# Research Papers — 2025-10 · bundle page 147 of 217

> Full-text markdown of papers #7301–7350 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/147
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/146.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/148.md)

### LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning

Authors: Changjiang Gao, Zixian Huang, Jingyang Gong, Shujian Huang, Lei Li, Fei Yuan
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09189v1

General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies layer-selective tuning only on parallel data. Following this pipeline, we introduce the Qwen3-XPlus models, which demonstrate significant improvements in translation performance across both high- and lowresource languages, achieving 15+ spBLEU and 40+ xComet in low-resource languages, like Swahili. Interestingly, training only with small parallel datasets, Qwen3-XPlus achieves an average improvement of 1+ points on 7 multilingual tasks while maintaining proficiency comparable to the Qwen3 instruct model in 15 popular reasoning datasets. This work offers a promising approach to multilingual enhancement, significantly reducing complexity and enhancing accessibility for a wider range of languages. The code and model are publicly available.

---

### Modern Deep Learning Approaches for Cricket Shot Classification: A Comprehensive Baseline Study

Authors: Sungwoo Kang
Published: 2025-10-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.09187v1

Cricket shot classification from video sequences remains a challenging problem in sports video analysis, requiring effective modeling of both spatial and temporal features. This paper presents the first comprehensive baseline study comparing seven different deep learning approaches across four distinct research paradigms for cricket shot classification. We implement and systematically evaluate traditional CNN-LSTM architectures, attention-based models, vision transformers, transfer learning approaches, and modern EfficientNet-GRU combinations on a unified benchmark. A critical finding of our study is the significant performance gap between claims in academic literature and practical implementation results. While previous papers reported accuracies of 96\% (Balaji LRCN), 99.2\% (IJERCSE), and 93\% (Sensors), our standardized re-implementations achieve 46.0\%, 55.6\%, and 57.7\% respectively. Our modern SOTA approach, combining EfficientNet-B0 with a GRU-based temporal model, achieves 92.25\% accuracy, demonstrating that substantial improvements are possible with modern architectures and systematic optimization. All implementations follow modern MLOps practices with PyTorch Lightning, providing a reproducible research platform that exposes the critical importance of standardized evaluation protocols in sports video analysis research.

---

### Stronger Re-identification Attacks through Reasoning and Aggregation

Authors: Lucas Georges Gabriel Charpentier, Pierre Lison
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09184v1

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has shown how the robustness of de-identification methods could be assessed by attempting the reverse process of _re-identification_, based on an automated adversary using its background knowledge to uncover the PIIs that have been masked. This paper presents two complementary strategies to build stronger re-identification attacks. We first show that (1) the _order_ in which the PII spans are re-identified matters, and that aggregating predictions across multiple orderings leads to improved results. We also find that (2) reasoning models can boost the re-identification performance, especially when the adversary is assumed to have access to extensive background knowledge.

---

### Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption

Authors: Johann-Friedrich Feiden, Tim Küchler, Denis Zavadski, Bogdan Savchynskyy, Carsten Rother
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09182v1

Depth estimation from monocular video has become a key component of many real-world computer vision systems. Recently, Video Depth Anything (VDA) has demonstrated strong performance on long video sequences. However, it relies on batch-processing which prohibits its use in an online setting. In this work, we overcome this limitation and introduce online VDA (oVDA). The key innovation is to employ techniques from Large Language Models (LLMs), namely, caching latent features during inference and masking frames at training. Our oVDA method outperforms all competing online video depth estimation methods in both accuracy and VRAM usage. Low VRAM usage is particularly important for deployment on edge devices. We demonstrate that oVDA runs at 42 FPS on an NVIDIA A100 and at 20 FPS on an NVIDIA Jetson edge device. We will release both, code and compilation scripts, making oVDA easy to deploy on low-power hardware.

---

### On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning

Authors: Ze Peng, Jian Zhang, Jintao Guo, Lei Qi, Yang Gao, Yinghuan Shi
Published: 2025-10-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09181v1

Continual learning seeks the human-like ability to accumulate new skills in machine intelligence. Its central challenge is catastrophic forgetting, whose underlying cause has not been fully understood for deep networks. In this paper, we demystify catastrophic forgetting by revealing that the new-task training is implicitly an adversarial attack against the old-task knowledge. Specifically, the new-task gradients automatically and accurately align with the sharp directions of the old-task loss landscape, rapidly increasing the old-task loss. This adversarial alignment is intriguingly counter-intuitive because the sharp directions are too sparsely distributed to align with by chance. To understand it, we theoretically show that it arises from training's low-rank bias, which, through forward and backward propagation, confines the two directions into the same low-dimensional subspace, facilitating alignment. Gradient projection (GP) methods, a representative family of forgetting-mitigating methods, reduce adversarial alignment caused by forward propagation, but cannot address the alignment due to backward propagation. We propose backGP to address it, which reduces forgetting by 10.8% and improves accuracy by 12.7% on average over GP methods.

---

### RepDL: Bit-level Reproducible Deep Learning Training and Inference

Authors: Peichen Xie, Xian Zhang, Shuo Chen
Published: 2025-10-10
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.09180v1

Non-determinism and non-reproducibility present significant challenges in deep learning, leading to inconsistent results across runs and platforms. These issues stem from two origins: random number generation and floating-point computation. While randomness can be controlled through deterministic configurations, floating-point inconsistencies remain largely unresolved. To address this, we introduce RepDL, an open-source library that ensures deterministic and bitwise-reproducible deep learning training and inference across diverse computing environments. RepDL achieves this by enforcing correct rounding and order invariance in floating-point computation. The source code is available at https://github.com/microsoft/RepDL .

---

### Distributionally robust approximation property of neural networks

Authors: Mihriban Ceylan, David J. Prömel
Published: 2025-10-10
Categories: stat.ML, cs.LG, math.FA, math.PR
arXiv: https://arxiv.org/abs/2510.09177v1

The universal approximation property uniformly with respect to weakly compact families of measures is established for several classes of neural networks. To that end, we prove that these neural networks are dense in Orlicz spaces, thereby extending classical universal approximation theorems even beyond the traditional $L^p$-setting. The covered classes of neural networks include widely used architectures like feedforward neural networks with non-polynomial activation functions, deep narrow networks with ReLU activation functions and functional input neural networks.

---

### Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints

Authors: Ling Zhan, Junjie Huang, Xiaoyao Yu, Wenyu Chen, Tao Jia
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09175v1

Functional brain network (FBN) modeling often relies on local pairwise interactions, whose limitation in capturing high-order dependencies is theoretically analyzed in this paper. Meanwhile, the computational burden and heuristic nature of current hypergraph modeling approaches hinder end-to-end learning of FBN structures directly from data distributions. To address this, we propose to extract high-order FBN structures under global constraints, and implement this as a Global Constraints oriented Multi-resolution (GCM) FBN structure learning framework. It incorporates 4 types of global constraint (signal synchronization, subject identity, expected edge numbers, and data labels) to enable learning FBN structures for 4 distinct levels (sample/subject/group/project) of modeling resolution. Experimental results demonstrate that GCM achieves up to a 30.6% improvement in relative accuracy and a 96.3% reduction in computational time across 5 datasets and 2 task settings, compared to 9 baselines and 10 state-of-the-art methods. Extensive experiments validate the contributions of individual components and highlight the interpretability of GCM. This work offers a novel perspective on FBN structure learning and provides a foundation for interdisciplinary applications in cognitive neuroscience. Code is publicly available on https://github.com/lzhan94swu/GCM.

---

### Robustness and Regularization in Hierarchical Re-Basin

Authors: Benedikt Franke, Florian Heinrich, Markus Lange, Arne Raulf
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09174v3

This paper takes a closer look at Git Re-Basin, an interesting new approach to merge trained models. We propose a hierarchical model merging scheme that significantly outperforms the standard MergeMany algorithm. With our new algorithm, we find that Re-Basin induces adversarial and perturbation robustness into the merged models, with the effect becoming stronger the more models participate in the hierarchical merging scheme. However, in our experiments Re-Basin induces a much bigger performance drop than reported by the original authors.

---

### Beyond Flat Unknown Labels in Open-World Object Detection

Authors: Yuchen Zhang, Yao Lu, Johannes Betz
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09173v2

Most object detectors operate under a closed-world assumption, recognizing only the classes annotated in the training dataset and failing when encountering novel objects. Open-World Object Detection (OWOD) relaxes this assumption by enabling unseen objects to be detected as "Unknown". However, collapsing all novel objects into a single undifferentiated label eliminates semantic granularity and limits informed decision-making. In this paper, we introduce BOUND, an open-world detector that advances OWOD by inferring coarse-grained categories of unknown objects rather than merely flagging their existence. This enriched representation offers semantic cues that may benefit real-world systems. For example, in autonomous driving, distinguishing between an "Unknown Animal" (requiring yielding) and an "Unknown Debris" (requiring rerouting) leads to fundamentally different planning behaviors. Technically, BOUND integrates a sparsemax-based head for modeling objectness, a hierarchy-guided relabeling component that provides auxiliary supervision, and a classification module that learns hierarchical relationships. Experiments on OWOD benchmarks demonstrate that BOUND achieves higher unknown recall than existing baselines without sacrificing known-class mAP, while additionally enabling structured hierarchical categorization of unknown instances. Furthermore, evaluations on the long-tail LVIS dataset demonstrate robust generalization. Code will be made available.

---

### Instance-Level Generation for Representation Learning

Authors: Yankun Wu, Zakaria Laskar, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09171v2

Instance-level recognition (ILR) focuses on identifying individual objects rather than broad categories, offering the highest granularity in image classification. However, this fine-grained nature makes creating large-scale annotated datasets challenging, limiting ILR's real-world applicability across domains. To overcome this, we introduce a novel approach that synthetically generates diverse object instances from multiple domains under varied conditions and backgrounds, forming a large-scale training set. Unlike prior work on automatic data synthesis, our method is the first to address ILR-specific challenges without relying on any real images. Fine-tuning foundation vision models on the generated data significantly improves retrieval performance across seven ILR benchmarks spanning multiple domains. Our approach offers a new, efficient, and effective alternative to extensive data collection and curation, introducing a new ILR paradigm where the only input is the names of the target domains, unlocking a wide range of real-world applications. The code and pretrained models are publicly available at https://github.com/yankungou/ILGen.

---

### Dr. Bias: Social Disparities in AI-Powered Medical Guidance

Authors: Emma Kondrup, Anne Imouza
Published: 2025-10-10
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.09162v2

With the rapid progress of Large Language Models (LLMs), the general public now has easy and affordable access to applications capable of answering most health-related questions in a personalized manner. These LLMs are increasingly proving to be competitive, and now even surpass professionals in some medical capabilities. They hold particular promise in low-resource settings, considering they provide the possibility of widely accessible, quasi-free healthcare support. However, evaluations that fuel these motivations highly lack insights into the social nature of healthcare, oblivious to health disparities between social groups and to how bias may translate into LLM-generated medical advice and impact users. We provide an exploratory analysis of LLM answers to a series of medical questions spanning key clinical domains, where we simulate these questions being asked by several patient profiles that vary in sex, age range, and ethnicity. By comparing natural language features of the generated responses, we show that, when LLMs are used for medical advice generation, they generate responses that systematically differ between social groups. In particular, Indigenous and intersex patients receive advice that is less readable and more complex. We observe these trends amplify when intersectional groups are considered. Considering the increasing trust individuals place in these models, we argue for higher AI literacy and for the urgent need for investigation and mitigation by AI developers to ensure these systemic differences are diminished and do not translate to unjust patient support. Our code is publicly available on GitHub.

---

### Efficient Resource-Constrained Training of Transformers via Subspace Optimization

Authors: Le-Trung Nguyen, Enzo Tartaglione, Van-Tam Nguyen
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09160v3

As AI increasingly shapes daily life, energy consumption and data privacy have become pressing concerns. On-device learning trains models directly on edge devices, cutting energy consumption and safeguarding data privacy. However, the expanding scale of modern neural networks creates a major obstacle for on-device training. Although prior work has concentrated on compact convolutional architectures, we instead apply subspace-based training to transformer models. Motivated by the idea that a model's essential information lies in a fixed subspace, we introduce Weight-Activation Subspace Iteration (WASI), a method that mitigates the memory bottleneck of backpropagation and boosts inference efficiency in transformer models by restricting training to this subspace. Our results demonstrate that WASI maintains accuracy comparable to vanilla training while reducing memory usage by up to $62\times$ and computational cost (FLOPs) by up to $2\times$. On a Raspberry Pi 5, WASI achieves roughly $1.4\times$ faster training and inference than vanilla training. The code is available at https://github.com/Le-TrungNguyen/ICLR2026-WASI.git.

---

### Cross-Representation Benchmarking in Time-Series Electronic Health Records for Clinical Outcome Prediction

Authors: Tianyi Chen, Mingcheng Zhu, Zhiyao Luo, Tingting Zhu
Published: 2025-10-10
Categories: cs.LG, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2510.09159v1

Electronic Health Records (EHRs) enable deep learning for clinical predictions, but the optimal method for representing patient data remains unclear due to inconsistent evaluation practices. We present the first systematic benchmark to compare EHR representation methods, including multivariate time-series, event streams, and textual event streams for LLMs. This benchmark standardises data curation and evaluation across two distinct clinical settings: the MIMIC-IV dataset for ICU tasks (mortality, phenotyping) and the EHRSHOT dataset for longitudinal care (30-day readmission, 1-year pancreatic cancer). For each paradigm, we evaluate appropriate modelling families--including Transformers, MLP, LSTMs and Retain for time-series, CLMBR and count-based models for event streams, 8-20B LLMs for textual streams--and analyse the impact of feature pruning based on data missingness. Our experiments reveal that event stream models consistently deliver the strongest performance. Pre-trained models like CLMBR are highly sample-efficient in few-shot settings, though simpler count-based models can be competitive given sufficient data. Furthermore, we find that feature selection strategies must be adapted to the clinical setting: pruning sparse features improves ICU predictions, while retaining them is critical for longitudinal tasks. Our results, enabled by a unified and reproducible pipeline, provide practical guidance for selecting EHR representations based on the clinical context and data regime.

---

### Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM

Authors: Seiya Ishikura, Hiroaki Yamada, Tatsuya Hiraoka, Hiroaki Yamada, Takenobu Tokunaga
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09158v2

This study proposes augmenting dialog data with think-aloud utterances (TAUs) for modeling individual personalities in text chat by LLM. TAU is a verbalization of a speaker's thought before articulating the utterance. We expect "persona LLMs" trained with TAU-augmented data can mimic the speaker's personality trait better. We tested whether the trained persona LLMs obtain the human personality with respect to Big Five, a framework characterizing human personality traits from five aspects. The results showed that LLMs trained with TAU-augmented data more closely align to the speakers' Agreeableness and Neuroticism of Big Five than those trained with original dialog data. We also found that the quality of TAU-augmentation impacts persona LLM's performance.

---

### Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learning

Authors: Jing Li, Zhijie Sun, Zhicheng Zhou, Suming Qiu, Junjie Huang, Haijia Sun, Linyuan Qiu
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09156v1

Current knowledge-enhanced large language models (LLMs) rely on static, pre-constructed knowledge bases that suffer from coverage gaps and temporal obsolescence, limiting their effectiveness in dynamic information environments. We present Agentic-KGR, a novel framework enabling co-evolution between LLMs and knowledge graphs (KGs) through multi-round reinforcement learning (RL). Our approach introduces three key innovations: (1) a dynamic schema expansion mechanism that systematically extends graph ontologies beyond pre-defined boundaries during training; (2) a retrieval-augmented memory system enabling synergistic co-evolution between model parameters and knowledge structures through continuous optimization; (3) a learnable multi-scale prompt compression approach that preserves critical information while reducing computational complexity through adaptive sequence optimization. Experimental results demonstrate substantial improvements over supervised baselines and single-round RL approaches in knowledge extraction tasks. When integrated with GraphRAG, our method achieves superior performance in downstream QA tasks, with significant gains in both accuracy and knowledge coverage compared to existing methods.

---

### Federated Data Analytics for Cancer Immunotherapy: A Privacy-Preserving Collaborative Platform for Patient Management

Authors: Mira Raheem, Michael Papazoglou, Bernd Krämer, Neamat El-Tazi, Amal Elgammal
Published: 2025-10-10
Categories: cs.CY, cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.09155v1

Connected health is a multidisciplinary approach focused on health management, prioritizing pa-tient needs in the creation of tools, services, and treatments. This paradigm ensures proactive and efficient care by facilitating the timely exchange of accurate patient information among all stake-holders in the care continuum. The rise of digital technologies and process innovations promises to enhance connected health by integrating various healthcare data sources. This integration aims to personalize care, predict health outcomes, and streamline patient management, though challeng-es remain, particularly in data architecture, application interoperability, and security. Data analytics can provide critical insights for informed decision-making and health co-creation, but solutions must prioritize end-users, including patients and healthcare professionals. This perspective was explored through an agile System Development Lifecycle in an EU-funded project aimed at developing an integrated AI-generated solution for managing cancer patients undergoing immunotherapy. This paper contributes with a collaborative digital framework integrating stakeholders across the care continuum, leveraging federated big data analytics and artificial intelligence for improved decision-making while ensuring privacy. Analytical capabilities, such as treatment recommendations and adverse event predictions, were validated using real-life data, achieving 70%-90% accuracy in a pilot study with the medical partners, demonstrating the framework's effectiveness.

---

### Logits Replay + MoClip: Stabilized, Low-Cost Post-Training with Minimal Forgetting

Authors: Suming Qiu, Jing Li, Zhicheng Zhou, Junjie Huang, Linyuan Qiu, Zhijie Sun
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09152v1

Large language models (LLMs) often face a trade-off in post-training: improvements on specialized domains frequently come at the expense of general capabilities. Existing solutions attempt to mitigate this tension via regularization, selective parameter updates, or data-centric replay, but each imposes significant costs in computation, data access, or adaptability. Recent work has shown that training signals can be compressed to subsets of logits without severe accuracy loss, suggesting a path toward efficient adaptation. However, naive truncation destabilizes optimization and exacerbates forgetting. We introduce Logits Replay + MoClip, a two-stage framework that compresses supervision in the logit space and stabilizes optimization at the update level. In Stage 0, we record dynamic Top-K token subsets that cover a probability threshold, always including the gold label. In Stage 1, we replay these compact subsets to compute exact renormalized losses, avoiding full softmax computation and implicitly regularizing. To ensure stability, we design MoClip, an optimizer that caps gradient-momentum rotation and applies an arctan2-based rescaling of updates. Empirically, our method improves domain performance on Communication Technology (CT) and NL2SQL tasks while mitigating forgetting on general benchmarks (MMLU, BBH, GPQA, MATH), and reduces training cost by over 40%. Together, these contributions offer a scalable, architecture-agnostic path for domain adaptation of LLMs without sacrificing generalization.

---

### Score-Based Density Estimation from Pairwise Comparisons

Authors: Petrus Mikkola, Luigi Acerbi, Arto Klami
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09146v2

We study density estimation from pairwise comparisons, motivated by expert knowledge elicitation and learning from human feedback. We relate the unobserved target density to a tempered winner density (marginal density of preferred choices), learning the winner's score via score-matching. This allows estimating the target by `de-tempering' the estimated winner density's score. We prove that the score vectors of the belief and the winner density are collinear, linked by a position-dependent tempering field. We give analytical formulas for this field and propose an estimator for it under the Bradley-Terry model. Using a diffusion model trained on tempered samples generated via score-scaled annealed Langevin dynamics, we can learn complex multivariate belief densities of simulated experts, from only hundreds to thousands of pairwise comparisons.

---

### Online Topological Localization for Navigation Assistance in Bronchoscopy

Authors: Clara Tomasini, Luis Riazuelo, Ana C. Murillo
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09144v2

Video bronchoscopy is a fundamental procedure in respiratory medicine, where medical experts navigate through the bronchial tree of a patient to diagnose or operate the patient. Surgeons need to determine the position of the scope as they go through the airway until they reach the area of interest. This task is very challenging for practitioners due to the complex bronchial tree structure and varying doctor experience and training. Navigation assistance to locate the bronchoscope during the procedure can improve its outcome. Currently used techniques for navigational guidance commonly rely on previous CT scans of the patient to obtain a 3D model of the airway, followed by tracking of the scope with additional sensors or image registration. These methods obtain accurate locations but imply additional setup, scans and training. Accurate metric localization is not always required, and a topological localization with regard to a generic airway model can often suffice to assist the surgeon with navigation. We present an image-based bronchoscopy topological localization pipeline to provide navigation assistance during the procedure, with no need of patient CT scan. Our approach is trained only on phantom data, eliminating the high cost of real data labeling, and presents good generalization capabilities. The results obtained surpass existing methods, particularly on real data test sequences.

---

### Controlled Personalization in Legacy Media Online Services: A Case Study in News Recommendation

Authors: Marlene Holzleitner, Stephan Leitner, Hanna Lind Jorgensen, Christoph Schmitz, Jacob Welander, Dietmar Jannach
Published: 2025-10-10
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.09136v2

Personalized news recommendations have become a standard feature of large news aggregation services, optimizing user engagement through automated content selection. In contrast, legacy news media often approach personalization cautiously, striving to balance technological innovation with core editorial values. As a result, online platforms of traditional news outlets typically combine editorially curated content with algorithmically selected articles - a strategy we term controlled personalization. In this industry article, we evaluate the effectiveness of controlled personalization through an A/B test conducted on the website of a major Norwegian legacy news organization. Our findings indicate that even a modest level of personalization yields substantial benefits. Specifically, we observe that users exposed to personalized content demonstrate higher click-through-rates and reduced navigation effort, suggesting improved discovery of relevant content. Moreover, our analysis reveals that controlled personalization contributes to greater content diversity and catalog coverage and in addition reduces popularity bias. Overall, our results suggest that controlled personalization can successfully align user needs with editorial goals, offering a viable path for legacy media to adopt personalization technologies while upholding journalistic values.

---

### Training Feature Attribution for Vision Models

Authors: Aziz Bacha, Thomas George
Published: 2025-10-10
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.09135v1

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g., pixels in an image) or to influential training examples. We argue that both perspectives should be studied jointly. This work explores *training feature attribution*, which links test predictions to specific regions of specific training images and thereby provides new insights into the inner workings of deep models. Our experiments on vision datasets show that training feature attribution yields fine-grained, test-specific explanations: it identifies harmful examples that drive misclassifications and reveals spurious correlations, such as patch-based shortcuts, that conventional attribution methods fail to expose.

---

### On the Provable Performance Guarantee of Efficient Reasoning Models

Authors: Hao Zeng, Jianguo Huang, Bingyi Jing, Hongxin Wei, Bo An
Published: 2025-10-10
Categories: cs.AI, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.09133v2

Large reasoning models (LRMs) have achieved remarkable progress in complex problem-solving tasks. Despite this success, LRMs typically suffer from high computational costs during deployment, highlighting a need for efficient inference. A practical direction of efficiency improvement is to switch the LRM between thinking and non-thinking modes dynamically. However, such approaches often introduce additional reasoning errors and lack statistical guarantees for the performance loss, which are critical for high-stakes applications. In this work, we propose Probably Approximately Correct (PAC) reasoning that controls the performance loss under the user-specified tolerance. Specifically, we construct an upper confidence bound on the performance loss and determine a threshold for switching to the non-thinking model. Theoretically, using the threshold to switch between the thinking and non-thinking modes ensures bounded performance loss in a distribution-free manner. Our comprehensive experiments on reasoning benchmarks show that the proposed method can save computational budgets and control the user-specified performance loss.

---

### Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback

Authors: Orin Levy, Liad Erez, Alon Cohen, Yishay Mansour
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09127v1

We present regret minimization algorithms for the contextual multi-armed bandit (CMAB) problem over $K$ actions in the presence of delayed feedback, a scenario where loss observations arrive with delays chosen by an adversary. As a preliminary result, assuming direct access to a finite policy class $Π$ we establish an optimal expected regret bound of $ O (\sqrt{KT \log |Π|} + \sqrt{D \log |Π|)} $ where $D$ is the sum of delays. For our main contribution, we study the general function approximation setting over a (possibly infinite) contextual loss function class $ \mathcal{F} $ with access to an online least-square regression oracle $\mathcal{O}$ over $\mathcal{F}$. In this setting, we achieve an expected regret bound of $O(\sqrt{KT\mathcal{R}_T(\mathcal{O})} + \sqrt{ d_{\max} D β})$ assuming FIFO order, where $d_{\max}$ is the maximal delay, $\mathcal{R}_T(\mathcal{O})$ is an upper bound on the oracle's regret and $β$ is a stability parameter associated with the oracle. We complement this general result by presenting a novel stability analysis of a Hedge-based version of Vovk's aggregating forecaster as an oracle implementation for least-square regression over a finite function class $\mathcal{F}$ and show that its stability parameter $β$ is bounded by $\log |\mathcal{F}|$, resulting in an expected regret bound of $O(\sqrt{KT \log |\mathcal{F}|} + \sqrt{d_{\max} D \log |\mathcal{F}|})$ which is a $\sqrt{d_{\max}}$ factor away from the lower bound of $Ω(\sqrt{KT \log |\mathcal{F}|} + \sqrt{D \log |\mathcal{F}|})$ that we also present.

---

### Polar Separable Transform for Efficient Orthogonal Rotation-Invariant Image Representation

Authors: Satya P. Singh, Rashmi Chaudhry, Anand Srivastava, Jagath C. Rajapakse
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09125v1

Orthogonal moment-based image representations are fundamental in computer vision, but classical methods suffer from high computational complexity and numerical instability at large orders. Zernike and pseudo-Zernike moments, for instance, require coupled radial-angular processing that precludes efficient factorization, resulting in $\mathcal{O}(n^3N^2)$ to $\mathcal{O}(n^6N^2)$ complexity and $\mathcal{O}(N^4)$ condition number scaling for the $n$th-order moments on an $N\times N$ image. We introduce \textbf{PSepT} (Polar Separable Transform), a separable orthogonal transform that overcomes the non-separability barrier in polar coordinates. PSepT achieves complete kernel factorization via tensor-product construction of Discrete Cosine Transform (DCT) radial bases and Fourier harmonic angular bases, enabling independent radial and angular processing. This separable design reduces computational complexity to $\mathcal{O}(N^2 \log N)$, memory requirements to $\mathcal{O}(N^2)$, and condition number scaling to $\mathcal{O}(\sqrt{N})$, representing exponential improvements over polynomial approaches. PSepT exhibits orthogonality, completeness, energy conservation, and rotation-covariance properties. Experimental results demonstrate better numerical stability, computational efficiency, and competitive classification performance on structured datasets, while preserving exact reconstruction. The separable framework enables high-order moment analysis previously infeasible with classical methods, opening new possibilities for robust image analysis applications.

---

### MSDM: Generating Task-Specific Pathology Images with a Multimodal Conditioned Diffusion Model for Cell and Nuclei Segmentation

Authors: Dominik Winter, Mai Bui, Monica Azqueta Gavaldon, Nicolas Triltsch, Marco Rosati, Nicolas Brieu
Published: 2025-10-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.09121v2

Scarcity of annotated data, particularly for rare or atypical morphologies, present significant challenges for cell and nuclei segmentation in computational pathology. While manual annotation is labor-intensive and costly, synthetic data offers a cost-effective alternative. We introduce a Multimodal Semantic Diffusion Model (MSDM) for generating realistic pixel-precise image-mask pairs for cell and nuclei segmentation. By conditioning the generative process with cellular/nuclear morphologies (using horizontal and vertical maps), RGB color characteristics, and BERT-encoded assay/indication metadata, MSDM generates datasests with desired morphological properties. These heterogeneous modalities are integrated via multi-head cross-attention, enabling fine-grained control over the generated images. Quantitative analysis demonstrates that synthetic images closely match real data, with low Wasserstein distances between embeddings of generated and real images under matching biological conditions. The incorporation of these synthetic samples, exemplified by columnar cells, significantly improves segmentation model accuracy on columnar cells. This strategy systematically enriches data sets, directly targeting model deficiencies. We highlight the effectiveness of multimodal diffusion-based augmentation for advancing the robustness and generalizability of cell and nuclei segmentation models. Thereby, we pave the way for broader application of generative models in computational pathology.

---

### DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation

Authors: Enze Zhang, Jiaying Wang, Mengxi Xiao, Jifei Liu, Ziyan Kuang, Rui Dong, Eric Dong, Sophia Ananiadou, Min Peng, Qianqian Xie
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09116v2

Large language models (LLMs) have substantially advanced machine translation (MT), yet their effectiveness in translating web novels remains unclear. Existing benchmarks rely on surface-level metrics that fail to capture the distinctive traits of this genre. To address these gaps, we introduce DITING, the first comprehensive evaluation framework for web novel translation, assessing narrative and cultural fidelity across six dimensions: idiom translation, lexical ambiguity, terminology localization, tense consistency, zero-pronoun resolution, and cultural safety, supported by over 18K expert-annotated Chinese-English sentence pairs. We further propose AgentEval, a reasoning-driven multi-agent evaluation framework that simulates expert deliberation to assess translation quality beyond lexical overlap, achieving the highest correlation with human judgments among seven tested automatic metrics. To enable metric comparison, we develop MetricAlign, a meta-evaluation dataset of 300 sentence pairs annotated with error labels and scalar quality scores. Comprehensive evaluation of fourteen open, closed, and commercial models reveals that Chinese-trained LLMs surpass larger foreign counterparts, and that DeepSeek-V3 delivers the most faithful and stylistically coherent translations. Our work establishes a new paradigm for exploring LLM-based web novel translation and provides public resources to advance future research.

---

### On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning

Authors: Zhi Yang, Changwu Huang, Ke Tang, Xin Yao
Published: 2025-10-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09114v3

While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups remains underexplored. Existing studies have proposed methods to assess group privacy risks, but these are based on the average-case privacy risks of data records. Such approaches may underestimate the group privacy risks, thereby potentially underestimating the disparity across group privacy risks. Moreover, the current method for assessing the worst-case privacy risks of data records is time-consuming, limiting their practical applicability. To address these limitations, we introduce a novel membership inference game that can efficiently audit the approximate worst-case privacy risks of data records. Experimental results demonstrate that our method provides a more stringent measurement of group privacy risks, yielding a reliable assessment of the disparity in group privacy risks. Furthermore, to promote privacy protection fairness in DPML, we enhance the standard DP-SGD algorithm with an adaptive group-specific gradient clipping strategy, inspired by the design of canaries in differential privacy auditing studies. Extensive experiments confirm that our algorithm effectively reduces the disparity in group privacy risks, thereby enhancing the fairness of privacy protection in DPML.

---

### Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding

Authors: Weikai Huang, Jieyu Zhang, Taoyang Jia, Chenhao Zheng, Ziqi Gao, Jae Sung Park, Winson Han, Ranjay Krishna
Published: 2025-10-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.09110v4

Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision are powered by large-scale, painstakingly annotated datasets. Despite their impact, these datasets are costly to build, biased in coverage, and difficult to scale. Synthetic datasets offer a promising alternative but struggle with flexibility, accuracy, and compositional diversity. We introduce Synthetic Object Compositions (SOC), an accurate and scalable data synthesis pipeline via a novel object-centric composition strategy. It composes high-quality synthetic object segments into new images using 3D geometric layout augmentation and camera configuration augmentation with generative harmonization and mask-area-weighted blending, yielding accurate and diverse masks, boxes, and referring expressions. Models trained on just 100K of our synthetic images outperform those trained on larger real datasets (GRIT 20M, V3Det 200K) and synthetic pipelines (Copy-Paste, X-Paste, SynGround, SegGen) by +24-36% -- achieving +10.9 AP on LVIS and +8.4 NAcc on gRefCOCO. Beyond the general open-vocabulary setup, SOC also enables controllable dataset construction for different use cases and boosts performance in both low-data and closed-vocabulary scenarios. Augmenting LVIS and COCO with synthetic object segments delivers strong performance across different real-data scales and yields even greater improvements under extremely limited real-data conditions, including +6.59 AP on a 1% COCO data setup. Furthermore, this controllability enables targeted data generation for intra-class referring, a diagnostic grounding task we propose that requires fine-grained attribute discrimination.

---

### A Novel Multi-branch ConvNeXt Architecture for Identifying Subtle Pathological Features in CT Scans

Authors: Irash Perera, Uthayasanker Thayasivam
Published: 2025-10-10
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.09107v2

Intelligent analysis of medical imaging plays a crucial role in assisting clinical diagnosis, especially for identifying subtle pathological features. This paper introduces a novel multi-branch ConvNeXt architecture designed specifically for the nuanced challenges of medical image analysis. While applied here to the specific problem of COVID-19 diagnosis, the methodology offers a generalizable framework for classifying a wide range of pathologies from CT scans. The proposed model incorporates a rigorous end-to-end pipeline, from meticulous data preprocessing and augmentation to a disciplined two-phase training strategy that leverages transfer learning effectively. The architecture uniquely integrates features extracted from three parallel branches: Global Average Pooling, Global Max Pooling, and a new Attention-weighted Pooling mechanism. The model was trained and validated on a combined dataset of 2,609 CT slices derived from two distinct datasets. Experimental results demonstrate a superior performance on the validation set, achieving a final ROC-AUC of 0.9937, a validation accuracy of 0.9757, and an F1-score of 0.9825 for COVID-19 cases, outperforming all previously reported models on this dataset. These findings indicate that a modern, multi-branch architecture, coupled with careful data handling, can achieve performance comparable to or exceeding contemporary state-of-the-art models, thereby proving the efficacy of advanced deep learning techniques for robust medical diagnostics.

---

### When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs

Authors: Yongjie Wang, Yue Yu, Kaisong Song, Jun Lin, Zhiqi Shen
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09106v1

Large Language Models (LLMs) have enabled a wide range of applications through their powerful capabilities in language understanding and generation. However, as LLMs are trained on static corpora, they face difficulties in addressing rapidly evolving information or domain-specific queries. Retrieval-Augmented Generation (RAG) was developed to overcome this limitation by integrating LLMs with external retrieval mechanisms, allowing them to access up-to-date and contextually relevant knowledge. However, as LLMs themselves continue to advance in scale and capability, the relative advantages of traditional RAG frameworks have become less pronounced and necessary. Here, we present a comprehensive review of RAG, beginning with its overarching objectives and core components. We then analyze the key challenges within RAG, highlighting critical weakness that may limit its effectiveness. Finally, we showcase applications where LLMs alone perform inadequately, but where RAG, when combined with LLMs, can substantially enhance their effectiveness. We hope this work will encourage researchers to reconsider the role of RAG and inspire the development of next-generation RAG systems.

---

### MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples

Authors: Soroush Mahdi, Maryam Amirmazlaghani, Saeed Saravani, Zahra Dehghanian
Published: 2025-10-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09105v1

In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance model robustness and accuracy without compromising performance on clean data. By using these examples across training epochs, MemLoss provides a balanced improvement in both natural accuracy and adversarial robustness. Experimental results on multiple datasets, including CIFAR-10, demonstrate that our method achieves better accuracy compared to existing adversarial training methods while maintaining strong robustness against attacks.

---

### AdaPM: a Partial Momentum Algorithm for LLM Training

Authors: Yimu Zhang, Yuanshi Liu, Cong Fang
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09103v1

In the training of large language models, momentum is widely used and often demonstrated to achieve significant acceleration. However, storing momentum typically presents memory challenges. In this paper, we propose AdaPM, an adaptive training strategy that leverages partial momentum to implement a memory-efficient optimizer. To this end, AdaPM utilizes a non-uniform momentum design: for most blocks, full momentum is not necessary to preserve the performance of the optimization. In the momentum design of AdaPM, to mitigate the bias and performance loss caused by partial momentum, we enhance the partial momentum by a bias correction technique. Empirically, we verify that our approach reduces memory by over $90\%$ in momentum while maintaining both efficiency and performance for pretraining various language models ranging from 60M to 1.5B, as well as for supervised fine-tuning and RLHF. AdaPM can further reduce memory by up to $95\%$ in optimizer states by combining the memory-efficient technique on the second-order statistic, saving over $30\%$ GPU hours for pretraining GPT-2 1.5B.

---

### FrameEOL: Semantic Frame Induction using Causal Language Models

Authors: Chihiro Yano, Kosuke Yamada, Hayato Tsukagoshi, Ryohei Sasano, Koichi Takeda
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09097v1

Semantic frame induction is the task of clustering frame-evoking words according to the semantic frames they evoke. In recent years, leveraging embeddings of frame-evoking words that are obtained using masked language models (MLMs) such as BERT has led to high-performance semantic frame induction. Although causal language models (CLMs) such as the GPT and Llama series succeed in a wide range of language comprehension tasks and can engage in dialogue as if they understood frames, they have not yet been applied to semantic frame induction. We propose a new method for semantic frame induction based on CLMs. Specifically, we introduce FrameEOL, a prompt-based method for obtaining Frame Embeddings that outputs One frame-name as a Label representing the given situation. To obtain embeddings more suitable for frame induction, we leverage in-context learning (ICL) and deep metric learning (DML). Frame induction is then performed by clustering the resulting embeddings. Experimental results on the English and Japanese FrameNet datasets demonstrate that the proposed methods outperform existing frame induction methods. In particular, for Japanese, which lacks extensive frame resources, the CLM-based method using only 5 ICL examples achieved comparable performance to the MLM-based method fine-tuned with DML.

---

### When a Robot is More Capable than a Human: Learning from Constrained Demonstrators

Authors: Xinhu Li, Ayush Jain, Zhaojing Yang, Yigit Korkmaz, Erdem Bıyık
Published: 2025-10-10
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.09096v3

Learning from demonstrations enables experts to teach robots complex tasks using interfaces such as kinesthetic teaching, joystick control, and sim-to-real transfer. However, these interfaces often constrain the expert's ability to demonstrate optimal behavior due to indirect control, setup restrictions, and hardware safety. For example, a joystick can move a robotic arm only in a 2D plane, even though the robot operates in a higher-dimensional space. As a result, the demonstrations collected by constrained experts lead to suboptimal performance of the learned policies. This raises a key question: Can a robot learn a better policy than the one demonstrated by a constrained expert? We address this by allowing the agent to go beyond direct imitation of expert actions and explore shorter and more efficient trajectories. We use the demonstrations to infer a state-only reward signal that measures task progress, and self-label reward for unknown states using temporal interpolation. Our approach outperforms common imitation learning in both sample efficiency and task completion time. On a real WidowX robotic arm, it completes the task in 12 seconds, 10x faster than behavioral cloning, as shown in real-robot videos on https://sites.google.com/view/constrainedexpert .

---

### Neural Codecs as Biosignal Tokenizers

Authors: Kleanthis Avramidis, Tiantian Feng, Woojae Jeong, Jihwan Lee, Wenhui Cui, Richard M Leahy, Shrikanth Narayanan
Published: 2025-10-10
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.09095v1

Neurophysiological recordings such as electroencephalography (EEG) offer accessible and minimally invasive means of estimating physiological activity for applications in healthcare, diagnostic screening, and even immersive entertainment. However, these recordings yield high-dimensional, noisy time-series data that typically require extensive pre-processing and handcrafted feature extraction to reveal meaningful information. Recently, there has been a surge of interest in applying representation learning techniques from large pre-trained (foundation) models to effectively decode and interpret biosignals. We discuss the challenges posed for incorporating such methods and introduce BioCodec, an alternative representation learning framework inspired by neural codecs to capture low-level signal characteristics in the form of discrete tokens. Pre-trained on thousands of EEG hours, BioCodec shows efficacy across multiple downstream tasks, ranging from clinical diagnostic tasks and sleep physiology to decoding speech and motor imagery, particularly in low-resource settings. Additionally, we provide a qualitative analysis of codebook usage and estimate the spatial coherence of codebook embeddings from EEG connectivity. Notably, we also document the suitability of our method to other biosignal data, i.e., electromyographic (EMG) signals. Overall, the proposed approach provides a versatile solution for biosignal tokenization that performs competitively with state-of-the-art models. The source code and model checkpoints are shared.

---

### Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

Authors: Youwei Zheng, Yuxi Ren, Xin Xia, Xuefeng Xiao, Xiaohua Xie
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09094v1

Diffusion Transformer (DiT) has demonstrated remarkable performance in text-to-image generation; however, its large parameter size results in substantial inference overhead. Existing parameter compression methods primarily focus on pruning, but aggressive pruning often leads to severe performance degradation due to reduced model capacity. To address this limitation, we pioneer the transformation of a dense DiT into a Mixture of Experts (MoE) for structured sparsification, reducing the number of activated parameters while preserving model capacity. Specifically, we replace the Feed-Forward Networks (FFNs) in DiT Blocks with MoE layers, reducing the number of activated parameters in the FFNs by 62.5\%. Furthermore, we propose the Mixture of Blocks (MoB) to selectively activate DiT blocks, thereby further enhancing sparsity. To ensure an effective dense-to-MoE conversion, we design a multi-step distillation pipeline, incorporating Taylor metric-based expert initialization, knowledge distillation with load balancing, and group feature loss for MoB optimization. We transform large diffusion transformers (e.g., FLUX.1 (dev)) into an MoE structure, reducing activated parameters by 60\% while maintaining original performance and surpassing pruning-based approaches in extensive experiments. Overall, Dense2MoE establishes a new paradigm for efficient text-to-image generation.

---

### Exploiting Web Search Tools of AI Agents for Data Exfiltration

Authors: Dennis Rall, Bernhard Bauer, Mohit Mittal, Thomas Fraunholz
Published: 2025-10-10
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.09093v2

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows LLMs to process and retrieve sensitive corporate data, amplifying both their functionality and vulnerability to abuse. As LLMs increasingly interact with external data sources, indirect prompt injection emerges as a critical and evolving attack vector, enabling adversaries to exploit models through manipulated inputs. Through a systematic evaluation of indirect prompt injection attacks across diverse models, we analyze how susceptible current LLMs are to such attacks, which parameters, including model size and manufacturer, specific implementations, shape their vulnerability, and which attack methods remain most effective. Our results reveal that even well-known attack patterns continue to succeed, exposing persistent weaknesses in model defenses. To address these vulnerabilities, we emphasize the need for strengthened training procedures to enhance inherent resilience, a centralized database of known attack vectors to enable proactive defense, and a unified testing framework to ensure continuous security validation. These steps are essential to push developers toward integrating security into the core design of LLMs, as our findings show that current models still fail to mitigate long-standing threats.

---

### GL-DT: Multi-UAV Detection and Tracking with Global-Local Integration

Authors: Juanqin Liu, Leonardo Plotegher, Eloy Roura, Shaoming He
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09092v1

The extensive application of unmanned aerial vehicles (UAVs) in military reconnaissance, environmental monitoring, and related domains has created an urgent need for accurate and efficient multi-object tracking (MOT) technologies, which are also essential for UAV situational awareness. However, complex backgrounds, small-scale targets, and frequent occlusions and interactions continue to challenge existing methods in terms of detection accuracy and trajectory continuity. To address these issues, this paper proposes the Global-Local Detection and Tracking (GL-DT) framework. It employs a Spatio-Temporal Feature Fusion (STFF) module to jointly model motion and appearance features, combined with a global-local collaborative detection strategy, effectively enhancing small-target detection. Building upon this, the JPTrack tracking algorithm is introduced to mitigate common issues such as ID switches and trajectory fragmentation. Experimental results demonstrate that the proposed approach significantly improves the continuity and stability of MOT while maintaining real-time performance, providing strong support for the advancement of UAV detection and tracking technologies.

---

### AI and Human Oversight: A Risk-Based Framework for Alignment

Authors: Laxmiraju Kandikatla, Branislav Radeljic
Published: 2025-10-10
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.09090v1

As Artificial Intelligence (AI) technologies continue to advance, protecting human autonomy and promoting ethical decision-making are essential to fostering trust and accountability. Human agency (the capacity of individuals to make informed decisions) should be actively preserved and reinforced by AI systems. This paper examines strategies for designing AI systems that uphold fundamental rights, strengthen human agency, and embed effective human oversight mechanisms. It discusses key oversight models, including Human-in-Command (HIC), Human-in-the-Loop (HITL), and Human-on-the-Loop (HOTL), and proposes a risk-based framework to guide the implementation of these mechanisms. By linking the level of AI model risk to the appropriate form of human oversight, the paper underscores the critical role of human involvement in the responsible deployment of AI, balancing technological innovation with the protection of individual values and rights. In doing so, it aims to ensure that AI technologies are used responsibly, safeguarding individual autonomy while maximizing societal benefits.

---

### MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modelling

Authors: Weijia Wang, Yuanzhi Su, Pei-Gen Ye, Yuan-Gen Wang
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09088v2

We present MambaH-Fit, a state space modelling framework tailored for hyper-surface fitting-based point cloud normal estimation. Existing normal estimation methods often fall short in modelling fine-grained geometric structures, thereby limiting the accuracy of the predicted normals. Recently, state space models (SSMs), particularly Mamba, have demonstrated strong modelling capability by capturing long-range dependencies with linear complexity and inspired adaptations to point cloud processing. However, existing Mamba-based approaches primarily focus on understanding global shape structures, leaving the modelling of local, fine-grained geometric details largely under-explored. To address the issues above, we first introduce an Attention-driven Hierarchical Feature Fusion (AHFF) scheme to adaptively fuse multi-scale point cloud patch features, significantly enhancing geometric context learning in local point cloud neighbourhoods. Building upon this, we further propose Patch-wise State Space Model (PSSM) that models point cloud patches as implicit hyper-surfaces via state dynamics, enabling effective fine-grained geometric understanding for normal prediction. Extensive experiments on benchmark datasets show that our method outperforms existing ones in terms of accuracy, robustness, and flexibility. Ablation studies further validate the contribution of the proposed components.

---

### The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games

Authors: Zhang Zheng, Deheng Ye, Peilin Zhao, Hao Wang
Published: 2025-10-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.09087v2

Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on information processing and strategy selection, overlooking the significance of persuasive communication in influencing other players' beliefs and responses. In SDGs, success depends not only on making correct deductions but on convincing others to response in alignment with one's intent. To address this limitation, we formalize turn-based dialogue in SDGs as a Stackelberg competition, where the current player acts as the leader who strategically influences the follower's response. Building on this theoretical foundation, we propose a reinforcement learning framework that trains agents to optimize utterances for persuasive impact. Through comprehensive experiments across three diverse SDGs, we demonstrate that our agents significantly outperform baselines. This work represents a significant step toward developing AI agents capable of strategic social influence, with implications extending to scenarios requiring persuasive communication. Our code and data are available at https://3dagentworld.github.io/leader_follower.

---

### FLToP CTC: Frame-Level Token Pruning via Relative Threshold for Efficient and Memory-Saving Decoding on Diverse Platforms

Authors: Atul Shree, Harshith Jupuru
Published: 2025-10-10
Categories: cs.LG, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2510.09085v1

CTC-based ASR systems face computational and memory bottlenecks in resource-limited environments. Traditional CTC decoders, requiring up to 90% of processing time in systems (e.g., wav2vec2-large on L4 GPUs), face inefficiencies due to exhaustive token-level operations. This paper introduces Frame Level Token Pruning for Connectionist Temporal Classification (FLToP CTC), a novel decoding algorithm that employs frame-level token pruning guided by a relative threshold probability. By dynamically eliminating low-probability tokens per frame, FLToP CTC reduces compute and memory demands while maintaining negligible WER degradation. On LibriSpeech, FLToP CTC achieves a 10.5x runtime speedup and 2.78x memory reduction versus standard CTC decoders. Its simplicity enables seamless integration into CTC decoders across platforms (CPUs, GPUs, etc.). FLToP CTC addresses CTC bottlenecks, offering scalability for resource-limited environments and realtime applications, enhancing speech recognition accessibility and efficiency.

---

### Physics-Informed High-order Graph Dynamics Identification Learning for Predicting Complex Networks Long-term Dynamics

Authors: Bicheng Wang, Junping Wang, Yibo Xue
Published: 2025-10-10
Categories: cs.AI, cs.CY, cs.SI, physics.soc-ph
arXiv: https://arxiv.org/abs/2510.09082v2

Learning complex network dynamics is fundamental to understanding, modelling and controlling real-world complex systems. There are two main problems in the task of predicting the dynamic evolution of complex networks: on the one hand, existing methods usually use simple graphs to describe the relationships in complex networks; however, this approach can only capture pairwise relationships, while there may be rich non-pairwise structured relationships in the network. First-order GNNs have difficulty in capturing dynamic non-pairwise relationships. On the other hand, theoretical prediction models lack accuracy and data-driven prediction models lack interpretability. To address the above problems, this paper proposes a higher-order network dynamics identification method for long-term dynamic prediction of complex networks. Firstly, to address the problem that traditional graph machine learning can only deal with pairwise relations, dynamic hypergraph learning is introduced to capture the higher-order non-pairwise relations among complex networks and improve the accuracy of complex network modelling. Then, a dual-driven dynamic prediction module for physical data is proposed. The Koopman operator theory is introduced to transform the nonlinear dynamical differential equations for the dynamic evolution of complex networks into linear systems for solving. Meanwhile, the physical information neural differential equation method is utilised to ensure that the dynamic evolution conforms to the physical laws. The dual-drive dynamic prediction module ensures both accuracy and interpretability of the prediction. Validated on public datasets and self-built industrial chain network datasets, the experimental results show that the method in this paper has good prediction accuracy and long-term prediction performance.

---

### Training Models to Detect Successive Robot Errors from Human Reactions

Authors: Shannon Liu, Maria Teresa Parreira, Wendy Ju
Published: 2025-10-10
Categories: cs.RO, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.09080v1

As robots become more integrated into society, detecting robot errors is essential for effective human-robot interaction (HRI). When a robot fails repeatedly, how can it know when to change its behavior? Humans naturally respond to robot errors through verbal and nonverbal cues that intensify over successive failures-from confusion and subtle speech changes to visible frustration and impatience. While prior work shows that human reactions can indicate robot failures, few studies examine how these evolving responses reveal successive failures. This research uses machine learning to recognize stages of robot failure from human reactions. In a study with 26 participants interacting with a robot that made repeated conversational errors, behavioral features were extracted from video data to train models for individual users. The best model achieved 93.5% accuracy for detecting errors and 84.1% for classifying successive failures. Modeling the progression of human reactions enhances error detection and understanding of repeated interaction breakdowns in HRI.

---

### Improving Anomaly Detection in Industrial Time Series: The Role of Segmentation and Heterogeneous Ensemble

Authors: Emilio Mastriani, Alessandro Costa, Federico Incardona, Kevin Munari, Sebastiano Spinello
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09079v1

Concerning machine learning, segmentation models can identify state changes within time series, facilitating the detection of transitions between normal and anomalous conditions. Specific techniques such as Change Point Detection (CPD), particularly algorithms like ChangeFinder, have been successfully applied to segment time series and improve anomaly detection by reducing temporal uncertainty, especially in multivariate environments. In this work, we explored how the integration of segmentation techniques, combined with a heterogeneous ensemble, can enhance anomaly detection in an industrial production context. The results show that applying segmentation as a pre-processing step before selecting heterogeneous ensemble algorithms provided a significant advantage in our case study, improving the AUC-ROC metric from 0.8599 (achieved with a PCA and LSTM ensemble) to 0.9760 (achieved with Random Forest and XGBoost). This improvement is imputable to the ability of segmentation to reduce temporal ambiguity and facilitate the learning process of supervised algorithms. In our future work, we intend to assess the benefit of introducing weighted features derived from the study of change points, combined with segmentation and the use of heterogeneous ensembles, to further optimize model performance in early anomaly detection.

---

### MCMC: Bridging Rendering, Optimization and Generative AI

Authors: Gurprit Singh, Wenzel Jakob
Published: 2025-10-10
Categories: cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2510.09078v1

Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. During the generative process, new samples (images) are generated from an unknown high-dimensional distribution. Markov Chain Monte Carlo (MCMC) methods are particularly effective in drawing samples from such complex, high-dimensional distributions. This makes MCMC methods an integral component for models like EBMs, ensuring accurate sample generation. Gradient-based optimization is at the core of modern generative models. The update step during the optimization forms a Markov chain where the new update depends only on the current state. This allows exploration of the parameter space in a memoryless manner, thus combining the benefits of gradient-based optimization and MCMC sampling. MCMC methods have shown an equally important role in physically based rendering where complex light paths are otherwise quite challenging to sample from simple importance sampling techniques. A lot of research is dedicated towards bringing physical realism to samples (images) generated from diffusion-based generative models in a data-driven manner, however, a unified framework connecting these techniques is still missing. In this course, we take the first steps toward understanding each of these components and exploring how MCMC could potentially serve as a bridge, linking these closely related areas of research. Our course aims to provide necessary theoretical and practical tools to guide students, researchers and practitioners towards the common goal of generative physically based rendering. All Jupyter notebooks with demonstrations associated to this tutorial can be found on the project webpage: https://sinbag.github.io/mcmc/

---

### Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition

Authors: Upasana Tiwari, Rupayan Chakraborty, Sunil Kumar Kopparapu
Published: 2025-10-10
Categories: cs.SD, cs.AI, cs.HC, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.09072v1

Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech emotion recognition models through improved representation learning. First, our model employs EDRL (Emotion-Disentangled Representation Learning) to extract class-specific discriminative features while preserving shared similarities across emotion categories. Next, MEA (Multiblock Embedding Alignment) refines these representations by projecting them into a joint discriminative latent subspace that maximizes covariance with the original speech input. The learned EDRL-MEA embeddings are subsequently used to train an emotion classifier using clean samples from publicly available datasets, and are evaluated on unseen noisy and cross-corpus speech samples. Improved performance under these challenging conditions demonstrates the effectiveness of the proposed method.

---

### Visual Anomaly Detection for Reliable Robotic Implantation of Flexible Microelectrode Array

Authors: Yitong Chen, Xinyao Xu, Ping Zhu, Xinyong Han, Fangbo Qin, Shan Yu
Published: 2025-10-10
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.09071v1

Flexible microelectrode (FME) implantation into brain cortex is challenging due to the deformable fiber-like structure of FME probe and the interaction with critical bio-tissue. To ensure reliability and safety, the implantation process should be monitored carefully. This paper develops an image-based anomaly detection framework based on the microscopic cameras of the robotic FME implantation system. The unified framework is utilized at four checkpoints to check the micro-needle, FME probe, hooking result, and implantation point, respectively. Exploiting the existing object localization results, the aligned regions of interest (ROIs) are extracted from raw image and input to a pretrained vision transformer (ViT). Considering the task specifications, we propose a progressive granularity patch feature sampling method to address the sensitivity-tolerance trade-off issue at different locations. Moreover, we select a part of feature channels with higher signal-to-noise ratios from the raw general ViT features, to provide better descriptors for each specific scene. The effectiveness of the proposed methods is validated with the image datasets collected from our implantation system.

---

### MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation

Authors: Akira Takahashi, Shusuke Takahashi, Yuki Mitsufuji
Published: 2025-10-10
Categories: cs.SD, cs.CV, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.09065v2

We introduce MMAudioSep, a generative model for video/text-queried sound separation that is founded on a pretrained video-to-audio model. By leveraging knowledge about the relationship between video/text and audio learned through a pretrained audio generative model, we can train the model more efficiently, i.e., the model does not need to be trained from scratch. We evaluate the performance of MMAudioSep by comparing it to existing separation models, including models based on both deterministic and generative approaches, and find it is superior to the baseline models. Furthermore, we demonstrate that even after acquiring functionality for sound separation via fine-tuning, the model retains the ability for original video-to-audio generation. This highlights the potential of foundational sound generation models to be adopted for sound-related downstream tasks. Our code is available at https://github.com/sony/mmaudiosep.

---