.08730 ht…

Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload variations, hardware changes, and system updates will inevitably introduce concept drifts at different levels - global drifts, which reshape the performance landscape of the entire configuration space; and local drifts, which only affect certain sub-regions of that space. As such, existing offline and transfer learning ap…

Investitionen in #Klimaanpassung zahlen sich aus.
Laut einer Analyse des World Resources Institute bringen sie im Schnitt mehr als das Zehnfache des eingesetzten Kapitals zurück.
Besonders hohe Renditen wurden im #Gesundheitswesen und bei der

Multi-Symbol Digital AirComp via Modulation Design and Power Adaptation
Xiaojing Yan, Saeed Razavikia, Carlo Fischione
https://arxiv.org/abs/2507.08670 htt…

Multi-Symbol Digital AirComp via Modulation Design and Power Adaptation
In this paper, we consider digital over-the-air computation (AirComp) and introduce a new multi-symbol modulation framework called sequential modulation for AirComp (SeMAC). Building upon ChannelComp, a general framework for designing modulation schemes to support arbitrary function computation over a multiple access channel (MAC), SeMAC maps each input value to a sequence of modulated symbols using distinct constellation diagrams across multiple time slots. This extension generalizes ChannelCo…

Climate change action could dramatically limit rising UK heat wave deaths #UnitedKingdom

Climate change action could dramatically limit rising UK heat wave deaths
A new study suggests that, under realistic scenarios of high emissions and socioeconomic development, annual heat-related deaths in the U.K. could rise to about 50 times current rates by the 2070s, but that climate change mitigation and adaptation could significantly limit this rise.

Weather Jiu-Jitsu: Climate Adaptation for the 21st Century
Qin Huang, Moyan Liu, Upmanu Lall
https://arxiv.org/abs/2508.09376 https://arxiv.org/pdf/2508.09…

Weather Jiu-Jitsu: Climate Adaptation for the 21st Century
Extreme climate events, e.g., droughts, floods, heat waves, and freezes, are becoming more frequent and intense with severe global socio-economic impacts. Growing populations and economic activity leads to increased exposure to these events. Scaling existing physical, financial, and social infrastructure to provide resilience against these extreme events is daunting, especially as one ponders projected climate changes. Climate extremes pose a challenge even if decarbonization and geoengineering…

UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
Shuhei Kato
https://arxiv.org/abs/2508.09767 https://ar…

UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
We propose UtterTune, a lightweight adaptation method that fine-tunes a multilingual text-to-speech (TTS) system based on a large language model (LLM) architecture, designed to enhance the controllability of pronunciation in a target language while preserving performance in others. While LLM architectures have enabled TTS models to achieve remarkable naturalness, accurately modeling grapheme-to-phoneme (G2P) mapping and prosody remains challenging, especially when the model omits an explicit G2…

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes
Rogier C. van Dalen, Shucong Zhang, Titouan Parcollet, Sourav Bhattacharya
https://arxiv.org/abs/2506.10653

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes
Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is usually unlabelled. This paper proposes a combination of approaches to make adaptation to a single minute of data robust. First, instead of estimating the adaptation parameters with cross-entropy on a single error-prone hypothesis or "pseudo-label", this paper pro…

Adaptique: Multi-objective and Context-aware Online Adaptation of Selection Techniques in Virtual Reality
Chao-Jung Lai, Mauricio Sousa, Tianyu Zhang, Ludwig Sidenmark, Tovi Grossman
https://arxiv.org/abs/2508.08505

Adaptique: Multi-objective and Context-aware Online Adaptation of Selection Techniques in Virtual Reality
Selection is a fundamental task that is challenging in virtual reality due to issues such as distant and small targets, occlusion, and target-dense environments. Previous research has tackled these challenges through various selection techniques, but complicates selection and can be seen as tedious outside of their designed use case. We present Adaptique, an adaptive model that infers and switches to the most optimal selection technique based on user and environmental information. Adaptique con…

Enhancing Human-Robot Collaboration: A Sim2Real Domain Adaptation Algorithm for Point Cloud Segmentation in Industrial Environments
Fatemeh Mohammadi Amin, Darwin G. Caldwell, Hans Wernher van de Venn
https://arxiv.org/abs/2506.09552

Enhancing Human-Robot Collaboration: A Sim2Real Domain Adaptation Algorithm for Point Cloud Segmentation in Industrial Environments
The robust interpretation of 3D environments is crucial for human-robot collaboration (HRC) applications, where safety and operational efficiency are paramount. Semantic segmentation plays a key role in this context by enabling a precise and detailed understanding of the environment. Considering the intense data hunger for real-world industrial annotated data essential for effective semantic segmentation, this paper introduces a pioneering approach in the Sim2Real domain adaptation for semantic…

BERTector: Intrusion Detection Based on Joint-Dataset Learning
Haoyang Hu, Xun Huang, Chenyu Wu, Shiwen Liu, Zhichao Lian, Shuangquan Zhang
https://arxiv.org/abs/2508.10327 http…

BERTector: Intrusion Detection Based on Joint-Dataset Learning
Intrusion detection systems (IDS) are facing challenges in generalization and robustness due to the heterogeneity of network traffic and the diversity of attack patterns. To address this issue, we propose a new joint-dataset training paradigm for IDS and propose a scalable BERTector framework based on BERT. BERTector integrates three key components: NSS-Tokenizer for traffic-aware semantic tokenization, supervised fine-tuning with a hybrid dataset, and low-rank adaptation (LoRA) for efficient t…

DINOMotion: advanced robust tissue motion tracking with DINOv2 in 2D-Cine MRI-guided radiotherapy
Soorena Salari, Catherine Spino, Laurie-Anne Pharand, Fabienne Lathuiliere, Hassan Rivaz, Silvain Beriault, Yiming Xiao
https://arxiv.org/abs/2508.10260

DINOMotion: advanced robust tissue motion tracking with DINOv2 in 2D-Cine MRI-guided radiotherapy
Accurate tissue motion tracking is critical to ensure treatment outcome and safety in 2D-Cine MRI-guided radiotherapy. This is typically achieved by registration of sequential images, but existing methods often face challenges with large misalignments and lack of interpretability. In this paper, we introduce DINOMotion, a novel deep learning framework based on DINOv2 with Low-Rank Adaptation (LoRA) layers for robust, efficient, and interpretable motion tracking. DINOMotion automatically detects…

Predictive Position Control for Movable Antenna Arrays in UAV Communications: A Spatio-Temporal Transformer-LSTM Framework
Kan Yu, Kaixuan Li, Xiaowu Liu, Qixun Zhang, Zhiyong Feng
https://arxiv.org/abs/2508.10720

Predictive Position Control for Movable Antenna Arrays in UAV Communications: A Spatio-Temporal Transformer-LSTM Framework
In complex urban environments, dynamic obstacles and multipath effects lead to significant link attenuation and pervasive coverage blind spots. Conventional approaches based on large-scale fixed antenna arrays and UAV trajectory optimization struggle to balance energy efficiency, real-time adaptation, and spatial flexibility. The movable antenna (MA) technology has emerged as a promising solution, offering enhanced spatial flexibility and reduced energy consumption to overcome the bottlenecks o…

Not Only Consistency: Enhance Test-Time Adaptation with Spatio-temporal Inconsistency for Remote Physiological Measurement
Xiao Yang, Yuxuan Fan, Can Liu, Houcheng Su, Weichen Guo, Jiyao Wang, Dengbo He
https://arxiv.org/abs/2507.07908

Not Only Consistency: Enhance Test-Time Adaptation with Spatio-temporal Inconsistency for Remote Physiological Measurement
Remote photoplethysmography (rPPG) has emerged as a promising non-invasive method for monitoring physiological signals using the camera. Although various domain adaptation and generalization methods were proposed to promote the adaptability of deep-based rPPG models in unseen deployment environments, considerations in aspects like privacy concerns and real-time adaptation restrict their application in real-world deployment. Thus, we aim to propose a novel fully Test-Time Adaptation (TTA) strate…

Collective dynamics of strategic classification
Marta C. Couto, Flavia Barsotti, Fernando P. Santos
https://arxiv.org/abs/2508.09340 https://arxiv.org/pdf/…

Collective dynamics of strategic classification
Classification algorithms based on Artificial Intelligence (AI) are nowadays applied in high-stakes decisions in finance, healthcare, criminal justice, or education. Individuals can strategically adapt to the information gathered about classifiers, which in turn may require algorithms to be re-trained. Which collective dynamics will result from users' adaptation and algorithms' retraining? We apply evolutionary game theory to address this question. Our framework provides a mathematically rigoro…

Enabling On-demand Guaranteed QoS for Real Time Video Streaming from Vehicles in 5G Advanced with CAPIF & NEF APIs
Pietro Piscione, Leonardo Lossi, Maziar Nekovee, Chathura Galkandage, Phil O Connor, Simon Davies
https://arxiv.org/abs/2508.09150

Enabling On-demand Guaranteed QoS for Real Time Video Streaming from Vehicles in 5G Advanced with CAPIF & NEF APIs
This paper presents the design and implementation of a Proof of Concept (PoC) that demonstrates how 5G Advanced Network Functions can be integrated with the Common API Framework (CAPIF) to support enhanced connectivity for automotive applications. The PoC shows the continuous monitoring of the mobile network performance and the on-demand and dynamic adaptation of Quality of Service (QoS) for selected 5G User Equipment (UE) video streaming traffic flows using standard 3GPP Network Exposure Funct…

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
Zhiyi Dong, Zixuan Liu, Yongyi Mao
https://arxiv.org/abs/2507.06552

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
This paper studies the hardness of unsupervised domain adaptation (UDA) under covariate shift. We model the uncertainty that the learner faces by a distribution $π$ in the ground-truth triples $(p, q, f)$ -- which we call a UDA class -- where $(p, q)$ is the source -- target distribution pair and $f$ is the classifier. We define the performance of a learner as the overall target domain risk, averaged over the randomness of the ground-truth triple. This formulation couples the source distributi…

Improving Robustness of Foundation Models in Domain Adaptation with Soup-Adapters
Marco Roschkowski
https://arxiv.org/abs/2507.05807 https://

Improving Robustness of Foundation Models in Domain Adaptation with Soup-Adapters
In this paper, we tackle two fundamental problems in few-shot domain adaptation of foundation models. First, hyperparameter tuning is often impractical due to the lack of large validation datasets. Second, model robustness under distribution shifts where test time data deviates slightly from training distributions, remains a concern. We show that by training multiple independent adapters and averaging their outputs, the new model has a higher performance and is more robust to distribution shift…

Teaching LLMs to Speak Spectroscopy
Nesar Ramachandra, Yuan-Sen Ting, Zechang Sun, Azton Wells, Salman Habib
https://arxiv.org/abs/2508.10075 https://arxiv…

Teaching LLMs to Speak Spectroscopy
Pre-trained Large Language Models (LLMs) have revolutionized text processing, yet adapting Transformer-based neural networks to non-textual scientific modalities typically requires specialized architectures and extensive computational resources. We demonstrate that LLaMA-3.1-8B can be efficiently repurposed to predict galaxy redshifts from spectroscopic data through Low-Rank Adaptation (LoRA), achieving competitive performance while preserving its linguistic capabilities. Using only 16 GPU-hour…

Homeostatic Adaptation of Optimal Population Codes under Metabolic Stress
Yi-Chun Hung, Gregory Schwartz, Emily A. Cooper, Emma Alexander
https://arxiv.org/abs/2507.07874

Homeostatic Adaptation of Optimal Population Codes under Metabolic Stress
Information processing in neural populations is inherently constrained by metabolic resource limits and noise properties, with dynamics that are not accurately described by existing mathematical models. Recent data, for example, shows that neurons in mouse visual cortex go into a "low power mode" in which they maintain firing rate homeostasis while expending less energy. This adaptation leads to increased neuronal noise and tuning curve flattening in response to metabolic stress. We have develo…

The economic, social & Environmental impact of Electric Vehicle (EV) adaptation on Bangladeshi Society
Abdullah Al Noman, Hasibul Hassan Siam
https://arxiv.org/abs/2508.08398

The economic, social & Environmental impact of Electric Vehicle (EV) adaptation on Bangladeshi Society
This study examines the economic social and environmental impacts of electric vehicle adoption in Bangladesh using survey data from 57 respondents and secondary research. Findings show strong public perception of electric vehicles as cost effective with ninety three percent agreement and environmentally beneficial with eighty two point five percent agreement. Electric vehicles have potential to reduce fuel imports lower operational costs and create over fifty thousand jobs by 2030. Socially ele…

Speciation by local adaptation and isolation by distance in extended environments
Lara D. Hissa, Flavia M. D. Marquitti, Marcus A. M. de Aguiar
https://arxiv.org/abs/2508.06719 …

Speciation by local adaptation and isolation by distance in extended environments
Speciation is often associated with geographical barriers that limit gene flow. However, species can also emerge in continuous homogeneous environments through isolation by distance. When the environment is not homogeneous, natural selection contributes to differentiation by local adaptation and tends to facilitate speciation. To explore how isolation by distance and adaptation combine to determine species diversity, we implemented a model regulated by these two components. The first is impleme…

Replaced article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Waveform proportionality and Taylor's law in coupled Lorenz systems
Yuzuru Mitsui, Hiroshi Kori

ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition
Qingliang Meng, Hao Wu, Wei Liang, Wei Xu, Qing Zhao
https://arxiv.org/abs/2507.08477

ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition
The deep integration of large language models and automatic speech recognition systems has become a promising research direction with high practical value. To address the overfitting issue commonly observed in Low-Rank Adaptation (LoRA) during the supervised fine-tuning (SFT) stage, this work proposes an innovative training paradigm Iterative LoRA Training (ILT) in combination with an Iterative Pseudo Labeling strategy, effectively enhancing the theoretical upper bound of model performance. Bas…

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Ken Yagel, Eyal German, Aviel Ben Siman Tov
https://arxiv.org/abs/2506.07563

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Mov…

Facilitating Longitudinal Interaction Studies of AI Systems
Tao Long, Sitong Wang, \'Emilie Fabre, Tony Wang, Anup Sathya, Jason Wu, Savvas Petridis, Dingzeyu Li, Tuhin Chakrabarty, Yue Jiang, Jingyi Li, Tiffany Tseng, Ken Nakagaki, Qian Yang, Nikolas Martelaro, Jeffrey V. Nickerson, Lydia B. Chilton
https://arxiv.org/abs/2508.10252

Facilitating Longitudinal Interaction Studies of AI Systems
UIST researchers develop tools to address user challenges. However, user interactions with AI evolve over time through learning, adaptation, and repurposing, making one time evaluations insufficient. Capturing these dynamics requires longer-term studies, but challenges in deployment, evaluation design, and data collection have made such longitudinal research difficult to implement. Our workshop aims to tackle these challenges and prepare researchers with practical strategies for longitudinal st…

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
Mattia Litrico, Mario Valerio Giuffrida, Sebastiano Battiato, Devis Tuia
https://arxiv.org/abs/2508.06452 ht…

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background and object appearances differ significantly across domains. Prior works showed that the language modality can help in the adaptation process, exhibiting more robustness to such complex shifts. In this paper, we introduce TRUST, a novel UDA approach that exploit…

Rising sea levels: adaptation has never been more urgent https://www.theguardian.com/commentisfree/2025/may/25/the-guardian-view-on-rising-sea-levels-adaptation-has-never-been-m…

Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
Xinran Li, Chenjia Bai, Zijian Li, Jiakun Zheng, Ting Xiao, Jun Zhang
https://arxiv.org/abs/2506.07232

Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the sophisticated modular design of agentic methods, existing LLM-based planning algorithms remain limited by weak adaptation capabilities to multi-agent embodied scenarios. We address this limitation by introducing a framework that enables LLM agents to learn and ev…

Bridging Classical and Quantum Computing for Next-Generation Language Models
Yi Pan, Hanqi Jiang, Junhao Chen, Yiwei Li, Huaqin Zhao, Lin Zhao, Yohannes Abate, Yingfeng Wang, Tianming Liu
https://arxiv.org/abs/2508.07026

Bridging Classical and Quantum Computing for Next-Generation Language Models
Integrating Large Language Models (LLMs) with quantum computing is a critical challenge, hindered by the severe constraints of Noisy Intermediate-Scale Quantum (NISQ) devices, including barren plateaus and limited coherence. Current approaches often fail due to static quantum-classical partitioning. We introduce Adaptive Quantum-Classical Fusion (AQCF), the first framework to bridge this gap through dynamic, quantum-classical co-design. AQCF's core principle is real-time adaptation: it analyzes…

Identification of pressure points in modern power systems using transfer entropy
Katerina Tang, M. Vivienne Liu, C. Lindsay Anderson, Vivek Srikrishnan
https://arxiv.org/abs/2508.08513

Identification of pressure points in modern power systems using transfer entropy
Integration of variable energy resources -- e.g., solar, wind, and hydro -- and end-use electrification increase modern energy systems' weather-dependence. Identifying critical infrastructure constraining the power grid's ability to meet electricity demand under weather-induced shocks and stressors is essential for understanding risks and guiding adaptation. We use transfer entropy to identify predictive pressure points: grid components whose utilization patterns provide early signals of downst…

Bridging Simulation and Experiment: A Self-Supervised Domain Adaptation Framework for Concrete Damage Classification
Chen Xu, Giao Vu, Ba Trung Cao, Zhen Liu, Fabian Diewald, Yong Yuan, G\"unther Meschke
https://arxiv.org/abs/2508.04538

Bridging Simulation and Experiment: A Self-Supervised Domain Adaptation Framework for Concrete Damage Classification
Reliable assessment of concrete degradation is critical for ensuring structural safety and longevity of engineering structures. This study proposes a self-supervised domain adaptation framework for robust concrete damage classification using coda wave signals. To support this framework, an advanced virtual testing platform is developed, combining multiscale modeling of concrete degradation with ultrasonic wave propagation simulations. This setup enables the generation of large-scale labeled syn…

idk why people seem shocked by the homestuck adaptation, like as a total outsider if u asked me to make up a way to expand the "homestuck brand" a year ago id sleepwalk into getting vivziepop and toby fox in just off vibes of the types online who devote their souls to that shit

#TuneTuesday (June 10)
For #PrideMonth 🏳️‍🌈, I’m selecting #HeatherSmall’s song “Proud”, notably used in the American adaptation of the TV show

MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification
Tianqi Xiang, Yi Li, Qixiang Zhang, Xiaomeng Li
https://arxiv.org/abs/2508.09967 https://

MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification
Recent advances in histopathology vision-language foundation models (VLFMs) have shown promise in addressing data scarcity for whole slide image (WSI) classification via zero-shot adaptation. However, these methods remain outperformed by conventional multiple instance learning (MIL) approaches trained on large datasets, motivating recent efforts to enhance VLFM-based WSI classification through fewshot learning paradigms. While existing few-shot methods improve diagnostic accuracy with limited a…

Making Effective Decisions: Machine Learning and the Ecogame in 1970
Catherine Mason
https://arxiv.org/abs/2508.07027 https://arxiv.org/pdf/2508.07027

Making Effective Decisions: Machine Learning and the Ecogame in 1970
This paper considers Ecogame, an innovative art project of 1970, whose creators believed in a positive vision of a technological future; an understanding, posited on cybernetics, of a future that could be participatory via digital means, and therefore more democratised. Using simulation and early machine learning techniques over a live network, Ecogame combined the power of visual art with cybernetic concepts of adaptation, feedback, and control to propose that behaviour had implications for th…

Beyond Robustness: Learning Unknown Dynamic Load Adaptation for Quadruped Locomotion on Rough Terrain
Leixin Chang, Yuxuan Nai, Hua Chen, Liangjing Yang
https://arxiv.org/abs/2507.07825

Beyond Robustness: Learning Unknown Dynamic Load Adaptation for Quadruped Locomotion on Rough Terrain
Unknown dynamic load carrying is one important practical application for quadruped robots. Such a problem is non-trivial, posing three major challenges in quadruped locomotion control. First, how to model or represent the dynamics of the load in a generic manner. Second, how to make the robot capture the dynamics without any external sensing. Third, how to enable the robot to interact with load handling the mutual effect and stabilizing the load. In this work, we propose a general load modeling…

Replaced article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Rhythmic sharing: A bio-inspired paradigm for zero-shot adaptive learning in neural networks
Hoony Kang, Wolfgang Losert

System Identification via Validation and Adaptation for Model Updating Applied to a Nonlinear Cantilever Beam
Cristian L\'opez, Jackson E. Herzlieb, Keegan J. Moore
https://arxiv.org/abs/2508.00931

System Identification via Validation and Adaptation for Model Updating Applied to a Nonlinear Cantilever Beam
The recently proposed System Identification via Validation and Adaptation (SIVA) method allows system identification, uncertainty quantification, and model validation directly from data. Inspired by generative modeling, SIVA employs a neural network that converts random noise to physically meaningful parameters. The known equation of motion utilizes these parameters to generate fake accelerations, which are compared to real training data using a mean square error loss. For concurrent parameter …

This https://arxiv.org/abs/2505.00533 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Test-time Correlation Alignment
Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test data) increasingly attractive. However, current TTA methods still face practical challenges: (1) a primary focus on instance-wise alignment, overlooking CORrelation ALignment (CORAL) due to missing source correlations; (2) complex backpropagation operations for…

Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
Heet Nitinkumar Dalsania
https://arxiv.org/abs/2507.07254 https://a…

Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
Modern deep learning implementations for medical imaging usually rely on large labeled datasets. These datasets are often difficult to obtain due to privacy concerns, high costs, and even scarcity of cases. In this paper, a label-efficient strategy is proposed for chest X-ray diagnosis that seeks to reflect real-world hospital scenarios. The experiments use the NIH Chest X-ray14 dataset and a pre-trained CLIP ViT-B/32 model. The model is adapted via partial fine-tuning of its visual encoder and…

A Hamilton-Jacobi approach for the evolutionary dynamics of a model with gene transfer: characterizing monomorphic dynamics for non-concave fitness functions
Alejandro G\'arriz (UGR), Sepideh Mirrahimi (IMT)
https://arxiv.org/abs/2508.07886

A Hamilton-Jacobi approach for the evolutionary dynamics of a model with gene transfer: characterizing monomorphic dynamics for non-concave fitness functions
We study the asymptotic behavior of an integro-dierential equation describing the evolutionary adaptation of a population structured by a phenotypic trait. The model takes into account mutation, selection, horizontal gene transfer and competition. Previous works, based on the numerical studies or theoretical study of the corresponding stationary problem, have shown that the dynamics of the solutions are rich and we may expect several qualitative outcomes. In this article, we characterize the dy…

MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data
Antoine Labatie, Michael Vaccaro, Nina Lardiere, Anatol Garioud, Nicolas Gonthier
https://arxiv.org/abs/2508.10894

MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data
Self-supervised learning holds great promise for remote sensing, but standard self-supervised methods must be adapted to the unique characteristics of Earth observation data. We take a step in this direction by conducting a comprehensive benchmark of fusion strategies and reconstruction target normalization schemes for multimodal, multitemporal, and multispectral Earth observation data. Based on our findings, we propose MAESTRO, a novel adaptation of the Masked Autoencoder, featuring optimized …

Stereographic Projections on Some Quadric Surfaces
W. F. C. Barboza, T. F. Cruz, R. B. Leal
https://arxiv.org/abs/2506.08289 https://…

Stereographic Projections on Some Quadric Surfaces
In this work, we present an adaptation of the classical stereographic projection, originally formulated for the sphere, now considering the context of the ellipsoid and the elliptic paraboloid. We begin by constructing the stereographic projections for both quadric surfaces separately, analyzing the geometric particularities of each surface and the challenges arising from their variable curvatures and, in the case of the paraboloid, its non-compactness. In the final part of the work, we establi…

Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision
Evelyne Ringoot, Rabab Alomairy, Valentin Churavy, Alan Edelman
https://arxiv.org/abs/2508.06339

Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision
This paper presents a portable, GPU-accelerated implementation of a QR-based singular value computation algorithm in Julia. The singular value ecomposition (SVD) is a fundamental numerical tool in scientific computing and machine learning, providing optimal low-rank matrix approximations. Its importance has increased even more in large-scale machine learning pipelines, including large language models (LLMs), where it enables low-rank adaptation (LoRA). The implemented algorithm is based on the …

Degrowth: a dead end or the way out? Capital’s future scam
Aurora Despierta In the series Prospects for Degrowth This article by the Spanish writer Aurora Despierta is her adaptation (highly summarised for translation into English), for the series Prospects for Degrowth, of the original article: Decrecer ¿callejón o salida? La futura estafa del capital’ (2-5-2025) Translated by Mark Burton and Anna Gregoletto For a radically anti-capitalist degrowth that cannot be…

Degrowth: a dead end or the way out? Capital’s future scam
Aurora Despierta In the series Prospects for Degrowth This article by the Spanish writer Aurora Despierta is her adaptation (highly summarised for translation into English), for the series Prospect…

Crosslisted article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Dynamic mode decomposition for detecting transient activity via sparsity and smoothness regulariz...
Yutaro Tanaka, Hiroya Nakao

Affecta-Context: The Context-Guided Behavior Adaptation Framework
Morten Roed Frederiksen, Kasper St{\o}y
https://arxiv.org/abs/2508.05359 https://arxiv.or…

Affecta-Context: The Context-Guided Behavior Adaptation Framework
This paper presents Affecta-context, a general framework to facilitate behavior adaptation for social robots. The framework uses information about the physical context to guide its behaviors in human-robot interactions. It consists of two parts: one that represents encountered contexts and one that learns to prioritize between behaviors through human-robot interactions. As physical contexts are encountered the framework clusters them by their measured physical properties. In each context, the f…

Civil Society in the Loop: Feedback-Driven Adaptation of (L)LM-Assisted Classification in an Open-Source Telegram Monitoring Tool
Milena Pustet, Elisabeth Steffen, Helena Mihaljevi\'c, Grischa Stanjek, Yannis Illies
https://arxiv.org/abs/2507.06734

Civil Society in the Loop: Feedback-Driven Adaptation of (L)LM-Assisted Classification in an Open-Source Telegram Monitoring Tool
The role of civil society organizations (CSOs) in monitoring harmful online content is increasingly crucial, especially as platform providers reduce their investment in content moderation. AI tools can assist in detecting and monitoring harmful content at scale. However, few open-source tools offer seamless integration of AI models and social media monitoring infrastructures. Given their thematic expertise and contextual understanding of harmful content, CSOs should be active partners in co-dev…

FLoRIST: Singular Value Thresholding for Efficient and Accurate Federated Fine-Tuning of Large Language Models
Hariharan Ramesh, Jyotikrishna Dass
https://arxiv.org/abs/2506.09199

FLoRIST: Singular Value Thresholding for Efficient and Accurate Federated Fine-Tuning of Large Language Models
Integrating Low-Rank Adaptation (LoRA) into federated learning offers a promising solution for parameter-efficient fine-tuning of Large Language Models (LLMs) without sharing local data. However, several methods designed for federated LoRA present significant challenges in balancing communication efficiency, model accuracy, and computational cost, particularly among heterogeneous clients. These methods either rely on simplistic averaging of local adapters, which introduces aggregation noise, re…

AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
Eunsu Baek, Keondo Park, Jeonggil Ko, Min-hwan Oh, Taesik Gong, Hyung-Sin Kim
https://arxiv.org/abs/2507.07820

AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs significant environmental, economic, and ethical costs, limiting sustainability and equitable access. Inspired by biological sensory systems, where adaptation occurs dynamically at the input (e.g., adjusting pupil size, refocusing vision)--we advocate for adaptive sensing as a necessary and foundational shift. Adaptiv…

Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation
Iing Muttakhiroh, Thomas Fevens
https://arxiv.org/abs/2508.03571 https://

Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation
Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowledge-Instructed Learning for Continual Adaptation), a novel continual learning framework that integrates dynamic knowledge graphs with instruction tuning. By leveraging retrieved domain-specific knowledge as guidance during training, KILO enhances both adaptability to new domains and retention of previously acquired k…

Mitigating Multi-Sequence 3D Prostate MRI Data Scarcity through Domain Adaptation using Locally-Trained Latent Diffusion Models for Prostate Cancer Detection
Emerson P. Grabke, Babak Taati, Masoom A. Haider
https://arxiv.org/abs/2507.06384

Mitigating Multi-Sequence 3D Prostate MRI Data Scarcity through Domain Adaptation using Locally-Trained Latent Diffusion Models for Prostate Cancer Detection
Objective: Latent diffusion models (LDMs) could mitigate data scarcity challenges affecting machine learning development for medical image interpretation. The recent CCELLA LDM improved prostate cancer detection performance using synthetic MRI for classifier training but was limited to the axial T2-weighted (AxT2) sequence, did not investigate inter-institutional domain shift, and prioritized radiology over histopathology outcomes. We propose CCELLA++ to address these limitations and improve cl…

SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
Borui Li, Li Yan, Junhao Han, Jianmin Liu, Lei Yu
https://arxiv.org/abs/2508.04100

SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
Homomorphic Encryption (HE) prevails in securing Federated Learning (FL), but suffers from high overhead and adaptation cost. Selective HE methods, which partially encrypt model parameters by a global mask, are expected to protect privacy with reduced overhead and easy adaptation. However, in cross-device scenarios with heterogeneous data and system capabilities, traditional Selective HE methods deteriorate client straggling, and suffer from degraded HE overhead reduction performance. According…

Enhanced V2X Communication Using Game-Theory Based Adaptive MAC Protocols
Dhrumil Bhatt, Nirbhay Singhal
https://arxiv.org/abs/2506.09817 https://

Enhanced V2X Communication Using Game-Theory Based Adaptive MAC Protocols
This paper presents an enhanced Vehicle-to-Everything (V2X) communication system featuring adaptive Medium Access Control (MAC) using game theory. Our approach integrates dynamic transmission power control, dynamic beacon rates, contention window adaptation, and implicit acknowledgment mechanisms within a Manhattan-like grid-based mobility scenario. Simulations are conducted in a circular coverage area, incorporating refined signal propagation models and probabilistic vehicle mobility with boun…

Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
Jim O'Connor, Derin Gezgin, Gary B. Parker
https://arxiv.org/abs/2508.07522 https://

Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
We present Evo-Sparrow, a deep learning-based agent for AI decision-making in Sparrow Mahjong, trained by optimizing Long Short-Term Memory (LSTM) networks using Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Our model evaluates board states and optimizes decision policies in a non-deterministic, partially observable game environment. Empirical analysis conducted over a significant number of simulations demonstrates that our model outperforms both random and rule-based agents, and ac…

going through my months-old screenshots and this motherfucker is a recurring pattern

DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics
Yayu Long, Kewei Chen, Long Jin, Mingsheng Shang
https://arxiv.org/abs/2507.04661

DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics
We introduce Dynamic Retrieval-Augmented Expert Networks (DRAE), a groundbreaking architecture that addresses the challenges of lifelong learning, catastrophic forgetting, and task adaptation by combining the dynamic routing capabilities of Mixture-of-Experts (MoE); leveraging the knowledge-enhancement power of Retrieval-Augmented Generation (RAG); incorporating a novel hierarchical reinforcement learning (RL) framework; and coordinating through ReflexNet-SchemaPlanner-HyperOptima (RSHO).DRAE d…

A Unified Analysis of Generalization and Sample Complexity for Semi-Supervised Domain Adaptation
Elif Vural, Huseyin Karaca
https://arxiv.org/abs/2507.22632 https://

A Unified Analysis of Generalization and Sample Complexity for Semi-Supervised Domain Adaptation
Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its theoretical foundations remain relatively underexplored. Most existing theoretical analyses focus on simplified settings where the source and target domains share the same input space and relate target-domain performance to measures of domain discrepancy. Although ins…

[2025-08-15 Fri (UTC), 1 new article found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

O_FT@EvalLLM2025 : \'etude comparative de choix de donn\'ees et de strat\'egies d'apprentissage pour l'adaptation de mod\`eles de langue \`a un domaine
Isma\"el Rousseau, Claire Perroux, Pierre Adam, Thomas Girault, Lionel Delphin-Poulat, Morgan Veyret, Gw\'enol\'e Lecorv\'e, G\'eraldine Damnati
https://

O_FT@EvalLLM2025 : étude comparative de choix de données et de stratégies d'apprentissage pour l'adaptation de modèles de langue à un domaine
This paper presents the work carried out by the O_FT team, joint with Orange and Ouest-France, on adapting language models to the defense domain as part of the EvalLLM2025 challenge. This work focused on adapting the \texttt{Mistral-7B-Instruct-v0.3} model using classical techniques of continued pre-training and instruction-tuning. The core of our efforts is based on collecting, generating, and selecting data for these two stages as well as for model evaluation. Experiments show that our adapte…

[2025-07-14 Mon (UTC), 2 new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation
Eman Ali, Chetan Arora, Muhammad Haris Khan
https://arxiv.org/abs/2507.22075 htt…

Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation
In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional pseudo-label filtering approaches, which rely on fixed confidence thresholds, tend to be unreliable in fully unsupervised settings. In this work, we propose a novel adaptive pseudo-labeling framework that enhances CLIP's adaptation performance by integrating prototype …

This https://arxiv.org/abs/2505.21904 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
Instance segmentation demands costly per-pixel annotations and large models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pretrained vision foundation models (VFM) into compact experts using limited labeled and abundant unlabeled data. CAST unfolds in three stages: (1) domain adaptation of the VFM teacher(s) via self-training with contrastive pixel calibration, (2) distillation into a compact student via a unified multi-objective loss that couples…

Discrepancy-Aware Contrastive Adaptation in Medical Time Series Analysis
Yifan Wang, Hongfeng Ai, Ruiqi Li, Maowei Jiang, Ruiyuan Kang, Jiahua Dong, Cheng Jiang, Chenzhong Li
https://arxiv.org/abs/2508.05572

Discrepancy-Aware Contrastive Adaptation in Medical Time Series Analysis
In medical time series disease diagnosis, two key challenges are identified. First, the high annotation cost of medical data leads to overfitting in models trained on label-limited, single-center datasets. To address this, we propose incorporating external data from related tasks and leveraging AE-GAN to extract prior knowledge, providing valuable references for downstream tasks. Second, many existing studies employ contrastive learning to derive more generalized medical sequence representation…

Why Evolve When You Can Adapt? Post-Evolution Adaptation of Genetic Memory for On-the-Fly Control
Hamze Hammami, Eva Denisa Barbulescu, Talal Shaikh, Mouayad Aldada, Muhammad Saad Munawar
https://arxiv.org/abs/2508.03600

Why Evolve When You Can Adapt? Post-Evolution Adaptation of Genetic Memory for On-the-Fly Control
Imagine a robot controller with the ability to adapt like human synapses, dynamically rewiring itself to overcome unforeseen challenges in real time. This paper proposes a novel zero-shot adaptation mechanism for evolutionary robotics, merging a standard Genetic Algorithm (GA) controller with online Hebbian plasticity. Inspired by biological systems, the method separates learning and memory, with the genotype acting as memory and Hebbian updates handling learning. In our approach, the fitness f…

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
Jiahao Chen, junhao li, Yiming Wang, Zhe Ma, Yi Jiang, Chunyi Zhou, Qingming Li, Tianyu Du, Shouling Ji
https://arxiv.org/abs/2507.07056

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.g., personal portraits) on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs can be weaponized by adversaries to generate harmful content (e.g., political, defamatory imagery), undermining creator rights and platform safety. Existing defenses like concept-erasure methods focu…

[2025-08-14 Thu (UTC), no new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Ziyue Li, Yang Li, Tianyi Zhou
https://arxiv.org/abs/2507.07996 https://arxiv.org/pdf/2507.07996 https://arxiv.org/html/2507.07996
arXiv:2507.07996v1 Announce Type: new
Abstract: Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This compositional space greatly expands the scope of existing works on looped/recurrent pretrained modules, layer pruning, or early-exit networks. We develop a Monte Carlo Tree Search (MCTS) protocol to explore and identify the optimal CoLa for each sample from math and commonsense reasoning benchmarks. Compared to a static model of a fixed depth, CoLa allows shortcut paths (fast thinking), recurrence of the same layer(s) (slow thinking), and combining both, offering more flexible, dynamic architectures for different inputs. We conduct an extensive analysis of the MCTS-optimized CoLa, which leads to two key findings: (1) For >75% of samples with correct predictions by the original LLM, we can find shorter CoLa, suggesting a large space for improving inference efficiency; (2) For >60% of samples with originally incorrect predictions, we can identify CoLa achieving correct predictions, suggesting a large space of performance enhancement. Our results highlight the shortcomings of using a fixed architecture of pre-trained LLMs for inference on different samples and pave the way to unlock the generalization power of test-time depth adaptation.
toXiv_bot_toot

Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
Yizhe Xiong, Zihan Zhou, Yiwen Liang, Hui Chen, Zijia Lin, Tianxiang Hao, Fan Zhang, Jungong Han, Guiguang Ding
https://arxiv.org/abs/2508.03388

Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
Test-Time Adaptation (TTA) has emerged as an effective solution for adapting Vision Transformers (ViT) to distribution shifts without additional training data. However, existing TTA methods often incur substantial computational overhead, limiting their applicability in resource-constrained real-world scenarios. To reduce inference cost, plug-and-play token aggregation methods merge redundant tokens in ViTs to reduce total processed tokens. Albeit efficient, it suffers from significant performan…

Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation
Tianyi Hu, Andrea Morales-Garz\'on, Jingyi Zheng, Maria Maistro, Daniel Hershcovich
https://arxiv.org/abs/2507.21934

Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation
In cross-cultural recipe adaptation, the goal is not only to ensure cultural appropriateness and retain the original dish's essence, but also to provide diverse options for various dietary needs and preferences. Retrieval Augmented Generation (RAG) is a promising approach, combining the retrieval of real recipes from the target cuisine for cultural adaptability with large language models (LLMs) for relevance. However, it remains unclear whether RAG can generate diverse adaptation results. Our a…

MPCA-based Domain Adaptation for Transfer Learning in Ultrasonic Guided Waves
Lucio Pinello, Francesco Cadini, Luca Lomazzi
https://arxiv.org/abs/2508.02726 https://

MPCA-based Domain Adaptation for Transfer Learning in Ultrasonic Guided Waves
Ultrasonic Guided Waves (UGWs) represent a promising diagnostic tool for Structural Health Monitoring (SHM) in thin-walled structures, and their integration with machine learning (ML) algorithms is increasingly being adopted to enable real-time monitoring capabilities. However, the large-scale deployment of UGW-based ML methods is constrained by data scarcity and limited generalisation across different materials and sensor configurations. To address these limitations, this work proposes a novel…

CueLearner: Bootstrapping and local policy adaptation from relative feedback
Giulio Schiavi, Andrei Cramariuc, Lionel Ott, Roland Siegwart
https://arxiv.org/abs/2507.04730

CueLearner: Bootstrapping and local policy adaptation from relative feedback
Human guidance has emerged as a powerful tool for enhancing reinforcement learning (RL). However, conventional forms of guidance such as demonstrations or binary scalar feedback can be challenging to collect or have low information content, motivating the exploration of other forms of human input. Among these, relative feedback (i.e., feedback on how to improve an action, such as "more to the left") offers a good balance between usability and information richness. Previous research has shown th…

Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation
Jun Luo, Zijing Zhao, Yang Liu
https://arxiv.org/abs/2508.03300 https://

Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation
Deep learning-based semantic segmentation models achieve impressive results yet remain limited in handling distribution shifts between training and test data. In this paper, we present SDGPA (Synthetic Data Generation and Progressive Adaptation), a novel method that tackles zero-shot domain adaptive semantic segmentation, in which no target images are available, but only a text description of the target domain's style is provided. To compensate for the lack of target domain training data, we ut…

Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision
Soham Walimbe, Britty Baby, Vinkle Srivastav, Nicolas Padoy
https://arxiv.org/abs/2507.05020

Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision
Surgical AI often involves multiple tasks within a single procedure, like phase recognition or assessing the Critical View of Safety in laparoscopic cholecystectomy. Traditional models, built for one task at a time, lack flexibility, requiring a separate model for each. To address this, we introduce MML-SurgAdapt, a unified multi-task framework with Vision-Language Models (VLMs), specifically CLIP, to handle diverse surgical tasks through natural language supervision. A key challenge in multi-t…

This https://arxiv.org/abs/2505.17663 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
As Large Language Models (LLMs) increasingly participate in human-AI interactions, evaluating their Theory of Mind (ToM) capabilities - particularly their ability to track dynamic mental states - becomes crucial. While existing benchmarks assess basic ToM abilities, they predominantly focus on static snapshots of mental states, overlooking the temporal evolution that characterizes real-world social interactions. We present \textsc{DynToM}, a novel benchmark specifically designed to evaluate LLM…

This https://arxiv.org/abs/2506.06105 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Text-to-LoRA: Instant Transformer Adaption
While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyper-parameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2…

Replaced article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Dynamical systems on torus related to general Heun equations: phase-lock areas and constriction b...
Artem Alexandrov, Alexey Glutsyuk

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[6/9]:
- UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation
Yue Zhou, Yuan Bi, Wenjuan Tong, Wei Wang, Nassir Navab, Zhongliang Jiang

DiWA: Diffusion Policy Adaptation with World Models
Akshay L Chandra, Iman Nematollahi, Chenguang Huang, Tim Welschehold, Wolfram Burgard, Abhinav Valada
https://arxiv.org/abs/2508.03645

DiWA: Diffusion Policy Adaptation with World Models
Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of real-world interactions, posing a major bottleneck for practical fine-tuning. Although prior work frames the denoising process in diffusion policies as a Markov Decision Process to enable RL-based updates, its strong dependence on environment interaction rema…

$\varphi$-Adapt: A Physics-Informed Adaptation Learning Approach to 2D Quantum Material Discovery
Hoang-Quan Nguyen, Xuan Bac Nguyen, Sankalp Pandey, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu
https://arxiv.org/abs/2507.05184

$φ$-Adapt: A Physics-Informed Adaptation Learning Approach to 2D Quantum Material Discovery
Characterizing quantum flakes is a critical step in quantum hardware engineering because the quality of these flakes directly influences qubit performance. Although computer vision methods for identifying two-dimensional quantum flakes have emerged, they still face significant challenges in estimating flake thickness. These challenges include limited data, poor generalization, sensitivity to domain shifts, and a lack of physical interpretability. In this paper, we introduce one of the first Phy…

This https://arxiv.org/abs/2505.19912 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation
We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization principles, APE evaluates multiple candidate parameter updates through fine-tuning on small data subsets and accepts only those exceeding a performance threshold. Unlike standard fine-tuning that follows single gradient directions, APE implements a filtered s…

Box Pose and Shape Estimation and Domain Adaptation for Large-Scale Warehouse Automation
Xihang Yu, Rajat Talak, Jingnan Shi, Ulrich Viereck, Igor Gilitschenski, Luca Carlone
https://arxiv.org/abs/2507.00984

Box Pose and Shape Estimation and Domain Adaptation for Large-Scale Warehouse Automation
Modern warehouse automation systems rely on fleets of intelligent robots that generate vast amounts of data -- most of which remains unannotated. This paper develops a self-supervised domain adaptation pipeline that leverages real-world, unlabeled data to improve perception models without requiring manual annotations. Our work focuses specifically on estimating the pose and shape of boxes and presents a correct-and-certify pipeline for self-supervised box pose and shape estimation. We extensive…

This https://arxiv.org/abs/2505.23868 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Noise-Robustness Through Noise: Asymmetric LoRA Adaption with Poisoning Expert
Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustne…

RedDino: A foundation model for red blood cell analysis
Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Carsten Marr
https://arxiv.org/abs/2508.08180 https://

RedDino: A foundation model for red blood cell analysis
Red blood cells (RBCs) are essential to human health, and their precise morphological analysis is important for diagnosing hematological disorders. Despite the promise of foundation models in medical diagnostics, comprehensive AI solutions for RBC analysis remain scarce. We present RedDino, a self-supervised foundation model designed for RBC image analysis. RedDino uses an RBC-specific adaptation of the DINOv2 self-supervised learning framework and is trained on a curated dataset of 1.25 millio…

Multiple Timescale Dynamics of Network Adaptation with Constraints
Erik Andreas Martens, Christian Bick
https://arxiv.org/abs/2507.06359 https://

Multiple Timescale Dynamics of Network Adaptation with Constraints
Adaptive network dynamical systems describe the co-evolution of dynamical quantities on the nodes as well as dynamics of the network connections themselves. For dense networks of many nodes, the resulting dynamics are typically high-dimensional. Here we consider adaptive dynamical systems subject to constraints on network adaptation: Asymptotically, the adaptive dynamics of network connections evolve on a low-dimensional subset of possible connectivity. Such dimension reduction may be intrinsic…

MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
Wei Shen, Yaxiang Zhang, Minhui Huang, Mengfan Xu, Jiawei Zhang, Cong Shen
https://arxiv.org/abs/2506.01897

MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a novel memory-efficient training paradigm called Momentum Low-rank compression (MLorc). By directly compressing and reconstructing momentum rather than gradients, MLorc avoids imposing a fixed-rank constraint on weight update matrices and better preserves the training dynamics of full-parameter fine-tuning, in contrast to existing low-rank approache…

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim
https://arxiv.org/abs/2507.18632 https://

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data. To enable adaptation without target images, existing studies utilize CLIP's embedding space and text description to simulate target-like style features. Despite the previous achievements in zero-shot domain adaptation, we observe that these text-driven methods struggle to capture complex real-world variations and significantly increase adaptation time due to their alignmen…

Surrogate-Enhanced Modeling and Adaptive Modular Control of All-Electric Heavy-Duty Robotic Manipulators
Amir Hossein Barjini, Mohammad Bahari, Mahdi Hejrati, Jouni Mattila
https://arxiv.org/abs/2508.06313

Surrogate-Enhanced Modeling and Adaptive Modular Control of All-Electric Heavy-Duty Robotic Manipulators
This paper presents a unified system-level modeling and control framework for an all-electric heavy-duty robotic manipulator (HDRM) driven by electromechanical linear actuators (EMLAs). A surrogate-enhanced actuator model, combining integrated electromechanical dynamics with a neural network trained on a dedicated testbed, is integrated into an extended virtual decomposition control (VDC) architecture augmented by a natural adaptation law. The derived analytical HDRM model supports a hierarchic…

Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining: Method, Evaluation and Applications
Seonwu Kim, Yohan Na, Kihun Kim, Hanhee Cho, Geun Lim, Mintae Kim, Seongik Park, Ki Hyun Kim, Youngsub Han, Byoung-Ki Jeon
https://arxiv.org/abs/2507.06795

Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining: Method, Evaluation and Applications
The emergence of open-source large language models (LLMs) has expanded opportunities for enterprise applications; however, many organizations still lack the infrastructure to deploy and maintain large-scale models. As a result, small LLMs (sLLMs) have become a practical alternative, despite their inherent performance limitations. While Domain Adaptive Continual Pretraining (DACP) has been previously explored as a method for domain adaptation, its utility in commercial applications remains under…

Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation
Irene Iele, Francesco Di Feola, Valerio Guarrasi, Paolo Soda
https://arxiv.org/abs/2508.00766 https://…

Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation
Image-to-image translation has emerged as a powerful technique in medical imaging, enabling tasks such as image denoising and cross-modality conversion. However, it suffers from limitations in handling out-of-distribution samples without causing performance degradation. To address this limitation, we propose a novel Test-Time Adaptation (TTA) framework that dynamically adjusts the translation process based on the characteristics of each test sample. Our method introduces a Reconstruction Module…

ADPro: a Test-time Adaptive Diffusion Policy for Robot Manipulation via Manifold and Initial Noise Constraints
Zezeng Li, Rui Yang, Ruochen Chen, ZhongXuan Luo, Liming Chen
https://arxiv.org/abs/2508.06266

ADPro: a Test-time Adaptive Diffusion Policy for Robot Manipulation via Manifold and Initial Noise Constraints
Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action generation as an unconstrained denoising process, ignoring valuable a priori knowledge about geometry and control structure. In this work, we propose the Adaptive Diffusion Policy (ADP), a test-time adaptation method that introduces two key inductive biases into the …

[2025-06-13 Fri (UTC), no new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

EA-ViT: Efficient Adaptation for Elastic Vision Transformer
Chen Zhu, Wangbo Zhao, Huiwen Zhang, Samir Khaki, Yuhao Zhou, Weidong Tang, Shuo Wang, Zhihang Yuan, Yuzhang Shang, Xiaojiang Peng, Kai Wang, Dawei Yang
https://arxiv.org/abs/2507.19360

EA-ViT: Efficient Adaptation for Elastic Vision Transformer
Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires retraining multiple, size-specific ViTs, which is both time-consuming and energy-intensive. To address this issue, we propose an efficient ViT adaptation framework that enables a single adaptation process to generate multiple models of varying sizes for deployment on …

[2025-08-13 Wed (UTC), no new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

This https://arxiv.org/abs/2409.12949 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Learning-based Quadcopter Controller with Extreme Adaptation
This paper introduces a learning-based low-level controller for quadcopters, which adaptively controls quadcopters with significant variations in mass, size, and actuator capabilities. Our approach leverages a combination of imitation learning and reinforcement learning, creating a fast-adapting and general control framework for quadcopters that eliminates the need for precise model estimation or manual tuning. The controller estimates a latent representation of the vehicle's system parameters …

Embodied Domain Adaptation for Object Detection
Xiangyu Shi, Yanyuan Qiao, Lingqiao Liu, Feras Dayoub
https://arxiv.org/abs/2506.21860 https://

Embodied Domain Adaptation for Object Detection
Mobile robots rely on object detectors for perception and object localization in indoor environments. However, standard closed-set methods struggle to handle the diverse objects and dynamic conditions encountered in real homes and labs. Open-vocabulary object detection (OVOD), driven by Vision Language Models (VLMs), extends beyond fixed labels but still struggles with domain shifts in indoor environments. We introduce a Source-Free Domain Adaptation (SFDA) approach that adapts a pre-trained mo…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/4]:
- Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision
Soham Walimbe, Britty Baby, Vinkle Srivastav, Nicolas Padoy

Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation
Jiaer Xia, Bingkui Tong, Yuhang Zang, Rui Shao, Kaiyang Zhou
https://arxiv.org/abs/2507.02859

Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in interpreting images using natural language. However, without using large-scale datasets for retraining, these models are difficult to adapt to specialized vision tasks, e.g., chart understanding. This problem is caused by a mismatch between pre-training and downstream datasets: pre-training datasets primarily concentrate on scenes and objects but contain limited information about specialized, non-object images…