# Research Papers — 2025-10 · bundle page 197 of 217

> Full-text markdown of papers #9801–9850 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/197
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/196.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/198.md)

### Gradient-enhanced global sensitivity analysis with Poincar{é} chaos expansions

Authors: O Roustant, N Lüthen, David Heredia, B Sudret
Published: 2025-10-03
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.03056v2

Spectral methods, also known as chaos expansions, are widely used in global sensitivity analysis (GSA), as they leverage orthogonal bases of L2 spaces to efficiently compute Sobol' indices, particularly in data-scarce settings. When derivatives of the model are available, a desirable property, both for modeling and GSA purposes, is for the derivatives of the basis functions to also form an orthogonal basis. We demonstrate that the only basis satisfying this property is the one associated with weighted Poincar{é} inequalities and Sturm--Liouville eigenvalue problems, which we call Poincar{é} basis. We also show that under certain conditions the Poincar{é} basis achieves the same convergence rate as the best polynomial approximation for classes of smooth functions. We then introduce a comprehensive framework for gradient-enhanced GSA that integrates recent advances both in the construction of the expansion - with gradient-enhanced regression - and in the construction of weights for derivative-based sensitivity analysis. Furthermore, the proposed methodology is applicable to a broad class of probability measures and various choices of weights. We illustrate its efficiency on a challenging flood modeling case study, where Sobol' indices are accurately estimated using limited data.

---

### ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization

Authors: Jamison Meindl, Yunsheng Tian, Tony Cui, Veronika Thost, Zhang-Wei Hong, Johannes Dürholt, Jie Chen, Wojciech Matusik, Mina Konaković Luković
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03051v1

Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function hyper-parameters that are often hand-tuned and fail to generalize across problem landscapes. We present ZeroShotOpt, a general-purpose, pretrained model for continuous black-box optimization tasks ranging from 2D to 20D. Our approach leverages offline reinforcement learning on large-scale optimization trajectories collected from 12 BO variants. To scale pretraining, we generate millions of synthetic Gaussian process-based functions with diverse landscapes, enabling the model to learn transferable optimization policies. As a result, ZeroShotOpt achieves robust zero-shot generalization on a wide array of unseen benchmarks, matching or surpassing the sample efficiency of leading global optimizers, including BO, while also offering a reusable foundation for future extensions and improvements. Our open-source code, dataset, and model are available at: https://github.com/jamisonmeindl/zeroshotopt

---

### When and Where do Events Switch in Multi-Event Video Generation?

Authors: Ruotong Liao, Guowen Huang, Qing Cheng, Thomas Seidl, Daniel Cremers, Volker Tresp
Published: 2025-10-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03049v1

Text-to-video (T2V) generation has surged in response to challenging questions, especially when a long video must depict multiple sequential events with temporal coherence and controllable content. Existing methods that extend to multi-event generation omit an inspection of the intrinsic factor in event shifting. The paper aims to answer the central question: When and where multi-event prompts control event transition during T2V generation. This work introduces MEve, a self-curated prompt suite for evaluating multi-event text-to-video (T2V) generation, and conducts a systematic study of two representative model families, i.e., OpenSora and CogVideoX. Extensive experiments demonstrate the importance of early intervention in denoising steps and block-wise model layers, revealing the essential factor for multi-event video generation and highlighting the possibilities for multi-event conditioning in future models.

---

### Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing

Authors: Soohaeng Yoo Willow, Tae Hyeon Park, Gi Beom Sim, Sung Wook Moon, Seung Kyu Min, D. ChangMo Yang, Hyun Woo Kim, Juho Lee, Chang Woo Myung
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03046v2

Machine learning potentials (MLPs) have become essential for large-scale atomistic simulations, enabling ab initio-level accuracy with computational efficiency. However, current MLPs struggle with uncertainty quantification, limiting their reliability for active learning, calibration, and out-of-distribution (OOD) detection. We address these challenges by developing Bayesian E(3) equivariant MLPs with iterative restratification of many-body message passing. Our approach introduces the joint energy-force negative log-likelihood (NLL$_\text{JEF}$) loss function, which explicitly models uncertainty in both energies and interatomic forces, yielding substantially improved accuracy compared to conventional NLL losses. We systematically benchmark multiple Bayesian approaches, including deep ensembles with mean-variance estimation, stochastic weight averaging Gaussian, improved variational online Newton, and Laplace approximation by evaluating their performance on uncertainty prediction, OOD detection, calibration, and active learning tasks. We further demonstrate that NLL$_\text{JEF}$ facilitates efficient active learning by quantifying energy and force uncertainties. Using Bayesian active learning by disagreement (BALD), our framework outperforms random sampling and energy-uncertainty-based sampling. Our results demonstrate that Bayesian MLPs achieve competitive accuracy with state-of-the-art models while enabling uncertainty-guided active learning, OOD detection, and energy/forces calibration. This work establishes Bayesian equivariant neural networks as a powerful framework for developing uncertainty-aware MLPs for atomistic simulations at scale.

---

### CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration

Authors: Tianqi Liu, Kairui Fu, Shengyu Zhang, Wenyan Fan, Zhaocheng Du, Jieming Zhu, Fan Wu, Fei Wu
Published: 2025-10-03
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.03038v1

With the advancement of mobile device capabilities, deploying reranking models directly on devices has become feasible, enabling real-time contextual recommendations. When migrating models from cloud to devices, resource heterogeneity inevitably necessitates model compression. Recent quantization methods show promise for efficient deployment, yet they overlook device-specific user interests, resulting in compromised recommendation accuracy. While on-device finetuning captures personalized user preference, it imposes additional computational burden through local retraining. To address these challenges, we propose a framework for \underline{\textbf{C}}ustomizing \underline{\textbf{H}}ybrid-precision \underline{\textbf{O}}n-device model for sequential \underline{\textbf{R}}ecommendation with \underline{\textbf{D}}evice-cloud collaboration (\textbf{CHORD}), leveraging channel-wise mixed-precision quantization to simultaneously achieve personalization and resource-adaptive deployment. CHORD distributes randomly initialized models across heterogeneous devices and identifies user-specific critical parameters through auxiliary hypernetwork modules on the cloud. Our parameter sensitivity analysis operates across multiple granularities (layer, filter, and element levels), enabling precise mapping from user profiles to quantization strategy. Through on-device mixed-precision quantization, CHORD delivers dynamic model adaptation and accelerated inference without backpropagation, eliminating costly retraining cycles. We minimize communication overhead by encoding quantization strategies using only 2 bits per channel instead of 32-bit weights. Experiments on three real-world datasets with two popular backbones (SASRec and Caser) demonstrate the accuracy, efficiency, and adaptivity of CHORD.

---

### Investigating The Smells of LLM Generated Code

Authors: Debalina Ghosh Paul, Hong Zhu, Ian Bayley
Published: 2025-10-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.03029v2

Context: Large Language Models (LLMs) are increasingly being used to generate program code. Much research has been reported on the functional correctness of generated code, but there is far less on code quality. Objectives: In this study, we propose a scenario-based method of evaluating the quality of LLM-generated code to identify the weakest scenarios, for which the quality of LLM-generated code should be improved. Methods: The method measures code smells, an important indicator of code quality, and compares them with a baseline formed from reference solutions of professionally written code. The test dataset is divided into various subsets according to the topics of the code and complexity of the coding tasks to represent different scenarios of using LLMs for code generation. We will also present an automated test system for this purpose and report experiments with the Java programs generated in response to prompts given to four state-of-the-art LLMs: Gemini Pro, ChatGPT, Codex, and Falcon. Results: We find that LLM-generated code has a higher incidence of code smells compared to reference solutions. Falcon performed the least badly, with a smell increase of 42.28%, followed by Gemini Pro (62.07%), ChatGPT (65.05%) and finally Codex (84.97%). The average smell increase across all LLMs was 63.34%, comprising 73.35% for implementation smells and 21.42% for design smells. We also found that the increase in code smells is greater for more complex coding tasks and for more advanced topics, such as those involving object-orientated concepts. Conclusion: In terms of code smells, LLMs' performances on various coding task complexities and topics are highly correlated to the quality of human-written code in the corresponding scenarios. However, the quality of LLM-generated code is noticeably poorer than human-written code.

---

### Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

Authors: Junyi Yao, Parham Eftekhar, Gene Cheung, Xujin Chris Liu, Yao Wang, Wei Hu
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03027v4

Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph -- graph with no cycles of odd number of negative edges. A balanced signed graph has well-defined frequencies that map to a corresponding positive graph via similarity transform of the graph Laplacian matrices. We implement an ideal low-pass filter efficiently on the mapped positive graph via Lanczos approximation, where the optimal cutoff frequency is learned from data. Given that two balanced signed graph denoisers learn posterior probabilities of two different signal classes during training, we evaluate their reconstruction errors for binary classification of EEG signals. Experiments show that our method achieves classification performance comparable to representative deep learning schemes, while employing dramatically fewer parameters.

---

### Differentially Private Wasserstein Barycenters

Authors: Anming Gu, Sasidhar Kunapuli, Mark Bun, Edward Chien, Kristjan Greenewald
Published: 2025-10-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03021v1

The Wasserstein barycenter is defined as the mean of a set of probability measures under the optimal transport metric, and has numerous applications spanning machine learning, statistics, and computer graphics. In practice these input measures are empirical distributions built from sensitive datasets, motivating a differentially private (DP) treatment. We present, to our knowledge, the first algorithms for computing Wasserstein barycenters under differential privacy. Empirically, on synthetic data, MNIST, and large-scale U.S. population datasets, our methods produce high-quality private barycenters with strong accuracy-privacy tradeoffs.

---

### Learning Robust Diffusion Models from Imprecise Supervision

Authors: Dong-Dong Wu, Jiacheng Cui, Wei Wang, Zhiqiang Shen, Masashi Sugiyama
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03016v2

Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such supervision, often stemming from noisy, ambiguous, or incomplete labels, will cause condition mismatch and degrade generation quality. To address this challenge, we propose DMIS, a unified framework for training robust Diffusion Models from Imprecise Supervision, which is the first systematic study within diffusion models. Our framework is derived from likelihood maximization and decomposes the objective into generative and classification components: the generative component models imprecise-label distributions, while the classification component leverages a diffusion classifier to infer class-posterior probabilities, with its efficiency further improved by an optimized timestep sampling strategy. Extensive experiments on diverse forms of imprecise supervision, covering tasks of image generation, weakly supervised learning, and noisy dataset condensation demonstrate that DMIS consistently produces high-quality and class-discriminative samples.

---

### Distributional Inverse Reinforcement Learning

Authors: Feiyang Wu, Ye Zhao, Anqi Wu
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03013v4

We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic reward estimate or match only expected returns, our method captures richer structure in expert behavior, particularly in learning the reward distribution, by minimizing first-order stochastic dominance (FSD) violations and thus integrating distortion risk measures (DRMs) into policy learning, enabling the recovery of both reward distributions and distribution-aware policies. This formulation is well-suited for behavior analysis and risk-aware imitation learning. Theoretical analysis shows that the algorithm converges with $\mathcal{O}(\varepsilon^{-2})$ iteration complexity. Empirical results on synthetic benchmarks, real-world neurobehavioral data, and MuJoCo control tasks demonstrate that our method recovers expressive reward representations and achieves state-of-the-art performance.

---

### PocketSR: The Super-Resolution Expert in Your Pocket Mobiles

Authors: Haoze Sun, Linfeng Jiang, Fan Li, Renjing Pei, Zhixin Wang, Yong Guo, Jiaqi Xu, Haoyu Chen, Jin Han, Fenglong Song, Yujiu Yang, Wenbo Li
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03012v1

Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, we design LiteED, a highly efficient alternative to the original computationally intensive VAE in SD, reducing parameters by 97.5% while preserving high-quality encoding and decoding. Additionally, we propose online annealing pruning for the U-Net, which progressively shifts generative priors from heavy modules to lightweight counterparts, ensuring effective knowledge transfer and further optimizing efficiency. To mitigate the loss of prior knowledge during pruning, we incorporate a multi-layer feature distillation loss. Through an in-depth analysis of each design component, we provide valuable insights for future research. PocketSR, with a model size of 146M parameters, processes 4K images in just 0.8 seconds, achieving a remarkable speedup over previous methods. Notably, it delivers performance on par with state-of-the-art single-step and even multi-step RealSR models, making it a highly practical solution for edge-device applications.

---

### Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources

Authors: Sara Mobsite, Renaud Hostache, Laure Berti Equille, Emmanuel Roux, Joris Guerin
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03006v1

Supervised deep learning for land cover semantic segmentation (LCS) relies on labeled satellite data. However, most existing Sentinel-2 datasets are cloud-free, which limits their usefulness in tropical regions where clouds are common. To properly evaluate the extent of this problem, we developed a cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar data can fill in the gaps caused by cloud-obstructed optical imagery. We also tackle the issue of losing spatial and/or spectral details during encoder downsampling in deep networks. To mitigate this loss, we propose a lightweight method that injects Normalized Difference Indices (NDIs) into the final decoding layers, enabling the model to retain key spatial features with minimal additional computation. Injecting NDIs enhanced land cover segmentation performance on the DFC2020 dataset, yielding improvements of 1.99% for U-Net and 2.78% for DeepLabV3 on cloud-free imagery. Under cloud-covered conditions, incorporating Sentinel-1 data led to significant performance gains across all models compared to using optical data alone, highlighting the effectiveness of radar-optical fusion in challenging atmospheric scenarios.

---

### BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia

Authors: Tianzheng Hu, Qiang Li, Shu Liu, Vince D. Calhoun, Guido van Wingen, Shujian Yu
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03004v1

The development of diagnostic models is gaining traction in the field of psychiatric disorders. Recently, machine learning classifiers based on resting-state functional magnetic resonance imaging (rs-fMRI) have been developed to identify brain biomarkers that differentiate psychiatric disorders from healthy controls. However, conventional machine learning-based diagnostic models often depend on extensive feature engineering, which introduces bias through manual intervention. While deep learning models are expected to operate without manual involvement, their lack of interpretability poses significant challenges in obtaining explainable and reliable brain biomarkers to support diagnostic decisions, ultimately limiting their clinical applicability. In this study, we introduce an end-to-end innovative graph neural network framework named BrainIB++, which applies the information bottleneck (IB) principle to identify the most informative data-driven brain regions as subgraphs during model training for interpretation. We evaluate the performance of our model against nine established brain network classification methods across three multi-cohort schizophrenia datasets. It consistently demonstrates superior diagnostic accuracy and exhibits generalizability to unseen data. Furthermore, the subgraphs identified by our model also correspond with established clinical biomarkers in schizophrenia, particularly emphasizing abnormalities in the visual, sensorimotor, and higher cognition brain functional network. This alignment enhances the model's interpretability and underscores its relevance for real-world diagnostic applications.

---

### From high-frequency sensors to noon reports: Using transfer learning for shaft power prediction in maritime

Authors: Akriti Sharma, Dogan Altan, Dusica Marijan, Arnbjørn Maressa
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03003v1

With the growth of global maritime transportation, energy optimization has become crucial for reducing costs and ensuring operational efficiency. Shaft power is the mechanical power transmitted from the engine to the shaft and directly impacts fuel consumption, making its accurate prediction a paramount step in optimizing vessel performance. Power consumption is highly correlated with ship parameters such as speed and shaft rotation per minute, as well as weather and sea conditions. Frequent access to this operational data can improve prediction accuracy. However, obtaining high-quality sensor data is often infeasible and costly, making alternative sources such as noon reports a viable option. In this paper, we propose a transfer learning-based approach for predicting vessels shaft power, where a model is initially trained on high-frequency data from a vessel and then fine-tuned with low-frequency daily noon reports from other vessels. We tested our approach on sister vessels (identical dimensions and configurations), a similar vessel (slightly larger with a different engine), and a different vessel (distinct dimensions and configurations). The experiments showed that the mean absolute percentage error decreased by 10.6 percent for sister vessels, 3.6 percent for a similar vessel, and 5.3 percent for a different vessel, compared to the model trained solely on noon report data.

---

### NonTextual Target Attack

Authors: Xinzhe Huang, Wenjing Hu, Kedong Xiu, Hongsheng Hu, Xiaojun Jia, Zhan Qin, Tianhang Zheng
Published: 2025-10-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.02999v6

Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However, restricting the objective as inducing fixed targets inherently constrains the adversarial search space, limiting the overall attack efficacy. Furthermore, existing methods typically require numerous optimization iterations to fulfill the large gap between the fixed target and the original LLM output, resulting in low attack efficiency. To overcome these limitations, we propose NonTextual Target Attack (NTA),the first gradient-based attack that relies on a non-textual constrained objective to maximize the unsafety probability of the LLM output, without enforcing any response patterns. For tractable optimization, we further decompose this objective into two constrained sub-objectives, which can be approximated by two differentiable unconstrained losses, to iteratively optimize the response and the adversarial prompt in the neighborhood of the original prompt, with a theoretical analysis to validate the decomposition. In contrast to existing attacks, NTA first realizes gradient-based prompt optimization on a non-textual target and significantly expands the attack space, enabling more flexible and efficient exploration of LLM vulnerabilities. Extensive evaluations show that NTA achieves an average attack success rate of 96.8% against recent safety-aligned LLMs with only 100 optimization iterations on AdvBench, outperforming state-of-the-art gradient-based attacks by over 40%.

---

### Onto-Epistemological Analysis of AI Explanations

Authors: Martina Mattioli, Eike Petersen, Aasa Feragen, Marcello Pelillo, Siavash A. Bigdeli
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.02996v1

Artificial intelligence (AI) is being applied in almost every field. At the same time, the currently dominant deep learning methods are fundamentally black-box systems that lack explanations for their inferences, significantly limiting their trustworthiness and adoption. Explainable AI (XAI) methods aim to overcome this challenge by providing explanations of the models' decision process. Such methods are often proposed and developed by engineers and scientists with a predominantly technical background and incorporate their assumptions about the existence, validity, and explanatory utility of different conceivable explanatory mechanisms. However, the basic concept of an explanation -- what it is, whether we can know it, whether it is absolute or relative -- is far from trivial and has been the subject of deep philosophical debate for millennia. As we point out here, the assumptions incorporated into different XAI methods are not harmless and have important consequences for the validity and interpretation of AI explanations in different domains. We investigate ontological and epistemological assumptions in explainability methods when they are applied to AI systems, meaning the assumptions we make about the existence of explanations and our ability to gain knowledge about those explanations. Our analysis shows how seemingly small technical changes to an XAI method may correspond to important differences in the underlying assumptions about explanations. We furthermore highlight the risks of ignoring the underlying onto-epistemological paradigm when choosing an XAI method for a given application, and we discuss how to select and adapt appropriate XAI methods for different domains of application.

---

### Towards Scalable and Consistent 3D Editing

Authors: Ruihao Xia, Yang Tang, Pan Zhou
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02994v1

3D editing - the task of locally modifying the geometry or appearance of a 3D asset - has wide applications in immersive content creation, digital entertainment, and AR/VR. However, unlike 2D editing, it remains challenging due to the need for cross-view consistency, structural fidelity, and fine-grained controllability. Existing approaches are often slow, prone to geometric distortions, or dependent on manual and accurate 3D masks that are error-prone and impractical. To address these challenges, we advance both the data and model fronts. On the data side, we introduce 3DEditVerse, the largest paired 3D editing benchmark to date, comprising 116,309 high-quality training pairs and 1,500 curated test pairs. Built through complementary pipelines of pose-driven geometric edits and foundation model-guided appearance edits, 3DEditVerse ensures edit locality, multi-view consistency, and semantic alignment. On the model side, we propose 3DEditFormer, a 3D-structure-preserving conditional transformer. By enhancing image-to-3D generation with dual-guidance attention and time-adaptive gating, 3DEditFormer disentangles editable regions from preserved structure, enabling precise and consistent edits without requiring auxiliary 3D masks. Extensive experiments demonstrate that our framework outperforms state-of-the-art baselines both quantitatively and qualitatively, establishing a new standard for practical and scalable 3D editing. Dataset and code will be released. Project: https://www.lv-lab.org/3DEditFormer/

---

### TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency

Authors: Juntong Wang, Huiyu Duan, Jiarui Wang, Ziheng Jia, Guangtao Zhai, Xiongkuo Min
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02987v1

With the rapid advancement of large multimodal models (LMMs), recent text-to-image (T2I) models can generate high-quality images and demonstrate great alignment to short prompts. However, they still struggle to effectively understand and follow long and detailed prompts, displaying inconsistent generation. To address this challenge, we introduce LPG-Bench, a comprehensive benchmark for evaluating long-prompt-based text-to-image generation. LPG-Bench features 200 meticulously crafted prompts with an average length of over 250 words, approaching the input capacity of several leading commercial models. Using these prompts, we generate 2,600 images from 13 state-of-the-art models and further perform comprehensive human-ranked annotations. Based on LPG-Bench, we observe that state-of-the-art T2I alignment evaluation metrics exhibit poor consistency with human preferences on long-prompt-based image generation. To address the gap, we introduce a novel zero-shot metric based on text-to-image-to-text consistency, termed TIT, for evaluating long-prompt-generated images. The core concept of TIT is to quantify T2I alignment by directly comparing the consistency between the raw prompt and the LMM-produced description on the generated image, which includes an efficient score-based instantiation TIT-Score and a large-language-model (LLM) based instantiation TIT-Score-LLM. Extensive experiments demonstrate that our framework achieves superior alignment with human judgment compared to CLIP-score, LMM-score, etc., with TIT-Score-LLM attaining a 7.31% absolute improvement in pairwise accuracy over the strongest baseline. LPG-Bench and TIT methods together offer a deeper perspective to benchmark and foster the development of T2I models. All resources will be made publicly available.

---

### FR-LUX: Friction-Aware, Regime-Conditioned Policy Optimization for Implementable Portfolio Management

Authors: Jian'an Zhang
Published: 2025-10-03
Categories: q-fin.TR, cs.LG
arXiv: https://arxiv.org/abs/2510.02986v1

Transaction costs and regime shifts are major reasons why paper portfolios fail in live trading. We introduce FR-LUX (Friction-aware, Regime-conditioned Learning under eXecution costs), a reinforcement learning framework that learns after-cost trading policies and remains robust across volatility-liquidity regimes. FR-LUX integrates three ingredients: (i) a microstructure-consistent execution model combining proportional and impact costs, directly embedded in the reward; (ii) a trade-space trust region that constrains changes in inventory flow rather than logits, yielding stable low-turnover updates; and (iii) explicit regime conditioning so the policy specializes to LL/LH/HL/HH states without fragmenting the data. On a 4 x 5 grid of regimes and cost levels with multiple random seeds, FR-LUX achieves the top average Sharpe ratio with narrow bootstrap confidence intervals, maintains a flatter cost-performance slope than strong baselines, and attains superior risk-return efficiency for a given turnover budget. Pairwise scenario-level improvements are strictly positive and remain statistically significant after multiple-testing corrections. We provide formal guarantees on optimality under convex frictions, monotonic improvement under a KL trust region, long-run turnover bounds and induced inaction bands due to proportional costs, positive value advantage for regime-conditioned policies, and robustness to cost misspecification. The methodology is implementable: costs are calibrated from standard liquidity proxies, scenario-level inference avoids pseudo-replication, and all figures and tables are reproducible from released artifacts.

---

### Oracle-based Uniform Sampling from Convex Bodies

Authors: Thanh Dang, Jiaming Liang
Published: 2025-10-03
Categories: cs.DS, cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2510.02983v2

We propose new Markov chain Monte Carlo algorithms to sample a uniform distribution on a convex body $K$. Our algorithms are based on the proximal sampler, which uses Gibbs sampling on an augmented distribution and assumes access to the so-called restricted Gaussian oracle (RGO). The key contribution of this work is an efficient implementation of the RGO for uniform sampling on convex $K$ that goes beyond the membership-oracle model used in many classical and modern uniform samplers, and instead leverages richer oracle access commonly assumed in convex optimization. We implement the RGO via rejection sampling and access to either a projection oracle or a separation oracle on $K$. In both oracle models, we provide non-asymptotic complexity guarantees for obtaining unbiased samples, with accuracy quantified in Rényi divergence and $χ^2$-divergence, and we support these theoretical guarantees with numerical experiments.

---

### oRANS: Online optimisation of RANS machine learning models with embedded DNS data generation

Authors: Daniel Dehtyriov, Jonathan F. MacArt, Justin Sirignano
Published: 2025-10-03
Categories: physics.flu-dyn, cs.LG
arXiv: https://arxiv.org/abs/2510.02982v1

Deep learning (DL) has demonstrated promise for accelerating and enhancing the accuracy of flow physics simulations, but progress is constrained by the scarcity of high-fidelity training data, which is costly to generate and inherently limited to a small set of flow conditions. Consequently, closures trained in the conventional offline paradigm tend to overfit and fail to generalise to new regimes. We introduce an online optimisation framework for DL-based Reynolds-averaged Navier--Stokes (RANS) closures which seeks to address the challenge of limited high-fidelity datasets. Training data is dynamically generated by embedding a direct numerical simulation (DNS) within a subdomain of the RANS domain. The RANS solution supplies boundary conditions to the DNS, while the DNS provides mean velocity and turbulence statistics that are used to update a DL closure model during the simulation. This feedback loop enables the closure to adapt to the embedded DNS target flow, avoiding reliance on precomputed datasets and improving out-of-distribution performance. The approach is demonstrated for the stochastically forced Burgers equation and for turbulent channel flow at $Re_τ=180$, $270$, $395$ and $590$ with varying embedded domain lengths $1\leq L_0/L\leq 8$. Online-optimised RANS models significantly outperform both offline-trained and literature-calibrated closures, with accurate training achieved using modest DNS subdomains. Performance degrades primarily when boundary-condition contamination dominates or when domains are too short to capture low-wavenumber modes. This framework provides a scalable route to physics-informed machine learning closures, enabling data-adaptive reduced-order models that generalise across flow regimes without requiring large precomputed training datasets.

---

### AI Generated Child Sexual Abuse Material -- What's the Harm?

Authors: Caoilte Ó Ciardha, John Buckley, Rebecca S. Portnoff
Published: 2025-10-03
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.02978v1

The development of generative artificial intelligence (AI) tools capable of producing wholly or partially synthetic child sexual abuse material (AI CSAM) presents profound challenges for child protection, law enforcement, and societal responses to child exploitation. While some argue that the harmfulness of AI CSAM differs fundamentally from other CSAM due to a perceived absence of direct victimization, this perspective fails to account for the range of risks associated with its production and consumption. AI has been implicated in the creation of synthetic CSAM of children who have not previously been abused, the revictimization of known survivors of abuse, the facilitation of grooming, coercion and sexual extortion, and the normalization of child sexual exploitation. Additionally, AI CSAM may serve as a new or enhanced pathway into offending by lowering barriers to engagement, desensitizing users to progressively extreme content, and undermining protective factors for individuals with a sexual interest in children. This paper provides a primer on some key technologies, critically examines the harms associated with AI CSAM, and cautions against claims that it may function as a harm reduction tool, emphasizing how some appeals to harmlessness obscure its real risks and may contribute to inertia in ecosystem responses.

---

### Corrosion Risk Estimation for Heritage Preservation: An Internet of Things and Machine Learning Approach Using Temperature and Humidity

Authors: Reginald Juan M. Mercado, Muhammad Kabeer, Haider Al-Obaidy, Rosdiadee Nordin
Published: 2025-10-03
Categories: cs.CY, cs.AI, cs.NI, eess.SY
arXiv: https://arxiv.org/abs/2510.02973v1

Proactive preservation of steel structures at culturally significant heritage sites like the San Sebastian Basilica in the Philippines requires accurate corrosion forecasting. This study developed an Internet of Things hardware system connected with LoRa wireless communications to monitor heritage buildings with steel structures. From a three year dataset generated by the IoT system, we built a machine learning framework for predicting atmospheric corrosion rates using only temperature and relative humidity data. Deployed via a Streamlit dashboard with ngrok tunneling for public access, the framework provides real-time corrosion monitoring and actionable preservation recommendations. This minimal-data approach is scalable and cost effective for heritage sites with limited monitoring resources, showing that advanced regression can extract accurate corrosion predictions from basic meteorological data enabling proactive preservation of culturally significant structures worldwide without requiring extensive sensor networks

---

### Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis

Authors: Xiaoyan Kui, Qianmu Xiao, Qqinsong Li, Zexin Ji, JIelin Zhang, Beiji Zou
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02970v1

Separating shared and independent features is crucial for multi-phase contrast-enhanced (CE) MRI synthesis. However, existing methods use deep autoencoder generators with low parameter efficiency and lack interpretable training strategies. In this paper, we propose Flip Distribution Alignment Variational Autoencoder (FDA-VAE), a lightweight feature-decoupled VAE model for multi-phase CE MRI synthesis. Our method encodes input and target images into two latent distributions that are symmetric concerning a standard normal distribution, effectively separating shared and independent features. The Y-shaped bidirectional training strategy further enhances the interpretability of feature separation. Experimental results show that compared to existing deep autoencoder-based end-to-end synthesis methods, FDA-VAE significantly reduces model parameters and inference time while effectively improving synthesis quality. The source code is publicly available at https://github.com/QianMuXiao/FDA-VAE.

---

### Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelines

Authors: Matthew Lewis, Samuel Thio, Amy Roberts, Catherine Siju, Whoasif Mukit, Rebecca Kuruvilla, Zhangshu Joshua Jiang, Niko Möller-Grell, Aditya Borakati, Richard JB Dobson, Spiros Denaxas
Published: 2025-10-03
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.02967v3

This paper presents the development and evaluation of a Retrieval-Augmented Generation (RAG) system for querying the United Kingdom's National Institute for Health and Care Excellence (NICE) clinical guidelines using Large Language Models (LLMs). The extensive length and volume of these guidelines can impede their utilisation within a time-constrained healthcare system, a challenge this project addresses through the creation of a system capable of providing users with precisely matched information in response to natural language queries. The system's retrieval architecture, composed of a hybrid embedding mechanism, was evaluated against a corpus of 10,195 text chunks derived from three hundred guidelines. It demonstrates high performance, with a Mean Reciprocal Rank (MRR) of 0.814, a Recall of 81% at the first chunk and of 99.1% within the top ten retrieved chunks, when evaluated on 7901 queries. The most significant impact of the RAG system was observed during the generation phase. When evaluated on a manually curated dataset of seventy question-answer pairs, RAG-enhanced models showed substantial gains in performance. Faithfulness, the measure of whether an answer is supported by the source text, was increased by 64.7 percentage points to 99.5% for the RAG-enhanced O4-Mini model and significantly outperformed the medical-focused Meditron3-8B LLM, which scored 43%. Clinical evaluation by seven Subject Matter Experts (SMEs) further validated these findings, with GPT-4.1 achieving 98.7% accuracy while reducing unsafe responses by 67% compared to O4-Mini (from 3.0 to 1.0 per evaluator). This study thus establishes RAG as an effective, reliable, and scalable approach for applying generative AI in healthcare, enabling cost-effective access to medical guidelines.

---

### Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking

Authors: Jingqi Zhang, Ruibo Chen, Yingqing Yang, Peihua Mai, Heng Huang, Yan Pang
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.02962v1

Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards against unauthorized use. Existing membership inference attacks (MIAs) and dataset-inference methods typically require access to internal signals such as logits, while current black-box approaches often rely on handcrafted prompts or a clean reference dataset for calibration, both of which limit practical applicability. Watermarking is a promising alternative, but prior techniques can degrade text quality or reduce task performance. We propose TRACE, a practical framework for fully black-box detection of copyrighted dataset usage in LLM fine-tuning. \texttt{TRACE} rewrites datasets with distortion-free watermarks guided by a private key, ensuring both text quality and downstream utility. At detection time, we exploit the radioactivity effect of fine-tuning on watermarked data and introduce an entropy-gated procedure that selectively scores high-uncertainty tokens, substantially amplifying detection power. Across diverse datasets and model families, TRACE consistently achieves significant detections (p<0.05), often with extremely strong statistical evidence. Furthermore, it supports multi-dataset attribution and remains robust even after continued pretraining on large non-watermarked corpora. These results establish TRACE as a practical route to reliable black-box verification of copyrighted dataset usage. We will make our code available at: https://github.com/NusIoraPrivacy/TRACE.

---

### Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking

Authors: Weijian Deng, Weijie Tu, Ibrahim Radwan, Mohammad Abu Alsheikh, Stephen Gould, Liang Zheng
Published: 2025-10-03
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.02956v1

Assessing model generalization under distribution shift is essential for real-world deployment, particularly when labeled test data is unavailable. This paper presents a unified and practical framework for unsupervised model evaluation and ranking in two common deployment settings: (1) estimating the accuracy of a fixed model on multiple unlabeled test sets (dataset-centric evaluation), and (2) ranking a set of candidate models on a single unlabeled test set (model-centric evaluation). We demonstrate that two intrinsic properties of model predictions, namely confidence (which reflects prediction certainty) and dispersity (which captures the diversity of predicted classes), together provide strong and complementary signals for generalization. We systematically benchmark a set of confidence-based, dispersity-based, and hybrid metrics across a wide range of model architectures, datasets, and distribution shift types. Our results show that hybrid metrics consistently outperform single-aspect metrics on both dataset-centric and model-centric evaluation settings. In particular, the nuclear norm of the prediction matrix provides robust and accurate performance across tasks, including real-world datasets, and maintains reliability under moderate class imbalance. These findings offer a practical and generalizable basis for unsupervised model assessment in deployment scenarios.

---

### ContextFlow: Context-Aware Flow Matching For Trajectory Inference From Spatial Omics Data

Authors: Santanu Subhash Rathod, Francesco Ceccarelli, Sean B. Holden, Pietro Liò, Xiao Zhang, Jovan Tanevski
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02952v3

Inferring trajectories from longitudinal spatially-resolved omics data is fundamental to understanding the dynamics of structural and functional tissue changes in development, regeneration and repair, disease progression, and response to treatment. We propose ContextFlow, a novel context-aware flow matching framework that incorporates prior knowledge to guide the inference of structural tissue dynamics from spatially resolved omics data. Specifically, ContextFlow integrates local tissue organization and ligand-receptor communication patterns into a transition plausibility matrix that regularizes the optimal transport objective. By embedding these contextual constraints, ContextFlow generates trajectories that are not only statistically consistent but also biologically meaningful, making it a generalizable framework for modeling spatiotemporal dynamics from longitudinal, spatially resolved omics data. Evaluated on three datasets, ContextFlow consistently outperforms state-of-the-art flow matching methods across multiple quantitative and qualitative metrics of inference accuracy and biological coherence. Our code is available at: \href{https://github.com/santanurathod/ContextFlow}{ContextFlow}

---

### Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning

Authors: Juan Sebastian Rojas, Chi-Guhn Lee
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.02945v3

Continual reinforcement learning (continual RL) seeks to formalize the notions of lifelong learning and endless adaptation in RL. In particular, the aim of continual RL is to develop RL agents that can maintain a careful balance between retaining useful information and adapting to new situations. To date, continual RL has been explored almost exclusively through the lens of risk-neutral decision-making, in which the agent aims to optimize the expected long-run performance. In this work, we present the first formal theoretical treatment of continual RL through the lens of risk-aware decision-making, in which the behaviour of the agent is directed towards optimizing a measure of long-run performance beyond the mean. In particular, we show that the classical theory of risk measures, widely used as a theoretical foundation in non-continual risk-aware RL, is, in its current form, incompatible with continual learning. Then, building on this insight, we extend risk measure theory into the continual setting by introducing a new class of ergodic risk measures, and showing that it is compatible with continual learning. Finally, we provide a case study of continual risk-aware learning, along with empirical results, which show the intuitive appeal of ergodic risk measures in continual settings.

---

### Finding Diamonds in Conversation Haystacks: A Benchmark for Conversational Data Retrieval

Authors: Yohan Lee, Yongwoo Song, Sangyeop Kim
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.02938v2

We present the Conversational Data Retrieval (CDR) benchmark, the first comprehensive test set for evaluating systems that retrieve conversation data for product insights. With 1.6k queries across five analytical tasks and 9.1k conversations, our benchmark provides a reliable standard for measuring conversational data retrieval performance. Our evaluation of 16 popular embedding models shows that even the best models reach only around NDCG@10 of 0.51, revealing a substantial gap between document and conversational data retrieval capabilities. Our work identifies unique challenges in conversational data retrieval (implicit state recognition, turn dynamics, contextual references) while providing practical query templates and detailed error analysis across different task categories. The benchmark dataset and code are available at https://github.com/l-yohai/CDR-Benchmark.

---

### RAxSS: Retrieval-Augmented Sparse Sampling for Explainable Variable-Length Medical Time Series Classification

Authors: Aydin Javadov, Samir Garibov, Tobias Hoesli, Qiyang Sun, Florian von Wangenheim, Joseph Ollier, Björn W. Schuller
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02936v1

Medical time series analysis is challenging due to data sparsity, noise, and highly variable recording lengths. Prior work has shown that stochastic sparse sampling effectively handles variable-length signals, while retrieval-augmented approaches improve explainability and robustness to noise and weak temporal correlations. In this study, we generalize the stochastic sparse sampling framework for retrieval-informed classification. Specifically, we weight window predictions by within-channel similarity and aggregate them in probability space, yielding convex series-level scores and an explicit evidence trail for explainability. Our method achieves competitive iEEG classification performance and provides practitioners with greater transparency and explainability. We evaluate our method in iEEG recordings collected in four medical centers, demonstrating its potential for reliable and explainable clinical variable-length time series classification.

---

### Scalable Quantum Optimisation using HADOF: Hamiltonian Auto-Decomposition Optimisation Framework

Authors: Namasi G Sankar, Georgios Miliotis, Simon Caton
Published: 2025-10-03
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.02926v1

Quantum Annealing (QA) and QAOA are promising quantum optimisation algorithms used for finding approximate solutions to combinatorial problems on near-term NISQ systems. Many NP-hard problems can be reformulated as Quadratic Unconstrained Binary Optimisation (QUBO), which maps naturally onto quantum Hamiltonians. However, the limited qubit counts of current NISQ devices restrict practical deployment of such algorithms. In this study, we present the Hamiltonian Auto-Decomposition Optimisation Framework (HADOF), which leverages an iterative strategy to automatically divide the Quadratic Unconstrained Binary Optimisation (QUBO) Hamiltonian into sub-Hamiltonians which can be optimised separately using Hamiltonian based optimisers such as QAOA, QA or Simulated Annealing (SA) and aggregated into a global solution. We compare HADOF with Simulated Annealing (SA) and the CPLEX exact solver, showing scalability to problem sizes far exceeding available qubits while maintaining competitive accuracy and runtime. Furthermore, we realise HADOF for a toy problem on an IBM quantum computer, showing promise for practical applications of quantum optimisation.

---

### Multimodal Carotid Risk Stratification with Large Vision-Language Models: Benchmarking, Fine-Tuning, and Clinical Insights

Authors: Daphne Tsolissou, Theofanis Ganitidis, Konstantinos Mitsis, Stergios CHristodoulidis, Maria Vakalopoulou, Konstantina Nikita
Published: 2025-10-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.02922v1

Reliable risk assessment for carotid atheromatous disease remains a major clinical challenge, as it requires integrating diverse clinical and imaging information in a manner that is transparent and interpretable to clinicians. This study investigates the potential of state-of-the-art and recent large vision-language models (LVLMs) for multimodal carotid plaque assessment by integrating ultrasound imaging (USI) with structured clinical, demographic, laboratory, and protein biomarker data. A framework that simulates realistic diagnostic scenarios through interview-style question sequences is proposed, comparing a range of open-source LVLMs, including both general-purpose and medically tuned models. Zero-shot experiments reveal that even if they are very powerful, not all LVLMs can accurately identify imaging modality and anatomy, while all of them perform poorly in accurate risk classification. To address this limitation, LLaVa-NeXT-Vicuna is adapted to the ultrasound domain using low-rank adaptation (LoRA), resulting in substantial improvements in stroke risk stratification. The integration of multimodal tabular data in the form of text further enhances specificity and balanced accuracy, yielding competitive performance compared to prior convolutional neural network (CNN) baselines trained on the same dataset. Our findings highlight both the promise and limitations of LVLMs in ultrasound-based cardiovascular risk prediction, underscoring the importance of multimodal integration, model calibration, and domain adaptation for clinical translation.

---

### Self-Reflective Generation at Test Time

Authors: Jian Mu, Qixin Zhang, Zhiyong Wang, Menglin Yang, Shuang Qiu, Chengwei Qin, Zhongxiang Dai, Yao Shu
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.02919v2

Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for self-reflection mechanisms. However, existing self-reflection either performs revisions over full drafts or learns self-correction via expensive training, both fundamentally reactive and inefficient. To address this, we propose Self-Reflective Generation at Test Time (SRGen), a lightweight test-time framework that reflects before generating at uncertain points. During token generation, SRGen utilizes dynamic entropy thresholding to identify high-uncertainty tokens. For each identified token, it trains a specific corrective vector, which fully exploits the already generated context for a self-reflective generation to correct the token probability distribution. By retrospectively analyzing the partial output, this self-reflection enables more trustworthy decisions, thereby significantly reducing the probability of errors at highly uncertain points. Evaluated on challenging mathematical reasoning benchmarks and a diverse set of LLMs, SRGen can significantly strengthen model reasoning. Moreover, our findings position SRGen as a plug-and-play method that integrates reflection into the generation process for reliable LLM reasoning, achieving consistent gains with bounded overhead and can be combined with other training-time (e.g., RLHF) and test-time (e.g., SLOT) techniques.

---

### Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders

Authors: Kriz Tahimic, Charibeth Cheng
Published: 2025-10-03
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2510.02917v1

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse autoencoders to decompose LLM representations, identifying directions that correspond to code correctness. We select predictor directions using t-statistics and steering directions through separation scores from base model representations, then analyze their mechanistic properties through steering, attention analysis, and weight orthogonalization. We find that code correctness directions in LLMs reliably predict incorrect code, while correction capabilities, though statistically significant, involve tradeoffs between fixing errors and preserving correct code. Mechanistically, successful code generation depends on attending to test cases rather than problem descriptions. Moreover, directions identified in base models retain their effectiveness after instruction-tuning, suggesting code correctness mechanisms learned during pre-training are repurposed during fine-tuning. Our mechanistic insights suggest three practical applications: prompting strategies should prioritize test examples over elaborate problem descriptions, predictor directions can serve as error alarms for developer review, and these same predictors can guide selective steering, intervening only when errors are anticipated to prevent the code corruption from constant steering.

---

### SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos

Authors: Amir Dellali, Luca A. Lanzendörfer, Florian Grötschla, Roger Wattenhofer
Published: 2025-10-03
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2510.02916v2

We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content. Our approach introduces a masked diffusion objective, enabling audio-conditioned generation and the seamless synthesis of unconstrained length audio sequences. Additionally, by integrating a shortcut loss into our training process, we achieve rapid generation of high-quality audio samples in as few as eight sampling steps, paving the way for near-real-time applications without requiring dedicated fine-tuning or retraining. We demonstrate that SALSA-V significantly outperforms existing state-of-the-art methods in both audiovisual alignment and synchronization with video content in quantitative evaluation and a human listening study. Furthermore, our use of random masking during training enables our model to match spectral characteristics of reference audio samples, broadening its applicability to professional audio synthesis tasks such as Foley generation and sound design.

---

### WavInWav: Time-domain Speech Hiding via Invertible Neural Network

Authors: Wei Fan, Kejiang Chen, Xiangkun Wang, Weiming Zhang, Nenghai Yu
Published: 2025-10-03
Categories: cs.SD, cs.AI, cs.CR, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.02915v1

Data hiding is essential for secure communication across digital media, and recent advances in Deep Neural Networks (DNNs) provide enhanced methods for embedding secret information effectively. However, previous audio hiding methods often result in unsatisfactory quality when recovering secret audio, due to their inherent limitations in the modeling of time-frequency relationships. In this paper, we explore these limitations and introduce a new DNN-based approach. We use a flow-based invertible neural network to establish a direct link between stego audio, cover audio, and secret audio, enhancing the reversibility of embedding and extracting messages. To address common issues from time-frequency transformations that degrade secret audio quality during recovery, we implement a time-frequency loss on the time-domain signal. This approach not only retains the benefits of time-frequency constraints but also enhances the reversibility of message recovery, which is vital for practical applications. We also add an encryption technique to protect the hidden data from unauthorized access. Experimental results on the VCTK and LibriSpeech datasets demonstrate that our method outperforms previous approaches in terms of subjective and objective metrics and exhibits robustness to various types of noise, suggesting its utility in targeted secure communication scenarios.

---

### FeDABoost: Fairness Aware Federated Learning with Adaptive Boosting

Authors: Tharuka Kasthuri Arachchige, Veselka Boeva, Shahrooz Abghari
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.02914v1

This work focuses on improving the performance and fairness of Federated Learning (FL) in non IID settings by enhancing model aggregation and boosting the training of underperforming clients. We propose FeDABoost, a novel FL framework that integrates a dynamic boosting mechanism and an adaptive gradient aggregation strategy. Inspired by the weighting mechanism of the Multiclass AdaBoost (SAMME) algorithm, our aggregation method assigns higher weights to clients with lower local error rates, thereby promoting more reliable contributions to the global model. In parallel, FeDABoost dynamically boosts underperforming clients by adjusting the focal loss focusing parameter, emphasizing hard to classify examples during local training. We have evaluated FeDABoost on three benchmark datasets MNIST, FEMNIST, and CIFAR10, and compared its performance with those of FedAvg and Ditto. The results show that FeDABoost achieves improved fairness and competitive performance.

---

### Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting

Authors: Nikoo Naghavian, Mostafa Tavassolipour
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02913v2

Vision-language models such as CLIP demonstrate impressive zero-shot generalization but remain highly vulnerable to adversarial attacks. Prior adversarial methods treat all samples equally in the loss function, despite the fact that not all inputs contribute equally to adversarial vulnerability. Some samples retain high confidence even under large perturbations, while others are unstable and change predictions with minor noise. To address this, we propose Confidence-Aware Weighting (CAW) to enhance the zero-shot robustness of vision-language models. CAW introduces two key components: (1) a Confidence-Aware Loss that prioritizes uncertain adversarial examples by scaling the KL divergence between clean and adversarial predictions, and (2) a Feature Alignment Regularization that preserves semantic consistency by minimizing the distance between frozen and fine-tuned image encoder features on adversarial inputs. Together, these components improve both clean and robust accuracy without compromising generalization. Extensive experiments on TinyImageNet and 14 additional datasets show that CAW outperforms recent state-of-the-art methods such as PMG-AFT and TGA-ZSR under strong adversarial attacks like AutoAttack, while also being more memory-efficient.

---

### Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

Authors: Xin Zou, Di Lu, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Xu Zheng, Linfeng Zhang, Xuming Hu
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02912v2

Despite their powerful capabilities, Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent studies have explored token pruning to alleviate this problem, which typically uses text-vision cross-attention or (\texttt{CLS}) attention to assess and discard redundant visual tokens. In this work, we identify a critical limitation of such attention-first pruning approaches, i.e., they tend to preserve semantically similar tokens, resulting in pronounced performance drops under high pruning ratios. To this end, we propose {HoloV}, a simple yet effective, plug-and-play visual token pruning framework for efficient inference. Distinct from previous attention-first schemes, HoloV rethinks token retention from a holistic perspective. By adaptively distributing the pruning budget across different spatial crops, HoloV ensures that the retained tokens capture the global visual context rather than isolated salient features. This strategy minimizes representational collapse and maintains task-relevant information even under aggressive pruning. Experimental results demonstrate that our HoloV achieves superior performance across various tasks, MLLM architectures, and pruning ratios compared to SOTA methods. For instance, LLaVA1.5 equipped with HoloV preserves 95.8\% of the original performance after pruning 88.9\% of visual tokens, achieving superior efficiency-accuracy trade-offs.

---

### Training-Free Out-Of-Distribution Segmentation With Foundation Models

Authors: Laith Nayal, Hadi Salloum, Ahmad Taha, Yaroslav Kholodov, Alexander Gasnikov
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02909v1

Detecting unknown objects in semantic segmentation is crucial for safety-critical applications such as autonomous driving. Large vision foundation models, including DINOv2, InternImage, and CLIP, have advanced visual representation learning by providing rich features that generalize well across diverse tasks. While their strength in closed-set semantic tasks is established, their capability to detect out-of-distribution (OoD) regions in semantic segmentation remains underexplored. In this work, we investigate whether foundation models fine-tuned on segmentation datasets can inherently distinguish in-distribution (ID) from OoD regions without any outlier supervision. We propose a simple, training-free approach that utilizes features from the InternImage backbone and applies K-Means clustering alongside confidence thresholding on raw decoder logits to identify OoD clusters. Our method achieves 50.02 Average Precision on the RoadAnomaly benchmark and 48.77 on the benchmark of ADE-OoD with InternImage-L, surpassing several supervised and unsupervised baselines. These results suggest a promising direction for generic OoD segmentation methods that require minimal assumptions or additional data.

---

### FinReflectKG -- MultiHop: Financial QA Benchmark for Reasoning with Knowledge Graph Evidence

Authors: Abhinav Arun, Reetu Raj Harsh, Bhaskarjit Sarmah, Stefano Pasquali
Published: 2025-10-03
Categories: q-fin.CP, cs.AI
arXiv: https://arxiv.org/abs/2510.02906v1

Multi-hop reasoning over financial disclosures is often a retrieval problem before it becomes a reasoning or generation problem: relevant facts are dispersed across sections, filings, companies, and years, and LLMs often expend excessive tokens navigating noisy context. Without precise Knowledge Graph (KG)-guided selection of relevant context, even strong reasoning models either fail to answer or consume excessive tokens, whereas KG-linked evidence enables models to focus their reasoning on composing already retrieved facts. We present FinReflectKG - MultiHop, a benchmark built on FinReflectKG, a temporally indexed financial KG that links audited triples to source chunks from S&P 100 filings (2022-2024). Mining frequent 2-3 hop subgraph patterns across sectors (via GICS taxonomy), we generate financial analyst style questions with exact supporting evidence from the KG. A two-phase pipeline first creates QA pairs via pattern-specific prompts, followed by a multi-criteria quality control evaluation to ensure QA validity. We then evaluate three controlled retrieval scenarios: (S1) precise KG-linked paths; (S2) text-only page windows centered on relevant text spans; and (S3) relevant page windows with randomizations and distractors. Across both reasoning and non-reasoning models, KG-guided precise retrieval yields substantial gains on the FinReflectKG - MultiHop QA benchmark dataset, boosting correctness scores by approximately 24 percent while reducing token utilization by approximately 84.5 percent compared to the page window setting, which reflects the traditional vector retrieval paradigm. Spanning intra-document, inter-year, and cross-company scopes, our work underscores the pivotal role of knowledge graphs in efficiently connecting evidence for multi-hop financial QA. We also release a curated subset of the benchmark (555 QA Pairs) to catalyze further research.

---

### Learning Explicit Single-Cell Dynamics Using ODE Representations

Authors: Jan-Philipp von Bassewitz, Adeel Pervez, Marco Fumero, Matthew Robinson, Theofanis Karaletsos, Francesco Locatello
Published: 2025-10-03
Categories: cs.LG, q-bio.CB
arXiv: https://arxiv.org/abs/2510.02903v2

Modeling the dynamics of cellular differentiation is fundamental to advancing the understanding and treatment of diseases associated with this process, such as cancer. With the rapid growth of single-cell datasets, this has also become a particularly promising and active domain for machine learning. Current state-of-the-art models, however, rely on computationally expensive optimal transport preprocessing and multi-stage training, while also not discovering explicit gene interactions. To address these challenges we propose Cell-Mechanistic Neural Networks (Cell-MNN), an encoder-decoder architecture whose latent representation is a locally linearized ODE governing the dynamics of cellular evolution from stem to tissue cells. Cell-MNN is fully end-to-end (besides a standard PCA pre-processing) and its ODE representation explicitly learns biologically consistent and interpretable gene interactions. Empirically, we show that Cell-MNN achieves competitive performance on single-cell benchmarks, surpasses state-of-the-art baselines in scaling to larger datasets and joint training across multiple datasets, while also learning interpretable gene interactions that we validate against the TRRUST database of gene interactions.

---

### DMark: Order-Agnostic Watermarking for Diffusion Large Language Models

Authors: Linyu Wu, Linhao Zhong, Wenjie Qu, Yuexin Li, Yue Liu, Shengfang Zhai, Chunhua Shen, Jiaheng Zhang
Published: 2025-10-03
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.02902v1

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive models that generate tokens left-to-right, dLLMs can finalize tokens in arbitrary order, breaking the causal design underlying traditional watermarks. We present DMark, the first watermarking framework designed specifically for dLLMs. DMark introduces three complementary strategies to restore watermark detectability: predictive watermarking uses model-predicted tokens when actual context is unavailable; bidirectional watermarking exploits both forward and backward dependencies unique to diffusion decoding; and predictive-bidirectional watermarking combines both approaches to maximize detection strength. Experiments across multiple dLLMs show that DMark achieves 92.0-99.5% detection rates at 1% false positive rate while maintaining text quality, compared to only 49.6-71.2% for naive adaptations of existing methods. DMark also demonstrates robustness against text manipulations, establishing that effective watermarking is feasible for non-autoregressive language models.

---

### One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

Authors: Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina, Giuseppe Amato, Fabrizio Falchi
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02898v5

Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of arbitrary regions without the need of region-level supervision. Instead of relying on global image representations, we treat individual patches as atomic captioning units and aggregate them to describe arbitrary regions, from single patches to non-contiguous areas and entire images. We analyze the key ingredients that enable current latent captioners to work in our novel proposed framework. Experiments demonstrate that backbones producing meaningful, dense visual features, such as DINO, are key to achieving state-of-the-art performance in multiple region-based captioning tasks. Compared to other baselines and state-of-the-art competitors, our models achieve better performance on zero-shot dense captioning and region-set captioning. We also introduce a new trace captioning task that further demonstrates the effectiveness of patch-wise semantic representations for flexible caption generation. Project page at https://paciosoft.com/Patch-ioner/ .

---

### Global Convergence of Policy Gradient for Entropy Regularized Linear-Quadratic Control with Multiplicative Noise

Authors: Gabriel Diaz, Lucky Li, Wenhao Zhang
Published: 2025-10-03
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2510.02896v4

Reinforcement Learning (RL) has emerged as a powerful framework for sequential decision-making in dynamic environments, particularly when system parameters are unknown. This paper investigates RL-based control for entropy-regularized linear-quadratic (LQ) control problems with multiplicative noise over an infinite time horizon. First, we adapt the regularized policy gradient (RPG) algorithm to stochastic optimal control settings, proving that despite the non-convexity of the problem, RPG converges globally under conditions of gradient domination and almost-smoothness. Second, based on zero-order optimization approach, we introduce a novel model free RL algorithm: Sample-based regularized policy gradient (SB-RPG). SB-RPG operates without knowledge of system parameters yet still retains strong theoretical guarantees of global convergence. Our model leverages entropy regularization to address the exploration versus exploitation trade-off inherent in RL. Numerical simulations validate the theoretical results and demonstrate the efficiency of SB-RPG in unknown-parameters environments.

---

### PyRadiomics-cuda: 3D features extraction from medical images for HPC using GPU acceleration

Authors: Jakub Lisowski, Piotr Tyrakowski, Szymon Zyguła, Krzysztof Kaczmarski
Published: 2025-10-03
Categories: cs.DC, cs.CV
arXiv: https://arxiv.org/abs/2510.02894v2

PyRadiomics-cuda is a GPU-accelerated extension of the PyRadiomics library, designed to address the computational challenges of extracting three-dimensional shape features from medical images. By offloading key geometric computations to GPU hardware it dramatically reduces processing times for large volumetric datasets. The system maintains full compatibility with the original PyRadiomics API, enabling seamless integration into existing AI workflows without code modifications. This transparent acceleration facilitates efficient, scalable radiomics analysis, supporting rapid feature extraction essential for high-throughput AI pipeline. Tests performed on a typical computational cluster, budget and home devices prove usefulness in all scenarios.

---

### RoiRL: Efficient, Self-Supervised Reasoning with Offline Iterative Reinforcement Learning

Authors: Aleksei Arzhantsev, Otmane Sakhi, Flavian Vasile
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02892v1

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies on heavy online RL and incurs substantial computational cost. We propose RoiRL: Reasoning with offline iterative Reinforcement Learning, a family of lightweight offline learning alternatives that can target the same regularized optimal policies. Unlike TTRL, RoiRL eliminates the need to maintain a reference model and instead optimizes weighted log-likelihood objectives, enabling stable training with significantly lower memory and compute requirements. Experimental results show that RoiRL trains to 2.5x faster and consistently outperforms TTRL on reasoning benchmarks, establishing a scalable path to self-improving LLMs without labels.

---

### Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models

Authors: Tianren Ma, Mu Zhang, Yibing Wang, Qixiang Ye
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.02880v1

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy Optimization (GRPO). In this study, we introduce MaskGRPO, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion with effective importance sampling and modality-specific adaptations. To this end, we first clarify the theoretical foundation for DDMs, which facilitates building an importance estimator that captures valuable token fluctuation for gradient updates. We then delicately tailored the rollout method for visual sequences, which yields diverse completions and reliable optimization gradients. Upon math reasoning, coding, and visual generation benchmarks, MaskGRPO brings more stable and efficient updates, leading to stronger reasoning performance and better generation quality. This study establishes MaskGRPO as a systematic policy optimization approach and the first practical way for discretized visual diffusion.

---

### ELMF4EggQ: Ensemble Learning with Multimodal Feature Fusion for Non-Destructive Egg Quality Assessment

Authors: Md Zahim Hassan, Md. Osama, Muhammad Ashad Kabir, Md. Saiful Islam, Zannatul Naim
Published: 2025-10-03
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.02876v1

Accurate, non-destructive assessment of egg quality is critical for ensuring food safety, maintaining product standards, and operational efficiency in commercial poultry production. This paper introduces ELMF4EggQ, an ensemble learning framework that employs multimodal feature fusion to classify egg grade and freshness using only external attributes - image, shape, and weight. A novel, publicly available dataset of 186 brown-shelled eggs was constructed, with egg grade and freshness levels determined through laboratory-based expert assessments involving internal quality measurements, such as yolk index and Haugh unit. To the best of our knowledge, this is the first study to apply machine learning methods for internal egg quality assessment using only external, non-invasive features, and the first to release a corresponding labeled dataset. The proposed framework integrates deep features extracted from external egg images with structural characteristics such as egg shape and weight, enabling a comprehensive representation of each egg. Image feature extraction is performed using top-performing pre-trained CNN models (ResNet152, DenseNet169, and ResNet152V2), followed by PCA-based dimensionality reduction, SMOTE augmentation, and classification using multiple machine learning algorithms. An ensemble voting mechanism combines predictions from the best-performing classifiers to enhance overall accuracy. Experimental results demonstrate that the multimodal approach significantly outperforms image-only and tabular (shape and weight) only baselines, with the multimodal ensemble approach achieving 86.57% accuracy in grade classification and 70.83% in freshness prediction. All code and data are publicly available at https://github.com/Kenshin-Keeps/Egg_Quality_Prediction_ELMF4EggQ, promoting transparency, reproducibility, and further research in this domain.

---