# Research Papers — 2025-10 · bundle page 191 of 217

> Full-text markdown of papers #9501–9550 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/191
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/190.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/192.md)

### Diverse Text-to-Image Generation via Contrastive Noise Optimization

Authors: Byungjun Kim, Soobin Um, Jong Chul Ye
Published: 2025-10-04
Categories: cs.GR, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.03813v3

Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as outputs tend to collapse into similar modes under strong text guidance. Existing approaches typically optimize intermediate latents or text conditions during inference, but these methods deliver only modest gains or remain sensitive to hyperparameter tuning. In this work, we introduce Contrastive Noise Optimization, a simple yet effective method that addresses the diversity issue from a distinct perspective. Unlike prior techniques that adapt intermediate latents, our approach shapes the initial noise to promote diverse outputs. Specifically, we develop a contrastive loss defined in the Tweedie data space and optimize a batch of noise latents. Our contrastive optimization repels instances within the batch to maximize diversity while keeping them anchored to a reference sample to preserve fidelity. We further provide theoretical insights into the mechanism of this preprocessing to substantiate its effectiveness. Extensive experiments across multiple T2I backbones demonstrate that our approach achieves a superior quality-diversity Pareto frontier while remaining robust to hyperparameter choices.

---

### ReTiDe: Real-Time Denoising for Energy-Efficient Motion Picture Processing with FPGAs

Authors: Changhong Li, Clément Bled, Rosa Fernandez, Shreejith Shanker
Published: 2025-10-04
Categories: eess.IV, cs.AI
arXiv: https://arxiv.org/abs/2510.03812v1

Denoising is a core operation in modern video pipelines. In codecs, in-loop filters suppress sensor noise and quantisation artefacts to improve rate-distortion performance; in cinema post-production, denoisers are used for restoration, grain management, and plate clean-up. However, state-of-the-art deep denoisers are computationally intensive and, at scale, are typically deployed on GPUs, incurring high power and cost for real-time, high-resolution streams. This paper presents Real-Time Denoise (ReTiDe), a hardware-accelerated denoising system that serves inference on data-centre Field Programmable Gate Arrays (FPGAs). A compact convolutional model is quantised (post-training quantisation plus quantisation-aware fine-tuning) to INT8 and compiled for AMD Deep Learning Processor Unit (DPU)-based FPGAs. A client-server integration offloads computation from the host CPU/GPU to a networked FPGA service, while remaining callable from existing workflows, e.g., NUKE, without disrupting artist tooling. On representative benchmarks, ReTiDe delivers 37.71$\times$ Giga Operations Per Second (GOPS) throughput and 5.29$\times$ higher energy efficiency than prior FPGA denoising accelerators, with negligible degradation in Peak Signal-to-Noise Ratio (PSNR)/Structural Similarity Index (SSIM). These results indicate that specialised accelerators can provide practical, scalable denoising for both encoding pipelines and post-production, reducing energy per frame without sacrificing quality or workflow compatibility. Code is available at https://github.com/RCSL-TCD/ReTiDe.

---

### Curriculum-Augmented GFlowNets For mRNA Sequence Generation

Authors: Aya Laajil, Abduragim Shtanchaev, Sajan Muhammad, Eric Moulines, Salem Lahlou
Published: 2025-10-04
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2510.03811v1

Designing mRNA sequences is a major challenge in developing next-generation therapeutics, since it involves exploring a vast space of possible nucleotide combinations while optimizing sequence properties like stability, translation efficiency, and protein expression. While Generative Flow Networks are promising for this task, their training is hindered by sparse, long-horizon rewards and multi-objective trade-offs. We propose Curriculum-Augmented GFlowNets (CAGFN), which integrate curriculum learning with multi-objective GFlowNets to generate de novo mRNA sequences. CAGFN integrates a length-based curriculum that progressively adapts the maximum sequence length guiding exploration from easier to harder subproblems. We also provide a new mRNA design environment for GFlowNets which, given a target protein sequence and a combination of biological objectives, allows for the training of models that generate plausible mRNA candidates. This provides a biologically motivated setting for applying and advancing GFlowNets in therapeutic sequence design. On different mRNA design tasks, CAGFN improves Pareto performance and biological plausibility, while maintaining diversity. Moreover, CAGFN reaches higher-quality solutions faster than a GFlowNet trained with random sequence sampling (no curriculum), and enables generalization to out-of-distribution sequences.

---

### Cellular Learning: Scattered Data Regression in High Dimensions via Voronoi Cells

Authors: Shankar Prasad Sastry
Published: 2025-10-04
Categories: cs.CG, cs.LG
arXiv: https://arxiv.org/abs/2510.03810v1

I present a regression algorithm that provides a continuous, piecewise-smooth function approximating scattered data. It is based on composing and blending linear functions over Voronoi cells, and it scales to high dimensions. The algorithm infers Voronoi cells from seed vertices and constructs a linear function for the input data in and around each cell. As the algorithm does not explicitly compute the Voronoi diagram, it avoids the curse of dimensionality. An accuracy of around 98.2% on the MNIST dataset with 722,200 degrees of freedom (without data augmentation, convolution, or other geometric operators) demonstrates the applicability and scalability of the algorithm.

---

### Spectral Thresholds for Identifiability and Stability:Finite-Sample Phase Transitions in High-Dimensional Learning

Authors: William Hao-Cheng Huang
Published: 2025-10-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.03809v2

In high-dimensional learning, models remain stable until they collapse abruptly once the sample size falls below a critical level. This instability is not algorithm-specific but a geometric mechanism: when the weakest Fisher eigendirection falls beneath sample-level fluctuations, identifiability fails. Our Fisher Threshold Theorem formalizes this by proving that stability requires the minimal Fisher eigenvalue to exceed an explicit $O(\sqrt{d/n})$ bound. Unlike prior asymptotic or model-specific criteria, this threshold is finite-sample and necessary, marking a sharp phase transition between reliable concentration and inevitable failure. To make the principle constructive, we introduce the Fisher floor, a verifiable spectral regularization robust to smoothing and preconditioning. Synthetic experiments on Gaussian mixtures and logistic models confirm the predicted transition, consistent with $d/n$ scaling. Statistically, the threshold sharpens classical eigenvalue conditions into a non-asymptotic law; learning-theoretically, it defines a spectral sample-complexity frontier, bridging theory with diagnostics for robust high-dimensional inference.

---

### Annotate Rhetorical Relations with INCEpTION: A Comparison with Automatic Approaches

Authors: Mehedi Hasan Emon
Published: 2025-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03808v1

This research explores the annotation of rhetorical relations in discourse using the INCEpTION tool and compares manual annotation with automatic approaches based on large language models. The study focuses on sports reports (specifically cricket news) and evaluates the performance of BERT, DistilBERT, and Logistic Regression models in classifying rhetorical relations such as elaboration, contrast, background, and cause-effect. The results show that DistilBERT achieved the highest accuracy, highlighting its potential for efficient discourse relation prediction. This work contributes to the growing intersection of discourse parsing and transformer-based NLP. (This paper was conducted as part of an academic requirement under the supervision of Prof. Dr. Ralf Klabunde, Linguistic Data Science Lab, Ruhr University Bochum.) Keywords: Rhetorical Structure Theory, INCEpTION, BERT, DistilBERT, Discourse Parsing, NLP.

---

### 6G-Enabled Digital Twin Framework for Real-Time Cyber-Physical Systems: An Experimental Validation with Industrial Bearing Fault Detection

Authors: Vaskar Chakma, Wooyeol Choi
Published: 2025-10-04
Categories: cs.NI, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03807v2

Current Cyber-Physical Systems (CPS) integrated with Digital Twin (DT) technology face critical limitations in achieving real-time performance for mission-critical industrial applications. Existing 5G-enabled systems suffer from latencies exceeding 10ms, which are inadequate for applications requiring sub-millisecond response times, such as autonomous industrial control and predictive maintenance. This research aims to develop and validate a 6G-enabled Digital Twin framework that achieves ultra-low latency communication and real-time synchronization between physical industrial assets and their digital counterparts, specifically targeting bearing fault detection as a critical industrial use case. The proposed framework integrates terahertz communications (0.1-1 THz), intelligent reflecting surfaces, and edge artificial intelligence within a five-layer architecture. Experimental validation was conducted using the Case Western Reserve University (CWRU) bearing dataset, implementing comprehensive feature extraction (15 time and frequency domain features) and Random Forest classification algorithms. The system performance was evaluated against traditional WiFi-6 and 5G networks across multiple metrics, including classification accuracy, end-to-end latency, and scalability. It achieved 97.7% fault classification accuracy with 0.8ms end-to-end latency, representing a 15.6x improvement over WiFi-6 (12.5ms) and 5.25x improvement over 5G (4.2ms) networks. The system demonstrated superior scalability with sub-linear processing time growth and maintained consistent performance across four bearing fault categories (normal, inner race, outer race, and ball faults) with macro-averaged F1-scores exceeding 97%.

---

### Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models

Authors: Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He
Published: 2025-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03805v3

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to promote conciseness. However, these methods encounter two challenges: responses with fewer tokens do not always correspond to fewer reasoning steps, and models may develop hacking behavior in later stages of training by discarding reasoning steps to minimize token usage. In this work, we introduce \textbf{Step Pruner (SP)}, an RL framework that steers LRMs toward more efficient reasoning by favoring compact reasoning steps. Our step-aware reward function prioritizes correctness while imposing penalties for redundant steps, and withholds rewards for incorrect responses to prevent the reinforcement of erroneous reasoning. Moreover, we propose a dynamic stopping mechanism: when the model's output no longer shortens, training is halted to prevent hacking behavior caused by the merging of steps. Extensive experiments across four reasoning benchmarks demonstrate that SP achieves state-of-the-art accuracy while significantly reducing response length. For instance, on AIME24, SP reduces token usage by \textbf{69.7\%}.

---

### Mechanistic Interpretability of Socio-Political Frames in Language Models

Authors: Hadi Asghari, Sami Nenno
Published: 2025-10-04
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.03799v1

This paper explores the ability of large language models to generate and recognize deep cognitive frames, particularly in socio-political contexts. We demonstrate that LLMs are highly fluent in generating texts that evoke specific frames and can recognize these frames in zero-shot settings. Inspired by mechanistic interpretability research, we investigate the location of the `strict father' and `nurturing parent' frames within the model's hidden representation, identifying singular dimensions that correlate strongly with their presence. Our findings contribute to understanding how LLMs capture and express meaningful human concepts.

---

### Batched Bandits with Heavy-Tailed Rewards

Authors: Yunwen Guo, Yunlun Shu, Gongyi Zhuo, Tianyu Wang
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03798v3

The batched multi-armed bandit (MAB) problem, where rewards are collected in batches, is pivotal in applications like clinical trials. While prior work assumes light-tailed reward distributions, real-world scenarios often exhibit heavy-tailed outcomes. This paper addresses this gap by introducing robust batched bandit algorithms for heavy-tailed rewards in both multi-arm and Lipschitz settings. We uncover somewhat surprising phenomena for such problems -- heavier tails require fewer batches to achieve near-optimal regret in the instance-independent setting, as well as the Lipschitz setting. In sharp contrast, in the instance-dependent setting, the number of batches required to achieve near-optimal regret does not depend on the tail heaviness.

---

### Road Damage and Manhole Detection using Deep Learning for Smart Cities: A Polygonal Annotation Approach

Authors: Rasel Hossen, Diptajoy Mistry, Mushiur Rahman, Waki As Sami Atikur Rahman Hridoy, Sajib Saha, Muhammad Ibrahim
Published: 2025-10-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.03797v1

Urban safety and infrastructure maintenance are critical components of smart city development. Manual monitoring of road damages is time-consuming, highly costly, and error-prone. This paper presents a deep learning approach for automated road damage and manhole detection using the YOLOv9 algorithm with polygonal annotations. Unlike traditional bounding box annotation, we employ polygonal annotations for more precise localization of road defects. We develop a novel dataset comprising more than one thousand images which are mostly collected from Dhaka, Bangladesh. This dataset is used to train a YOLO-based model for three classes, namely Broken, Not Broken, and Manhole. We achieve 78.1% overall image-level accuracy. The YOLOv9 model demonstrates strong performance for Broken (86.7% F1-score) and Not Broken (89.2% F1-score) classes, with challenges in Manhole detection (18.2% F1-score) due to class imbalance. Our approach offers an efficient and scalable solution for monitoring urban infrastructure in developing countries.

---

### Investigating LLM Variability in Personalized Conversational Information Retrieval

Authors: Simon Lupart, Daniël van Dijk, Eric Langezaal, Ian van Dort, Mohammad Aliannejadi
Published: 2025-10-04
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.03795v1

Personalized Conversational Information Retrieval (CIR) has seen rapid progress in recent years, driven by the development of Large Language Models (LLMs). Personalized CIR aims to enhance document retrieval by leveraging user-specific information, such as preferences, knowledge, or constraints, to tailor responses to individual needs. A key resource for this task is the TREC iKAT 2023 dataset, designed to evaluate personalization in CIR pipelines. Building on this resource, Mo et al. explored several strategies for incorporating Personal Textual Knowledge Bases (PTKB) into LLM-based query reformulation. Their findings suggested that personalization from PTKBs could be detrimental and that human annotations were often noisy. However, these conclusions were based on single-run experiments using the GPT-3.5 Turbo model, raising concerns about output variability and repeatability. In this reproducibility study, we rigorously reproduce and extend their work, focusing on LLM output variability and model generalization. We apply the original methods to the new TREC iKAT 2024 dataset and evaluate a diverse range of models, including Llama (1B-70B), Qwen-7B, GPT-4o-mini. Our results show that human-selected PTKBs consistently enhance retrieval performance, while LLM-based selection methods do not reliably outperform manual choices. We further compare variance across datasets and observe higher variability on iKAT than on CAsT, highlighting the challenges of evaluating personalized CIR. Notably, recall-oriented metrics exhibit lower variance than precision-oriented ones, a critical insight for first-stage retrievers. Finally, we underscore the need for multi-run evaluations and variance reporting when assessing LLM-based CIR systems. By broadening evaluation across models, datasets, and metrics, our study contributes to more robust and generalizable practices for personalized CIR.

---

### Lightweight and Data-Efficient MultivariateTime Series Forecasting using Residual-Stacked Gaussian (RS-GLinear) Architecture

Authors: Abukar Ali
Published: 2025-10-04
Categories: cs.CE, cs.AI
arXiv: https://arxiv.org/abs/2510.03788v1

Following the success of Transformer architectures in language modeling, particularly their ability to capture long-range dependencies, researchers have explored how these architectures can be adapted for time-series forecasting. Transformer-based models have been proposed to handle both short- and long-term dependencies when predicting future values from historical data. However, studies such as those by Zeng et al. (2022) and Rizvi et al. (2025) have reported mixed results in long-term forecasting tasks. In this work, we evaluate the Gaussian-based Linear architecture introduced by Rizvi et al. (2025) and present an enhanced version called the Residual Stacked Gaussian Linear (RSGL) model. We also investigate the broader applicability of the RSGL model in additional domains, including financial time series and epidemiological data. Experimental results show that the RSGL model achieves improved prediction accuracy and robustness compared to both the baseline Gaussian Linear and Transformer-based models.

---

### MambaCAFU: Hybrid Multi-Scale and Multi-Attention Model with Mamba-Based Fusion for Medical Image Segmentation

Authors: T-Mai Bui, Fares Bougourzi, Fadi Dornaika, Vinh Truong Hoang
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03786v2

In recent years, deep learning has shown near-expert performance in segmenting complex medical tissues and tumors. However, existing models are often task-specific, with performance varying across modalities and anatomical regions. Balancing model complexity and performance remains challenging, particularly in clinical settings where both accuracy and efficiency are critical. To address these issues, we propose a hybrid segmentation architecture featuring a three-branch encoder that integrates CNNs, Transformers, and a Mamba-based Attention Fusion (MAF) mechanism to capture local, global, and long-range dependencies. A multi-scale attention-based CNN decoder reconstructs fine-grained segmentation maps while preserving contextual consistency. Additionally, a co-attention gate enhances feature selection by emphasizing relevant spatial and semantic information across scales during both encoding and decoding, improving feature interaction and cross-scale communication. Extensive experiments on multiple benchmark datasets show that our approach outperforms state-of-the-art methods in accuracy and generalization, while maintaining comparable computational complexity. By effectively balancing efficiency and effectiveness, our architecture offers a practical and scalable solution for diverse medical imaging tasks. Source code and trained models will be publicly released upon acceptance to support reproducibility and further research.

---

### Performance-Efficiency Tradeoffs in Transformers: An Approximation Theory Perspective

Authors: Ruoxi Yu, Haotian Jiang, Jingpu Cheng, Penghao Yu, Qianxiao Li, Zhong Li
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03784v2

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention heads and head dimensions -- should be allocated across layers to balance expressivity and efficiency. We first provide mathematical analysis on the role of early layers in information extraction from an approximation perspective, with a theoretical characterization on the trade-off between the number of heads and head dimension under a fixed parameter budget. In addition, we uncover and prove the \emph{saturation} behavior of softmax activations: Continuously increasing head dimensions can lead to diminishing returns in learning errors, particularly for long sequences. Supported by both theory and experiments, this saturation pattern suggests that later layers can operate more efficiently with reduced parameters. Combining these insights, we propose principled strategies for allocating attention heads and dimensions across Transformers' layers, shedding light on theoretically-grounded model efficiency of Transformer-based architectures.

---

### Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation

Authors: Guofu Xie, Chen Zhang, Xiao Zhang, Yunsheng Shi, Ting Yao, Jun Xu
Published: 2025-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03782v2

Adapting to diverse user needs at test time is a key challenge in controllable multi-objective generation. Existing methods are insufficient: merging-based approaches provide indirect, suboptimal control at the parameter level, often disregarding the impacts of multiple objectives. While decoding-based guidance is more direct, it typically requires aggregating logits from multiple expert models, incurring significant space overhead and relying heavily on individual model capacity. To address these issues, we introduce Merge-And-GuidE (MAGE), a two-stage framework that leverages model merging for guided decoding. We first identify a critical compatibility problem between the guidance and base models. In Stage 1, MAGE resolves this by dynamically constructing a more robust base model, merging a series of backbone models that account for multiple objectives. In Stage 2, we merge explicit and implicit value models into a unified guidance proxy, which then steers the decoding of the base model from Stage 1. Our analysis empirically validates Linear Mode Connectivity (LMC) in value models, explores the relationship between model merging and prediction ensembling, and demonstrates the enhanced controllability afforded by our approach. Extensive experiments show that our method outperforms existing approaches, achieving superior controllability, Pareto-optimal performance, and enhanced adaptability.

---

### Rezwan: Leveraging Large Language Models for Comprehensive Hadith Text Processing: A 1.2M Corpus Development

Authors: Majid Asgari-Bidhendi, Muhammad Amin Ghaseminia, Alireza Shahbazi, Sayyed Ali Hossayni, Najmeh Torabian, Behrouz Minaei-Bidgoli
Published: 2025-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03781v1

This paper presents the development of Rezwan, a large-scale AI-assisted Hadith corpus comprising over 1.2M narrations, extracted and structured through a fully automated pipeline. Building on digital repositories such as Maktabat Ahl al-Bayt, the pipeline employs Large Language Models (LLMs) for segmentation, chain--text separation, validation, and multi-layer enrichment. Each narration is enhanced with machine translation into twelve languages, intelligent diacritization, abstractive summarization, thematic tagging, and cross-text semantic analysis. This multi-step process transforms raw text into a richly annotated research-ready infrastructure for digital humanities and Islamic studies. A rigorous evaluation was conducted on 1,213 randomly sampled narrations, assessed by six domain experts. Results show near-human accuracy in structured tasks such as chain--text separation (9.33/10) and summarization (9.33/10), while highlighting ongoing challenges in diacritization and semantic similarity detection. Comparative analysis against the manually curated Noor Corpus demonstrates the superiority of Najm in both scale and quality, with a mean overall score of 8.46/10 versus 3.66/10. Furthermore, cost analysis confirms the economic feasibility of the AI approach: tasks requiring over 229,000 hours of expert labor were completed within months at a fraction of the cost. The work introduces a new paradigm in religious text processing by showing how AI can augment human expertise, enabling large-scale, multilingual, and semantically enriched access to Islamic heritage.

---

### A Benchmark Study of Deep Learning Methods for Multi-Label Pediatric Electrocardiogram-Based Cardiovascular Disease Classification

Authors: Yiqiao Chen
Published: 2025-10-04
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2510.03780v1

Cardiovascular disease (CVD) is a major pediatric health burden, and early screening is of critical importance. Electrocardiography (ECG), as a noninvasive and accessible tool, is well suited for this purpose. This paper presents the first benchmark study of deep learning for multi-label pediatric CVD classification on the recently released ZZU-pECG dataset, comprising 3716 recordings with 19 CVD categories. We systematically evaluate four representative paradigms--ResNet-1D, BiLSTM, Transformer, and Mamba 2--under both 9-lead and 12-lead configurations. All models achieved strong results, with Hamming Loss as low as 0.0069 and F1-scores above 85% in most settings. ResNet-1D reached a macro-F1 of 94.67% on the 12-lead subset, while BiLSTM and Transformer also showed competitive performance. Per-class analysis indicated challenges for rare conditions such as hypertrophic cardiomyopathy in the 9-lead subset, reflecting the effect of limited positive samples. This benchmark establishes reusable baselines and highlights complementary strengths across paradigms. It further points to the need for larger-scale, multi-center validation, age-stratified analysis, and broader disease coverage to support real-world pediatric ECG applications.

---

### GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time

Authors: Divij Handa, Mihir Parmar, Aswin RRV, Md Nayem Uddin, Hamid Palangi, Chitta Baral
Published: 2025-10-04
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03777v2

Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often struggles to generate diverse solution candidates, frequently relying on the same underlying approach to solve the problem and thus producing redundant samples. To address this limitation, we propose a new inference algorithm, GuidedSampling, which decouples the exploration and generation phases during inference, increasing diversity of generated candidate solutions. The exploration phase identifies multiple concepts that can be utilized to solve the problem, while the generation phase applies a specific concept to provide final solution candidates. We first define the theoretical bounds of GuidedSampling and then empirically demonstrate that it improves the performance of base model at pass@50 by on an average ~21.6% across various benchmarks compared to RS. Furthermore, models trained on trajectories of GuidedSampling exhibit substantial performance improvements at pass@5 by on an average ~9.7%, compared to models trained on traditional RS. Additionally, models trained with GuidedSampling increases the average number of concepts per instance (1.67 -> 3.03), yielding a diverse set of candidates than traditional RS.

---

### Trajectory prediction for heterogeneous agents: A performance analysis on small and imbalanced datasets

Authors: Tiago Rodrigues de Almeida, Yufei Zhu, Andrey Rudenko, Tomasz P. Kucner, Johannes A. Stork, Martin Magnusson, Achim J. Lilienthal
Published: 2025-10-04
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.03776v1

Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly depends on their tasks, roles, or observable labels. Class-conditioned motion prediction is thus an appealing way to reduce forecast uncertainty and get more accurate predictions for heterogeneous agents. However, this is hardly explored in the prior art, especially for mobile robots and in limited data applications. In this paper, we analyse different class-conditioned trajectory prediction methods on two datasets. We propose a set of conditional pattern-based and efficient deep learning-based baselines, and evaluate their performance on robotics and outdoors datasets (THÖR-MAGNI and Stanford Drone Dataset). Our experiments show that all methods improve accuracy in most of the settings when considering class labels. More importantly, we observe that there are significant differences when learning from imbalanced datasets, or in new environments where sufficient data is not available. In particular, we find that deep learning methods perform better on balanced datasets, but in applications with limited data, e.g., cold start of a robot in a new environment, or imbalanced classes, pattern-based methods may be preferable.

---

### OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation

Authors: Divij Handa, David Blincoe, Orson Adams, Yinlin Fu
Published: 2025-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03771v1

Deploying capable and user-aligned LLM-based systems necessitates reliable evaluation. While LLMs excel in verifiable tasks like coding and mathematics, where gold-standard solutions are available, adoption remains challenging for subjective tasks that lack a single correct answer. E-commerce Query Rewriting (QR) is one such problem where determining whether a rewritten query properly captures the user intent is extremely difficult to figure out algorithmically. In this work, we introduce OptAgent, a novel framework that combines multi-agent simulations with genetic algorithms to verify and optimize queries for QR. Instead of relying on a static reward model or a single LLM judge, our approach uses multiple LLM-based agents, each acting as a simulated shopping customer, as a dynamic reward signal. The average of these agent-derived scores serves as an effective fitness function for an evolutionary algorithm that iteratively refines the user's initial query. We evaluate OptAgent on a dataset of 1000 real-world e-commerce queries in five different categories, and we observe an average improvement of 21.98% over the original user query and 3.36% over a Best-of-N LLM rewriting baseline.

---

### Efficiency vs. Efficacy: Assessing the Compression Ratio-Dice Score Relationship through a Simple Benchmarking Framework for Cerebrovascular 3D Segmentation

Authors: Shimaa Elbana, Ahmad Kamal, Shahd Ahmed Ali, Ahmad Al-Kabbany
Published: 2025-10-04
Categories: cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2510.03769v3

The increasing size and complexity of medical imaging datasets, particularly in 3D formats, present significant barriers to collaborative research and transferability. This study investigates whether the ZFP compression technique can mitigate these challenges without compromising the performance of automated cerebrovascular segmentation, a critical first step in intracranial aneurysm detection. We apply ZFP in both its error tolerance and fixed-rate modes to a large scale, and one of the most recent, datasets in the literature, 3D medical dataset containing ground-truth vascular segmentations. The segmentation quality on the compressed volumes is rigorously compared to the uncompressed baseline (Dice approximately equals 0.8774). Our findings reveal that ZFP can achieve substantial data reduction--up to a 22.89:1 ratio in error tolerance mode--while maintaining a high degree of fidelity, with the mean Dice coefficient remaining high at 0.87656. These results demonstrate that ZFP is a viable and powerful tool for enabling more efficient and accessible research on large-scale medical datasets, fostering broader collaboration across the community.

---

### CoPA: Hierarchical Concept Prompting and Aggregating Network for Explainable Diagnosis

Authors: Yiheng Dong, Yi Lin, Xin Yang
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03767v1

The transparency of deep learning models is essential for clinical diagnostics. Concept Bottleneck Model provides clear decision-making processes for diagnosis by transforming the latent space of black-box models into human-understandable concepts. However, concept-based methods still face challenges in concept capture capabilities. These methods often rely on encode features solely from the final layer, neglecting shallow and multiscale features, and lack effective guidance in concept encoding, hindering fine-grained concept extraction. To address these issues, we introduce Concept Prompting and Aggregating (CoPA), a novel framework designed to capture multilayer concepts under prompt guidance. This framework utilizes the Concept-aware Embedding Generator (CEG) to extract concept representations from each layer of the visual encoder. Simultaneously, these representations serve as prompts for Concept Prompt Tuning (CPT), steering the model towards amplifying critical concept-related visual cues. Visual representations from each layer are aggregated to align with textual concept representations. With the proposed method, valuable concept-wise information in the images is captured and utilized effectively, thus improving the performance of concept and disease prediction. Extensive experimental results demonstrate that CoPA outperforms state-of-the-art methods on three public datasets. Code is available at https://github.com/yihengd/CoPA.

---

### Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization

Authors: Jiaxin Deng, Junbiao Pang
Published: 2025-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03763v1

Sharpness-Aware Minimization (SAM) improves model generalization but doubles the computational cost of Stochastic Gradient Descent (SGD) by requiring twice the gradient calculations per optimization step. To mitigate this, we propose Adaptively sampling-Reusing-mixing decomposed gradients to significantly accelerate SAM (ARSAM). Concretely, we firstly discover that SAM's gradient can be decomposed into the SGD gradient and the Projection of the Second-order gradient onto the First-order gradient (PSF). Furthermore, we observe that the SGD gradient and PSF dynamically evolve during training, emphasizing the growing role of the PSF to achieve a flat minima. Therefore, ARSAM is proposed to the reused PSF and the timely updated PSF still maintain the model's generalization ability. Extensive experiments show that ARSAM achieves state-of-the-art accuracies comparable to SAM across diverse network architectures. On CIFAR-10/100, ARSAM is comparable to SAM while providing a speedup of about 40\%. Moreover, ARSAM accelerates optimization for the various challenge tasks (\textit{e.g.}, human pose estimation, and model quantization) without sacrificing performance, demonstrating its broad practicality.% The code is publicly accessible at: https://github.com/ajiaaa/ARSAM.

---

### Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs

Authors: Deshan Sumanathilaka, Nicholas Micallef, Julian Hough
Published: 2025-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03762v1

Recent advances in Large Language Models (LLMs) have significantly reshaped the landscape of Natural Language Processing (NLP). Among the various prompting techniques, few-shot prompting has gained considerable attention for its practicality and effectiveness. This study investigates how few-shot prompting strategies impact the Word Sense Disambiguation (WSD) task, particularly focusing on the biases introduced by imbalanced sample distributions. We use the GLOSSGPT prompting method, an advanced approach for English WSD, to test its effectiveness across five languages: English, German, Spanish, French, and Italian. Our results show that imbalanced few-shot examples can cause incorrect sense predictions in multilingual languages, but this issue does not appear in English. To assess model behavior, we evaluate both the GPT-4o and LLaMA-3.1-70B models and the results highlight the sensitivity of multilingual WSD to sample distribution in few-shot settings, emphasizing the need for balanced and representative prompting strategies.

---

### You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models

Authors: Richard A. Dubniczky, Bertalan Borsos, Tamas Bisztray, Norbert Tihanyi
Published: 2025-10-04
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.03761v2

The widespread use of preprint repositories such as arXiv has accelerated the communication of scientific results but also introduced overlooked security risks. Beyond PDFs, these platforms provide unrestricted access to original source materials, including LaTeX sources, auxiliary code, figures, and embedded comments. In the absence of sanitization, submissions may disclose sensitive information that adversaries can harvest using open-source intelligence. In this work, we present the first large-scale security audit of preprint archives, analyzing more than 1.2 TB of source data from 100,000 arXiv submissions. We introduce LaTeXpOsEd, a four-stage framework that integrates pattern matching, logical filtering, traditional harvesting techniques, and large language models (LLMs) to uncover hidden disclosures within non-referenced files and LaTeX comments. To evaluate LLMs' secret-detection capabilities, we introduce LLMSec-DB, a benchmark on which we tested 25 state-of-the-art models. Our analysis uncovered thousands of PII leaks, GPS-tagged EXIF files, publicly available Google Drive and Dropbox folders, editable private SharePoint links, exposed GitHub and Google credentials, and cloud API keys. We also uncovered confidential author communications, internal disagreements, and conference submission credentials, exposing information that poses serious reputational risks to both researchers and institutions. We urge the research community and repository operators to take immediate action to close these hidden security gaps. To support open science, we release all scripts and methods from this study but withhold sensitive findings that could be misused, in line with ethical principles. The source code and related material are available at the project website https://github.com/LaTeXpOsEd

---

### EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

Authors: Ping Guo, Chenyu Zhu, Siyuan Chen, Fei Liu, Xi Lin, Zhichao Lu, Qingfu Zhang
Published: 2025-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03760v1

CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for automating kernel optimization, this field suffers from a fragmented ecosystem of isolated and incomparable approaches with unclear problem formulations. Furthermore, general-purpose LLM code evolution methods cannot meet strict correctness requirements of CUDA kernel optimization. We address these fundamental challenges by first formalizing CUDA kernel optimization as a code optimization task with a clear objective, constraints, and evaluation metrics. We then establish the first systematic LLM-based code evolution framework, EvoEngineer, that provides guidance for designing and adapting optimization strategies to achieve a balance between performance and correctness. Finally, we implement a kernel optimization system based on this framework and conduct extensive experiments on 91 real-world CUDA kernels. Our results demonstrate that EvoEngineer achieves a principled balance between performance and correctness, with the highest averaged median speedup of \textbf{2.72}$\times$ over baseline CUDA kernels and a code validity rate of \textbf{69.8}\%, outperforming existing methods on both dimensions. Our method achieves a maximum speedup of \textbf{36.75}$\times$ among all operations over PyTorch kernels and delivers the highest speedup on \textbf{28} (\textbf{56.0\%}) of 50 operations that achieve over \textbf{2$\times$} acceleration.

---

### Cross-Lingual Multi-Granularity Framework for Interpretable Parkinson's Disease Diagnosis from Speech

Authors: Ilias Tougui, Mehdi Zakroum, Mounir Ghogho
Published: 2025-10-04
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2510.03758v1

Parkinson's Disease (PD) affects over 10 million people worldwide, with speech impairments in up to 89% of patients. Current speech-based detection systems analyze entire utterances, potentially overlooking the diagnostic value of specific phonetic elements. We developed a granularity-aware approach for multilingual PD detection using an automated pipeline that extracts time-aligned phonemes, syllables, and words from recordings. Using Italian, Spanish, and English datasets, we implemented a bidirectional LSTM with multi-head attention to compare diagnostic performance across the different granularity levels. Phoneme-level analysis achieved superior performance with AUROC of 93.78% +- 2.34% and accuracy of 92.17% +- 2.43%. This demonstrates enhanced diagnostic capability for cross-linguistic PD detection. Importantly, attention analysis revealed that the most informative speech features align with those used in established clinical protocols: sustained vowels (/a/, /e/, /o/, /i/) at phoneme level, diadochokinetic syllables (/ta/, /pa/, /la/, /ka/) at syllable level, and /pataka/ sequences at word level. Source code will be available at https://github.com/jetliqs/clearpd.

---

### Code4MeV2: a Research-oriented Code-completion Platform

Authors: Roham Koohestani, Parham Bateni, Aydin Ebrahimi, Behdad Etezadi, Kiarash Karimi, Maliheh Izadi
Published: 2025-10-04
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.03755v1

The adoption of AI-powered code completion tools in software development has increased substantially, yet the user interaction data produced by these systems remain proprietary within large corporations. This creates a barrier for the academic community, as researchers must often develop dedicated platforms to conduct studies on human--AI interaction, making reproducible research and large-scale data analysis impractical. In this work, we introduce Code4MeV2, a research-oriented, open-source code completion plugin for JetBrains IDEs, as a solution to this limitation. Code4MeV2 is designed using a client--server architecture and features inline code completion and a context-aware chat assistant. Its core contribution is a modular and transparent data collection framework that gives researchers fine-grained control over telemetry and context gathering. Code4MeV2 achieves industry-comparable performance in terms of code completion, with an average latency of 200~ms. We assess our tool through a combination of an expert evaluation and a user study with eight participants. Feedback from both researchers and daily users highlights its informativeness and usefulness. We invite the community to adopt and contribute to this tool. More information about the tool can be found at https://app.code4me.me.

---

### The Overlooked Value of Test-time Reference Sets in Visual Place Recognition

Authors: Mubariz Zaffar, Liangliang Nan, Sebastian Scherer, Julian F. P. Kooij
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03751v1

Given a query image, Visual Place Recognition (VPR) is the task of retrieving an image of the same place from a reference database with robustness to viewpoint and appearance changes. Recent works show that some VPR benchmarks are solved by methods using Vision-Foundation-Model backbones and trained on large-scale and diverse VPR-specific datasets. Several benchmarks remain challenging, particularly when the test environments differ significantly from the usual VPR training datasets. We propose a complementary, unexplored source of information to bridge the train-test domain gap, which can further improve the performance of State-of-the-Art (SOTA) VPR methods on such challenging benchmarks. Concretely, we identify that the test-time reference set, the "map", contains images and poses of the target domain, and must be available before the test-time query is received in several VPR applications. Therefore, we propose to perform simple Reference-Set-Finetuning (RSF) of VPR models on the map, boosting the SOTA (~2.3% increase on average for Recall@1) on these challenging datasets. Finetuned models retain generalization, and RSF works across diverse test datasets.

---

### TreePrompt: Leveraging Hierarchical Few-Shot Example Selection for Improved English-Persian and English-German Translation

Authors: Ramtin Kakavand, Ebrahim Ansari
Published: 2025-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03748v1

Large Language Models (LLMs) have consistently demonstrated strong performance in machine translation, especially when guided by high-quality prompts. Few-shot prompting is an effective technique to improve translation quality; however, most existing example selection methods focus solely on query-to-example similarity and do not account for the quality of the examples. In this work, we propose TreePrompt, a novel example selection approach that learns LLM preferences to identify high-quality, contextually relevant examples within a tree-structured framework. To further explore the balance between similarity and quality, we combine TreePrompt with K-Nearest Neighbors (K-NN) and Adaptive Few-Shot Prompting (AFSP). Evaluations on two language pairs - English-Persian (MIZAN) and English-German (WMT19) - show that integrating TreePrompt with AFSP or Random selection leads to improved translation performance.

---

### LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes

Authors: Zuomin Qu, Yimao Guo, Qianyue Hu, Wei Lu
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03747v2

Deepfakes pose significant societal risks, motivating the development of proactive defenses that embed adversarial perturbations in facial images to prevent manipulation. However, in this paper, we show that these preemptive defenses often lack robustness and reliability. We propose a novel approach, Low-Rank Adaptation (LoRA) patching, which injects a plug-and-play LoRA patch into Deepfake generators to bypass state-of-the-art defenses. A learnable gating mechanism adaptively controls the effect of the LoRA patch and prevents gradient explosions during fine-tuning. We also introduce a Multi-Modal Feature Alignment (MMFA) loss, encouraging the features of adversarial outputs to align with those of the desired outputs at the semantic level. Beyond bypassing, we present defensive LoRA patching, embedding visible warnings in the outputs as a complementary solution to mitigate this newly identified security vulnerability. With only 1,000 facial examples and a single epoch of fine-tuning, LoRA patching successfully defeats multiple proactive defenses. These results reveal a critical weakness in current paradigms and underscore the need for more robust Deepfake defense strategies. Our code is available at https://github.com/ZOMIN28/LoRA-Patching.

---

### Neural Low-Discrepancy Sequences

Authors: Michael Etienne Van Huffel, Nathan Kirk, Makram Chahine, Daniela Rus, T. Konstantin Rusch
Published: 2025-10-04
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.03745v2

Low-discrepancy points are designed to efficiently fill the space in a uniform manner. This uniformity is highly advantageous in many problems in science and engineering, including in numerical integration, computer vision, machine perception, computer graphics, machine learning, and simulation. Whereas most previous low-discrepancy constructions rely on abstract algebra and number theory, Message-Passing Monte Carlo (MPMC) was recently introduced to exploit machine learning methods for generating point sets with lower discrepancy than previously possible. However, MPMC is limited to generating point sets and cannot be extended to low-discrepancy sequences (LDS), i.e., sequences of points in which every prefix has low discrepancy, a property essential for many applications. To address this limitation, we introduce Neural Low-Discrepancy Sequences (NeuroLDS), the first machine learning-based framework for generating finite LDS. Drawing inspiration from classical LDS, we train a neural network to map indices to points such that the resulting sequences exhibit minimal discrepancy across all prefixes. To this end, we deploy a two-stage learning process: supervised approximation of classical constructions followed by unsupervised fine-tuning to minimize prefix discrepancies. We demonstrate that NeuroLDS outperforms all previous LDS constructions by a significant margin with respect to discrepancy measures. Moreover, we demonstrate the effectiveness of NeuroLDS across diverse applications, including numerical integration, robot motion planning, and scientific machine learning. These results highlight the promise and broad significance of Neural Low-Discrepancy Sequences. Our code can be found at https://github.com/camail-official/neuro-lds.

---

### HydroFusion-LMF: Semi-Supervised Multi-Network Fusion with Large-Model Adaptation for Long-Term Daily Runoff Forecasting

Authors: Qianfei Fan, Jiayu Wei, Peijun Zhu, Wensheng Ye, Meie Fang
Published: 2025-10-04
Categories: cs.LG, cs.AI, cs.DC, cs.NE, physics.geo-ph
arXiv: https://arxiv.org/abs/2510.03744v1

Accurate decade-scale daily runoff forecasting in small watersheds is difficult because signals blend drifting trends, multi-scale seasonal cycles, regime shifts, and sparse extremes. Prior deep models (DLinear, TimesNet, PatchTST, TiDE, Nonstationary Transformer, LSTNet, LSTM) usually target single facets and under-utilize unlabeled spans, limiting regime adaptivity. We propose HydroFusion-LMF, a unified framework that (i) performs a learnable trend-seasonal-residual decomposition to reduce non-stationarity, (ii) routes residuals through a compact heterogeneous expert set (linear refinement, frequency kernel, patch Transformer, recurrent memory, dynamically normalized attention), (iii) fuses expert outputs via a hydrologic context-aware gate conditioned on day-of-year phase, antecedent precipitation, local variance, flood indicators, and static basin attributes, and (iv) augments supervision with a semi-supervised multi-task objective (composite MSE/MAE + extreme emphasis + NSE/KGE, masked reconstruction, multi-scale contrastive alignment, augmentation consistency, variance-filtered pseudo-labeling). Optional adapter / LoRA layers inject a frozen foundation time-series encoder efficiently. On a ~10-year daily dataset HydroFusion-LMF attains MSE 1.0128 / MAE 0.5818, improving the strongest baseline (DLinear) by 10.2% / 10.3% and the mean baseline by 24.6% / 17.1%. We observe simultaneous MSE and MAE reductions relative to baselines. The framework balances interpretability (explicit components, sparse gating) with performance, advancing label-efficient hydrologic forecasting under non-stationarity.

---

### Cost Efficient Fairness Audit Under Partial Feedback

Authors: Nirjhar Das, Mohit Sharma, Praharsh Nanavati, Kirankumar Shiragur, Amit Deshpande
Published: 2025-10-04
Categories: cs.LG, cs.AI, cs.CY, stat.ML
arXiv: https://arxiv.org/abs/2510.03734v2

We study the problem of auditing the fairness of a given classifier under partial feedback, where true labels are available only for positively classified individuals, (e.g., loan repayment outcomes are observed only for approved applicants). We introduce a novel cost model for acquiring additional labeled data, designed to more accurately reflect real-world costs such as credit assessment, loan processing, and potential defaults. Our goal is to find optimal fairness audit algorithms that are more cost-effective than random exploration and natural baselines. In our work, we consider two audit settings: a black-box model with no assumptions on the data distribution, and a mixture model, where features and true labels follow a mixture of exponential family distributions. In the black-box setting, we propose a near-optimal auditing algorithm under mild assumptions and show that a natural baseline can be strictly suboptimal. In the mixture model setting, we design a novel algorithm that achieves significantly lower audit cost than the black-box case. Our approach leverages prior work on learning from truncated samples and maximum-a-posteriori oracles, and extends known results on spherical Gaussian mixtures to handle exponential family mixtures, which may be of independent interest. Moreover, our algorithms apply to popular fairness metrics including demographic parity, equal opportunity, and equalized odds. Empirically, we demonstrate strong performance of our algorithms on real-world fair classification datasets like Adult Income and Law School, consistently outperforming natural baselines by around 50% in terms of audit cost.

---

### Optimizing Fine-Tuning through Advanced Initialization Strategies for Low-Rank Adaptation

Authors: Yongfu Xue
Published: 2025-10-04
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.03731v4

The rapid development of parameter-efficient fine-tuning methods has noticeably improved the efficiency of adapting large language models. Among these, LoRA has gained widespread popularity due to its strong balance of effectiveness and parameter efficiency. However, LoRA relies on initializing two low-rank matrices whose product is zero, which limits its ability to effectively activate and leverage the original model weights-creating a potential bottleneck for optimal performance. To address this limitation, we propose \textbf{IniLoRA}, a novel initialization strategy that initializes the low-rank matrices to closely approximate the original model weights. Experimental results indicate that IniLoRA achieves better performance than LoRA across a range of models and tasks. Additionally, we introduce two variants, IniLoRA-$α$ and IniLoRA-$β$, both leveraging distinct initialization methods to enhance performance further.

---

### Lightweight and Generalizable Acoustic Scene Representations via Contrastive Fine-Tuning and Distillation

Authors: Kuang Yuan, Yang Gao, Xilin Li, Xinhao Mei, Syavosh Zadissa, Tarun Pruthi, Saeed Bagheri Sereshki
Published: 2025-10-04
Categories: cs.SD, cs.LG, eess.AS, eess.SP
arXiv: https://arxiv.org/abs/2510.03728v2

Acoustic scene classification (ASC) models on edge devices typically operate under fixed class assumptions, lacking the transferability needed for real-world applications that require adaptation to new or refined acoustic categories. We propose ContrastASC, which learns generalizable acoustic scene representations by structuring the embedding space to preserve semantic relationships between scenes, enabling adaptation to unseen categories without retraining. Our approach combines supervised contrastive fine-tuning of pre-trained models with contrastive representation distillation to transfer this structured knowledge to compact student models. Our evaluation shows that ContrastASC demonstrates improved few-shot adaptation to unseen categories while maintaining strong closed-set performance.

---

### Bridging the Gap Between Multimodal Foundation Models and World Models

Authors: Xuehai He
Published: 2025-10-04
Categories: cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.03727v1

Humans understand the world through the integration of multiple sensory modalities, enabling them to perceive, reason about, and imagine dynamic physical processes. Inspired by this capability, multimodal foundation models (MFMs) have emerged as powerful tools for multimodal understanding and generation. However, today's MFMs fall short of serving as effective world models. They lack the essential ability such as perform counterfactual reasoning, simulate dynamics, understand the spatiotemporal information, control generated visual outcomes, and perform multifaceted reasoning. We investigates what it takes to bridge the gap between multimodal foundation models and world models. We begin by improving the reasoning capabilities of MFMs through discriminative tasks and equipping MFMs with structured reasoning skills, such as causal inference, counterfactual thinking, and spatiotemporal reasoning, enabling them to go beyond surface correlations and understand deeper relationships within visual and textual data. Next, we explore generative capabilities of multimodal foundation models across both image and video modalities, introducing new frameworks for structured and controllable generation. Our approaches incorporate scene graphs, multimodal conditioning, and multimodal alignment strategies to guide the generation process, ensuring consistency with high-level semantics and fine-grained user intent. We further extend these techniques to controllable 4D generation, enabling interactive, editable, and morphable object synthesis over time and space.

---

### Personalized federated prototype learning in mixed heterogeneous data scenarios

Authors: Jiahao Zeng, Wolong Xing, Liangtao Shi, Xin Huang, Jialin Wang, Zhile Cao, Zhenkui Shi
Published: 2025-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03726v1

Federated learning has received significant attention for its ability to simultaneously protect customer privacy and leverage distributed data from multiple devices for model training. However, conventional approaches often focus on isolated heterogeneous scenarios, resulting in skewed feature distributions or label distributions. Meanwhile, data heterogeneity is actually a key factor in improving model performance. To address this issue, we propose a new approach called PFPL in mixed heterogeneous scenarios. The method provides richer domain knowledge and unbiased convergence targets by constructing personalized, unbiased prototypes for each client. Moreover, in the local update phase, we introduce consistent regularization to align local instances with their personalized prototypes, which significantly improves the convergence of the loss function. Experimental results on Digits and Office Caltech datasets validate the effectiveness of our approach and successfully reduce the communication cost.

---

### Mapping Rio de Janeiro's favelas: general-purpose vs. satellite-specific neural networks

Authors: Thomas Hallopeau, Joris Guérin, Laurent Demagistri, Youssef Fouzai, Renata Gracie, Vanderlei Pascoal De Matos, Helen Gurgel, Nadine Dessay
Published: 2025-10-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.03725v1

While deep learning methods for detecting informal settlements have already been developed, they have not yet fully utilized the potential offered by recent pretrained neural networks. We compare two types of pretrained neural networks for detecting the favelas of Rio de Janeiro: 1. Generic networks pretrained on large diverse datasets of unspecific images, 2. A specialized network pretrained on satellite imagery. While the latter is more specific to the target task, the former has been pretrained on significantly more images. Hence, this research investigates whether task specificity or data volume yields superior performance in urban informal settlement detection.

---

### Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition

Authors: Martin Kocour, Martin Karafiat, Alexander Polok, Dominik Klement, Lukáš Burget, Jan Černocký
Published: 2025-10-04
Categories: eess.AS, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2510.03723v2

We propose a speaker-attributed (SA) Whisper-based model for multi-talker speech recognition that combines target-speaker modeling with serialized output training (SOT). Our approach leverages a Diarization-Conditioned Whisper (DiCoW) encoder to extract target-speaker embeddings, which are concatenated into a single representation and passed to a shared decoder. This enables the model to transcribe overlapping speech as a serialized output stream with speaker tags and timestamps. In contrast to target-speaker ASR systems such as DiCoW, which decode each speaker separately, our approach performs joint decoding, allowing the decoder to condition on the context of all speakers simultaneously. Experiments show that the model outperforms existing SOT-based approaches and surpasses DiCoW on multi-talker mixtures (e.g., LibriMix).

---

### Balancing Interpretability and Performance in Reinforcement Learning: An Adaptive Spectral Based Linear Approach

Authors: Qianxin Yi, Shao-Bo Lin, Jun Fan, Yao Wang
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03722v1

Reinforcement learning (RL) has been widely applied to sequential decision making, where interpretability and performance are both critical for practical adoption. Current approaches typically focus on performance and rely on post hoc explanations to account for interpretability. Different from these approaches, we focus on designing an interpretability-oriented yet performance-enhanced RL approach. Specifically, we propose a spectral based linear RL method that extends the ridge regression-based approach through a spectral filter function. The proposed method clarifies the role of regularization in controlling estimation error and further enables the design of an adaptive regularization parameter selection strategy guided by the bias-variance trade-off principle. Theoretical analysis establishes near-optimal bounds for both parameter estimation and generalization error. Extensive experiments on simulated environments and real-world datasets from Kuaishou and Taobao demonstrate that our method either outperforms or matches existing baselines in decision quality. We also conduct interpretability analyses to illustrate how the learned policies make decisions, thereby enhancing user trust. These results highlight the potential of our approach to bridge the gap between RL theory and practical decision making, providing interpretability, accuracy, and adaptability in management contexts.

---

### Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models

Authors: Leander Girrbach, Stephan Alaniz, Genevieve Smith, Trevor Darrell, Zeynep Akata
Published: 2025-10-04
Categories: cs.CV, cs.CL, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.03721v2

Vision-language models trained on large-scale multimodal datasets show strong demographic biases, but the role of training data in producing these biases remains unclear. A major barrier has been the lack of demographic annotations in web-scale datasets such as LAION-400M. We address this gap by creating person-centric annotations for the full dataset, including over 276 million bounding boxes, perceived gender and race/ethnicity labels, and automatically generated captions. These annotations are produced through validated automatic labeling pipelines combining object detection, multimodal captioning, and finetuned classifiers. Using them, we uncover demographic imbalances and harmful associations, such as the disproportionate linking of men and individuals perceived as Black or Middle Eastern with crime-related and negative content. We also show that a linear fit predicts 60-70% of gender bias in CLIP and Stable Diffusion from direct co-occurrences in the data. Our resources establish the first large-scale empirical link between dataset composition and downstream model bias. Code is available at https://github.com/ExplainableML/LAION-400M-Person-Centric-Annotations.

---

### Artery-Vein Segmentation from Fundus Images using Deep Learning

Authors: Sharan SK, Subin Sahayam, Umarani Jayaraman, Lakshmi Priya A
Published: 2025-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03717v1

Segmenting of clinically important retinal blood vessels into arteries and veins is a prerequisite for retinal vessel analysis. Such analysis can provide potential insights and bio-markers for identifying and diagnosing various retinal eye diseases. Alteration in the regularity and width of the retinal blood vessels can act as an indicator of the health of the vasculature system all over the body. It can help identify patients at high risk of developing vasculature diseases like stroke and myocardial infarction. Over the years, various Deep Learning architectures have been proposed to perform retinal vessel segmentation. Recently, attention mechanisms have been increasingly used in image segmentation tasks. The work proposes a new Deep Learning approach for artery-vein segmentation. The new approach is based on the Attention mechanism that is incorporated into the WNet Deep Learning model, and we call the model as Attention-WNet. The proposed approach has been tested on publicly available datasets such as HRF and DRIVE datasets. The proposed approach has outperformed other state-of-art models available in the literature.

---

### EmbodiSwap for Zero-Shot Robot Imitation Learning

Authors: Eadom Dessalene, Pavan Mantripragada, Michael Maynord, Yiannis Aloimonos
Published: 2025-10-04
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.03706v1

We introduce EmbodiSwap - a method for producing photorealistic synthetic robot overlays over human video. We employ EmbodiSwap for zero-shot imitation learning, bridging the embodiment gap between in-the-wild ego-centric human video and a target robot embodiment. We train a closed-loop robot manipulation policy over the data produced by EmbodiSwap. We make novel use of V-JEPA as a visual backbone, repurposing V-JEPA from the domain of video understanding to imitation learning over synthetic robot videos. Adoption of V-JEPA outperforms alternative vision backbones more conventionally used within robotics. In real-world tests, our zero-shot trained V-JEPA model achieves an $82\%$ success rate, outperforming a few-shot trained $π_0$ network as well as $π_0$ trained over data produced by EmbodiSwap. We release (i) code for generating the synthetic robot overlays which takes as input human videos and an arbitrary robot URDF and generates a robot dataset, (ii) the robot dataset we synthesize over EPIC-Kitchens, HOI4D and Ego4D, and (iii) model checkpoints and inference code, to facilitate reproducible research and broader adoption.

---

### Referring Expression Comprehension for Small Objects

Authors: Kanoko Goto, Takumi Hirose, Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue
Published: 2025-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03701v1

Referring expression comprehension (REC) aims to localize the target object described by a natural language expression. Recent advances in vision-language learning have led to significant performance improvements in REC tasks. However, localizing extremely small objects remains a considerable challenge despite its importance in real-world applications such as autonomous driving. To address this issue, we introduce a novel dataset and method for REC targeting small objects. First, we present the small object REC (SOREC) dataset, which consists of 100,000 pairs of referring expressions and corresponding bounding boxes for small objects in driving scenarios. Second, we propose the progressive-iterative zooming adapter (PIZA), an adapter module for parameter-efficient fine-tuning that enables models to progressively zoom in and localize small objects. In a series of experiments, we apply PIZA to GroundingDINO and demonstrate a significant improvement in accuracy on the SOREC dataset. Our dataset, codes and pre-trained models are publicly available on the project page.

---

### H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis

Authors: Seungseop Lim, Gibaeg Kim, Hyunkyung Lee, Wooseok Han, Jean Seo, Jaehyo Yoo, Eunho Yang
Published: 2025-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03700v1

An accurate differential diagnosis (DDx) is essential for patient care, shaping therapeutic decisions and influencing outcomes. Recently, Large Language Models (LLMs) have emerged as promising tools to support this process by generating a DDx list from patient narratives. However, existing evaluations of LLMs in this domain primarily rely on flat metrics, such as Top-k accuracy, which fail to distinguish between clinically relevant near-misses and diagnostically distant errors. To mitigate this limitation, we introduce H-DDx, a hierarchical evaluation framework that better reflects clinical relevance. H-DDx leverages a retrieval and reranking pipeline to map free-text diagnoses to ICD-10 codes and applies a hierarchical metric that credits predictions closely related to the ground-truth diagnosis. In benchmarking 22 leading models, we show that conventional flat metrics underestimate performance by overlooking clinically meaningful outputs, with our results highlighting the strengths of domain-specialized open-source models. Furthermore, our framework enhances interpretability by revealing hierarchical error patterns, demonstrating that LLMs often correctly identify the broader clinical context even when the precise diagnosis is missed.

---

### Dissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN Agents

Authors: Raaghav Malik, Satpreet H. Singh, Sonja Johnson-Yu, Nathan Wu, Roy Harpaz, Florian Engert, Kanaka Rajan
Published: 2025-10-04
Categories: q-bio.NC, cs.AI, cs.LG, cs.NE, eess.SY
arXiv: https://arxiv.org/abs/2510.03699v1

Larval zebrafish hunting provides a tractable setting to study how ecological and energetic constraints shape adaptive behavior in both biological brains and artificial agents. Here we develop a minimal agent-based model, training recurrent policies with deep reinforcement learning in a bout-based zebrafish simulator. Despite its simplicity, the model reproduces hallmark hunting behaviors -- including eye vergence-linked pursuit, speed modulation, and stereotyped approach trajectories -- that closely match real larval zebrafish. Quantitative trajectory analyses show that pursuit bouts systematically reduce prey angle by roughly half before strike, consistent with measurements. Virtual experiments and parameter sweeps vary ecological and energetic constraints, bout kinematics (coupled vs. uncoupled turns and forward motion), and environmental factors such as food density, food speed, and vergence limits. These manipulations reveal how constraints and environments shape pursuit dynamics, strike success, and abort rates, yielding falsifiable predictions for neuroscience experiments. These sweeps identify a compact set of constraints -- binocular sensing, the coupling of forward speed and turning in bout kinematics, and modest energetic costs on locomotion and vergence -- that are sufficient for zebrafish-like hunting to emerge. Strikingly, these behaviors arise in minimal agents without detailed biomechanics, fluid dynamics, circuit realism, or imitation learning from real zebrafish data. Taken together, this work provides a normative account of zebrafish hunting as the optimal balance between energetic cost and sensory benefit, highlighting the trade-offs that structure vergence and trajectory dynamics. We establish a virtual lab that narrows the experimental search space and generates falsifiable predictions about behavior and neural coding.

---

### Mind the Goal: Data-Efficient Goal-Oriented Evaluation of Conversational Agents and Chatbots using Teacher Models

Authors: Deepak Babu Piskala, Sharlene Chen, Udita Patel, Parul Kalra, Rafael Castrillo
Published: 2025-10-04
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.03696v1

Evaluating the quality of multi-turn chatbot interactions remains challenging, as most existing methods assess interactions at the turn level without addressing whether a user's overarching goal was fulfilled. A ``goal'' here refers to an information need or task, such as asking for policy information or applying for leave. We propose a comprehensive framework for goal-oriented evaluation of multi-agent systems (MAS), introducing the \textbf{Goal Success Rate (GSR)} to measure the percentage of fulfilled goals, and a \textbf{Root Cause of Failure (RCOF)} taxonomy to identify reasons for failure in multi-agent chatbots. Our method segments conversations by user goals and evaluates success using all relevant turns. We present a model-based evaluation system combining teacher LLMs, where domain experts define goals, set quality standards serving as a guidance for the LLMs. The LLMs use ``thinking tokens'' to produce interpretable rationales, enabling \textit{explainable}, \textit{data-efficient} evaluations. In an enterprise setting, we apply our framework to evaluate AIDA, a zero-to-one employee conversational agent system built as a ground-up multi-agent conversational agent, and observe GSR improvement from 63\% to 79\% over six months since its inception. Our framework is generic and offers actionable insights through a detailed defect taxonomy based on analysis of failure points in multi-agent chatbots, diagnosing overall success, identifying key failure modes, and informing system improvements.

---

### REG: A Regularization Optimizer for Robust Training Dynamics

Authors: Zehua Liu, Han Wu, Xiaojin Fu, Shuqi Liu, Xiongwei Han, Tao Zhong, Mingxuan Yuan
Published: 2025-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03691v1

Optimizers are crucial for the efficient training of Large Language Models (LLMs). While AdamW is the de facto standard, recent structure-aware optimizers like Muon have emerged, which regularize gradient updates by operating on entire weight matrices. The Muon optimizer balances the gradient updates along all the directions. However, Muon's reliance on the matrix sign function can lead to training instability, exhibits incompatibility when fine-tuning models pre-trained with AdamW. To address these limitations, we propose \textbf{REG}, a novel optimizer that replaces Muon's aggressive matrix sign operator with the Row-and-Column-Scaling (RACS) operator. Theoretically grounded in balancing a matrix, the RACS operator regularizes the update steps in a less drastic manner, making it simpler to implement and more compatible with established training dynamics. Through extensive empirical experiments on LLM training, we demonstrate that our REG optimizer not only achieves superior performance and stability over AdamW, but also maintains consistency with the AdamW training paradigm. This consistency is particularly evident during the fine-tuning stage, where REG optimizer avoids the performance degradation observed with Muon.

---