# Research Papers — 2025-10 · bundle page 15 of 217

> Full-text markdown of papers #701–750 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/15
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/14.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/16.md)

### Retrieval-Augmented Multimodal Depression Detection

Authors: Ruibo Hou, Shiyu Teng, Jiaqing Liu, Shurong Chai, Yinhao Li, Lanfen Lin, Yen-Wei Chen
Published: 2025-10-29
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.01892v1

Multimodal deep learning has shown promise in depression detection by integrating text, audio, and video signals. Recent work leverages sentiment analysis to enhance emotional understanding, yet suffers from high computational cost, domain mismatch, and static knowledge limitations. To address these issues, we propose a novel Retrieval-Augmented Generation (RAG) framework. Given a depression-related text, our method retrieves semantically relevant emotional content from a sentiment dataset and uses a Large Language Model (LLM) to generate an Emotion Prompt as an auxiliary modality. This prompt enriches emotional representation and improves interpretability. Experiments on the AVEC 2019 dataset show our approach achieves state-of-the-art performance with CCC of 0.593 and MAE of 3.95, surpassing previous transfer learning and multi-task learning baselines.

---

### Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph

Authors: Fali Wang, Jihai Chen, Shuhua Yang, Runxue Bao, Tianxiang Zhao, Zhiwei Zhang, Xianfeng Tang, Hui Liu, Qi He, Suhang Wang
Published: 2025-10-29
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.00086v1

Test-Time Scaling (TTS) improves large language models (LLMs) by allocating additional computation during inference, typically through parallel, sequential, or hybrid scaling. However, prior studies often assume fixed collaboration architectures (e.g., topologies) and single-model usage, overlooking that optimal architectures and model combinations can vary across tasks. Therefore, we study the novel problem of searching for compute-optimal model combinations and architectures in TTS under a fixed budget. We formalize it as a multi-LLM collaboration graph, where nodes encode roles and LLM model assignments, and edges capture information flow. This problem is challenging because (i) the combinatorial search space is prohibitively large, and (ii) task-specific requirements demand tailored designs. To address these, we reformulate the problem as probabilistic graph optimization and, through pilot experiments, derive three empirical insights into TTS collaboration graphs. Guided by these insights, we propose Agent-REINFORCE, an LLM-agent-augmented framework that mirrors the REINFORCE pipeline by mapping sampling-gradient-update to sampling-feedback-update, where feedback serves as a textual gradient to update the probabilistic graph and efficiently search for optimal multi-LLM collaboration graphs. Experiments show that Agent-REINFORCE outperforms both traditional and LLM-based baselines in sample efficiency and search performance, and effectively identifies optimal graphs under joint objectives of accuracy and inference latency.

---

### MaGNet: A Mamba Dual-Hypergraph Network for Stock Prediction via Temporal-Causal and Global Relational Learning

Authors: Peilin Tan, Chuanqi Shi, Dian Tu, Liang Xie
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00085v1

Stock trend prediction is crucial for profitable trading strategies and portfolio management yet remains challenging due to market volatility, complex temporal dynamics and multifaceted inter-stock relationships. Existing methods struggle to effectively capture temporal dependencies and dynamic inter-stock interactions, often neglecting cross-sectional market influences, relying on static correlations, employing uniform treatments of nodes and edges, and conflating diverse relationships. This work introduces MaGNet, a novel Mamba dual-hyperGraph Network for stock prediction, integrating three key innovations: (1) a MAGE block, which leverages bidirectional Mamba with adaptive gating mechanisms for contextual temporal modeling and integrates a sparse Mixture-of-Experts layer to enable dynamic adaptation to diverse market conditions, alongside multi-head attention for capturing global dependencies; (2) Feature-wise and Stock-wise 2D Spatiotemporal Attention modules enable precise fusion of multivariate features and cross-stock dependencies, effectively enhancing informativeness while preserving intrinsic data structures, bridging temporal modeling with relational reasoning; and (3) a dual hypergraph framework consisting of the Temporal-Causal Hypergraph (TCH) that captures fine-grained causal dependencies with temporal constraints, and Global Probabilistic Hypergraph (GPH) that models market-wide patterns through soft hyperedge assignments and Jensen-Shannon Divergence weighting mechanism, jointly disentangling localized temporal influences from instantaneous global structures for multi-scale relational learning. Extensive experiments on six major stock indices demonstrate MaGNet outperforms state-of-the-art methods in both superior predictive performance and exceptional investment returns with robust risk management capabilities. Codes available at: https://github.com/PeilinTime/MaGNet.

---

### Application of predictive machine learning in pen & paper RPG game design

Authors: Jolanta Śliwa
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00084v1

In recent years, the pen and paper RPG market has experienced significant growth. As a result, companies are increasingly exploring the integration of AI technologies to enhance player experience and gain a competitive edge. One of the key challenges faced by publishers is designing new opponents and estimating their challenge level. Currently, there are no automated methods for determining a monster's level; the only approaches used are based on manual testing and expert evaluation. Although these manual methods can provide reasonably accurate estimates, they are time-consuming and resource-intensive. Level prediction can be approached using ordinal regression techniques. This thesis presents an overview and evaluation of state-of-the-art methods for this task. It also details the construction of a dedicated dataset for level estimation. Furthermore, a human-inspired model was developed to serve as a benchmark, allowing comparison between machine learning algorithms and the approach typically employed by pen and paper RPG publishers. In addition, a specialized evaluation procedure, grounded in domain knowledge, was designed to assess model performance and facilitate meaningful comparisons.

---

### Fixed-point graph convolutional networks against adversarial attacks

Authors: Shakib Khan, A. Ben Hamza, Amr Youssef
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00083v1

Adversarial attacks present a significant risk to the integrity and performance of graph neural networks, particularly in tasks where graph structure and node features are vulnerable to manipulation. In this paper, we present a novel model, called fixed-point iterative graph convolutional network (Fix-GCN), which achieves robustness against adversarial perturbations by effectively capturing higher-order node neighborhood information in the graph without additional memory or computational complexity. Specifically, we introduce a versatile spectral modulation filter and derive the feature propagation rule of our model using fixed-point iteration. Unlike traditional defense mechanisms that rely on additional design elements to counteract attacks, the proposed graph filter provides a flexible-pass filtering approach, allowing it to selectively attenuate high-frequency components while preserving low-frequency structural information in the graph signal. By iteratively updating node representations, our model offers a flexible and efficient framework for preserving essential graph information while mitigating the impact of adversarial manipulation. We demonstrate the effectiveness of the proposed model through extensive experiments on various benchmark graph datasets, showcasing its resilience against adversarial attacks.

---

### Forecasting Occupational Survivability of Rickshaw Pullers in a Changing Climate with Wearable Data

Authors: Masfiqur Rahaman, Maoyejatun Hasana, Shahad Shahriar Rahman, MD Sajid Mostafiz Noor, Razin Reaz Abedin, Md Toki Tahmid, Duncan Watson Parris, Tanzeem Choudhury, A. B. M. Alim Al Islam, Tauhidur Rahman
Published: 2025-10-29
Categories: cs.CY, cs.HC, cs.IR, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2511.00081v1

Cycle rickshaw pullers are highly vulnerable to extreme heat, yet little is known about how their physiological biomarkers respond under such conditions. This study collected real-time weather and physiological data using wearable sensors from 100 rickshaw pullers in Dhaka, Bangladesh. In addition, interviews with 12 pullers explored their knowledge, perceptions, and experiences related to climate change. We developed a Linear Gaussian Bayesian Network (LGBN) regression model to predict key physiological biomarkers based on activity, weather, and demographic features. The model achieved normalized mean absolute error values of 0.82, 0.47, 0.65, and 0.67 for skin temperature, relative cardiac cost, skin conductance response, and skin conductance level, respectively. Using projections from 18 CMIP6 climate models, we layered the LGBN on future climate forecasts to analyze survivability for current (2023-2025) and future years (2026-2100). Based on thresholds of WBGT above 31.1°C and skin temperature above 35°C, 32% of rickshaw pullers already face high heat exposure risk. By 2026-2030, this percentage may rise to 37% with average exposure lasting nearly 12 minutes, or about two-thirds of the trip duration. A thematic analysis of interviews complements these findings, showing that rickshaw pullers recognize their increasing climate vulnerability and express concern about its effects on health and occupational survivability.

---

### flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R

Authors: Maximilian Willer, Peter Ruckdeschel
Published: 2025-10-29
Categories: cs.LG, cs.CY, stat.ME
arXiv: https://arxiv.org/abs/2511.00079v2

flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpose machine learning pipelines. It is motivated by the rapidly evolving field of algorithmic fairness, where new metrics, mitigation strategies, and methods continuously emerge. A central challenge in fairness, but also far beyond, is that existing toolkits either focus narrowly on single interventions or treat reproducibility and extensibility as secondary considerations rather than core design principles. flowengineR addresses this by introducing a unified architecture of standardized engines for data splitting, execution, preprocessing, training, inprocessing, postprocessing, evaluation, and reporting. Each engine encapsulates one methodological task yet communicates via a lightweight interface, ensuring workflows remain transparent, auditable, and easily extensible. Although implemented in R, flowengineR builds on ideas from workflow languages (CWL, YAWL), graph-oriented visual programming languages (KNIME), and R frameworks (BatchJobs, batchtools). Its emphasis, however, is less on orchestrating engines for resilient parallel execution than on the straightforward setup and management of distinct engines as data structures. This orthogonalization enables distributed responsibilities, independent development, and streamlined integration. In the context of fairness, by structuring fairness methods as interchangeable engines, flowengineR lets researchers integrate, compare, and evaluate interventions across the modeling pipeline. At the same time, the architecture generalizes to explainability, robustness, and compliance metrics without core modifications. While motivated by fairness, flowengineR ultimately provides a general infrastructure for any workflow context where reproducibility, transparency, and extensibility are essential.

---

### RailEstate: An Interactive System for Metro Linked Property Trends

Authors: Chen-Wei Chang, Yu-Chieh Cheng, Yun-En Tsai, Fanglan Chen, Chang-Tien Lu
Published: 2025-10-29
Categories: cs.CY, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2511.00078v1

Access to metro systems plays a critical role in shaping urban housing markets by enhancing neighborhood accessibility and driving property demand. We present RailEstate, a novel web based system that integrates spatial analytics, natural language interfaces, and interactive forecasting to analyze how proximity to metro stations influences residential property prices in the Washington metropolitan area. Unlike static mapping tools or generic listing platforms, RailEstate combines 25 years of historical housing data with transit infrastructure to support low latency geospatial queries, time series visualizations, and predictive modeling. Users can interactively explore ZIP code level price patterns, investigate long term trends, and forecast future housing values around any metro station. A key innovation is our natural language chatbot, which translates plain-English questions e.g., What is the highest price in Falls Church in the year 2000? into executable SQL over a spatial database. This unified and interactive platform empowers urban planners, investors, and residents to derive actionable insights from metro linked housing data without requiring technical expertise.

---

### Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves

Authors: Zihao Wan, Pau Tong Lin Xu, Fuwen Luo, Ziyue Wang, Peng Li, Yang Liu
Published: 2025-10-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00076v1

While Vision-language Models (VLMs) have demonstrated strong semantic capabilities, their ability to interpret the underlying geometric structure of visual information is less explored. Pictographic characters, which combine visual form with symbolic structure, provide an ideal test case for this capability. We formulate this visual recognition challenge in the mathematical domain, where each character is represented by an executable program of geometric primitives. This is framed as a program synthesis task, training a VLM to decompile raster images into programs composed of Bézier curves. Our model, acting as a "visual decompiler", demonstrates performance superior to strong zero-shot baselines, including GPT-4o. The most significant finding is that when trained solely on modern Chinese characters, the model is able to reconstruct ancient Oracle Bone Script in a zero-shot context. This generalization provides strong evidence that the model acquires an abstract and transferable geometric grammar, moving beyond pixel-level pattern recognition to a more structured form of visual understanding.

---

### PDA-LSTM: Knowledge-driven page data arrangement based on LSTM for LCM supression in QLC 3D NAND flash memories

Authors: Qianhui Li, Weiya Wang, Qianqi Zhao, Tong Qu, Jing He, Xuhong Qiang, Jingwen Hou, Ke Chen, Bao Zhang, Qi Wang
Published: 2025-10-29
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2511.00075v1

Quarter level cell (QLC) 3D NAND flash memory is emerging as the predominant storage solution in the era of artificial intelligence. QLC 3D NAND flash stores 4 bit per cell to expand the storage density, resulting in narrower read margins. Constrained to read margins, QLC always suffers from lateral charge migration (LCM), which caused by non-uniform charge density across adjacent memory cells. To suppress charge density gap between cells, there are some algorithm in form of intra-page data mapping such as WBVM, DVDS. However, we observe inter-page data arrangements also approach the suppression. Thus, we proposed an intelligent model PDA-LSTM to arrange intra-page data for LCM suppression, which is a physics-knowledge-driven neural network model. PDA-LSTM applies a long-short term memory (LSTM) neural network to compute a data arrangement probability matrix from input page data pattern. The arrangement is to minimize the global impacts derived from the LCM among wordlines. Since each page data can be arranged only once, we design a transformation from output matrix of LSTM network to non-repetitive sequence generation probability matrix to assist training process. The arranged data pattern can decrease the bit error rate (BER) during data retention. In addition, PDA-LSTM do not need extra flag bits to record data transport of 3D NAND flash compared with WBVM, DVDS. The experiment results show that the PDA-LSTM reduces the average BER by 80.4% compared with strategy without data arrangement, and by 18.4%, 15.2% compared respectively with WBVM and DVDS with code-length 64.

---

### Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures

Authors: Harald Kristen, Daniel Kulmer, Manuela Hirschmugl
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00073v1

Rapid climate change and other disturbances in alpine ecosystems demand frequent habitat monitoring, yet manual mapping remains prohibitively expensive for the required temporal resolution. We employ deep learning for change detection using long-term alpine habitat data from Gesaeuse National Park, Austria, addressing a major gap in applying geospatial foundation models (GFMs) to complex natural environments with fuzzy class boundaries and highly imbalanced classes. We compare two paradigms: post-classification change detection (CD) versus direct CD. For post-classification CD, we evaluate GFMs Prithvi-EO-2.0 and Clay v1.0 against U-Net CNNs; for direct CD, we test the transformer ChangeViT against U-Net baselines. Using high-resolution multimodal data (RGB, NIR, LiDAR, terrain attributes) covering 4,480 documented changes over 15.3 km2, results show Clay v1.0 achieves 51% overall accuracy versus U-Net's 41% for multi-class habitat change, while both reach 67% for binary change detection. Direct CD yields superior IoU (0.53 vs 0.35) for binary but only 28% accuracy for multi-class detection. Cross-temporal evaluation reveals GFM robustness, with Clay maintaining 33% accuracy on 2020 data versus U-Net's 23%. Integrating LiDAR improves semantic segmentation from 30% to 50% accuracy. Although overall accuracies are lower than in more homogeneous landscapes, they reflect realistic performance for complex alpine habitats. Future work will integrate object-based post-processing and physical constraints to enhance applicability.

---

### LookSync: Large-Scale Visual Product Search System for AI-Generated Fashion Looks

Authors: Pradeep M, Ritesh Pallod, Satyen Abrol, Muthu Raman, Ian Anderson
Published: 2025-10-29
Categories: cs.IR, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.00072v1

Generative AI is reshaping fashion by enabling virtual looks and avatars making it essential to find real products that best match AI-generated styles. We propose an end-to-end product search system that has been deployed in a real-world, internet scale which ensures that AI-generated looks presented to users are matched with the most visually and semantically similar products from the indexed vector space. The search pipeline is composed of four key components: query generation, vectorization, candidate retrieval, and reranking based on AI-generated looks. Recommendation quality is evaluated using human-judged accuracy scores. The system currently serves more than 350,000 AI Looks in production per day, covering diverse product categories across global markets of over 12 million products. In our experiments, we observed that across multiple annotators and categories, CLIP outperformed alternative models by a small relative margin of 3--7\% in mean opinion scores. These improvements, though modest in absolute numbers, resulted in noticeably better user perception matches, establishing CLIP as the most reliable backbone for production deployment.

---

### Wavelet-Based Parity Detection Revisited: Representation Dependence, Generalization, and Mechanistic Analysis

Authors: Ertuğrul Mutlu
Published: 2025-10-29
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.00071v2

Parity is exactly determined by the least significant bit (LSB), so machine learning is unnecessary for solving the task. This work instead uses parity as a controlled diagnostic for studying how a classical signal-processing pipeline preserves, amplifies, or suppresses access to symbolic information embedded in a numerical representation. Integers from 0 to 10,000 are encoded as fixed-width 32-bit binary signals, decomposed with a level-3 Daubechies-2 (db2) discrete wavelet transform, summarized by mean absolute coefficient magnitude, and clustered independently per subband with k-means. Clustering is unsupervised, while cluster-to-parity calibration uses training labels only under a stratified 60/20/20 train/validation/test protocol. The frozen configuration reaches 84.26% accuracy on the held-out test set (95% Wilson CI: 82.60-85.79%), and 84.20% +/- 0.57% across 20 stratified resplits. Raw binary summary statistics reach 61.30%, while masking the LSB reduces validation accuracy to 48.15%, consistent with chance. The A3 approximation band alone retains 83.20%, whereas detail bands remain near chance. Performance is strongly representation-dependent: moving the parity bit changes validation accuracy up to 98.60%, and changing the wavelet boundary mode ranges from 54.45% to 83.20%. Cross-magnitude extrapolation degrades from 79.98% on 10,001-20,000 to 59.69% on 100,001-1,000,000. These results do not show that wavelets discover the arithmetic rule of parity. Rather, they show that information already present in the binary encoding becomes more or less recoverable depending on multiscale filtering, spatial alignment, and boundary handling.

---

### Benchmarking Generative AI Against Bayesian Optimization for Constrained Multi-Objective Inverse Design

Authors: Muhammad Bilal Awan, Abdul Razzaq, Abdul Shahid
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00070v1

This paper investigates the performance of Large Language Models (LLMs) as generative optimizers for solving constrained multi-objective regression tasks, specifically within the challenging domain of inverse design (property-to-structure mapping). This problem, critical to materials informatics, demands finding complex, feasible input vectors that lie on the Pareto optimal front. While LLMs have demonstrated universal effectiveness across generative and reasoning tasks, their utility in constrained, continuous, high-dimensional numerical spaces tasks they weren't explicitly architected for remains an open research question. We conducted a rigorous comparative study between established Bayesian Optimization (BO) frameworks and a suite of fine-tuned LLMs and BERT models. For BO, we benchmarked the foundational BoTorch Ax implementation against the state-of-the-art q-Expected Hypervolume Improvement (qEHVI, BoTorchM). The generative approach involved fine-tuning models via Parameter-Efficient Fine-Tuning (PEFT), framing the challenge as a regression problem with a custom output head. Our results show that BoTorch qEHVI achieved perfect convergence (GD=0.0), setting the performance ceiling. Crucially, the best-performing LLM (WizardMath-7B) achieved a Generational Distance (GD) of 1.21, significantly outperforming the traditional BoTorch Ax baseline (GD=15.03). We conclude that specialized BO frameworks remain the performance leader for guaranteed convergence, but fine-tuned LLMs are validated as a promising, computationally fast alternative, contributing essential comparative metrics to the field of AI-driven optimization. The findings have direct industrial applications in optimizing formulation design for resins, polymers, and paints, where multi-objective trade-offs between mechanical, rheological, and chemical properties are critical to innovation and production efficiency.

---

### Latent Domain Prompt Learning for Vision-Language Models

Authors: Zhixing Li, Arsham Gholamzadeh Khoee, Yinan Yu
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00067v2

The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that may not be available and often ambiguous. We instead study the DG setting where models must generalize well without access to explicit domain labels. Our key idea is to represent an unseen target domain as a combination of latent domains automatically discovered from training data, enabling the model to adaptively transfer knowledge across domains. To realize this, we perform latent domain clustering on image features and fuse domain-specific text features based on the similarity between the input image and each latent domain. Experiments on four benchmarks show that this strategy yields consistent gains over VLM-based baselines and provides new insights into improving robustness under domain shift.

---

### Sharpness-Guided Group Relative Policy Optimization via Probability Shaping

Authors: Tue Le, Linh Ngo Van, Trung Le
Published: 2025-10-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00066v4

Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Policy Optimization (GRPO) is a widely used optimizer in this setting. However, RLVR training is typically performed with limited control over generalization. We revisit GRPO through a robustness-based generalization view, where the generalization loss is upper bounded by a combination of the empirical loss and a sharpness surrogate measured by the gradient norm. Building on this perspective, we propose Sharpness-Guided GRPO (GRPO-SG), a simple token-weighted variant of GRPO that downweights tokens likely to cause overly large gradients, reducing sharp updates and stabilizing optimization, thereby improving generalization. Experiments across mathematical reasoning, logic puzzles and tool-augmented question answering show consistent improvements over GRPO, along with smoother gradient-norm trajectories, supporting GRPO-SG as a simple and effective generalization-oriented upgrade to GRPO for RLVR.

---

### Aligning Brain Signals with Multimodal Speech and Vision Embeddings

Authors: Kateryna Shapovalenko, Quentin Auster
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00065v2

When we hear the word "house", we don't just process sound, we imagine walls, doors, memories. The brain builds meaning through layers, moving from raw acoustics to rich, multimodal associations. Inspired by this, we build on recent work from Meta that aligned EEG signals with averaged wav2vec2 speech embeddings, and ask a deeper question: which layers of pre-trained models best reflect this layered processing in the brain? We compare embeddings from two models: wav2vec2, which encodes sound into language, and CLIP, which maps words to images. Using EEG recorded during natural speech perception, we evaluate how these embeddings align with brain activity using ridge regression and contrastive decoding. We test three strategies: individual layers, progressive concatenation, and progressive summation. The findings suggest that combining multimodal, layer-aware representations may bring us closer to decoding how the brain understands language, not just as sound, but as experience.

---

### SPORE: Skeleton Propagation Over Recalibrating Expansions

Authors: Randolph Wiredu-Aidoo
Published: 2025-10-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00064v7

Many real-world datasets are not linearly separable, limiting the effectiveness of centroid-based clustering methods such as K-means. Density-based clustering methods address this limitation by identifying clusters with arbitrary geometric structure; however, existing approaches exhibit two persistent shortcomings. First, they often underperform in the presence of heterogeneous local densities, where a single density threshold cannot adequately capture clusters across multiple density scales. Second, they generally lack the clear boundary delineation naturally induced by the linear partitioning mechanism of centroid-based methods. This paper introduces SPORE (Skeleton Propagation Over Recalibrating Expansions), a clustering algorithm designed to address both challenges while preserving the geometric flexibility of density-based approaches. SPORE operates in two stages: an adaptive cluster expansion phase followed by a proximity-driven boundary propagation phase that maintains discriminative capability even under weak density contrast. The proposed method is evaluated on 28 benchmark datasets against established density-based baselines, with K-means included as a reference centroid-based method. Experimental results demonstrate that SPORE achieves significantly improved cluster recovery relative to all evaluated baselines (p < 0.01), while strong-performing configurations can be identified within five random-search evaluations.

---

### Multi-Representation Attention Framework for Underwater Bioacoustic Denoising and Recognition

Authors: Amine Razig, Youssef Soulaymani, Loubna Benabbou, Pierre Cauchy
Published: 2025-10-29
Categories: eess.AS, cs.LG, cs.SD, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.26838v1

Automated monitoring of marine mammals in the St. Lawrence Estuary faces extreme challenges: calls span low-frequency moans to ultrasonic clicks, often overlap, and are embedded in variable anthropogenic and environmental noise. We introduce a multi-step, attention-guided framework that first segments spectrograms to generate soft masks of biologically relevant energy and then fuses these masks with the raw inputs for multi-band, denoised classification. Image and mask embeddings are integrated via mid-level fusion, enabling the model to focus on salient spectrogram regions while preserving global context. Using real-world recordings from the Saguenay St. Lawrence Marine Park Research Station in Canada, we demonstrate that segmentation-driven attention and mid-level fusion improve signal discrimination, reduce false positive detections, and produce reliable representations for operational marine mammal monitoring across diverse environmental conditions and signal-to-noise ratios. Beyond in-distribution evaluation, we further assess the generalization of Mask-Guided Classification (MGC) under distributional shifts by testing on spectrograms generated with alternative acoustic transformations. While high-capacity baseline models lose accuracy in this Out-of-distribution (OOD) setting, MGC maintains stable performance, with even simple fusion mechanisms (gated, concat) achieving comparable results across distributions. This robustness highlights the capacity of MGC to learn transferable representations rather than overfitting to a specific transformation, thereby reinforcing its suitability for large-scale, real-world biodiversity monitoring. We show that in all experimental settings, the MGC framework consistently outperforms baseline architectures, yielding substantial gains in accuracy on both in-distribution and OOD data.

---

### Category-Aware Semantic Caching for Heterogeneous LLM Workloads

Authors: Chen Wang, Xunzhuo Liu, Yue Zhu, Alaa Youssef, Priya Nagpurkar, Huamin Chen
Published: 2025-10-29
Categories: cs.DB, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.26835v1

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness varies from minutes (stock data) to months (code patterns). Query repetition patterns range from power-law (code) to uniform (conversation), producing long tail cache hit rate distributions: high-repetition categories achieve 40-60% hit rates while low-repetition or volatile categories achieve 5-15% hit rates. Vector databases must exclude the long tail because remote search costs (30ms) require 15--20% hit rates to break even, leaving 20-30% of production traffic uncached. Uniform cache policies compound this problem: fixed thresholds cause false positives in dense spaces and miss valid paraphrases in sparse spaces; fixed TTLs waste memory or serve stale data. This paper presents category-aware semantic caching where similarity thresholds, TTLs, and quotas vary by query category. We present a hybrid architecture separating in-memory HNSW search from external document storage, reducing miss cost from 30ms to 2ms. This reduction makes low-hit-rate categories economically viable (break-even at 3-5% versus 15-20%), enabling cache coverage across the entire workload distribution. Adaptive load-based policies extend this framework to respond to downstream model load, dynamically adjusting thresholds and TTLs to reduce traffic to overloaded models by 9-17% in theoretical projections.

---

### MedForj: An open, large-scale foundational generative prior for high-resolution 3D brain MRI

Authors: Samuel W. Remedios, Aaron Carass, Jerry L. Prince, Blake E. Dewey
Published: 2025-10-29
Categories: eess.IV, cs.AI
arXiv: https://arxiv.org/abs/2510.26834v2

This work introduces MedForj, a suite of 3D foundational generative priors based on diffusion models. The MedForj models were trained on $72{,}659$ 1~mm isotropic 3D $T_1$-weighted MRI human brain image volumes from $38{,}174$ subjects, drawn from a curated corpus of $80{,}675$ volumes from $42{,}506$ subjects spanning $38$ publicly available datasets. These training images were manually inspected to exclude those with poor quality and excessive pathology, and otherwise were minimally processed. The models include six different diffusion training strategies: rectified flow, latent diffusion rectified flow, flow matching, velocity prediction, clean prediction, and noise prediction. Image samples produced by each of these models were compared to each other and against real, ground truth data under downstream segmentation distributions, FID, five inverse problems, and blind human inspection in an observer study. Flow matching was the strongest strategy overall, achieving the best inverse problem solving results at $28.80$~dB PSNR and $0.874$ SSIM averaged over the five forward problems, the highest rate of reconstructions judged real by blind human raters at $72.6\%$, and the closest per-structure match to real segmented anatomy in a permutation test. It was not best everywhere: rectified flow produced the most convincing unconditional samples in the observer study and the best FID, and the latent rectified-flow model achieved the smallest joint distributional distance to real anatomy. No other strategy, however, performed consistently well across all four evaluations. We therefore recommend flow matching as the default MedForj prior, while releasing every strategy so that the choice can be revisited per application. All model weights and corresponding code are publicly available at https://github.com/piksl-research/medforj.

---

### VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes

Authors: Simon Yu, Peilin Yu, Hongbo Zheng, Huajie Shao, Han Zhao, Lui Sha
Published: 2025-10-29
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.26833v1

We present VISAT, a novel open dataset and benchmarking suite for evaluating model robustness in the task of traffic sign recognition with the presence of visual attributes. Built upon the Mapillary Traffic Sign Dataset (MTSD), our dataset introduces two benchmarks that respectively emphasize robustness against adversarial attacks and distribution shifts. For our adversarial attack benchmark, we employ the state-of-the-art Projected Gradient Descent (PGD) method to generate adversarial inputs and evaluate their impact on popular models. Additionally, we investigate the effect of adversarial attacks on attribute-specific multi-task learning (MTL) networks, revealing spurious correlations among MTL tasks. The MTL networks leverage visual attributes (color, shape, symbol, and text) that we have created for each traffic sign in our dataset. For our distribution shift benchmark, we utilize ImageNet-C's realistic data corruption and natural variation techniques to perform evaluations on the robustness of both base and MTL models. Moreover, we further explore spurious correlations among MTL tasks through synthetic alterations of traffic sign colors using color quantization techniques. Our experiments focus on two major backbones, ResNet-152 and ViT-B/32, and compare the performance between base and MTL models. The VISAT dataset and benchmarking framework contribute to the understanding of model robustness for traffic sign recognition, shedding light on the challenges posed by adversarial attacks and distribution shifts. We believe this work will facilitate advancements in developing more robust models for real-world applications in autonomous driving and cyber-physical systems.

---

### SmoothGuard: Defending Multimodal Large Language Models with Noise Perturbation and Clustering Aggregation

Authors: Guangzhi Su, Shuchang Huang, Yutong Ke, Zhuohang Liu, Long Qian, Kaizhu Huang
Published: 2025-10-29
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2510.26830v1

Multimodal large language models (MLLMs) have achieved impressive performance across diverse tasks by jointly reasoning over textual and visual inputs. Despite their success, these models remain highly vulnerable to adversarial manipulations, raising concerns about their safety and reliability in deployment. In this work, we first generalize an approach for generating adversarial images within the HuggingFace ecosystem and then introduce SmoothGuard, a lightweight and model-agnostic defense framework that enhances the robustness of MLLMs through randomized noise injection and clustering-based prediction aggregation. Our method perturbs continuous modalities (e.g., images and audio) with Gaussian noise, generates multiple candidate outputs, and applies embedding-based clustering to filter out adversarially influenced predictions. The final answer is selected from the majority cluster, ensuring stable responses even under malicious perturbations. Extensive experiments on POPE, LLaVA-Bench (In-the-Wild), and MM-SafetyBench demonstrate that SmoothGuard improves resilience to adversarial attacks while maintaining competitive utility. Ablation studies further identify an optimal noise range (0.1-0.2) that balances robustness and utility.

---

### Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning

Authors: Svetlana Churina, Niranjan Chebrolu, Kokil Jaidka
Published: 2025-10-29
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2510.26829v3

We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall performance. Unlike prior poisoning work under static pretraining, we study repeated exposure to counterfactual claims during continual updates. Using paired fact-counterfact items with graded poisoning ratios, we track how internal preferences between competing facts evolve across checkpoints, layers, and model scales. Even moderate poisoning (50-100%) flips over 55% of responses from correct to counterfactual while leaving ambiguity nearly unchanged. These belief flips emerge abruptly, concentrate in late layers (e.g., Layers 29-36 in 3B models), and are partially reversible via patching (up to 56.8%). The corrupted beliefs generalize beyond poisoned prompts, selectively degrading commonsense reasoning while leaving alignment benchmarks largely intact and transferring imperfectly across languages. These results expose a failure mode of continual pre-training in which targeted misinformation replaces internal factual representations without triggering broad performance collapse, motivating representation-level monitoring of factual integrity during model updates.

---

### Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets

Authors: Tsung-Wei Pan, Chang-Hong Wu, Jung-Hua Wang, Ming-Jer Chen, Yu-Chiao Yi, Tsung-Hsien Lee
Published: 2025-10-29
Categories: eess.IV, cs.AI
arXiv: https://arxiv.org/abs/2510.26828v2

Medical image datasets frequently exhibit significant class imbalance, a challenge that is further amplified by the inherently limited sample sizes that characterize clinical imaging data. Using human embryo time-lapse imaging (TLI) as a case study, this work investigates how generative adversarial networks (GANs) can be optimized for small datasets to generate realistic and diagnostically meaningful images. Based on systematic experiments with R3GAN, we established effective training strategies and designed an optimized configuration for 256x256-resolution datasets, featuring a full burn-in phase and a low, gradually increasing gamma range (5 to 40). The generated samples were used to balance an imbalanced embryo dataset, leading to substantial improvement in classification performance. The recall and F1-score of the three-cell (t3) class increased from 0.06 to 0.69 and from 0.11 to 0.60, respectively, without compromising the performance of other classes. These results demonstrate that tailored R3GAN training strategies can effectively alleviate data scarcity and improve model robustness in small-scale medical imaging tasks.

---

### Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling

Authors: Jiarong Du, Zhan Jin, Peijun Yang, Juan Liu, Zhuo Li, Xin Liu, Ming Li
Published: 2025-10-29
Categories: cs.SD, cs.CV, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2510.26825v1

Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various interfering sounds and reverberation. Most previous methods struggle to cope with such complex conditions, resulting in poor perceptual quality of the extracted speech. In this paper, we propose an effective AVSE system that performs well in complex acoustic environments. Specifically, we design a "separation before dereverberation" pipeline that can be extended to other AVSE networks. The 4th COGMHEAR Audio-Visual Speech Enhancement Challenge (AVSEC) aims to explore new approaches to speech processing in multimodal complex environments. We validated the performance of our system in AVSEC-4: we achieved excellent results in the three objective metrics on the competition leaderboard, and ultimately secured first place in the human subjective listening test.

---

### Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders

Authors: Ali Rasekh, Erfan Bagheri Soula, Omid Daliran, Simon Gottschalk, Mohsen Fayyaz
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26027v1

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures have critical limitations in temporal understanding, struggling with tasks that require detailed comprehension of action sequences and temporal progression. In this work, we propose a Video-LLM architecture that introduces stacked temporal attention modules directly within the vision encoder. This design incorporates a temporal attention in vision encoder, enabling the model to better capture the progression of actions and the relationships between frames before passing visual tokens to the LLM. Our results show that this approach significantly improves temporal reasoning and outperforms existing models in video question answering tasks, specifically in action recognition. We improve on benchmarks including VITATECS, MVBench, and Video-MME by up to +5.5%. By enhancing the vision encoder with temporal structure, we address a critical gap in video understanding for Video-LLMs. Project page and code are available at: https://alirasekh.github.io/STAVEQ2/.

---

### Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation

Authors: Feichen Gan, Youcun Lu, Yingying Zhang, Yukun Liu
Published: 2025-10-29
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.26026v1

Reliable uncertainty quantification is crucial for reinforcement learning (RL) in high-stakes settings. We propose a unified conformal prediction framework for infinite-horizon policy evaluation that constructs distribution-free prediction intervals {for returns} in both on-policy and off-policy settings. Our method integrates distributional RL with conformal calibration, addressing challenges such as unobserved returns, temporal dependencies, and distributional shifts. We propose a modular pseudo-return construction based on truncated rollouts and a time-aware calibration strategy using experience replay and weighted subsampling. These innovations mitigate model bias and restore approximate exchangeability, enabling uncertainty quantification even under policy shifts. Our theoretical analysis provides coverage guarantees that account for model misspecification and importance weight estimation. Empirical results, including experiments in synthetic and benchmark environments like Mountain Car, show that our method significantly improves coverage and reliability over standard distributional RL baselines.

---

### Exploring Human-AI Conceptual Alignment through the Prism of Chess

Authors: Semyon Lomasov, Judah Goldfeder, Mehmet Hamza Erol, Matthew So, Yao Yan, Addison Howard, Nathan Kutz, Ravid Shwartz Ziv
Published: 2025-10-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26025v2

Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzing a 270M-parameter transformer that achieves grandmaster-level play, we uncover a striking paradox: while early layers encode human concepts like center control and knight outposts with up to 85\% accuracy, deeper layers, despite driving superior performance, drift toward alien representations, dropping to 50-65\% accuracy. To test conceptual robustness beyond memorization, we introduce the first Chess960 dataset: 240 expert-annotated positions across 6 strategic concepts. When opening theory is eliminated through randomized starting positions, concept recognition drops 10-20\% across all methods, revealing the model's reliance on memorized patterns rather than abstract understanding. Our layer-wise analysis exposes a fundamental tension in current architectures: the representations that win games diverge from those that align with human thinking. These findings suggest that as AI systems optimize for performance, they develop increasingly alien intelligence, a critical challenge for creative AI applications requiring genuine human-AI collaboration. Dataset and code are available at: https://github.com/slomasov/ChessConceptsLLM.

---

### Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs

Authors: HyoJung Han, Sweta Agrawal, Eleftheria Briakou
Published: 2025-10-29
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.26024v1

Cross-lingual alignment (CLA) aims to align multilingual representations, enabling Large Language Models (LLMs) to seamlessly transfer knowledge across languages. While intuitive, we hypothesize, this pursuit of representational convergence can inadvertently cause "cultural erasure", the functional loss of providing culturally-situated responses that should diverge based on the query language. In this work, we systematically analyze this trade-off by introducing a holistic evaluation framework, the transfer-localization plane, which quantifies both desirable knowledge transfer and undesirable cultural erasure. Using this framework, we re-evaluate recent CLA approaches and find that they consistently improve factual transfer at the direct cost of cultural localization across all six languages studied. Our investigation into the internal representations of these models reveals a key insight: universal factual transfer and culturally-specific knowledge are optimally steerable at different model layers. Based on this finding, we propose Surgical Steering, a novel inference-time method that disentangles these two objectives. By applying targeted activation steering to distinct layers, our approach achieves a better balance between the two competing dimensions, effectively overcoming the limitations of current alignment techniques.

---

### Large Language Model-assisted Autonomous Vehicle Recovery from Immobilization

Authors: Zhipeng Bao, Qianwen Li
Published: 2025-10-29
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.26023v2

Despite significant advancements in recent decades, autonomous vehicles (AVs) continue to face challenges in navigating certain traffic scenarios where human drivers excel. In such situations, AVs often become immobilized, disrupting overall traffic flow. Current recovery solutions, such as remote intervention (which is costly and inefficient) and manual takeover (which excludes non-drivers and limits AV accessibility), are inadequate. This paper introduces StuckSolver, a novel Large Language Model (LLM) driven recovery framework that enables AVs to resolve immobilization scenarios through self-reasoning and/or passenger-guided decision-making. StuckSolver is designed as a plug-in add-on module that operates on top of the AV's existing perception-planning-control stack, requiring no modification to its internal architecture. Instead, it interfaces with standard sensor data streams to detect immobilization states, interpret environmental context, and generate high-level recovery commands that can be executed by the AV's native planner. We evaluate StuckSolver on the Bench2Drive benchmark and in custom-designed uncertainty scenarios. Results show that StuckSolver achieves near-state-of-the-art performance through autonomous self-reasoning alone and exhibits further improvements when passenger guidance is incorporated.

---

### Groupwise Registration with Physics-Informed Test-Time Adaptation on Multi-parametric Cardiac MRI

Authors: Xinqi Li, Yi Zhang, Li-Ting Huang, Hsiao-Huang Chang, Thoralf Niendorf, Min-Chi Ku, Qian Tao, Hsin-Jung Yang
Published: 2025-10-29
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.26022v1

Multiparametric mapping MRI has become a viable tool for myocardial tissue characterization. However, misalignment between multiparametric maps makes pixel-wise analysis challenging. To address this challenge, we developed a generalizable physics-informed deep-learning model using test-time adaptation to enable group image registration across contrast weighted images acquired from multiple physical models (e.g., a T1 mapping model and T2 mapping model). The physics-informed adaptation utilized the synthetic images from specific physics model as registration reference, allows for transductive learning for various tissue contrast. We validated the model in healthy volunteers with various MRI sequences, demonstrating its improvement for multi-modal registration with a wide range of image contrast variability.

---

### PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning

Authors: Feijie Wu, Weiwu Zhu, Yuxiang Zhang, Soumya Chatterjee, Jiarong Zhu, Fan Mo, Rong Luo, Jing Gao
Published: 2025-10-29
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.26020v2

Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls to external tools. However, training such agents from outcome-only rewards suffers from credit-assignment ambiguity, obscuring which intermediate tool-use decisions drive success or failure. In this paper, we propose PORTool, an importance-aware policy-optimization algorithm that reinforces agents' tool-use competence from outcome-level supervision while assigning reward at the step level. Specifically, PORTool generates a rewarded rollout tree in which trajectories share prefixes before branching, enabling direct comparisons among alternative tool-use decisions within the same context. It then estimates each step's importance by a correctness-dominant signal, i.e., whether descendants of that step can ultimately produce a correct final answer, plus an auxiliary term indicating whether the step's tool calls satisfy formatting constraints and execute successfully. Using these step-wise importance estimates, PORTool updates the policy to generate efficient tool-call steps, guided by both local comparisons within each branching decision and the overall quality of entire trajectories. Experiments show that PORTool improves final-answer accuracy while reducing tool-call steps compared with state-of-the-art policy-optimization baselines, and ablation studies confirm the robustness of the proposed step-wise importance estimates.

---

### RADRON: Cooperative Localization of Ionizing Radiation Sources by MAVs with Compton Cameras

Authors: Petr Stibinger, Tomas Baca, Daniela Doubravova, Jan Rusnak, Jaroslav Solc, Jan Jakubek, Petr Stepan, Martin Saska
Published: 2025-10-29
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.26018v1

We present a novel approach to localizing radioactive material by cooperating Micro Aerial Vehicles (MAVs). Our approach utilizes a state-of-the-art single-detector Compton camera as a highly sensitive, yet miniature detector of ionizing radiation. The detector's exceptionally low weight (40 g) opens up new possibilities of radiation detection by a team of cooperating agile MAVs. We propose a new fundamental concept of fusing the Compton camera measurements to estimate the position of the radiation source in real time even from extremely sparse measurements. The data readout and processing are performed directly onboard and the results are used in a dynamic feedback to drive the motion of the vehicles. The MAVs are stabilized in a tightly cooperating swarm to maximize the information gained by the Compton cameras, rapidly locate the radiation source, and even track a moving radiation source.

---

### Climate Adaptation-Aware Flood Prediction for Coastal Cities Using Deep Learning

Authors: Bilal Hassan, Areg Karapetyan, Aaron Chung Hin Chow, Samer Madanat
Published: 2025-10-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.26017v1

Climate change and sea-level rise (SLR) pose escalating threats to coastal cities, intensifying the need for efficient and accurate methods to predict potential flood hazards. Traditional physics-based hydrodynamic simulators, although precise, are computationally expensive and impractical for city-scale coastal planning applications. Deep Learning (DL) techniques offer promising alternatives, however, they are often constrained by challenges such as data scarcity and high-dimensional output requirements. Leveraging a recently proposed vision-based, low-resource DL framework, we develop a novel, lightweight Convolutional Neural Network (CNN)-based model designed to predict coastal flooding under variable SLR projections and shoreline adaptation scenarios. Furthermore, we demonstrate the ability of the model to generalize across diverse geographical contexts by utilizing datasets from two distinct regions: Abu Dhabi and San Francisco. Our findings demonstrate that the proposed model significantly outperforms state-of-the-art methods, reducing the mean absolute error (MAE) in predicted flood depth maps on average by nearly 20%. These results highlight the potential of our approach to serve as a scalable and practical tool for coastal flood management, empowering decision-makers to develop effective mitigation strategies in response to the growing impacts of climate change. Project Page: https://caspiannet.github.io/

---

### Dual Mixture-of-Experts Framework for Discrete-Time Survival Analysis

Authors: Hyeonjun Lee, Hyungseob Shin, Gunhee Nam, Hyeonsoo Lee
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.26014v1

Survival analysis is a task to model the time until an event of interest occurs, widely used in clinical and biomedical research. A key challenge is to model patient heterogeneity while also adapting risk predictions to both individual characteristics and temporal dynamics. We propose a dual mixture-of-experts (MoE) framework for discrete-time survival analysis. Our approach combines a feature-encoder MoE for subgroup-aware representation learning with a hazard MoE that leverages patient features and time embeddings to capture temporal dynamics. This dual-MoE design flexibly integrates with existing deep learning based survival pipelines. On METABRIC and GBSG breast cancer datasets, our method consistently improves performance, boosting the time-dependent C-index up to 0.04 on the test sets, and yields further gains when incorporated into the Consurv framework.

---

### AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys

Authors: Siyi Wu, Chiaxin Liang, Ziqian Bi, Leyi Zhao, Tianyang Wang, Junhao Song, Yichao Zhang, Keyu Chen, Benji Peng, Xinyuan Song
Published: 2025-10-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.26012v3

The rapid growth of research literature, particularly in large language models (LLMs), has made producing comprehensive and current survey papers increasingly difficult. This paper introduces autosurvey2, a multi-stage pipeline that automates survey generation through retrieval-augmented synthesis and structured evaluation. The system integrates parallel section generation, iterative refinement, and real-time retrieval of recent publications to ensure both topical completeness and factual accuracy. Quality is assessed using a multi-LLM evaluation framework that measures coverage, structure, and relevance in alignment with expert review standards. Experimental results demonstrate that autosurvey2 consistently outperforms existing retrieval-based and automated baselines, achieving higher scores in structural coherence and topical relevance while maintaining strong citation fidelity. By combining retrieval, reasoning, and automated evaluation into a unified framework, autosurvey2 provides a scalable and reproducible solution for generating long-form academic surveys and contributes a solid foundation for future research on automated scholarly writing. All code and resources are available at https://github.com/annihi1ation/auto_research.

---

### Detecting Anomalies in Machine Learning Infrastructure via Hardware Telemetry

Authors: Ziji Chen, Steven W. D. Chien, Peng Qian, Noa Zilberman
Published: 2025-10-29
Categories: cs.PF, cs.AR, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2510.26008v2

Modern machine learning (ML) has grown into a tightly coupled, full-stack ecosystem that combines hardware, software, network, and applications. Many users rely on cloud providers for elastic, isolated, and cost-efficient resources. Unfortunately, these platforms as a service use virtualization, which means operators have little insight into the users' workloads. This hinders resource optimizations by the operator, which is essential to ensure cost efficiency and minimize execution time. In this paper, we argue that workload knowledge is unnecessary for system-level optimization. We propose Reveal, which takes a hardware-centric approach, relying only on hardware signals - fully accessible by operators. Using low-level signals collected from the system, Reveal detects anomalies through an unsupervised learning pipeline. The pipeline is developed by analyzing over 30 popular ML models on various hardware platforms, ensuring adaptability to emerging workloads and unknown deployment patterns. Using Reveal, we successfully identified both network and system configuration issues, accelerating the DeepSeek model by 5.97%.

---

### The Quest for Reliable Metrics of Responsible AI

Authors: Theresia Veronika Rampisela, Maria Maistro, Tuukka Ruotsalo, Christina Lioma
Published: 2025-10-29
Categories: cs.CY, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.26007v1

The development of Artificial Intelligence (AI), including AI in Science (AIS), should be done following the principles of responsible AI. Progress in responsible AI is often quantified through evaluation metrics, yet there has been less work on assessing the robustness and reliability of the metrics themselves. We reflect on prior work that examines the robustness of fairness metrics for recommender systems as a type of AI application and summarise their key takeaways into a set of non-exhaustive guidelines for developing reliable metrics of responsible AI. Our guidelines apply to a broad spectrum of AI applications, including AIS.

---

### CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments

Authors: Rishika Bhagwatkar, Syrielle Montariol, Angelika Romanou, Beatriz Borges, Irina Rish, Antoine Bosselut
Published: 2025-10-29
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.26006v1

Humans can naturally identify, reason about, and explain anomalies in their environment. In computer vision, this long-standing challenge remains limited to industrial defects or unrealistic, synthetically generated anomalies, failing to capture the richness and unpredictability of real-world anomalies. In this work, we introduce CAVE, the first benchmark of real-world visual anomalies. CAVE supports three open-ended tasks: anomaly description, explanation, and justification; with fine-grained annotations for visual grounding and categorizing anomalies based on their visual manifestations, their complexity, severity, and commonness. These annotations draw inspiration from cognitive science research on how humans identify and resolve anomalies, providing a comprehensive framework for evaluating Vision-Language Models (VLMs) in detecting and understanding anomalies. We show that state-of-the-art VLMs struggle with visual anomaly perception and commonsense reasoning, even with advanced prompting strategies. By offering a realistic and cognitively grounded benchmark, CAVE serves as a valuable resource for advancing research in anomaly detection and commonsense reasoning in VLMs.

---

### DARTS: A Drone-Based AI-Powered Real-Time Traffic Incident Detection System

Authors: Bai Li, Achilleas Kourtellis, Rong Cao, Joseph Post, Brian Porter, Yu Zhang
Published: 2025-10-29
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.26004v1

Rapid and reliable incident detection is critical for reducing crash-related fatalities, injuries, and congestion. However, conventional methods, such as closed-circuit television, dashcam footage, and sensor-based detection, separate detection from verification, suffer from limited flexibility, and require dense infrastructure or high penetration rates, restricting adaptability and scalability to shifting incident hotspots. To overcome these challenges, we developed DARTS, a drone-based, AI-powered real-time traffic incident detection system. DARTS integrates drones' high mobility and aerial perspective for adaptive surveillance, thermal imaging for better low-visibility performance and privacy protection, and a lightweight deep learning framework for real-time vehicle trajectory extraction and incident detection. The system achieved 99% detection accuracy on a self-collected dataset and supports simultaneous online visual verification, severity assessment, and incident-induced congestion propagation monitoring via a web-based interface. In a field test on Interstate 75 in Florida, DARTS detected and verified a rear-end collision 12 minutes earlier than the local transportation management center and monitored incident-induced congestion propagation, suggesting potential to support faster emergency response and enable proactive traffic control to reduce congestion and secondary crash risk. Crucially, DARTS's flexible deployment architecture reduces dependence on frequent physical patrols, indicating potential scalability and cost-effectiveness for use in remote areas and resource-constrained settings. This study presents a promising step toward a more flexible and integrated real-time traffic incident detection system, with significant implications for the operational efficiency and responsiveness of modern transportation management.

---

### Larger Hausdorff Dimension in Scanning Pattern Facilitates Mamba-Based Methods in Low-Light Image Enhancement

Authors: Xinhua Wang, Caibo Feng, Xiangjun Fu, Chunxiao Liu
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26001v2

We propose an innovative enhancement to the Mamba framework by increasing the Hausdorff dimension of its scanning pattern through a novel Hilbert Selective Scan mechanism. This mechanism explores the feature space more effectively, capturing intricate fine-scale details and improving overall coverage. As a result, it mitigates information inconsistencies while refining spatial locality to better capture subtle local interactions without sacrificing the model's ability to handle long-range dependencies. Extensive experiments on publicly available benchmarks demonstrate that our approach significantly improves both the quantitative metrics and qualitative visual fidelity of existing Mamba-based low-light image enhancement methods, all while reducing computational resource consumption and shortening inference time. We believe that this refined strategy not only advances the state-of-the-art in low-light image enhancement but also holds promise for broader applications in fields that leverage Mamba-based techniques.

---

### Infrequent Exploration in Linear Bandits

Authors: Harin Lee, Min-hwan Oh
Published: 2025-10-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26000v1

We study the problem of infrequent exploration in linear bandits, addressing a significant yet overlooked gap between fully adaptive exploratory methods (e.g., UCB and Thompson Sampling), which explore potentially at every time step, and purely greedy approaches, which require stringent diversity assumptions to succeed. Continuous exploration can be impractical or unethical in safety-critical or costly domains, while purely greedy strategies typically fail without adequate contextual diversity. To bridge these extremes, we introduce a simple and practical framework, INFEX, explicitly designed for infrequent exploration. INFEX executes a base exploratory policy according to a given schedule while predominantly choosing greedy actions in between. Despite its simplicity, our theoretical analysis demonstrates that INFEX achieves instance-dependent regret matching standard provably efficient algorithms, provided the exploration frequency exceeds a logarithmic threshold. Additionally, INFEX is a general, modular framework that allows seamless integration of any fully adaptive exploration method, enabling wide applicability and ease of adoption. By restricting intensive exploratory computations to infrequent intervals, our approach can also enhance computational efficiency. Empirical evaluations confirm our theoretical findings, showing state-of-the-art regret performance and runtime improvements over existing methods.

---

### From Queries to Insights: Agentic LLM Pipelines for Spatio-Temporal Text-to-SQL

Authors: Manu Redd, Tao Zhe, Dongjie Wang
Published: 2025-10-29
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.25997v1

Natural-language-to-SQL (NL-to-SQL) systems hold promise for democratizing access to structured data, allowing users to query databases without learning SQL. Yet existing systems struggle with realistic spatio-temporal queries, where success requires aligning vague user phrasing with schema-specific categories, handling temporal reasoning, and choosing appropriate outputs. We present an agentic pipeline that extends a naive text-to-SQL baseline (llama-3-sqlcoder-8b) with orchestration by a Mistral-based ReAct agent. The agent can plan, decompose, and adapt queries through schema inspection, SQL generation, execution, and visualization tools. We evaluate on 35 natural-language queries over the NYC and Tokyo check-in dataset, covering spatial, temporal, and multi-dataset reasoning. The agent achieves substantially higher accuracy than the naive baseline 91.4% vs. 28.6% and enhances usability through maps, plots, and structured natural-language summaries. Crucially, our design enables more natural human-database interaction, supporting users who lack SQL expertise, detailed schema knowledge, or prompting skill. We conclude that agentic orchestration, rather than stronger SQL generators alone, is a promising foundation for interactive geospatial assistants.

---

### Efficient Online Learning with Predictive Coding Networks: Exploiting Temporal Correlations

Authors: Darius Masoum Zadeh-Jousdani, Elvin Hajizada, Eyke Hüllermeier
Published: 2025-10-29
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.25993v1

Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Traditional backpropagation, while effective, conflicts with biological plausibility principles and may be suboptimal for continuous adaptation scenarios. The Predictive Coding (PC) framework offers a biologically plausible alternative with local, Hebbian-like update rules, making it suitable for neuromorphic hardware implementation. However, PC's main limitation is its computational overhead due to multiple inference iterations during training. We present Predictive Coding Network with Temporal Amortization (PCN-TA), which preserves latent states across temporal frames. By leveraging temporal correlations, PCN-TA significantly reduces computational demands while maintaining learning performance. Our experiments on the COIL-20 robotic perception dataset demonstrate that PCN-TA achieves 10% fewer weight updates compared to backpropagation and requires 50% fewer inference steps than baseline PC networks. These efficiency gains directly translate to reduced computational overhead for moving another step toward edge deployment and real-time adaptation support in resource-constrained robotic systems. The biologically-inspired nature of our approach also makes it a promising candidate for future neuromorphic hardware implementations, enabling efficient online learning at the edge.

---

### Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Authors: Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei Chen, Wei Wang, Tomas Pfister, Chen-Yu Lee
Published: 2025-10-29
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.25992v3

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even after many attempts, while Supervised Fine-Tuning (SFT) tends to overfit long demonstrations through rigid token-by-token imitation. To address this gap, we propose Supervised Reinforcement Learning (SRL), a framework that reformulates problem solving as generating a sequence of logical "actions". SRL trains the model to generate an internal reasoning monologue before committing to each action. It provides smoother rewards based on the similarity between the model's actions and expert actions extracted from the SFT dataset in a step-wise manner. This supervision offers richer learning signals even when all rollouts are incorrect, while encouraging flexible reasoning guided by expert demonstrations. As a result, SRL enables small models to learn challenging problems previously unlearnable by SFT or RLVR. Moreover, initializing training with SRL before refining with RLVR yields the strongest overall performance. Beyond reasoning benchmarks, SRL generalizes effectively to agentic software engineering tasks, establishing it as a robust and versatile training framework for reasoning-oriented LLMs.

---

### Fine-tuning Segment Anything for Real-Time Tumor Tracking in Cine-MRI

Authors: Valentin Boussot, Cédric Hémon, Jean-Claude Nunes, Jean-Louis Dillenseger
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.25990v1

In this work, we address the TrackRAD2025 challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints. Two complementary strategies were explored: (i) unsupervised registration with the IMPACT similarity metric and (ii) foundation model-based segmentation leveraging SAM 2.1 and its recent variants through prompt-based interaction. Due to the one-second runtime constraint, the SAM-based method was ultimately selected. The final configuration used SAM2.1 b+ with mask-based prompts from the first annotated slice, fine-tuned solely on the small labeled subset from TrackRAD2025. Training was configured to minimize overfitting, using 1024x1024 patches (batch size 1), standard augmentations, and a balanced Dice + IoU loss. A low uniform learning rate (0.0001) was applied to all modules (prompt encoder, decoder, Hiera backbone) to preserve generalization while adapting to annotator-specific styles. Training lasted 300 epochs (~12h on RTX A6000, 48GB). The same inference strategy was consistently applied across all anatomical sites and MRI field strengths. Test-time augmentation was considered but ultimately discarded due to negligible performance gains. The final model was selected based on the highest Dice Similarity Coefficient achieved on the validation set after fine-tuning. On the hidden test set, the model reached a Dice score of 0.8794, ranking 6th overall in the TrackRAD2025 challenge. These results highlight the strong potential of foundation models for accurate and real-time tumor tracking in MRI-guided radiotherapy.

---

### A General and Streamlined Differentiable Optimization Framework

Authors: Andrew W. Rosemberg, Joaquim Dias Garcia, François Pacaud, Robert B. Parker, Benoît Legat, Kaarthik Sundar, Russell Bent, Pascal Van Hentenryck
Published: 2025-10-29
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.25986v1

Differentiating through constrained optimization problems is increasingly central to learning, control, and large-scale decision-making systems, yet practical integration remains challenging due to solver specialization and interface mismatches. This paper presents a general and streamlined framework-an updated DiffOpt.jl-that unifies modeling and differentiation within the Julia optimization stack. The framework computes forward - and reverse-mode solution and objective sensitivities for smooth, potentially nonconvex programs by differentiating the KKT system under standard regularity assumptions. A first-class, JuMP-native parameter-centric API allows users to declare named parameters and obtain derivatives directly with respect to them - even when a parameter appears in multiple constraints and objectives - eliminating brittle bookkeeping from coefficient-level interfaces. We illustrate these capabilities on convex and nonconvex models, including economic dispatch, mean-variance portfolio selection with conic risk constraints, and nonlinear robot inverse kinematics. Two companion studies further demonstrate impact at scale: gradient-based iterative methods for strategic bidding in energy markets and Sobolev-style training of end-to-end optimization proxies using solver-accurate sensitivities. Together, these results demonstrate that differentiable optimization can be deployed as a routine tool for experimentation, learning, calibration, and design-without deviating from standard JuMP modeling practices and while retaining access to a broad ecosystem of solvers.

---

### Contrastive Predictive Coding Done Right for Mutual Information Estimation

Authors: J. Jon Ryu, Pavan Yeddanapudi, Xiangxiang Xu, Gregory W. Wornell
Published: 2025-10-29
Categories: cs.LG, cs.IT, stat.ML
arXiv: https://arxiv.org/abs/2510.25983v1

The InfoNCE objective, originally introduced for contrastive representation learning, has become a popular choice for mutual information (MI) estimation, despite its indirect connection to MI. In this paper, we demonstrate why InfoNCE should not be regarded as a valid MI estimator, and we introduce a simple modification, which we refer to as InfoNCE-anchor, for accurate MI estimation. Our modification introduces an auxiliary anchor class, enabling consistent density ratio estimation and yielding a plug-in MI estimator with significantly reduced bias. Beyond this, we generalize our framework using proper scoring rules, which recover InfoNCE-anchor as a special case when the log score is employed. This formulation unifies a broad spectrum of contrastive objectives, including NCE, InfoNCE, and $f$-divergence variants, under a single principled framework. Empirically, we find that InfoNCE-anchor with the log score achieves the most accurate MI estimates; however, in self-supervised representation learning experiments, we find that the anchor does not improve the downstream task performance. These findings corroborate that contrastive representation learning benefits not from accurate MI estimation per se, but from the learning of structured density ratios.

---

### Enabling Fast and Accurate Neutral Atom Readout through Image Denoising

Authors: Chaithanya Naik Mude, Linipun Phuttitarn, Satvik Maurya, Kunal Sinha, Mark Saffman, Swamit Tannu
Published: 2025-10-29
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.25982v2

Neutral atom quantum computers hold promise for scaling up to hundreds of thousands or more qubits, but their progress is constrained by slow qubit readout. Parallel measurement of qubit arrays currently takes milliseconds, much longer than the underlying quantum gate operations-making readout the primary bottleneck in deploying quantum error correction. Because each round of QEC depends on measurement, long readout times increase cycle duration and slow down program execution. Reducing the readout duration speeds up cycles and reduces decoherence errors that accumulate while qubits idle, but it also lowers the number of collected photons, making measurements noisier and more error-prone. This tradeoff leaves neutral atom systems stuck between slow but accurate readout and fast but unreliable readout. We show that image denoising can resolve this tension. Our framework, GANDALF, uses explicit denoising using image translation to reconstruct clear signals from short, low-photon measurements, enabling reliable classification at up to 1.6x shorter readout times. Combined with lightweight classifiers and a pipelined readout design, our approach both reduces logical error rate by up to 35x and overall QEC cycle time up to 1.77x compared to state-of-the-art convolutional neural network (CNN)-based readout for Cesium (Cs) Neutral Atom arrays.

---