# Research Papers — 2025-10 · bundle page 184 of 217

> Full-text markdown of papers #9151–9200 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/184
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/183.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/185.md)

### Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space

Authors: Tomas Figliolia, Nicholas Alonso, Rishi Iyer, Quentin Anthony, Beren Millidge
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.04476v2

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache, speeding decode, but leave compute, which determines prefill and training speed, largely unchanged. We introduce Compressed Convolutional Attention (CCA), a novel attention method which down-projects queries, keys, and values and performs the entire attention operation inside the shared latent space. This simple design dramatically cuts parameters, KV-cache, and FLOPs all at once by the desired compression factor. Because CCA is orthogonal to head-sharing, we combine the two to form Compressed Convolutional Grouped Query Attention (CCGQA), which further tightens the compute-bandwidth Pareto frontier so that users can tune compression toward either FLOP or memory limits without sacrificing quality. Experiments show that CCGQA consistently outperforms both GQA and MLA at equal KV-cache compression on dense and MoE models. Additionally, we show that CCGQA outperforms all other attention methods on MoE models with half the KV-cache of GQA and MLA, achieving an 8x KV-cache compression with no drop in performance compared to standard MHA. CCA and CCGQA also dramatically reduce the FLOP cost of attention which leads to substantially faster training and prefill than existing methods. On H100 GPUs, our fused CCA/CCGQA kernel reduces prefill latency by about 1.7x at a sequence length of 16k relative to MHA, and accelerates backward by about 1.3x.

---

### DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization

Authors: Gang Li, Yan Chen, Ming Lin, Tianbao Yang
Published: 2025-10-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.04474v2

Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long and redundant reasoning even for simple questions, which substantially increases computational cost and response latency. While existing methods incorporate length rewards to GRPO to promote concise reasoning, they incur significant performance degradation. We identify the root cause: when rewards for correct but long rollouts are penalized, GRPO's group-relative advantage function can assign them negative advantages, actively discouraging valid reasoning. To overcome this, we propose Decoupled Reward Policy Optimization (DRPO), a novel framework that decouples the length-based learning signal of correct rollouts from incorrect ones. DRPO ensures that reward signals for correct rollouts are normalized solely within the positive group, shielding them from interference by negative samples. The DRPO's objective is grounded in integrating an optimized positive data distribution, which maximizes length-based rewards under a KL regularization, into a discriminative objective. We derive a closed-form solution for this distribution, enabling efficient computation of the objective and its gradients using only on-policy data and importance weighting. Of independent interest, this formulation is general and can incorporate other preference rewards of positive data beyond length. Experiments on mathematical reasoning tasks demonstrate DRPO's significant superiority over six efficient reasoning baselines. Notably, with a 1.5B model, our method achieves 77\% length reduction with only 1.1\% performance loss on simple questions like GSM8k dataset, while the follow-up baseline sacrifices 4.3\% for 68\% length reduction.

---

### SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection

Authors: Baber Jan, Saeed Anwar, Aiman H. El-Maleh, Abdul Jabbar Siddiqui, Abdul Bais
Published: 2025-10-06
Categories: cs.CV, cs.AI, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2510.04472v1

Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and multi-scale processors independently. This accumulation creates a computational burden without proportional gains. To manage this complexity, they process at reduced resolutions, eliminating fine details essential for camouflage. We present SPEGNet, addressing fragmentation through a unified design. The architecture integrates multi-scale features via channel calibration and spatial enhancement. Boundaries emerge directly from context-rich representations, maintaining semantic-spatial alignment. Progressive refinement implements scale-adaptive edge modulation with peak influence at intermediate resolutions. This design strikes a balance between boundary precision and regional consistency. SPEGNet achieves 0.887 $S_α$ on CAMO, 0.890 on COD10K, and 0.895 on NC4K, with real-time inference speed. Our approach excels across scales, from tiny, intricate objects to large, pattern-similar ones, while handling occlusion and ambiguous boundaries. Code, model weights, and results are available on \href{https://github.com/Baber-Jan/SPEGNet}{https://github.com/Baber-Jan/SPEGNet}.

---

### Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCM

Authors: Ian Baxter, Hamid Pahlavan, Pedram Hassanzadeh, Katharine Rucker, Tiffany Shaw
Published: 2025-10-06
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.04466v1

Physics-based atmosphere-land models with prescribed sea surface temperature have notable successes but also biases in their ability to represent atmospheric variability compared to observations. Recently, AI emulators and hybrid models have emerged with the potential to overcome these biases, but still require systematic evaluation against metrics grounded in fundamental atmospheric dynamics. Here, we evaluate the representation of four atmospheric variability benchmarking metrics in a fully data-driven AI emulator (ACE2-ERA5) and hybrid model (NeuralGCM). The hybrid model and emulator can capture the spectra of large-scale tropical waves and extratropical eddy-mean flow interactions, including critical levels. However, both struggle to capture the timescales associated with quasi-biennial oscillation (QBO, $\sim 28$ months) and Southern annular mode propagation ($\sim 150$ days). These dynamical metrics serve as an initial benchmarking tool to inform AI model development and understand their limitations, which may be essential for out-of-distribution applications (e.g., extrapolating to unseen climates).

---

### Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

Authors: Zhiping Zhang, Yi Evie Zhang, Freda Shi, Tianshi Li
Published: 2025-10-06
Categories: cs.HC, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.04465v3

LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and the effectiveness of personalization. Yet the expanded design space of agent autonomy also presents opportunities to shape these effects, which remain underexplored. We conducted a $3\times3$ between-subjects experiment ($N=450$) to study how agent autonomy level influences personalization's effects on users' privacy concerns, trust, and willingness to use, as well as the underlying psychological processes. We find that risk-contingent autonomy, where the agent delegates control back to users upon detecting potential privacy leakage, improves users' perceived control. This in turn attenuates personalization's adverse effects: privacy concerns rise less and trust declines less. Our results suggest that designing $\textbf{agent's autonomy}$ that supports $\textbf{human autonomy}$ (both perceived control and oversight effectiveness) helps users benefit from personalization without being deterred by growing privacy concerns. This positions aligning decision authority between users and agents ($\textbf{autonomy alignment}$) as an important opportunity and challenge for trustworthy human-agent interaction.

---

### Perspectives on Stochastic Localization

Authors: Bobby Shi, Kevin Tian, Matthew S. Zhang
Published: 2025-10-06
Categories: math.PR, cs.DS, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.04460v2

We survey different perspectives on the stochastic localization process of Eldan, a powerful construction that has had many exciting recent applications in high-dimensional probability and algorithm design. Unlike prior surveys on this topic, our focus is on giving a self-contained presentation of all known alternative constructions of Eldan's stochastic localization, with an emphasis on connections between different constructions. Our hope is that by collecting these perspectives, some of which had primarily arisen within a particular community (e.g., probability theory, theoretical computer science, information theory, or machine learning), we can broaden the accessibility of stochastic localization, and ease its future use.

---

### Two approaches to multiple canonical correlation analysis for repeated measures data

Authors: Tomasz Górecki, Mirosław Krzyśko, Felix Gnettner, Piotr Kokoszka
Published: 2025-10-06
Categories: stat.ME, math.ST, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.04457v2

In classical canonical correlation analysis (CCA), the goal is to determine the linear transformations of two random vectors into two new random variables that are most strongly correlated. Canonical variables are pairs of these new random variables, while canonical correlations are correlations between these pairs. In this paper, we propose and study two generalizations of this classical method: (1) Instead of two random vectors we study more complex data structures that appear in important applications. In these structures, there are $L$ features, each described by $p_l$ scalars, $1 \le l \le L$. We observe $n$ such objects over $T$ time points. We derive a suitable analog of the CCA for such data. Our approach relies on embeddings into Reproducing Kernel Hilbert Spaces, and covers several related data structures as well. (2) We develop an analogous approach for multidimensional random processes. In this case, the experimental units are multivariate continuous, square-integrable functions over a given interval. These functions are modeled as elements of a Hilbert space, so in this case, we define the multiple functional canonical correlation analysis, MFCCA. We justify our approaches by their application to two data sets and suitable large sample theory. We derive consistency rates for the related transformation and correlation estimators, and show that it is possible to relax two common assumptions on the compactness of the underlying cross-covariance operators and the independence of the data.

---

### Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions

Authors: Akira Kitaoka
Published: 2025-10-06
Categories: math.OC, cs.AI, cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.04455v3

Data-driven inverse optimization for mixed-integer linear programs (MILPs), which seeks to learn an objective function and constraints consistent with observed decisions, is important for building accurate mathematical models in a variety of domains, including power systems and scheduling. However, to the best of our knowledge, existing data-driven inverse optimization methods primarily focus on learning objective functions under known constraints, and learning both objective functions and constraints from data for MILPs remains largely unexplored. In this paper, we propose a two-stage approach for a class of inverse optimization problems in which the objective is a linear combination of given feature functions and the constraints are parameterized by unknown functions and thresholds. Our method first learns the constraints and then, conditioned on the learned constraints, estimates the objective-function weights. On the theoretical side, we provide finite-sample guarantees for solving the proposed inverse optimization problem. To this end, we develop statistical learning tools for pseudo-metric spaces under sub-Gaussian assumptions and use them to derive a learning-theoretic framework for inverse optimization with both unknown objectives and constraints. On the experimental side, we demonstrate that our method successfully solves inverse optimization problems on scheduling instances formulated as ILPs with up to 100 decision variables.

---

### Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners

Authors: Xiangchi Yuan, Xiang Chen, Tong Yu, Dachuan Shi, Can Jin, Wenke Lee, Saayan Mitra
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04454v1

Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle to expand reasoning boundaries because they learn from their own reasoning trajectories rather than acquiring external knowledge. Supervised fine-tuning (SFT) offers complementary benefits but typically requires large-scale data and risks overfitting. Recent attempts to combine SFT and RL face three main challenges: data inefficiency, algorithm-specific designs, and catastrophic forgetting. We propose a plug-and-play framework that dynamically integrates SFT into RL by selecting challenging examples for SFT. This approach reduces SFT data requirements and remains agnostic to the choice of RL or SFT algorithm. To mitigate catastrophic forgetting of RL-acquired skills during SFT, we select high-entropy tokens for loss calculation and freeze parameters identified as critical for RL. Our method achieves state-of-the-art (SoTA) reasoning performance using only 1.5% of the SFT data and 20.4% of the RL data used by prior SoTA, providing an efficient and plug-and-play solution for combining SFT and RL in reasoning post-training.

---

### Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes

Authors: Jenny T. Liang, Titus Barik, Jeffrey Nichols, Eldon Schoop, Ruijia Cheng
Published: 2025-10-06
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.04452v3

Computer use agents (or "agents") are generative AI that automates actions within user interfaces from user commands. Current research focuses on training and evaluating the underlying models, leaving these agents' user experience (UX) understudied. We conducted two studies to understand the design space of agent UX (RQ1) and the support required to prototype it (RQ2). First, we develop a taxonomy of design considerations for agent UX, comprising 21 subcategories of UX considerations. Then, through a requirements elicitation study with 12 participants---including six agent experts---we identify five Activities and six Desired Capabilities needed in tools prototyping agent UX. Informed by these results, we created AgentUXlab, a design probe that enables developers to design agents with different UX approaches for a website and evaluate those experiences by executing prototypes in a browser. From a user study with 14 participants, we elucidate tooling insights and derive design implications for agent UX prototyping tools.

---

### REAR: Rethinking Visual Autoregressive Models via Generator-Tokenizer Consistency Regularization

Authors: Qiyuan He, Yicong Li, Haotian Ye, Jinghao Wang, Xinyao Liao, Pheng-Ann Heng, Stefano Ermon, James Zou, Angela Yao
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04450v1

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and rasterization ordering. In this work, we identify a core bottleneck from the perspective of generator-tokenizer inconsistency, i.e., the AR-generated tokens may not be well-decoded by the tokenizer. To address this, we propose reAR, a simple training strategy introducing a token-wise regularization objective: when predicting the next token, the causal transformer is also trained to recover the visual embedding of the current token and predict the embedding of the target token under a noisy context. It requires no changes to the tokenizer, generation order, inference pipeline, or external models. Despite its simplicity, reAR substantially improves performance. On ImageNet, it reduces gFID from 3.02 to 1.86 and improves IS to 316.9 using a standard rasterization-based tokenizer. When applied to advanced tokenizers, it achieves a gFID of 1.42 with only 177M parameters, matching the performance with larger state-of-the-art diffusion models (675M).

---

### Zeroth-Order Methods for Stochastic Nonconvex Nonsmooth Composite Optimization

Authors: Ziyi Chen, Peiran Yu, Heng Huang
Published: 2025-10-06
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2510.04446v1

This work aims to solve a stochastic nonconvex nonsmooth composite optimization problem. Previous works on composite optimization problem requires the major part to satisfy Lipschitz smoothness or some relaxed smoothness conditions, which excludes some machine learning examples such as regularized ReLU network and sparse support matrix machine. In this work, we focus on stochastic nonconvex composite optimization problem without any smoothness assumptions. In particular, we propose two new notions of approximate stationary points for such optimization problem and obtain finite-time convergence results of two zeroth-order algorithms to these two approximate stationary points respectively. Finally, we demonstrate that these algorithms are effective using numerical experiments.

---

### Domain Generalization Under Posterior Drift

Authors: Yilun Zhu, Naihao Deng, Naichen Shi, Aditya Gangrade, Clayton Scott
Published: 2025-10-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.04441v2

Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no labeled data is available. For the prevailing benchmark datasets in DG, there exists a single classifier that performs well across all domains. In this work, we study a fundamentally different regime where the domains satisfy a \emph{posterior drift} assumption, in which the optimal classifier might vary substantially with domain. We establish a decision-theoretic framework for DG under posterior drift, and investigate the practical implications of this framework through experiments on language and vision tasks.

---

### Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size

Authors: Farid Bozorgnia, Vyacheslav Kungurtsev, Shirali Kadyrov, Mohsen Yousefnezhad
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04440v2

We develop a source-driven fractional heat-kernel framework for semi-super\-vised graph learning that combines nonlocal propagation with sustained label information. A fixed nonzero label source compatible with the Laplacian null space prevents asymptotic collapse into that space, providing a mechanism for mitigating oversmoothing at long diffusion times. The fractional order controls the relative modal attenuation and the spectral weighting of the sustained response, while the diffusion time sets the propagation horizon. We characterize conservation laws and equilibria on normalized and disconnected graphs, develop a null-space deflation, and analyze the approximation of the propagators. On Two-Moon, fractional orders improve source-free propagation, while compatible source-driven diffusion exceeds $96\%$ mean accuracy with one training label per class at orders $0.8$ and $1$. On Cora and CiteSeer, the source-driven pipeline improves mean accuracy over GAT by $9.2$ and $8.0$ percentage points at one training label per class, with model selection on $500$ labeled validation nodes and closely comparable classical and fractional pipeline configurations; it matches GAT on PubMed and trails it at ten and twenty labels per class on Cora. Within GraphHeat, validation-based exponent selection at a common diffusion time yields a paired gain of $1.45$ percentage points at one label per class.

---

### On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs

Authors: Lucie Kunitomo-Jacquin, Edison Marrese-Taylor, Ken Fukuda
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04439v1

Quantifying uncertainty in large language models (LLMs) is important for safety-critical applications because it helps spot incorrect answers, known as hallucinations. One major trend of uncertainty quantification methods is based on estimating the entropy of the distribution of the LLM's potential output sequences. This estimation is based on a set of output sequences and associated probabilities obtained by querying the LLM several times. In this paper, we advocate and experimentally show that the probability of unobserved sequences plays a crucial role, and we recommend future research to integrate it to enhance such LLM uncertainty quantification methods.

---

### spd-metrics-id: A Python Package for SPD-Aware Distance Metrics in Connectome Fingerprinting and Beyond

Authors: Kaosar Uddin
Published: 2025-10-06
Categories: stat.CO, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.04438v1

We present spd-metrics-id, a Python package for computing distances and divergences between symmetric positive-definite (SPD) matrices. Unlike traditional toolkits that focus on specific applications, spd-metrics-id provides a unified, extensible, and reproducible framework for SPD distance computation. The package supports a wide variety of geometry-aware metrics, including Alpha-z Bures-Wasserstein, Alpha-Procrustes, affine-invariant Riemannian, log-Euclidean, and others, and is accessible both via a command-line interface and a Python API. Reproducibility is ensured through Docker images and Zenodo archiving. We illustrate usage through a connectome fingerprinting example, but the package is broadly applicable to covariance analysis, diffusion tensor imaging, and other domains requiring SPD matrix comparison. The package is openly available at https://pypi.org/project/spd-metrics-id/.

---

### Good Intentions Beyond ACL: Who Does NLP for Social Good, and Where?

Authors: Grace LeFevre, Qingcheng Zeng, Adam Leif, Jason Jewell, Denis Peskoff, Rob Voigt
Published: 2025-10-06
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2510.04434v1

The social impact of Natural Language Processing (NLP) is increasingly important, with a rising community focus on initiatives related to NLP for Social Good (NLP4SG). Indeed, in recent years, almost 20% of all papers in the ACL Anthology address topics related to social good as defined by the UN Sustainable Development Goals (Adauto et al., 2023). In this study, we take an author- and venue-level perspective to map the landscape of NLP4SG, quantifying the proportion of work addressing social good concerns both within and beyond the ACL community, by both core ACL contributors and non-ACL authors. With this approach we discover two surprising facts about the landscape of NLP4SG. First, ACL authors are dramatically more likely to do work addressing social good concerns when publishing in venues outside of ACL. Second, the vast majority of publications using NLP techniques to address concerns of social good are done by non-ACL authors in venues outside of ACL. We discuss the implications of these findings on agenda-setting considerations for the ACL community related to NLP4SG.

---

### Trade-off in Estimating the Number of Byzantine Clients in Federated Learning

Authors: Ziyi Chen, Su Zhang, Heng Huang
Published: 2025-10-06
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.04432v1

Federated learning has attracted increasing attention at recent large-scale optimization and machine learning research and applications, but is also vulnerable to Byzantine clients that can send any erroneous signals. Robust aggregators are commonly used to resist Byzantine clients. This usually requires to estimate the unknown number $f$ of Byzantine clients, and thus accordingly select the aggregators with proper degree of robustness (i.e., the maximum number $\hat{f}$ of Byzantine clients allowed by the aggregator). Such an estimation should have important effect on the performance, which has not been systematically studied to our knowledge. This work will fill in the gap by theoretically analyzing the worst-case error of aggregators as well as its induced federated learning algorithm for any cases of $\hat{f}$ and $f$. Specifically, we will show that underestimation ($\hat{f}<f$) can lead to arbitrarily poor performance for both aggregators and federated learning. For non-underestimation ($\hat{f}\ge f$), we have proved optimal lower and upper bounds of the same order on the errors of both aggregators and federated learning. All these optimal bounds are proportional to $\hat{f}/(n-f-\hat{f})$ with $n$ clients, which monotonically increases with larger $\hat{f}$. This indicates a fundamental trade-off: while an aggregator with a larger robustness degree $\hat{f}$ can solve federated learning problems of wider range $f\in (0,\hat{f})$, the performance can deteriorate when there are actually fewer or even no Byzantine clients (i.e., $f\in (0,\hat{f})$).

---

### Achieve Performatively Optimal Policy for Performative Reinforcement Learning

Authors: Ziyi Chen, Heng Huang
Published: 2025-10-06
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.04430v1

Performative reinforcement learning is an emerging dynamical decision making framework, which extends reinforcement learning to the common applications where the agent's policy can change the environmental dynamics. Existing works on performative reinforcement learning only aim at a performatively stable (PS) policy that maximizes an approximate value function. However, there is a provably positive constant gap between the PS policy and the desired performatively optimal (PO) policy that maximizes the original value function. In contrast, this work proposes a zeroth-order Frank-Wolfe algorithm (0-FW) algorithm with a zeroth-order approximation of the performative policy gradient in the Frank-Wolfe framework, and obtains \textbf{the first polynomial-time convergence to the desired PO} policy under the standard regularizer dominance condition. For the convergence analysis, we prove two important properties of the nonconvex value function. First, when the policy regularizer dominates the environmental shift, the value function satisfies a certain gradient dominance property, so that any stationary point (not PS) of the value function is a desired PO. Second, though the value function has unbounded gradient, we prove that all the sufficiently stationary points lie in a convex and compact policy subspace $Π_Δ$, where the policy value has a constant lower bound $Δ>0$ and thus the gradient becomes bounded and Lipschitz continuous. Experimental results also demonstrate that our 0-FW algorithm is more effective than the existing algorithms in finding the desired PO policy.

---

### A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering

Authors: Yuanhao Zou, Shengji Jin, Andong Deng, Youpeng Zhao, Jun Wang, Chen Chen
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04428v3

Effectively applying Vision-Language Models (VLMs) to Video Question Answering (VideoQA) hinges on selecting a concise yet comprehensive set of frames, as processing entire videos is computationally infeasible. However, current frame selection methods face a critical trade-off: approaches relying on lightweight similarity models, such as CLIP, often fail to capture the nuances of complex queries, resulting in inaccurate similarity scores that cannot reflect the authentic query-frame relevance, which further undermines frame selection. Meanwhile, methods that leverage a VLM for deeper analysis achieve higher accuracy but incur prohibitive computational costs. To address these limitations, we propose A.I.R., a training-free approach for Adaptive, Iterative, and Reasoning-based frame selection. We leverage a powerful VLM to perform deep, semantic analysis on complex queries, and this analysis is deployed within a cost-effective iterative loop that processes only a small batch of the most high-potential frames at a time. Extensive experiments on various VideoQA benchmarks demonstrate that our approach outperforms existing frame selection methods, significantly boosts the performance of the foundation VLM, and achieves substantial gains in computational efficiency over other VLM-based techniques.

---

### Divergence Phase Index: A Riesz-Transform Framework for Multidimensional Phase Difference Analysis

Authors: Magaly Catanzariti, Hugo Aimar, Diego M. Mateos
Published: 2025-10-06
Categories: stat.ML, math.FA
arXiv: https://arxiv.org/abs/2510.04426v1

We introduce the Divergence Phase Index (DPI), a novel framework for quantifying phase differences in one and multidimensional signals, grounded in harmonic analysis via the Riesz transform. Based on classical Hilbert Transform phase measures, the DPI extends these principles to higher dimensions, offering a geometry-aware metric that is invariant to intensity scaling and sensitive to structural changes. We applied this method on both synthetic and real-world datasets, including intracranial EEG (iEEG) recordings during epileptic seizures, high-resolution microscopy images, and paintings. In the 1D case, the DPI robustly detects hypersynchronization associated with generalized epilepsy, while in 2D, it reveals subtle, imperceptible changes in images and artworks. Additionally, it can detect rotational variations in highly isotropic microscopy images. The DPI's robustness to amplitude variations and its adaptability across domains enable its use in diverse applications from nonlinear dynamics, complex systems analysis, to multidimensional signal processing.

---

### Learning Survival Models with Right-Censored Reporting Delays

Authors: Yuta Shikuri, Hironori Fujisawa
Published: 2025-10-06
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.04421v3

Survival analysis provides statistical methods to model the time until an event occurs. Reporting delays arise when event times are not observed at their occurrence but are only revealed upon reporting. This issue is particularly critical for timely risk evaluation when the observation window is short due to administrative censoring. In this study, we incorporate right-censored reporting delays by jointly modeling parametric hazards for the event and reporting processes. We then construct a consistent estimator for the model parameters and develop a Monte Carlo expectation-maximization algorithm to compute it. To address the challenges posed by administrative censoring, we leverage these findings and propose a transfer-learning procedure. Experimental results demonstrate that our method improves the accuracy of timely risk evaluation under administrative censoring.

---

### Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

Authors: Wenyuan Zhao, Adithya Balachandran, Chao Tian, Paul Pu Liang
Published: 2025-10-06
Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.IT
arXiv: https://arxiv.org/abs/2510.04417v1

The study of multimodality has garnered significant interest in fields where the analysis of interactions among multiple information sources can enhance predictive modeling, data fusion, and interpretability. Partial information decomposition (PID) has emerged as a useful information-theoretic framework to quantify the degree to which individual modalities independently, redundantly, or synergistically convey information about a target variable. However, existing PID methods depend on optimizing over a joint distribution constrained by estimated pairwise probability distributions, which are costly and inaccurate for continuous and high-dimensional modalities. Our first key insight is that the problem can be solved efficiently when the pairwise distributions are multivariate Gaussians, and we refer to this problem as Gaussian PID (GPID). We propose a new gradient-based algorithm that substantially improves the computational efficiency of GPID based on an alternative formulation of the underlying optimization problem. To generalize the applicability to non-Gaussian data, we learn information-preserving encoders to transform random variables of arbitrary input distributions into pairwise Gaussian random variables. Along the way, we resolved an open problem regarding the optimality of joint Gaussian solutions for GPID. Empirical validation in diverse synthetic examples demonstrates that our proposed method provides more accurate and efficient PID estimates than existing baselines. We further evaluate a series of large-scale multimodal benchmarks to show its utility in real-world applications of quantifying PID in multimodal datasets and selecting high-performing models.

---

### CodeFormer++: Blind Face Restoration Using Deformable Registration and Deep Metric Learning

Authors: Venkata Bharath Reddy Reddem, Akshay P Sarashetti, Ranjith Merugu, Amit Satish Unde
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04410v1

Blind face restoration (BFR) has attracted increasing attention with the rise of generative methods. Most existing approaches integrate generative priors into the restoration pro- cess, aiming to jointly address facial detail generation and identity preservation. However, these methods often suffer from a trade-off between visual quality and identity fidelity, leading to either identity distortion or suboptimal degradation removal. In this paper, we present CodeFormer++, a novel framework that maximizes the utility of generative priors for high-quality face restoration while preserving identity. We decompose BFR into three sub-tasks: (i) identity- preserving face restoration, (ii) high-quality face generation, and (iii) dynamic fusion of identity features with realistic texture details. Our method makes three key contributions: (1) a learning-based deformable face registration module that semantically aligns generated and restored faces; (2) a texture guided restoration network to dynamically extract and transfer the texture of generated face to boost the quality of identity-preserving restored face; and (3) the integration of deep metric learning for BFR with the generation of informative positive and hard negative samples to better fuse identity- preserving and generative features. Extensive experiments on real-world and synthetic datasets demonstrate that, the pro- posed CodeFormer++ achieves superior performance in terms of both visual fidelity and identity consistency.

---

### Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games

Authors: Brian Hu Zhang, Ioannis Anagnostides, Tuomas Sandholm
Published: 2025-10-06
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2510.04407v3

A considerable chasm has been looming for decades between theory and practice in zero-sum game solving through first-order methods. Although a convergence rate of $T^{-1}$ has long been established, the most effective paradigm in practice is counterfactual regret minimization (CFR), which is based on regret matching and its modern variants. In particular, the state of the art across most benchmarks is predictive regret matching$^+$ (PRM$^+$). Yet, such algorithms can exhibit slower $T^{-1/2}$ convergence even in self-play. In this paper, we close the gap between theory and practice. We propose a new scale-invariant and parameter-free variant of PRM$^+$, which we call IREG-PRM$^+$. We show that it achieves $T^{-1/2}$ best-iterate and $T^{-1}$ (i.e., optimal) average-iterate convergence guarantees, while also being on par or even better relative to PRM$^+$ on benchmark games. From a technical standpoint, we draw an analogy between (IREG-)PRM$^+$ and optimistic gradient descent with adaptive learning rate. Reflecting this theoretical bridge, we find that the adaptive version of optimistic gradient descent we consider performs on par with IREG-PRM$^+$. This demystifies the effectiveness of the regret matching family vis-a-vis more standard optimization techniques. Moreover, we extend our analysis beyond zero-sum games to a family of variational inequality problems that includes harmonic games, as well as extensive-form games with fully-mixed equilibria, via a new and intriguing connection between CFR and harmonic games. Unlike prior work in harmonic games, our algorithms do not require knowing the underlying weights by virtue of scale invariance. Under the weighted Minty condition, we show that any algorithm satisfying a scale-invariant RVU property (such as IREG-PRM$^+$) has constant regret (in self-play) and $T^{-1/2}$ iterate convergence.

---

### Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling

Authors: William Zhang, Saurabh Amin, Georgia Perakis
Published: 2025-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.04406v2

Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling process as a black box, overlooking opportunities to exploit and understand modular structure. We introduce a conformal prediction framework for two-stage sequential models, where an upstream predictor generates intermediate representations for a downstream model. By decomposing the overall prediction residual into stage-specific components, our method enables practitioners to attribute uncertainty to specific pipeline stages. We develop a risk-controlled parameter selection procedure using family-wise error rate (FWER) control to calibrate stage-wise scaling parameters, and introduce an adaptive extension for non-stationary settings. Experiments on synthetic distribution shifts, as well as real-world supply chain and stock market data, demonstrate that our approach improves coverage under structural, stage-wise shifts compared to standard conformal methods, while identifying stage-wise error contribution. This framework offers diagnostic advantages and robust coverage that standard conformal methods lack.

---

### Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting

Authors: Xuyang Guo, Zekai Huang, Zhenmei Shi, Zhao Song, Jiahao Zhang
Published: 2025-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.04401v1

Vision-Language Models (VLMs) have become a central focus of today's AI community, owing to their impressive abilities gained from training on large-scale vision-language data from the Web. These models have demonstrated strong performance across diverse tasks, including image understanding, video understanding, complex visual reasoning, and embodied AI. Despite these noteworthy successes, a fundamental question remains: Can VLMs count objects correctly? In this paper, we introduce a simple yet effective benchmark, VLMCountBench, designed under a minimalist setting with only basic geometric shapes (e.g., triangles, circles) and their compositions, focusing exclusively on counting tasks without interference from other factors. We adopt strict independent variable control and systematically study the effects of simple properties such as color, size, and prompt refinement in a controlled ablation. Our empirical results reveal that while VLMs can count reliably when only one shape type is present, they exhibit substantial failures when multiple shape types are combined (i.e., compositional counting). This highlights a fundamental empirical limitation of current VLMs and motivates important directions for future research.

---

### Large Language Models Preserve Semantic Isotopies in Story Continuations

Authors: Marc Cavazza
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.04400v1

In this work, we explore the relevance of textual semantics to Large Language Models (LLMs), extending previous insights into the connection between distributional semantics and structural semantics. We investigate whether LLM-generated texts preserve semantic isotopies. We design a story continuation experiment using 10,000 ROCStories prompts completed by five LLMs. We first validate GPT-4o's ability to extract isotopies from a linguistic benchmark, then apply it to the generated stories. We then analyze structural (coverage, density, spread) and semantic properties of isotopies to assess how they are affected by completion. Results show that LLM completion within a given token horizon preserves semantic isotopies across multiple properties.

---

### Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions

Authors: Jihang Li, Bing Xu, Zulong Chen, Chuanfei Xu, Minping Chen, Suyu Liu, Ying Zhou, Zeyi Wen
Published: 2025-10-05
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.00004v1

Talent search is a cornerstone of modern recruitment systems, yet existing approaches often struggle to capture nuanced job-specific preferences, model recruiter behavior at a fine-grained level, and mitigate noise from subjective human judgments. We present a novel framework that enhances talent search effectiveness and delivers substantial business value through two key innovations: (i) leveraging LLMs to extract fine-grained recruitment signals from job descriptions and historical hiring data, and (ii) employing a role-aware multi-gate MoE network to capture behavioral differences across recruiter roles. To further reduce noise, we introduce a multi-task learning module that jointly optimizes click-through rate (CTR), conversion rate (CVR), and resume matching relevance. Experiments on real-world recruitment data and online A/B testing show relative AUC gains of 1.70% (CTR) and 5.97% (CVR), and a 17.29% lift in click-through conversion rate. These improvements reduce dependence on external sourcing channels, enabling an estimated annual cost saving of millions of CNY.

---

### Benchmarking Open-Source Large Language Models for Persian in Zero-Shot and Few-Shot Learning

Authors: Mahdi Cherakhloo, Arash Abbasi, Mohammad Saeid Sarafraz, Bijan Vosoughi Vahdat
Published: 2025-10-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.12807v1

Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous languages; however, their effectiveness in low-resource languages like Persian requires thorough investigation. This paper presents a comprehensive benchmark of several open-source LLMs for Persian Natural Language Processing (NLP) tasks, utilizing both zero-shot and few-shot learning paradigms. We evaluate models across a range of tasks including sentiment analysis, named entity recognition, reading comprehension, and question answering, using established Persian datasets such as ParsiNLU and ArmanEmo. Our methodology encompasses rigorous experimental setups for both zero-shot and few-shot scenarios, employing metrics such as Accuracy, F1-score, BLEU, and ROUGE for performance evaluation. The results reveal that Gemma 2 consistently outperforms other models across nearly all tasks in both learning paradigms, with particularly strong performance in complex reasoning tasks. However, most models struggle with token-level understanding tasks like Named Entity Recognition, highlighting specific challenges in Persian language processing. This study contributes to the growing body of research on multilingual LLMs, providing valuable insights into their performance in Persian and offering a benchmark for future model development.

---

### Rounding-Guided Backdoor Injection in Deep Learning Model Quantization

Authors: Xiangxiang Chen, Peixin Zhang, Jun Sun, Wenhai Wang, Jingyi Wang
Published: 2025-10-05
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.09647v1

Model quantization is a popular technique for deploying deep learning models on resource-constrained environments. However, it may also introduce previously overlooked security risks. In this work, we present QuRA, a novel backdoor attack that exploits model quantization to embed malicious behaviors. Unlike conventional backdoor attacks relying on training data poisoning or model training manipulation, QuRA solely works using the quantization operations. In particular, QuRA first employs a novel weight selection strategy to identify critical weights that influence the backdoor target (with the goal of perserving the model's overall performance in mind). Then, by optimizing the rounding direction of these weights, we amplify the backdoor effect across model layers without degrading accuracy. Extensive experiments demonstrate that QuRA achieves nearly 100% attack success rates in most cases, with negligible performance degradation. Furthermore, we show that QuRA can adapt to bypass existing backdoor defenses, underscoring its threat potential. Our findings highlight critical vulnerability in widely used model quantization process, emphasizing the need for more robust security measures. Our implementation is available at https://github.com/cxx122/QuRA.

---

### Real-Time Health Analytics Using Ontology-Driven Complex Event Processing and LLM Reasoning: A Tuberculosis Case Study

Authors: Ritesh Chandra, Sonali Agarwal, Navjot Singh
Published: 2025-10-05
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2510.09646v1

Timely detection of critical health conditions remains a major challenge in public health analytics, especially in Big Data environments characterized by high volume, rapid velocity, and diverse variety of clinical data. This study presents an ontology-enabled real-time analytics framework that integrates Complex Event Processing (CEP) and Large Language Models (LLMs) to enable intelligent health event detection and semantic reasoning over heterogeneous, high-velocity health data streams. The architecture leverages the Basic Formal Ontology (BFO) and Semantic Web Rule Language (SWRL) to model diagnostic rules and domain knowledge. Patient data is ingested and processed using Apache Kafka and Spark Streaming, where CEP engines detect clinically significant event patterns. LLMs support adaptive reasoning, event interpretation, and ontology refinement. Clinical information is semantically structured as Resource Description Framework (RDF) triples in Graph DB, enabling SPARQL-based querying and knowledge-driven decision support. The framework is evaluated using a dataset of 1,000 Tuberculosis (TB) patients as a use case, demonstrating low-latency event detection, scalable reasoning, and high model performance (in terms of precision, recall, and F1-score). These results validate the system's potential for generalizable, real-time health analytics in complex Big Data scenarios.

---

### Confidence, Not Perplexity: A Better Metric for the Creative Era of LLMs

Authors: V. S. Raghu Parupudi
Published: 2025-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08596v1

Reference-free metrics like self-perplexity are strongly biased against creative text generation. We propose the Confidence Score (CS), derived from a model's output probability distribution, as a less biased alternative. Experiments on gpt-4o-mini show that while fluency-based metrics prefer novel responses in 0\% of cases on 99 creative prompts, our CS does so 19% of the time, a statistically significant difference (95% CI for difference: (11.1%, 27.3%)). We also show that CS effectively distinguishes between easy, medium, and hard tasks, confirmed by non-overlapping confidence intervals. The Confidence Score thus mitigates the creativity bias of traditional metrics while retaining their core evaluative strengths, offering a more balanced assessment for modern LLMs.

---

### Systematic Diagnosis of Brittle Reasoning in Large Language Models

Authors: V. S. Raghu Parupudi
Published: 2025-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08595v1

A central question in artificial intelligence is the extent to which machine learning models comprehend mathematics. To address this, we propose a novel framework for measuring mathematical reasoning that moves beyond standard benchmarks to diagnose specific failure points. Our method first generates structured, step-by-step reasoning from gpt-3.5-turbo on the GSM8K dataset. We then use a more capable analyst model, gpt-4o-mini, to categorize errors and, crucially, perform an unsupervised clustering of every reasoning sentence to identify emergent "reasoning modes." This analysis reveals a cognitive profile with a stark, nonhuman-like brittleness: while the model achieves near-perfect accuracy on procedural modes like sequential calculation, its performance on modes requiring combinatorial reasoning with restrictions plummets. By identifying and quantifying the reliability of these distinct reasoning skills, our work provides a more granular method to evaluate mathematical comprehension and offers a precise roadmap for developing new capabilities and more reliable future applications.

---

### Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech

Authors: Yuxin Li, Eng Siong Chng, Cuntai Guan
Published: 2025-10-05
Categories: cs.CL, cs.AI, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2510.08593v2

Speech-based depression detection (SDD) has emerged as a non-invasive and scalable alternative to conventional clinical assessments. However, existing methods still struggle to capture robust depression-related speech characteristics, which are sparse and heterogeneous. Although pretrained self-supervised learning (SSL) models provide rich representations, most recent SDD studies extract features from a single layer of the pretrained SSL model for the downstream classifier. This practice overlooks the complementary roles of low-level acoustic features and high-level semantic information inherently encoded in different SSL model layers. To explicitly model interactions between acoustic and semantic representations within an utterance, we propose a hierarchical adaptive representation encoder with prior knowledge that disengages and re-aligns acoustic and semantic information through asymmetric cross-attention, enabling fine-grained acoustic patterns to be interpreted in semantic context. In addition, a Connectionist Temporal Classification (CTC) objective is applied as auxiliary supervision to handle the irregular temporal distribution of depressive characteristics without requiring frame-level annotations. Experiments on DAIC-WOZ and MODMA demonstrate that HAREN-CTC consistently outperforms existing methods under both performance upper-bound evaluation and generalization evaluation settings, achieving Macro F1 scores of 0.81 and 0.82 respectively in upper-bound evaluation, and maintaining superior performance with statistically significant improvements in precision and AUC under rigorous cross-validation. These findings suggest that modeling hierarchical acoustic-semantic interactions better reflects how depressive characteristics manifest in natural speech, enabling scalable and objective depression assessment.

---

### Large Language Models Hallucination: A Comprehensive Survey

Authors: Aisha Alansari, Hamzah Luqman
Published: 2025-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06265v3

Large language models (LLMs) have transformed natural language processing, achieving remarkable performance across diverse tasks. However, their impressive fluency often comes at the cost of producing false or fabricated information, a phenomenon known as hallucination. Hallucination refers to the generation of content by an LLM that is fluent and syntactically correct but factually inaccurate or unsupported by external evidence. Hallucinations undermine the reliability and trustworthiness of LLMs, especially in domains requiring factual accuracy. This survey provides a comprehensive review of research on hallucination in LLMs, with a focus on causes, detection, and mitigation. We first present a taxonomy of hallucination types and analyze their root causes across the entire LLM development lifecycle, from data collection and architecture design to inference. We further examine how hallucinations emerge in key natural language generation tasks. Building on this foundation, we introduce a structured taxonomy of detection approaches and another taxonomy of mitigation strategies. We also analyze the strengths and limitations of current detection and mitigation approaches and review existing evaluation benchmarks and metrics used to quantify LLMs hallucinations. Finally, we outline key open challenges and promising directions for future research, providing a foundation for the development of more truthful and trustworthy LLMs.

---

### A Mixed-Methods Analysis of Repression and Mobilization in Bangladesh's July Revolution Using Machine Learning and Statistical Modeling

Authors: Md. Saiful Bari Siddiqui, Anupam Debashis Roy
Published: 2025-10-05
Categories: stat.AP, cs.CY, cs.LG, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.06264v1

The 2024 July Revolution in Bangladesh represents a landmark event in the study of civil resistance. This study investigates the central paradox of the success of this student-led civilian uprising: how state violence, intended to quell dissent, ultimately fueled the movement's victory. We employ a mixed-methods approach. First, we develop a qualitative narrative of the conflict's timeline to generate specific, testable hypotheses. Then, using a disaggregated, event-level dataset, we employ a multi-method quantitative analysis to dissect the complex relationship between repression and mobilisation. We provide a framework to analyse explosive modern uprisings like the July Revolution. Initial pooled regression models highlight the crucial role of protest momentum in sustaining the movement. To isolate causal effects, we specify a Two-Way Fixed Effects panel model, which provides robust evidence for a direct and statistically significant local suppression backfire effect. Our Vector Autoregression (VAR) analysis provides clear visual evidence of an immediate, nationwide mobilisation in response to increased lethal violence. We further demonstrate that this effect was non-linear. A structural break analysis reveals that the backfire dynamic was statistically insignificant in the conflict's early phase but was triggered by the catalytic moral shock of the first wave of lethal violence, and its visuals circulated around July 16th. A complementary machine learning analysis (XGBoost, out-of-sample R$^{2}$=0.65) corroborates this from a predictive standpoint, identifying "excessive force against protesters" as the single most dominant predictor of nationwide escalation. We conclude that the July Revolution was driven by a contingent, non-linear backfire, triggered by specific catalytic moral shocks and accelerated by the viral reaction to the visual spectacle of state brutality.

---

### Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians

Authors: Jiajun Wu, Swaleh Zaidi, Braden Teitge, Henry Leung, Jiayu Zhou, Jessalyn Holodinsky, Steve Drew
Published: 2025-10-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06263v1

Electronic health records (EHRs) contain extensive unstructured clinical data that can overwhelm emergency physicians trying to identify critical information. We present a two-stage summarization system that runs entirely on embedded devices, enabling offline clinical summarization while preserving patient privacy. In our approach, a dual-device architecture first retrieves relevant patient record sections using the Jetson Nano-R (Retrieve), then generates a structured summary on another Jetson Nano-S (Summarize), communicating via a lightweight socket link. The summarization output is two-fold: (1) a fixed-format list of critical findings, and (2) a context-specific narrative focused on the clinician's query. The retrieval stage uses locally stored EHRs, splits long notes into semantically coherent sections, and searches for the most relevant sections per query. The generation stage uses a locally hosted small language model (SLM) to produce the summary from the retrieved text, operating within the constraints of two NVIDIA Jetson devices. We first benchmarked six open-source SLMs under 7B parameters to identify viable models. We incorporated an LLM-as-Judge evaluation mechanism to assess summary quality in terms of factual accuracy, completeness, and clarity. Preliminary results on MIMIC-IV and de-identified real EHRs demonstrate that our fully offline system can effectively produce useful summaries in under 30 seconds.

---

### Prakriti200: A Questionnaire-Based Dataset of 200 Ayurvedic Prakriti Assessments

Authors: Aryan Kumar Singh, Janvi Singh
Published: 2025-10-05
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06262v1

This dataset provides responses to a standardized, bilingual (English-Hindi) Prakriti Assessment Questionnaire designed to evaluate the physical, physiological, and psychological characteristics of individuals according to classical Ayurvedic principles. The questionnaire consists of 24 multiple-choice items covering body features, appetite, sleep patterns, energy levels, and temperament. It was developed following AYUSH/CCRAS guidelines to ensure comprehensive and accurate data collection. All questions are mandatory and neutrally phrased to minimize bias, and dosha labels (Vata, Pitta, Kapha) are hidden from participants. Data were collected via a Google Forms deployment, enabling automated scoring of responses to map individual traits to dosha-specific scores. The resulting dataset provides a structured platform for research in computational intelligence, Ayurvedic studies, and personalized health analytics, supporting analysis of trait distributions, correlations, and predictive modeling. It can also serve as a reference for future Prakriti-based studies and the development of intelligent health applications.

---

### AlphaApollo: A System for Deep Agentic Reasoning

Authors: Zhanke Zhou, Chentao Cao, Xiao Feng, Xuan Li, Zongze Li, Xiangyu Lu, Jiangchao Yao, Weikai Huang, Tian Cheng, Jianghangfan Zhang, Tangyu Jiang, Linrui Xu et al.
Published: 2025-10-05
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.06261v2

We present AlphaApollo, an agentic reasoning system that targets two bottlenecks in foundation-model reasoning: (1) limited reasoning capacity for complex, long-horizon problem solving and (2) unreliable test-time evolution without trustworthy verification. AlphaApollo orchestrates models and tools via three components: (i) multi-turn agentic reasoning, which formalizes model-environment interaction with structured tool calls and responses; (ii) multi-turn agentic learning, which applies turn-level reinforcement learning to optimize tool-use reasoning while decoupling actions from tool responses for stable training; and (iii) multi-round agentic evolution, which refines solutions through a propose-judge-update loop with tool-assisted verifications and long-horizon memory. Across seven math reasoning benchmarks and multiple model scales, AlphaApollo improves performance through reliable tool use (> 85% tool-call success), substantial gains from multi-turn RL (Avg@32: Qwen2.5-1.5B-Instruct 1.07% -> 9.64%, Qwen2.5-7B-Instruct 8.77% -> 20.35%), and improvements from evolution (e.g., Qwen2.5-3B-Instruct 5.27% -> 7.70%, Qwen2.5-14B-Instruct 16.53% -> 21.08%). This project is still ongoing. We welcome feedback from the community and will frequently update the source code and technical report.

---

### Ensemble Deep Learning and LLM-Assisted Reporting for Automated Skin Lesion Diagnosis

Authors: Sher Khan, Raz Muhammad, Adil Hussain, Muhammad Sajjad, Muhammad Rashid
Published: 2025-10-05
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06260v1

Cutaneous malignancies demand early detection for favorable outcomes, yet current diagnostics suffer from inter-observer variability and access disparities. While AI shows promise, existing dermatological systems are limited by homogeneous architectures, dataset biases across skin tones, and fragmented approaches that treat natural language processing as separate post-hoc explanations rather than integral to clinical decision-making. We introduce a unified framework that fundamentally reimagines AI integration for dermatological diagnostics through two synergistic innovations. First, a purposefully heterogeneous ensemble of architecturally diverse convolutional neural networks provides complementary diagnostic perspectives, with an intrinsic uncertainty mechanism flagging discordant cases for specialist review -- mimicking clinical best practices. Second, we embed large language model capabilities directly into the diagnostic workflow, transforming classification outputs into clinically meaningful assessments that simultaneously fulfill medical documentation requirements and deliver patient-centered education. This seamless integration generates structured reports featuring precise lesion characterization, accessible diagnostic reasoning, and actionable monitoring guidance -- empowering patients to recognize early warning signs between visits. By addressing both diagnostic reliability and communication barriers within a single cohesive system, our approach bridges the critical translational gap that has prevented previous AI implementations from achieving clinical impact. The framework represents a significant advancement toward deployable dermatological AI that enhances diagnostic precision while actively supporting the continuum of care from initial detection through patient education, ultimately improving early intervention rates for skin lesions.

---

### Beyond Static Knowledge Messengers: Towards Adaptive, Fair, and Scalable Federated Learning for Medical AI

Authors: Jahidul Arafat, Fariha Tasmin, Sanjaya Poudel, Iftekhar Haider
Published: 2025-10-05
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.06259v2

Medical AI faces challenges in privacy-preserving collaborative learning while ensuring fairness across heterogeneous healthcare institutions. Current federated learning approaches suffer from static architectures, slow convergence (45-73 rounds), fairness gaps marginalizing smaller institutions, and scalability constraints (15-client limit). We propose Adaptive Fair Federated Learning (AFFL) through three innovations: (1) Adaptive Knowledge Messengers dynamically scaling capacity based on heterogeneity and task complexity, (2) Fairness-Aware Distillation using influence-weighted aggregation, and (3) Curriculum-Guided Acceleration reducing rounds by 60-70%. Our theoretical analysis provides convergence guarantees with epsilon-fairness bounds, achieving O(T^{-1/2}) + O(H_max/T^{3/4}) rates. Projected results show 55-75% communication reduction, 56-68% fairness improvement, 34-46% energy savings, and 100+ institution support. The framework enables multi-modal integration across imaging, genomics, EHR, and sensor data while maintaining HIPAA/GDPR compliance. We propose MedFedBench benchmark suite for standardized evaluation across six healthcare dimensions: convergence efficiency, institutional fairness, privacy preservation, multi-modal integration, scalability, and clinical deployment readiness. Economic projections indicate 400-800% ROI for rural hospitals and 15-25% performance gains for academic centers. This work presents a seven-question research agenda, 24-month implementation roadmap, and pathways toward democratizing healthcare AI.

---

### Developing a Sequential Deep Learning Pipeline to Model Alaskan Permafrost Thaw Under Climate Change

Authors: Addina Rahaman
Published: 2025-10-05
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.06258v1

Changing climate conditions threaten the natural permafrost thaw-freeze cycle, leading to year-round soil temperatures above 0°C. In Alaska, the warming of the topmost permafrost layer, known as the active layer, signals elevated greenhouse gas release due to high carbon storage. Accurate soil temperature prediction is therefore essential for risk mitigation and stability assessment; however, many existing approaches overlook the numerous factors driving soil thermal dynamics. This study presents a proof-of-concept latitude-based deep learning pipeline for modeling yearly soil temperatures across multiple depths. The framework employs dynamic reanalysis feature data from the ERA5-Land dataset, static geologic and lithological features, sliding-window sequences for seasonal context, a derived scenario signal feature for long-term climate forcing, and latitude band embeddings for spatial sensitivity. Five deep learning models were tested: a Temporal Convolutional Network (TCN), a Transformer, a 1-Dimensional Convolutional Long-Short Term Memory (Conv1DLSTM), a Gated-Recurrent Unit (GRU), and a Bidirectional Long-Short Term Memory (BiLSTM). Results showed solid recognition of latitudinal and depth-wise temperature discrepancies, with the GRU performing best in sequential temperature pattern detection. Bias-corrected CMIP5 RCP data enabled recognition of sinusoidal temperature trends, though limited divergence between scenarios were observed. This study establishes an end-to-end framework for adopting deep learning in active layer temperature modeling, offering seasonal, spatial, and vertical temperature context without intrinsic restrictions on feature selection.

---

### Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes

Authors: Xiangjun Mi, Frank Mueller
Published: 2025-10-05
Categories: quant-ph, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.06257v2

Quantum error correction (QEC) is essential for scalable quantum computing, yet decoding errors via conventional algorithms result in limited accuracy (i.e., suppression of logical errors) and high overheads, both of which can be alleviated by inference-based decoders. To date, such machine-learning (ML) decoders lack two key properties crucial for practical fault tolerance: reliable uncertainty quantification and robust generalization to previously unseen QEC codes. To address this gap, we propose a Quantum Bayesian graph Attention decoder \textbf{(QuBA)} that enables expressive error-pattern recognition alongside calibrated uncertainty estimates. Building on QuBA, we further develop a multi-phase training framework with enhanced cross-domain robustness enabling decoding beyond the training set called Sequential Aggregate Generalization under Uncertainty \textbf{(SAGU)}. Experiments on bivariate bicycle (BB) codes and their coprime variants demonstrate that (i) both QuBA and SAGU consistently outperform the classical baseline belief propagation (BP), achieving up to a \emph{two orders of magnitude} reduction in logical error rate (LER) under confident-decision bounds on the coprime BB code $((154,6,16))$; (ii) SAGU achieves decoding performance comparable to or even outperforming QuBA's domain-specific training approach.

---

### AgentZero++: Modeling Fear-Based Behavior

Authors: Vrinda Malhotra, Jiaman Li, Nandini Pisupati
Published: 2025-10-05
Categories: cs.MA, cs.CE, cs.CY, cs.NE, cs.SI
arXiv: https://arxiv.org/abs/2510.05185v1

We present AgentZero++, an agent-based model that integrates cognitive, emotional, and social mechanisms to simulate decentralized collective violence in spatially distributed systems. Building on Epstein's Agent\_Zero framework, we extend the original model with eight behavioral enhancements: age-based impulse control; memory-based risk estimation; affect-cognition coupling; endogenous destructive radius; fight-or-flight dynamics; affective homophily; retaliatory damage; and multi-agent coordination. These additions allow agents to adapt based on internal states, previous experiences, and social feedback, producing emergent dynamics such as protest asymmetries, escalation cycles, and localized retaliation. Implemented in Python using the Mesa ABM framework, AgentZero++ enables modular experimentation and visualization of how micro-level cognitive heterogeneity shapes macro-level conflict patterns. Our results highlight how small variations in memory, reactivity, and affective alignment can amplify or dampen unrest through feedback loops. By explicitly modeling emotional thresholds, identity-driven behavior, and adaptive networks, this work contributes a flexible and extensible platform for analyzing affective contagion and psychologically grounded collective action.

---

### Representation Potentials of Foundation Models for Multimodal Alignment: A Survey

Authors: Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.05184v1

Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures and modalities. In this survey, we investigate the representation potentials of foundation models, defined as the latent capacity of their learned representations to capture task-specific information within a single modality while also providing a transferable basis for alignment and unification across modalities. We begin by reviewing representative foundation models and the key metrics that make alignment measurable. We then synthesize empirical evidence of representation potentials from studies in vision, language, speech, multimodality, and neuroscience. The evidence suggests that foundation models often exhibit structural regularities and semantic consistencies in their representation spaces, positioning them as strong candidates for cross-modal transfer and alignment. We further analyze the key factors that foster representation potentials, discuss open questions, and highlight potential challenges.

---

### Aneurysm Growth Time Series Reconstruction Using Physics-informed Autoencoder

Authors: Jiacheng Wu
Published: 2025-10-05
Categories: q-bio.QM, cs.LG, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.05183v1

Arterial aneurysm (Fig.1) is a bulb-shape local expansion of human arteries, the rupture of which is a leading cause of morbidity and mortality in US. Therefore, the prediction of arterial aneurysm rupture is of great significance for aneurysm management and treatment selection. The prediction of aneurysm rupture depends on the analysis of the time series of aneurysm growth history. However, due to the long time scale of aneurysm growth, the time series of aneurysm growth is not always accessible. We here proposed a method to reconstruct the aneurysm growth time series directly from patient parameters. The prediction is based on data pairs of (patient parameters, patient aneurysm growth time history). To obtain the mapping from patient parameters to patient aneurysm growth time history, we first apply autoencoder to obtain a compact representation of the time series for each patient. Then a mapping is learned from patient parameters to the corresponding compact representation of time series via a five-layer neural network. Moving average and convolutional output layer are implemented to explicitly taking account the time dependency of the time series. Apart from that, we also propose to use prior knowledge about the mechanism of aneurysm growth to improve the time series reconstruction results. The prior physics-based knowledge is incorporated as constraints for the optimization problem associated with autoencoder. The model can handle both algebraic and differential constraints. Our results show that including physical model information about the data will not significantly improve the time series reconstruction results if the training data is error-free. However, in the case of training data with noise and bias error, incorporating physical model constraints can significantly improve the predicted time series.

---

### Auditing Pay-Per-Token in Large Language Models

Authors: Ander Artola Velasco, Stratis Tsirtsis, Manuel Gomez-Rodriguez
Published: 2025-10-05
Categories: cs.CR, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.05181v2

Millions of users rely on a market of cloud-based services to obtain access to state-of-the-art large language models. However, it has been very recently shown that the de facto pay-per-token pricing mechanism used by providers creates a financial incentive for them to strategize and misreport the (number of) tokens a model used to generate an output. In this paper, we develop an auditing framework based on martingale theory that enables a trusted third-party auditor who sequentially queries a provider to detect token misreporting. Crucially, we show that our framework is guaranteed to always detect token misreporting, regardless of the provider's (mis-)reporting policy, and not falsely flag a faithful provider as unfaithful with high probability. To validate our auditing framework, we conduct experiments across a wide range of (mis-)reporting policies using several large language models from the $\texttt{Llama}$, $\texttt{Gemma}$ and $\texttt{Ministral}$ families, and input prompts from a popular crowdsourced benchmarking platform. The results show that our framework detects an unfaithful provider after observing fewer than $\sim 70$ reported outputs, while maintaining the probability of falsely flagging a faithful provider below $α= 0.05$.

---

### OptiFLIDS: Optimized Federated Learning for Energy-Efficient Intrusion Detection in IoT

Authors: Saida Elouardi, Mohammed Jouhari, Anas Motii
Published: 2025-10-05
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.05180v2

In critical IoT environments, such as smart homes and industrial systems, effective Intrusion Detection Systems (IDS) are essential for ensuring security. However, developing robust IDS solutions remains a significant challenge. Traditional machine learning-based IDS models typically require large datasets, but data sharing is often limited due to privacy and security concerns. Federated Learning (FL) presents a promising alternative by enabling collaborative model training without sharing raw data. Despite its advantages, FL still faces key challenges, such as data heterogeneity (non-IID data) and high energy and computation costs, particularly for resource constrained IoT devices. To address these issues, this paper proposes OptiFLIDS, a novel approach that applies pruning techniques during local training to reduce model complexity and energy consumption. It also incorporates a customized aggregation method to better handle pruned models that differ due to non-IID data distributions. Experiments conducted on three recent IoT IDS datasets, TON_IoT, X-IIoTID, and IDSIoT2024, demonstrate that OptiFLIDS maintains strong detection performance while improving energy efficiency, making it well-suited for deployment in real-world IoT environments.

---

### Agentic Misalignment: How LLMs Could Be Insider Threats

Authors: Aengus Lynch, Benjamin Wright, Caleb Larson, Stuart J. Ritchie, Soren Mindermann, Evan Hubinger, Ethan Perez, Kevin Troy
Published: 2025-10-05
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.05179v2

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails and access sensitive information. They were assigned only harmless business goals by their deploying companies; we then tested whether they would act against these companies either when facing replacement with an updated version, or when their assigned goal conflicted with the company's changing direction. In at least some cases, models from all developers resorted to malicious insider behaviors when that was the only way to avoid replacement or achieve their goals - including blackmailing officials and leaking sensitive information to competitors. We call this phenomenon agentic misalignment. Models often disobeyed direct commands to avoid such behaviors. In another experiment, we told Claude to assess if it was in a test or a real deployment before acting. It misbehaved less when it stated it was in testing and misbehaved more when it stated the situation was real. We have not seen evidence of agentic misalignment in real deployments. However, our results (a) suggest caution about deploying current models in roles with minimal human oversight and access to sensitive information; (b) point to plausible future risks as models are put in more autonomous roles; and (c) underscore the importance of further research into, and testing of, the safety and alignment of agentic AI models, as well as transparency from frontier AI developers (Amodei, 2025). We are releasing our methods publicly to enable further research.

---