Tootfinder

IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation
Yuan Yin, Shashanka Venkataramanan, Tuan-Hung Vu, Andrei Bursuc, Matthieu Cord
https://arxiv.org/abs/2509.04398

IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, reduce adaptation cost by injecting low-rank updates into pretrained weights. However, LoRA's down-projection is randomly initialized and data-agnostic, discarding potentially useful information. Prior analyses show that this projection changes little during training, while the up-projection carries most of the adaptation, making the random input compression a performance bottleneck. We propose IPA, a feature-aware projection framewo…

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models
Ci-Siang Lin, Min-Hung Chen, Yu-Yang Sheng, Yu-Chiang Frank Wang
https://arxiv.org/abs/2510.03232

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have achieved strong performance on general visual benchmarks but struggle with out-of-distribution (OOD) tasks in specialized domains such as medical imaging, where labeled data is limited and expensive. We introduce LEAML, a label-efficient adaptation framework that leverages both scarce labeled VQA samples and abundant unlabeled images. Our approach generates domain-relevant pseudo question-answer pairs for unlabeled data using a QA generator regulari…

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…

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…

World Model Implanting for Test-time Adaptation of Embodied Agents
Minjong Yoo, Jinwoo Jang, Sihyung Yoon, Honguk Woo
https://arxiv.org/abs/2509.03956 https://

World Model Implanting for Test-time Adaptation of Embodied Agents
In embodied AI, a persistent challenge is enabling agents to robustly adapt to novel domains without requiring extensive data collection or retraining. To address this, we present a world model implanting framework (WorMI) that combines the reasoning capabilities of large language models (LLMs) with independently learned, domain-specific world models through test-time composition. By allowing seamless implantation and removal of the world models, the embodied agent's policy achieves and maintai…

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 …

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…

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…

Optimal rate-variance coding due to firing threshold adaptation near criticality
Mauricio Girardi-Schappo, Leonard Maler, Andr\'e Longtin
https://arxiv.org/abs/2509.04106 ht…

Optimal rate-variance coding due to firing threshold adaptation near criticality
Recurrently connected neuron populations play key roles in sensory perception and memory storage across various brain regions. While these populations are often assumed to encode information through firing rates, this method becomes unreliable with weak stimuli. We propose that in such cases, information can be transmitted via spatial spike patterns, employing a sparse or combinatorial coding based on firing rate variance. Around the critical point of a stochastic recurrent excitable network, w…

Test-Time Adaptation for Speech Enhancement via Domain Invariant Embedding Transformation
Tobias Raichle, Niels Edinger, Bin Yang
https://arxiv.org/abs/2509.04280 https://

Test-Time Adaptation for Speech Enhancement via Domain Invariant Embedding Transformation
Deep learning-based speech enhancement models achieve remarkable performance when test distributions match training conditions, but often degrade when deployed in unpredictable real-world environments with domain shifts. To address this challenge, we present LaDen (latent denoising), the first test-time adaptation method specifically designed for speech enhancement. Our approach leverages powerful pre-trained speech representations to perform latent denoising, approximating clean speech represe…

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…

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…

Should we teach vibe coding? Here's why not.
Should AI coding be taught in undergrad CS education?
1/2
I teach undergraduate computer science labs, including for intro and more-advanced core courses. I don't publish (non-negligible) scholarly work in the area, but I've got years of craft expertise in course design, and I do follow the academic literature to some degree. In other words, In not the world's leading expert, but I have spent a lot of time thinking about course design, and consider myself competent at it, with plenty of direct experience in what knowledge & skills I can expect from students as they move through the curriculum.
I'm also strongly against most uses of what's called "AI" these days (specifically, generative deep neutral networks as supplied by our current cadre of techbro). There are a surprising number of completely orthogonal reasons to oppose the use of these systems, and a very limited number of reasonable exceptions (overcoming accessibility barriers is an example). On the grounds of environmental and digital-commons-pollution costs alone, using specifically the largest/newest models is unethical in most cases.
But as any good teacher should, I constantly question these evaluations, because I worry about the impact on my students should I eschew teaching relevant tech for bad reasons (and even for his reasons). I also want to make my reasoning clear to students, who should absolutely question me on this. That inspired me to ask a simple question: ignoring for one moment the ethical objections (which we shouldn't, of course; they're very stark), at what level in the CS major could I expect to teach a course about programming with AI assistance, and expect students to succeed at a more technically demanding final project than a course at the same level where students were banned from using AI? In other words, at what level would I expect students to actually benefit from AI coding "assistance?"
To be clear, I'm assuming that students aren't using AI in other aspects of coursework: the topic of using AI to "help you study" is a separate one (TL;DR it's gross value is not negative, but it's mostly not worth the harm to your metacognitive abilities, which AI-induced changes to the digital commons are making more important than ever).
So what's my answer to this question?
If I'm being incredibly optimistic, senior year. Slightly less optimistic, second year of a masters program. Realistic? Maybe never.
The interesting bit for you-the-reader is: why is this my answer? (Especially given that students would probably self-report significant gains at lower levels.) To start with, [this paper where experienced developers thought that AI assistance sped up their work on real tasks when in fact it slowed it down] (https://arxiv.org/abs/2507.09089) is informative. There are a lot of differences in task between experienced devs solving real bugs and students working on a class project, but it's important to understand that we shouldn't have a baseline expectation that AI coding "assistants" will speed things up in the best of circumstances, and we shouldn't trust self-reports of productivity (or the AI hype machine in general).
Now we might imagine that coding assistants will be better at helping with a student project than at helping with fixing bugs in open-source software, since it's a much easier task. For many programming assignments that have a fixed answer, we know that many AI assistants can just spit out a solution based on prompting them with the problem description (there's another elephant in the room here to do with learning outcomes regardless of project success, but we'll ignore this over too, my focus here is on project complexity reach, not learning outcomes). My question is about more open-ended projects, not assignments with an expected answer. Here's a second study (by one of my colleagues) about novices using AI assistance for programming tasks. It showcases how difficult it is to use AI tools well, and some of these stumbling blocks that novices in particular face.
But what about intermediate students? Might there be some level where the AI is helpful because the task is still relatively simple and the students are good enough to handle it? The problem with this is that as task complexity increases, so does the likelihood of the AI generating (or copying) code that uses more complex constructs which a student doesn't understand. Let's say I have second year students writing interactive websites with JavaScript. Without a lot of care that those students don't know how to deploy, the AI is likely to suggest code that depends on several different frameworks, from React to JQuery, without actually setting up or including those frameworks, and of course three students would be way out of their depth trying to do that. This is a general problem: each programming class carefully limits the specific code frameworks and constructs it expects students to know based on the material it covers. There is no feasible way to limit an AI assistant to a fixed set of constructs or frameworks, using current designs. There are alternate designs where this would be possible (like AI search through adaptation from a controlled library of snippets) but those would be entirely different tools.
So what happens on a sizeable class project where the AI has dropped in buggy code, especially if it uses code constructs the students don't understand? Best case, they understand that they don't understand and re-prompt, or ask for help from an instructor or TA quickly who helps them get rid of the stuff they don't understand and re-prompt or manually add stuff they do. Average case: they waste several hours and/or sweep the bugs partly under the rug, resulting in a project with significant defects. Students in their second and even third years of a CS major still have a lot to learn about debugging, and usually have significant gaps in their knowledge of even their most comfortable programming language. I do think regardless of AI we as teachers need to get better at teaching debugging skills, but the knowledge gaps are inevitable because there's just too much to know. In Python, for example, the LLM is going to spit out yields, async functions, try/finally, maybe even something like a while/else, or with recent training data, the walrus operator. I can't expect even a fraction of 3rd year students who have worked with Python since their first year to know about all these things, and based on how students approach projects where they have studied all the relevant constructs but have forgotten some, I'm not optimistic seeing these things will magically become learning opportunities. Student projects are better off working with a limited subset of full programming languages that the students have actually learned, and using AI coding assistants as currently designed makes this impossible. Beyond that, even when the "assistant" just introduces bugs using syntax the students understand, even through their 4th year many students struggle to understand the operation of moderately complex code they've written themselves, let alone written by someone else. Having access to an AI that will confidently offer incorrect explanations for bugs will make this worse.
To be sure a small minority of students will be able to overcome these problems, but that minority is the group that has a good grasp of the fundamentals and has broadened their knowledge through self-study, which earlier AI-reliant classes would make less likely to happen. In any case, I care about the average student, since we already have plenty of stuff about our institutions that makes life easier for a favored few while being worse for the average student (note that our construction of that favored few as the "good" students is a large part of this problem).
To summarize: because AI assistants introduce excess code complexity and difficult-to-debug bugs, they'll slow down rather than speed up project progress for the average student on moderately complex projects. On a fixed deadline, they'll result in worse projects, or necessitate less ambitious project scoping to ensure adequate completion, and I expect this remains broadly true through 4-6 years of study in most programs (don't take this as an endorsement of AI "assistants" for masters students; we've ignored a lot of other problems along the way).
There's a related problem: solving open-ended project assignments well ultimately depends on deeply understanding the problem, and AI "assistants" allow students to put a lot of code in their file without spending much time thinking about the problem or building an understanding of it. This is awful for learning outcomes, but also bad for project success. Getting students to see the value of thinking deeply about a problem is a thorny pedagogical puzzle at the best of times, and allowing the use of AI "assistants" makes the problem much much worse. This is another area I hope to see (or even drive) pedagogical improvement in, for what it's worth.
1/2

Understanding Heterogeneity in Adaptation to Intermittent Water Supply: Clustering Household Types in Amman, Jordan
Shreyas Gadge, V\'itor V. Vasconcelos, Andr\'e de Roos, Elisabeth H. Krueger
https://arxiv.org/abs/2508.02569

Understanding Heterogeneity in Adaptation to Intermittent Water Supply: Clustering Household Types in Amman, Jordan
More than a billion people around the world experience intermittence in their water supply, posing challenges for urban households in Global South cities. An intermittent water supply (IWS) system prompts water users to adapt to service deficits which entails coping costs. Adaptation and its impacts can vary between households within the same city, leading to intra-urban inequality. Studies on household adaptation to IWS through survey data are limited to exploring income-based heterogeneity an…

TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models
Yuxuan Gu, Wuyang Zhou, Giorgos Iacovides, Danilo Mandic
https://arxiv.org/abs/2509.03234

TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models
Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), have significantly reduced the number of trainable parameters needed in fine-tuning large language models (LLMs). Subsequent developments of LoRA-style adapters have diverged into two main directions: (1) enhancing model expressivity with high-rank adapters, and (2) pushing for further parameter reduction, as exemplified by vector-based methods. However, these approaches present a trade-off, as achieving the exp…

VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs
Zixuan Gu, Qiufeng Fan, Long Sun, Yang Liu, Xiaojun Ye
https://arxiv.org/abs/2508.03097 https://…

VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs
With the advancement of Large Language Models (LLMs), LLM applications have expanded into a growing number of fields. However, users with data privacy concerns face limitations in directly utilizing LLM APIs, while private deployments incur significant computational demands. This creates a substantial challenge in achieving secure LLM adaptation under constrained local resources. To address this issue, collaborative learning methods, such as Split Learning (SL), offer a resource-efficient and p…

Algorithm Adaptation Bias in Recommendation System Online Experiments
Chen Zheng, Zhenyu Zhao
https://arxiv.org/abs/2509.00199 https://arxiv.org/pdf/2509.0…

Algorithm Adaptation Bias in Recommendation System Online Experiments
Online experiments (A/B tests) are widely regarded as the gold standard for evaluating recommender system variants and guiding launch decisions. However, a variety of biases can distort the results of the experiment and mislead decision-making. An underexplored but critical bias is algorithm adaptation effect. This bias arises from the flywheel dynamics among production models, user data, and training pipelines: new models are evaluated on user data whose distributions are shaped by the incumbe…

Crosslisted article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Optimal rate-variance coding due to firing threshold adaptation near criticality
Mauricio Girardi-Schappo, Leonard Maler, Andr\'e Longtin

The asymptotic rank of adjacency matrices of weighted configuration models over arbitrary fields
Remco van der Hofstad, Noela M\"uller, Haodong Zhu
https://arxiv.org/abs/2508.02813

The asymptotic rank of adjacency matrices of weighted configuration models over arbitrary fields
We study the asymptotic rank of adjacency matrices of a large class of edge-weighted configuration models. Here, the weight of a (multi-)edge can be any fixed non-zero element from an arbitrary field, as long as it is independent of the (multi-)graph. Our main result demonstrates that the asymptotic behavior of the normalized rank of the adjacency matrix neither depends on the fixed edge-weights, nor on which field they are chosen from. Our approach relies on a novel adaptation of the component…

To Remember, To Adapt, To Preempt: A Stable Continual Test-Time Adaptation Framework for Remote Physiological Measurement in Dynamic Domain Shifts
Shuyang Chu, Jingang Shi, Xu Cheng, Haoyu Chen, Xin Liu, Jian Xu, Guoying Zhao
https://arxiv.org/abs/2510.01282

To Remember, To Adapt, To Preempt: A Stable Continual Test-Time Adaptation Framework for Remote Physiological Measurement in Dynamic Domain Shifts
Remote photoplethysmography (rPPG) aims to extract non-contact physiological signals from facial videos and has shown great potential. However, existing rPPG approaches struggle to bridge the gap between source and target domains. Recent test-time adaptation (TTA) solutions typically optimize rPPG model for the incoming test videos using self-training loss under an unrealistic assumption that the target domain remains stationary. However, time-varying factors like weather and lighting in dynami…

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation
Mariia Drozdova, Erica Lastufka, Vitaliy Kinakh, Taras Holotyak, Daniel Schaerer, Slava Voloshynovskiy
https://arxiv.org/abs/2509.02615

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation
Vision-Language Models (VLMs), such as recent Qwen and Gemini models, are positioned as general-purpose AI systems capable of reasoning across domains. Yet their capabilities in scientific imaging, especially on unfamiliar and potentially previously unseen data distributions, remain poorly understood. In this work, we assess whether generic VLMs, presumed to lack exposure to astronomical corpora, can perform morphology-based classification of radio galaxies using the MiraBest FR-I/FR-II dataset…

Community-Centered Spatial Intelligence for Climate Adaptation at Nova Scotia's Eastern Shore
Gabriel Spadon, Oladapo Oyebode, Camilo M. Botero, Tushar Sharma, Floris Goerlandt, Ronald Pelot
https://arxiv.org/abs/2509.01845

Community-Centered Spatial Intelligence for Climate Adaptation at Nova Scotia's Eastern Shore
This paper presents an overview of a human-centered initiative aimed at strengthening climate resilience along Nova Scotia's Eastern Shore. This region, a collection of rural villages with deep ties to the sea, faces existential threats from climate change that endanger its way of life. Our project moves beyond a purely technical response, weaving together expertise from Computer Science, Industrial Engineering, and Coastal Geography to co-create tools with the community. By integrating generat…

Modeling the Impact of NATO Policy Actions on Taliban Disinformation Campaigns with Lotka-Volterra Models
Timothy Tarter, Bella Santos
https://arxiv.org/abs/2508.01904 https://

Modeling the Impact of NATO Policy Actions on Taliban Disinformation Campaigns with Lotka-Volterra Models
In this paper, we use an adaptation of the Lotka-Volterra Predator-Prey framework (via Affili Et. Al.) to model the relationship between Taliban disinformation campaigns and NATO's attempts to counter them. We find that aggression is a significantly preferred strategy over stagnation; this result should prompt decisionmakers to take strong stances against disinformation campaigns while maintaining a healthy defense against retribution. This leads us to propose the NATO Afghan Youth for Change p…

Replaced article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Case Study of Novelty, Complexity, and Adaptation in a Multicellular System
Matthew Andres Moreno, Santiago Rodriguez Papa, Charles Ofria

EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition
Jiacheng Shi, Hongfei Du, Y. Alicia Hong, Ye Gao
https://arxiv.org/abs/2509.25495

EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition
Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance degradation in out-of-domain scenarios. Test-time adaptation (TTA) provides a promising solution but often relies on gradient-based updates or prompt tuning, limiting flexibility and practicality. We propose Emo-TTA, a lightweight, training-free adaptation framework that incrementally updates class-conditional statistics via an Expectation-Maximizatio…

Numerical investigation of engine position effects on contrail formation and evolution in the near-field of a realistic aircraft configuration
R\'emy Annunziata (ETS), Nicolas Bonne (ETS), Fran\c{c}ois Garnier (ETS)
https://arxiv.org/abs/2508.02706

Numerical investigation of engine position effects on contrail formation and evolution in the near-field of a realistic aircraft configuration
The present study investigates the impact of engine position on contrail formation and near-field evolution in a realistic three-dimensional aircraft configuration. Detailed numerical simulations are conducted using a Reynolds-Averaged Navier-Stokes (RANS) approach coupled with mesh adaptation techniques. A Eulerian microphysical model is used to characterize contrail ice crystal properties and their evolution under varying dilution conditions. The setup is based on a Boeing 777-like geometry, …

CausalARC: Abstract Reasoning with Causal World Models
Jacqueline Maasch, John Kalantari, Kia Khezeli
https://arxiv.org/abs/2509.03636 https://arxiv.org/pd…

CausalARC: Abstract Reasoning with Causal World Models
Reasoning requires adaptation to novel problem settings under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution regimes, modeled after the Abstraction and Reasoning Corpus (ARC). Each CausalARC reasoning task is sampled from a fully specified causal world model, formally expressed as a structural causal model. Principled data augmentations provide observational, interventional, and counterfactual fee…

CardiffNLP at CLEARS-2025: Prompting Large Language Models for Plain Language and Easy-to-Read Text Rewriting
Mutaz Ayesh, Nicol\'as Guti\'errez-Rol\'on, Fernando Alva-Manchego
https://arxiv.org/abs/2508.03240

CardiffNLP at CLEARS-2025: Prompting Large Language Models for Plain Language and Easy-to-Read Text Rewriting
This paper details the CardiffNLP team's contribution to the CLEARS shared task on Spanish text adaptation, hosted by IberLEF 2025. The shared task contained two subtasks and the team submitted to both. Our team took an LLM-prompting approach with different prompt variations. While we initially experimented with LLaMA-3.2, we adopted Gemma-3 for our final submission, and landed third place in Subtask 1 and second place in Subtask 2. We detail our numerous prompt variations, examples, and experi…

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…

Coexistence of two adaptation processes in a visuomotor rotation task
Alexis Berland (ISIR, CAOR), Youssouf Ismail Cherifi (CAOR), Alexis Paljic (CAOR), Emmanuel Guigon (ISIR)
https://arxiv.org/abs/2509.26090

Coexistence of two adaptation processes in a visuomotor rotation task
Motor adaptation is a learning process that enables humans to regain proficiency when sensorimotor conditions are sustainably altered. Many studies have documented the properties of motor adaptation, yet the underlying mechanisms of motor adaptation remain imperfectly understood. In this study, we propose a computational analysis of adaptation to a visuomotor rotation task and examine it through an experiment. Our analysis suggests that two distinct processes contribute to produce adaptation: o…

A Physics-Informed Multi-Source Domain Adaptation Framework for Label-Free Post-Earthquake Damage Assessment
Yifeng Zhang, Xiao Liang
https://arxiv.org/abs/2509.26356 https://…

A Physics-Informed Multi-Source Domain Adaptation Framework for Label-Free Post-Earthquake Damage Assessment
Efficient and intelligent assessment of post-earthquake structural damage is critical for rapid disaster response. While data-driven approaches have shown promise, traditional supervised learning methods rely on extensive labeled datasets, which are often impractical to obtain for damaged structures. To address this limitation, we propose a physics-informed multi-source domain adaptation framework to predict post-earthquake structural damage for a target building without requiring damage labels…

New paper published! ➡️ Climate change adaptation preferences of small enterprises
Vulnerable entrepreneurs’ preferences for climate risk management: A discrete choice experiment with micro-enterprises in the Philippines
Authors: #AnnKristin_Becker @…

ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
Shyma Alhuwaider, Motasem Alfarra, Juan C. Perez, Merey Ramazanova, Bernard Ghanem
https://arxiv.org/abs/2509.02182

ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
We introduce a novel tracklet-based dataset for benchmarking test-time adaptation (TTA) methods. The aim of this dataset is to mimic the intricate challenges encountered in real-world environments such as images captured by hand-held cameras, self-driving cars, etc. The current benchmarks for TTA focus on how models face distribution shifts, when deployed, and on violations to the customary independent-and-identically-distributed (i.i.d.) assumption in machine learning. Yet, these benchmarks fa…

Fitness and Overfitness: Implicit Regularization in Evolutionary Dynamics
Hagai Rappeport, Mor Nitzan
https://arxiv.org/abs/2508.03187 https://arxiv.org/pd…

Fitness and Overfitness: Implicit Regularization in Evolutionary Dynamics
A common assumption in evolutionary thought is that adaptation drives an increase in biological complexity. However, the rules governing evolution of complexity appear more nuanced. Evolution is deeply connected to learning, where complexity is much better understood, with established results on optimal complexity appropriate for a given learning task. In this work, we suggest a mathematical framework for studying the relationship between evolved organismal complexity and enviroenmntal complexi…

Signal Classification Recovery Across Domains Using Unsupervised Domain Adaptation
Mohammad Ali, Fuhao Li, Jielun Zhang
https://arxiv.org/abs/2510.00589 https://

Signal Classification Recovery Across Domains Using Unsupervised Domain Adaptation
Signal classification models based on deep neural networks are typically trained on datasets collected under controlled conditions, either simulated or over-the-air (OTA), which are constrained to specific channel environments with limited variability, such as fixed signal-to-noise ratio (SNR) levels. As a result, these models often fail to generalize when deployed in real-world scenarios where the feature distribution significantly differs from the training domain. This paper explores unsuperv…

Modeling and Exploiting the Time Course of Chromatic Adaptation for Display Power Optimizations in Virtual Reality
Ethan Chen, Sushant Kondguli, Carl Marshall, Yuhao Zhu
https://arxiv.org/abs/2509.23489

Modeling and Exploiting the Time Course of Chromatic Adaptation for Display Power Optimizations in Virtual Reality
We introduce a gaze-tracking--free method to reduce OLED display power consumption in VR with minimal perceptual impact. This technique exploits the time course of chromatic adaptation, the human visual system's ability to maintain stable color perception under changing illumination. To that end, we propose a novel psychophysical paradigm that models how human adaptation state changes with the scene illuminant. We exploit this model to compute an optimal illuminant shift trajectory, controlling…

LoRA-based methods on Unet for transfer learning in Subarachnoid Hematoma Segmentation
Cristian Minoccheri, Matthew Hodgman, Haoyuan Ma, Rameez Merchant, Emily Wittrup, Craig Williamson, Kayvan Najarian
https://arxiv.org/abs/2508.01772

LoRA-based methods on Unet for transfer learning in Subarachnoid Hematoma Segmentation
Aneurysmal subarachnoid hemorrhage (SAH) is a life-threatening neurological emergency with mortality rates exceeding 30%. Transfer learning from related hematoma types represents a potentially valuable but underexplored approach. Although Unet architectures remain the gold standard for medical image segmentation due to their effectiveness on limited datasets, Low-Rank Adaptation (LoRA) methods for parameter-efficient transfer learning have been rarely applied to convolutional neural networks in…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/9]:
- BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation
Peijia Qin, Ruiyi Zhang, Pengtao Xie

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…

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
Jiahao Zhao
https://arxiv.org/abs/2508.03275 https://arxiv.org/pdf…

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
Spaced repetition systems are fundamental to efficient learning and memory retention, but existing algorithms often struggle with semantic interference and personalized adaptation. We present LECTOR (\textbf{L}LM-\textbf{E}nhanced \textbf{C}oncept-based \textbf{T}est-\textbf{O}riented \textbf{R}epetition), a novel adaptive scheduling algorithm specifically designed for test-oriented learning scenarios, particularly language examinations where success rate is paramount. LECTOR leverages large la…

Automatic Generation of Combinatorial Reoptimisation Problem Specifications: A Vision
Maximilian Kratz, Steffen Zschaler, Jens Kosiol, Gabriele Taentzer
https://arxiv.org/abs/2510.02002

Automatic Generation of Combinatorial Reoptimisation Problem Specifications: A Vision
Once an optimisation problem has been solved, the solution may need adaptation when contextual factors change. This challenge, also known as reoptimisation, has been addressed in various problem domains, such as railway crew rescheduling, nurse rerostering, or aircraft recovery. This requires a modified problem to be solved again to ensure that the adapted solution is optimal in the new context. However, the new optimisation problem differs notably from the original problem: (i) we want to make…

Multi-layer Digital Twin System for Future Mobile Metaverse
Gaosheng Zhao, Dong In Kim
https://arxiv.org/abs/2509.03049 https://arxiv.org/pdf/2509.03049

Multi-layer Digital Twin System for Future Mobile Metaverse
In the upcoming 6G era, the communication networks are expected to face unprecedented challenges in terms of complexity and dynamics. Digital Twin (DT) technology, with its various digital capabilities, holds great potential to facilitate the transformation of the communication network from passive responding to proactive adaptation. Thus, in this paper, we propose a multi-layer DT system that coordinates local DT, edge DT, and cloud DT for future network architecture and functions. In our visi…

Control across scales: signals, information, and adaptive biological mechanical function
James Clarke, Jake McGrath, Colin Johnson, Jos\'e Alvarado
https://arxiv.org/abs/2509.03418

Control across scales: signals, information, and adaptive biological mechanical function
Biological systems perform an astonishing array of dynamical processes -- including development and repair, regulation, behavior and motor control, sensing and signaling, and adaptation, among others. Powered by the transduction of stored energy resources, these behaviors enable biological systems to regulate functions, achieve specific outcomes, and maintain stability far from thermodynamic equilibrium. These behaviors span orders of magnitude in length and time: from nanometer-scale molecular…

EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative Captioning
Liang-Yuan Wu, Dhruv Jain
https://arxiv.org/abs/2510.02181 https://arxiv.or…

EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative Captioning
Automatic Speech Recognition (ASR) systems often fail to accurately transcribe speech from Deaf and Hard of Hearing (DHH) individuals, especially during real-time conversations. Existing personalization approaches typically require extensive pre-recorded data and place the burden of adaptation on the DHH speaker. We present EvolveCaptions, a real-time, collaborative ASR adaptation system that supports in-situ personalization with minimal effort. Hearing participants correct ASR errors during li…

A Unified Denoising and Adaptation Framework for Self-Supervised Bengali Dialectal ASR
Swadhin Biswas, Imran, Tuhin Sheikh
https://arxiv.org/abs/2509.00988 https://

A Unified Denoising and Adaptation Framework for Self-Supervised Bengali Dialectal ASR
Automatic Speech Recognition (ASR) for Bengali, the world's fifth most spoken language, remains a significant challenge, critically hindering technological accessibility for its over 270 million speakers. This challenge is compounded by two persistent and intertwined factors: the language's vast dialectal diversity and the prevalence of acoustic noise in real-world environments. While state-of-the-art self-supervised learning (SSL) models have advanced ASR for low-resource languages, they often…

A Variant of Non-uniform Cylindrical Algebraic Decomposition for Real Quantifier Elimination
Jasper Nalbach, Erika \'Abrah\'am
https://arxiv.org/abs/2508.00505 https://

A Variant of Non-uniform Cylindrical Algebraic Decomposition for Real Quantifier Elimination
The Cylindrical Algebraic Decomposition (CAD) method is currently the only complete algorithm used in practice for solving real-algebraic problems. To ameliorate its doubly-exponential complexity, different exploration-guided adaptations try to avoid some of the computations. The first such adaptation named NLSAT was followed by Non-uniform CAD (NuCAD) and the Cylindrical Algebraic Covering (CAlC). Both NLSAT and CAlC have been developed and implemented in SMT solvers for satisfiability checkin…

Crosslisted article(s) found for physics.bio-ph. https://arxiv.org/list/physics.bio-ph/new
[1/1]:
- Perfect adaptation in eukaryotic gradient sensing using cooperative allosteric binding
Vishnu Srinivasan, Wei Wang, Brian A. Camley

DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving
Mingyu Yang, Jae-Young Choi, Kihyo Moon, Minsung Jang, Eunjoo Joen
https://arxiv.org/abs/2509.01083 …

DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving
Speculative decoding accelerates large language model inference, but its reliance on a fixed speculation length is suboptimal in large-batch serving environments with diverse requests. This paper explores a new direction for dynamic adaptation by investigating a novel class of post-hoc, diagnostic signals. We propose Dynamic Speculative Decoding Engine (DSDE), a training-free framework built on two primary components: (1) a predictive signal based on the variance of the Kullback-Leibler (KLD) d…

Privacy Risks in Time Series Forecasting: User- and Record-Level Membership Inference
Nicolas Johansson (Chalmers University of Technology), Tobias Olsson (Chalmers University of Technology), Daniel Nilsson (AI Sweden), Johan \"Ostman (AI Sweden), Fazeleh Hoseini (AI Sweden)
https://arxiv.org/abs/2509.04169

Privacy Risks in Time Series Forecasting: User- and Record-Level Membership Inference
Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this gap by introducing two new attacks: (i) an adaptation of multivariate LiRA, a state-of-the-art MIA originally developed for classification models, to the time-series forecasting setting, and (ii) a novel end-to-end learning approach called Deep Time Series (DT…

Replaced article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- A More Convex Ising Formulation of Max-3-Cut Using Higher-Order Spin Interactions
Robbe De Prins, Guy Van der Sande, Peter Bienstman, Thomas Van Vaerenbergh

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[5/5]:
- LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
Juzheng Zhang, Jiacheng You, Ashwinee Panda, Tom Goldstein

Context dependent adaptation in a neural computation
Charles J. Edelson, Sima Setayeshgar, William Bialek, Rob R. de Ruyter van Steveninck
https://arxiv.org/abs/2509.01760 https…

Context dependent adaptation in a neural computation
Brains adapt to the statistical structure of their input. In the visual system, local light intensities change rapidly, the variance of the intensity changes more slowly, and the dynamic range of contrast itself changes more slowly still. We use a motion-sensitive neuron in the fly visual system to probe this hierarchy of adaptation phenomena, delivering naturalistic stimuli that have been simplified to have a clear separation of time scales. We show that the neural response to visual motion de…

Dynamic Real-Time Ambisonics Order Adaptation for Immersive Networked Music Performances
Paolo Ostan, Carlo Centofanti, Mirco Pezzoli, Alberto Bernardini, Claudia Rinaldi, Fabio Antonacci
https://arxiv.org/abs/2508.00509

Dynamic Real-Time Ambisonics Order Adaptation for Immersive Networked Music Performances
Advanced remote applications such as Networked Music Performance (NMP) require solutions to guarantee immersive real-world-like interaction among users. Therefore, the adoption of spatial audio formats, such as Ambisonics, is fundamental to let the user experience an immersive acoustic scene. The accuracy of the sound scene reproduction increases with the order of the Ambisonics enconding, resulting in an improved immersivity at the cost of a greater number of audio channels, which in turn esca…

Commmunication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptation
Le-Tuan Nguyen, Minh-Duong Nguyen, Seon-Geun Jeong, Dung D. Le, Quoc-Viet Pham
https://arxiv.org/abs/2509.26399

Commmunication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptation
With the rapid emergence of foundation models and the increasing need for fine-tuning across distributed environments, Federated Low-Rank Adaptation (FedLoRA) has recently gained significant attention. Despite enormous potential, current FedLoRA methods face notable challenges due to inexact updates. Existing approaches have attempted to mitigate this issue, but they often introduce a \emph{local-global generalization gap} and incur \emph{substantial communication overhead}, limiting their scal…

ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation
Wenye Yu, Jun Lv, Zixi Ying, Yang Jin, Chuan Wen, Cewu Lu
https://arxiv.org/abs/2510.02298

ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation
Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without sufficient in-domain data. Besides, human-collected demonstrations entail substantial labour and tend to encompass mixed-quality data and redundant information. As a workaround, human-in-the-loop systems gather domain-specific data for policy post-training, and exploit closed-loop policy feedback to offer informative guidance, but usually require ful…

microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification
Sathira Silva, Eman Ali, Chetan Arora, Muhammad Haris Khan
https://arxiv.org/abs/2510.02270

microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification
Unsupervised adaptation of CLIP-based vision-language models (VLMs) for fine-grained image classification requires sensitivity to microscopic local cues. While CLIP exhibits strong zero-shot transfer, its reliance on coarse global features restricts its performance on fine-grained classification tasks. Prior efforts inject fine-grained knowledge by aligning large language model (LLM) descriptions with the CLIP $\texttt{[CLS]}$ token; however, this approach overlooks spatial precision. We propos…

EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models
Xiaoming Hou, Jiquan Zhang, Zibin Lin, DaCheng Tao, Shengli Zhang
https://arxiv.org/abs/2508.03533

EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models
Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or continuous adaptation via additional trainable parameters. Both exhibit limitations-discrete methods lack refinement precision while parameter-based techniques increase complexity and reduce interpretability. To address these constraints, we propose EmbedGrad, a…

Replaced article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Why collective behaviours self-organise to criticality: A primer on information-theoretic and the...
Qianyang Chen, Mikhail Prokopenko

Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
Julian Lemmel, Manuel Kranzl, Adam Lamine, Philipp Neubauer, Radu Grosu, Sophie Neubauer
https://arxiv.org/abs/2508.00804

Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
This paper introduces a new approach for fine-tuning the predictions of structured state space models (SSMs) at inference time using real-time recurrent learning. While SSMs are known for their efficiency and long-range modeling capabilities, they are typically trained offline and remain static during deployment. Our method enables online adaptation by continuously updating model parameters in response to incoming data. We evaluate our approach for linear-recurrent-unit SSMs using a small carbo…

VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
Duy Nguyen, Dat Nguyen
https://arxiv.org/abs/2510.01660 https://arxiv.…

VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
Existing UDA pipelines fine-tune already well-trained backbone parameters for every new source-and-target pair, resulting in the number of training parameters and storage memory growing linearly with each new pair, and also preventing the reuse of these well-trained backbone parameters. Inspired by recent implications that existing backbones have textural biases, we propose making use of domain-specific textural bias for domain adaptation via visual reprogramming, namely VirDA.Instead of fine…

MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
Parush Gera, Tempestt Neal
https://arxiv.org/abs/2509.03725 https://

MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
We present the novel approach for stance detection across domains and targets, Metric Learning-Based Few-Shot Learning for Cross-Target and Cross-Domain Stance Detection (MLSD). MLSD utilizes metric learning with triplet loss to capture semantic similarities and differences between stance targets, enhancing domain adaptation. By constructing a discriminative embedding space, MLSD allows a cross-target or cross-domain stance detection model to acquire useful examples from new target domains. We …

Crosslisted article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- StableSleep: Source-Free Test-Time Adaptation for Sleep Staging with Lightweight Safety Rails
Hritik Arasu, Faisal R Jahangiri

Unsupervised Domain Adaptation with an Unobservable Source Subpopulation
Chao Ying, Jun Jin, Haotian Zhang, Qinglong Tian, Yanyuan Ma, Yixuan Li, Jiwei Zhao
https://arxiv.org/abs/2509.20587

Unsupervised Domain Adaptation with an Unobservable Source Subpopulation
We study an unsupervised domain adaptation problem where the source domain consists of subpopulations defined by the binary label $Y$ and a binary background (or environment) $A$. We focus on a challenging setting in which one such subpopulation in the source domain is unobservable. Naively ignoring this unobserved group can result in biased estimates and degraded predictive performance. Despite this structured missingness, we show that the prediction in the target domain can still be recovered…

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 …

Measuring How (Not Just Whether) VLMs Build Common Ground
Saki Imai, Mert \.Inan, Anthony Sicilia, Malihe Alikhani
https://arxiv.org/abs/2509.03805 https://

Measuring How (Not Just Whether) VLMs Build Common Ground
Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop shared understanding through ongoing communication. We introduce a four-metric suite (grounding efficiency, content alignment, lexical adaptation, and human-likeness) to systematically evaluate VLM performance in interactive grounding contexts. We deploy the suit…

An Age-Agnostic System for Robust Speaker Verification
Jiusi Zheng, Vishwas Shetty, Natarajan Balaji Shankar, Abeer Alwan
https://arxiv.org/abs/2508.01637 https://

An Age-Agnostic System for Robust Speaker Verification
In speaker verification (SV), the acoustic mismatch between children's and adults' speech leads to suboptimal performance when adult-trained SV systems are applied to children's speaker verification (C-SV). While domain adaptation techniques can enhance performance on C-SV tasks, they often do so at the expense of significant degradation in performance on adults' SV (A-SV) tasks. In this study, we propose an Age Agnostic Speaker Verification (AASV) system that achieves robust performance across…

Time-Frequency Analysis of Non-Uniformly Sampled Signals via Sample Density Adaptation
Ashwini Kulkarni, Santosh Nannuru
https://arxiv.org/abs/2509.22891 https://

Time-Frequency Analysis of Non-Uniformly Sampled Signals via Sample Density Adaptation
The analysis of non-stationary signals in non-uniformly sampled data is a challenging task. Time-integrated methods, such as the generalised Lomb-Scargle (GLS) periodogram, provide a robust statistical assessment of persistent periodicities but are insensitive to transient events. Conversely, existing time-frequency methods often rely on fixed-duration windows or interpolation, which can be suboptimal for non-uniform data. We introduce the non-uniform Stockwell-transform (NUST), a time-frequenc…

User Prompting Strategies and ChatGPT Contextual Adaptation Shape Conversational Information-Seeking Experiences
Haoning Xue, Yoo Jung Oh, Xinyi Zhou, Xinyu Zhang, Berit Oxley
https://arxiv.org/abs/2509.25513

User Prompting Strategies and ChatGPT Contextual Adaptation Shape Conversational Information-Seeking Experiences
Conversational AI, such as ChatGPT, is increasingly used for information seeking. However, little is known about how ordinary users actually prompt and how ChatGPT adapts its responses in real-world conversational information seeking (CIS). In this study, a nationally representative sample of 937 U.S. adults engaged in multi-turn CIS with ChatGPT on both controversial and non-controversial topics across science, health, and policy contexts. We analyzed both user prompting strategies and the com…

FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
Matteo Caligiuri, Francesco Barbato, Donald Shenaj, Umberto Michieli, Pietro Zanuttigh
https://arxiv.org/abs/2508.03356

FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
Federated Learning (FL) is an established paradigm for training deep learning models on decentralized data. However, as the size of the models grows, conventional FL approaches often require significant computational resources on client devices, which may not be feasible. We introduce FedPromo, a novel framework that enables efficient adaptation of large-scale foundation models stored on a central server to new domains encountered only by remote clients. Instead of directly training the large m…

Replaced article(s) found for nlin.AO. https://arxiv.org/list/nlin.AO/new
[1/1]:
- Mixed-feedback oscillations in the foraging dynamics of arboreal turtle ants
Alia Valentine, Deborah M. Gordon, Anastasia Bizyaeva

Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
Piotr Giedziun, Jan So{\l}tysik, Mateusz G\'orczany, Norbert Ropiak, Marcin Przymus, Piotr Krajewski, Jaros{\l}aw Kwiecie\'n, Artur Bartczak, Izabela Wasiak, Mateusz Maniewski
https://arxiv.org/abs/2509.02601

Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
We present a solution for the MIDOG 2025 Challenge Track~2, addressing binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs). The approach leverages pathology-specific foundation model H-optimus-0, selected based on recent cross-domain generalization benchmarks and our empirical testing, with Low-Rank Adaptation (LoRA) fine-tuning and MixUp augmentation. Implementation includes soft labels based on multi-expert consensus, hard negative mining, and adaptiv…

QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models
Jessica Liang, Anirudh Bharadwaj
https://arxiv.org/abs/2508.21810 https://

QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models
The growing scale of Large Language Models (LLMs) has necessitated the development of parameter-efficient fine-tuning techniques. Low-Rank Adaptation (LoRA) has emerged as a promising approach, reducing the number of trainable parameters by applying low-rank updates to pretrained weights. While standard LoRA learns both update factors directly, several recent variants first initialize those matrices via an SVD of the pretrained weights -- an operation that can be expensive on large models and y…

Cross-Border Legal Adaptation of Autonomous Vehicle Design based on Logic and Non-monotonic Reasoning
Zhe Yu, Yiwei Lu, Burkhard Schafer, Zhe Lin
https://arxiv.org/abs/2507.22432

Cross-Border Legal Adaptation of Autonomous Vehicle Design based on Logic and Non-monotonic Reasoning
This paper focuses on the legal compliance challenges of autonomous vehicles in a transnational context. We choose the perspective of designers and try to provide supporting legal reasoning in the design process. Based on argumentation theory, we introduce a logic to represent the basic properties of argument-based practical (normative) reasoning, combined with partial order sets of natural numbers to express priority. Finally, through case analysis of legal texts, we show how the reasoning sys…

Crosslisted article(s) found for eess.AS. https://arxiv.org/list/eess.AS/new
[1/1]:
- Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies
Taherinezhad, Nezhad, Karimi, Rashidi, Zolnour, Dadkhah, Haghbin, AzadMaleki, Zolnoori

Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification
Mieko Ochi, Bae Yuan
https://arxiv.org/abs/2509.02591 https://

Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification
Mitotic figures are classified into typical and atypical variants, with atypical counts correlating strongly with tumor aggressiveness. Accurate differentiation is therefore essential for patient prognostication and resource allocation, yet remains challenging even for expert pathologists. Here, we leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets and applied parameter-efficient fine-tuning via low-rank adaptation. During training, we employ a fisheye tra…

Preference-Guided Multi-Objective UI Adaptation
Yao Song, Christoph Gebhardt, Yi-Chi Liao, Christian Holz
https://arxiv.org/abs/2509.18960 https://arxiv.or…

Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning
Seonsoo Kim, Jun-Gill Kang, Taehong Kim, Seongil Hong
https://arxiv.org/abs/2509.01297 h…

Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning
In meta-learning and its downstream tasks, many methods rely on implicit adaptation to task variations, where multiple factors are mixed together in a single entangled representation. This makes it difficult to interpret which factors drive performance and can hinder generalization. In this work, we introduce a disentangled multi-context meta-learning framework that explicitly assigns each task factor to a distinct context vector. By decoupling these variations, our approach improves robustness…

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…

[2025-08-05 Tue (UTC), 2 new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Quy Minh Le, Minh Sao Khue Luu, Khanh-Tung Tran, Duc-Hai Nguyen, Hoang-Quoc-Viet Pham, Quan Le, Hoang Thanh Lam, Hoang D. Nguyen
https://arxiv.org/abs/2510.00023

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for coaching tool use in agentic models with flexible reinforcement learning (RL), easing the barriers for researchers and practitioners to adapt LLM-…

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 …

A Robust Multi-Scale Framework with Test-Time Adaptation for sEEG-Based Speech Decoding
Suli Wang, Yang-yang Li, Siqi Cai, Haizhou Li
https://arxiv.org/abs/2509.24700 https://…

A Robust Multi-Scale Framework with Test-Time Adaptation for sEEG-Based Speech Decoding
Decoding speech from stereo-electroencephalography (sEEG) signals has emerged as a promising direction for brain-computer interfaces (BCIs). Its clinical applicability, however, is limited by the inherent non-stationarity of neural signals, which causes domain shifts between training and testing, undermining decoding reliability. To address this challenge, a two-stage framework is proposed for enhanced robustness. First, a multi-scale decomposable mixing (MDM) module is introduced to model the …

[2025-08-06 Wed (UTC), no new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data
Chu-Cheng Lin, Daiyi Peng, Yifeng Lu, Ming Zhang, Eugene Ie
https://arxiv.org/abs/2508.18244 https…

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data
Reliably composing Large Language Models (LLMs) for complex, multi-step workflows remains a significant challenge. The dominant paradigm-optimizing discrete prompts in a pipeline-is notoriously brittle and struggles to enforce the formal compliance required for structured tasks. We introduce Type-Compliant Adaptation Cascades (TACs), a framework that recasts workflow adaptation as learning typed probabilistic programs. TACs treats the entire workflow, which is composed of parameter-efficiently …

MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
Maisha Maliha, Dean Hougen
https://arxiv.org/abs/2510.00274 ht…

MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
Understanding the decision-making process of Deep Reinforcement Learning agents remains a key challenge for deploying these systems in safety-critical and multi-agent environments. While prior explainability methods like StateMask, have advanced the identification of critical states, they remain limited by computational cost, exploration coverage, and lack of adaptation to multi-agent settings. To overcome these limitations, we propose a mathematically grounded framework, MAGIC-MASK (Multi-Agen…

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…

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
Ryan Punamiya, Dhruv Patel, Patcharapong Aphiwetsa, Pranav Kuppili, Lawrence Y. Zhu, Simar Kareer, Judy Hoffman, Danfei Xu
https://arxiv.org/abs/2509.19626

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
Egocentric human experience data presents a vast resource for scaling up end-to-end imitation learning for robotic manipulation. However, significant domain gaps in visual appearance, sensor modalities, and kinematics between human and robot impede knowledge transfer. This paper presents EgoBridge, a unified co-training framework that explicitly aligns the policy latent spaces between human and robot data using domain adaptation. Through a measure of discrepancy on the joint policy latent featu…

[2025-09-05 Fri (UTC), no new articles found for nlin.AO Adaptation and Self-Organizing Systems]
toXiv_bot_toot

Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation
Matteo Cardoni, Sam Leroux
https://arxiv.org/abs/2509.20269 https://

Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation
As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate continual model adaptation. In this paper, we propose a hybrid training methodology that enables efficient on-device domain adaptation by combining the strengths of Backpropagation and Predictive Coding. The method begins with a deep neural network trained offli…

Domain Adaptation via Feature Refinement
Savvas Karatsiolis, Andreas Kamilaris
https://arxiv.org/abs/2508.16124 https://arxiv.org/pdf/2508.16124

Domain Adaptation via Feature Refinement
We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer. By aligning feature distributions at the statistical and representational levels, DAFR2 produces robust and domain-invariant feat…

Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
Jiahe Pan, Jiaxu Xing, Rudolf Reiter, Yifan Zhai, Elie Aljalbout, Davide Scaramuzza
https://arxiv.org/abs/2508.21065

Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
Learning control policies in simulation enables rapid, safe, and cost-effective development of advanced robotic capabilities. However, transferring these policies to the real world remains difficult due to the sim-to-real gap, where unmodeled dynamics and environmental disturbances can degrade policy performance. Existing approaches, such as domain randomization and Real2Sim2Real pipelines, can improve policy robustness, but either struggle under out-of-distribution conditions or require costly…

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning
Benedikt Roth, Stephan Rappensperger, Tianming Qiu, Hamza Imamovi\'c, Julian W\"ormann, Hao Shen
https://arxiv.org/abs/2507.22729

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning
Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling these vectors into a text embedding discards crucial information. Nevertheless, many non-generative downstream tasks, such as clustering, classification, or retrieval, still depend on accurate and controllable sentence- or document-level embeddings. We explore se…

Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation
Guangyu Sun, Jingtao Li, Weiming Zhuang, Chen Chen, Chen Chen, Lingjuan Lyu
https://arxiv.org/abs/2508.16568

Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation
Foundation models (FMs) exhibit remarkable generalization but require adaptation to downstream tasks, particularly in privacy-sensitive applications. Due to data privacy regulations, cloud-based FMs cannot directly access private edge data, limiting their adaptation. Federated learning (FL) provides a privacy-aware alternative, but existing FL approaches overlook the constraints imposed by edge devices -- namely, limited computational resources and the scarcity of labeled data. To address these…

MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
Francisco Caetano, Christiaan Viviers, Peter H. H. de With, Fons van der Sommen
https://arxiv.org/abs/2508.21435

MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation
Synthetic medical data offers a scalable solution for training robust models, but significant domain gaps limit its generalizability to real-world clinical settings. This paper addresses the challenge of cross-domain translation between synthetic and real X-ray images of the head, focusing on bridging discrepancies in attenuation behavior, noise characteristics, and soft tissue representation. We propose MedShift, a unified class-conditional generative model based on Flow Matching and Schroding…

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
Yongqi Huang, Jitao Zhao, Dongxiao He, Xiaobao Wang, Yawen Li, Yuxiao Huang, Di Jin, Zhiyong Feng
https://arxiv.org/abs/2509.22416 …

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
Graph Prompt Learning (GPL) has emerged as a promising paradigm that bridges graph pretraining models and downstream scenarios, mitigating label dependency and the misalignment between upstream pretraining and downstream tasks. Although existing GPL studies explore various prompt strategies, their effectiveness and underlying principles remain unclear. We identify two critical limitations: (1) Lack of consensus on underlying mechanisms: Despite current GPLs have advanced the field, there is no …

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/4]:
- SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
Christoph Timmermann, Hyunse Lee, Woojin Lee

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Neeraj Gangwar, Anshuka Rangi, Rishabh Deshmukh, Holakou Rahmanian, Yesh Dattatreya, Nickvash Kani
https://arxiv.org/abs/2509.19602

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning exacerbates common challenges, such as task interference and negative transfer, due to the limited number of trainable parameters. To address these issues, we introduce progressive task-specific multi-task adaptation, a novel parameter-efficient approach for multi-…

SmaRT: Style-Modulated Robust Test-Time Adaptation for Cross-Domain Brain Tumor Segmentation in MRI
Yuanhan Wang, Yifei Chen, Shuo Jiang, Wenjing Yu, Mingxuan Liu, Beining Wu, Jinying Zong, Feiwei Qin, Changmiao Wang, Qiyuan Tian
https://arxiv.org/abs/2509.17925

SmaRT: Style-Modulated Robust Test-Time Adaptation for Cross-Domain Brain Tumor Segmentation in MRI
Reliable brain tumor segmentation in MRI is indispensable for treatment planning and outcome monitoring, yet models trained on curated benchmarks often fail under domain shifts arising from scanner and protocol variability as well as population heterogeneity. Such gaps are especially severe in low-resource and pediatric cohorts, where conventional test-time or source-free adaptation strategies often suffer from instability and structural inconsistency. We propose SmaRT, a style-modulated robust…

Lost in Translation? Vocabulary Alignment for Source-Free Domain Adaptation in Open-Vocabulary Semantic Segmentation
Silvio Mazzucco, Carl Persson, Mattia Segu, Pier Luigi Dovesi, Federico Tombari, Luc Van Gool, Matteo Poggi
https://arxiv.org/abs/2509.15225

Lost in Translation? Vocabulary Alignment for Source-Free Domain Adaptation in Open-Vocabulary Semantic Segmentation
We introduce VocAlign, a novel source-free domain adaptation framework specifically designed for VLMs in open-vocabulary semantic segmentation. Our method adopts a student-teacher paradigm enhanced with a vocabulary alignment strategy, which improves pseudo-label generation by incorporating additional class concepts. To ensure efficiency, we use Low-Rank Adaptation (LoRA) to fine-tune the model, preserving its original capabilities while minimizing computational overhead. In addition, we propos…