# Research Papers — 2025-10 · bundle page 150 of 217

> Full-text markdown of papers #7451–7500 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/150
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/149.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/151.md)

### BEACON: Bayesian Optimal Stopping for Efficient LLM Sampling

Authors: Guangya Wan, Zixin Stephen Xu, Sasa Zorc, Manel Baucells, Mengxuan Hu, Hao Wang, Sheng Li
Published: 2025-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15945v1

Sampling multiple responses is a common way to improve LLM output quality, but it comes at the cost of additional computation. The key challenge is deciding when to stop generating new samples to balance accuracy gains against efficiency. To address this, we introduce BEACON (Bayesian Efficient Adaptive Criterion for Optimal N-stopping), a principled adaptive sampling framework grounded in Sequential Search with Bayesian Learning. BEACON sequentially generates responses from the policy LLM, updates posterior belief over reward distributions in real time without further training, and determines when to stop by weighing expected gains against computational cost. Sampling terminates once the marginal utility of further exploration no longer justifies the expense. We establish both theoretical optimality guarantees and practical tractability, and show empirically that BEACON reduces average sampling by up to 80% while maintaining response quality. We further demonstrate BEACON's utility for cost-efficient preference data generation and outline practical extensions, offering actionable insights for future researchers.

---

### Lyapunov-Stable Adaptive Control for Multimodal Concept Drift

Authors: Tianyu Bell Pan, Mengdi Zhu, Alexa Jordyn Cole, Ronald Wilson, Damon L. Woodard
Published: 2025-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15944v1

Multimodal learning systems often struggle in non-stationary environments due to concept drift, where changing data distributions can degrade performance. Modality-specific drifts and the lack of mechanisms for continuous, stable adaptation compound this challenge. This paper introduces LS-OGD, a novel adaptive control framework for robust multimodal learning in the presence of concept drift. LS-OGD uses an online controller that dynamically adjusts the model's learning rate and the fusion weights between different data modalities in response to detected drift and evolving prediction errors. We prove that under bounded drift conditions, the LS-OGD system's prediction error is uniformly ultimately bounded and converges to zero if the drift ceases. Additionally, we demonstrate that the adaptive fusion strategy effectively isolates and mitigates the impact of severe modality-specific drift, thereby ensuring system resilience and fault tolerance. These theoretical guarantees establish a principled foundation for developing reliable and continuously adapting multimodal learning systems.

---

### Towards Neurocognitive-Inspired Intelligence: From AI's Structural Mimicry to Human-Like Functional Cognition

Authors: Noorbakhsh Amiri Golilarz, Hassan S. Al Khatib, Shahram Rahimi
Published: 2025-10-09
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2510.13826v1

Artificial intelligence has advanced significantly through deep learning, reinforcement learning, and large language and vision models. However, these systems often remain task specific, struggle to adapt to changing conditions, and cannot generalize in ways similar to human cognition. Additionally, they mainly focus on mimicking brain structures, which often leads to black-box models with limited transparency and adaptability. Inspired by the structure and function of biological cognition, this paper introduces the concept of "Neurocognitive-Inspired Intelligence (NII)," a hybrid approach that combines neuroscience, cognitive science, computer vision, and AI to develop more general, adaptive, and robust intelligent systems capable of rapid learning, learning from less data, and leveraging prior experience. These systems aim to emulate the human brain's ability to flexibly learn, reason, remember, perceive, and act in real-world settings with minimal supervision. We review the limitations of current AI methods, define core principles of neurocognitive-inspired intelligence, and propose a modular, biologically inspired architecture that emphasizes integration, embodiment, and adaptability. We also discuss potential implementation strategies and outline various real-world applications, from robotics to education and healthcare. Importantly, this paper offers a hybrid roadmap for future research, laying the groundwork for building AI systems that more closely resemble human cognition.

---

### Beyond Discrete Categories: Multi-Task Valence-Arousal Modeling for Pet Vocalization Analysis

Authors: Junyao Huang, Rumin Situ
Published: 2025-10-09
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.12819v1

Traditional pet emotion recognition from vocalizations, based on discrete classification, struggles with ambiguity and capturing intensity variations. We propose a continuous Valence-Arousal (VA) model that represents emotions in a two-dimensional space. Our method uses an automatic VA label generation algorithm, enabling large-scale annotation of 42,553 pet vocalization samples. A multi-task learning framework jointly trains VA regression with auxiliary tasks (emotion, body size, gender) to enhance prediction by improving feature learning. Our Audio Transformer model achieves a validation Valence Pearson correlation of r = 0.9024 and an Arousal r = 0.7155, effectively resolving confusion between discrete categories like "territorial" and "happy." This work introduces the first continuous VA framework for pet vocalization analysis, offering a more expressive representation for human-pet interaction, veterinary diagnostics, and behavioral training. The approach shows strong potential for deployment in consumer products like AI pet emotion translators.

---

### MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning

Authors: Rajarshi Ghosh, Abhay Gupta, Hudson McBride, Anurag Vaidya, Faisal Mahmood
Published: 2025-10-09
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.12818v1

Large language models (LLMs) are increasingly deployed in clinical decision support, yet subtle demographic cues can influence their reasoning. Prior work has documented disparities in outputs across patient groups, but little is known about how internal reasoning shifts under controlled demographic changes. We introduce MEDEQUALQA, a counterfactual benchmark that perturbs only patient pronouns (he/him, she/her, they/them) while holding critical symptoms and conditions (CSCs) constant. Each clinical vignette is expanded into single-CSC ablations, producing three parallel datasets of approximately 23,000 items each (69,000 total). We evaluate a GPT-4.1 model and compute Semantic Textual Similarity (STS) between reasoning traces to measure stability across pronoun variants. Our results show overall high similarity (mean STS >0.80), but reveal consistent localized divergences in cited risk factors, guideline anchors, and differential ordering, even when final diagnoses remain unchanged. Our error analysis highlights certain cases in which the reasoning shifts, underscoring clinically relevant bias loci that may cascade into inequitable care. MEDEQUALQA offers a controlled diagnostic setting for auditing reasoning stability in medical AI.

---

### From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP

Authors: Shanshan Xu, Santosh T. Y. S. S, Barbara Plank
Published: 2025-10-09
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.12817v3

Human Label Variation (HLV) refers to legitimate disagreement in annotation that reflects the diversity of human perspectives rather than mere error. Long treated in NLP as noise to be eliminated, HLV has only recently been reframed as a signal for improving model robustness. With the rise of large language models (LLMs) and post-training methods such as human feedback-based alignment, the role of HLV has become increasingly consequential. Yet current preference-learning datasets routinely collapse multiple annotations into a single label, flattening diverse perspectives into artificial consensus. Preserving HLV is necessary not only for pluralistic alignment but also for sociotechnical safety evaluation, where model behavior must be assessed in relation to human interaction and societal context. This position paper argues that preserving HLV as an embodiment of human pluralism must be treated as a Selbstzweck, an intrinsic value in itself. We analyze the limitations of existing preference datasets and propose actionable strategies for incorporating HLV into dataset construction to better preserve pluralistic human values.

---

### Modeling Hypergraph Using Large Language Models

Authors: Bingqiao Gu, Jiale Zeng, Xingqin Qi, Dong Li
Published: 2025-10-09
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2510.11728v1

Due to the advantages of hypergraphs in modeling high-order relationships in complex systems, they have been applied to higher-order clustering, hypergraph neural networks and computer vision. These applications rely heavily on access to high-quality, large-scale real-world hypergraph data. Yet, compared to traditional pairwise graphs, real hypergraph datasets remain scarce in both scale and diversity. This shortage significantly limits the development and evaluation of advanced hypergraph learning algorithms. Therefore, how to quickly generate large-scale hypergraphs that conform to the characteristics of real networks is a crucial task that has not received sufficient attention. Motivated by recent advances in large language models (LLMs), particularly their capabilities in semantic reasoning, structured generation, and simulating human behavior, we investigate whether LLMs can facilitate hypergraph generation from a fundamentally new perspective. We introduce HyperLLM, a novel LLM-driven hypergraph generator that simulates the formation and evolution of hypergraphs through a multi-agent collaboration. The framework integrates prompts and structural feedback mechanisms to ensure that the generated hypergraphs reflect key real-world patterns. Extensive experiments across diverse datasets demonstrate that HyperLLM achieves superior fidelity to structural and temporal hypergraph patterns, while requiring minimal statistical priors. Our findings suggest that LLM-based frameworks offer a promising new direction for hypergraph modeling.

---

### A Multi-Component Reward Function with Policy Gradient for Automated Feature Selection with Dynamic Regularization and Bias Mitigation

Authors: Sudip Khadka, L. S. Paudel
Published: 2025-10-09
Categories: cs.LG, cs.CY, stat.ML
arXiv: https://arxiv.org/abs/2510.09705v1

Static feature exclusion strategies often fail to prevent bias when hidden dependencies influence the model predictions. To address this issue, we explore a reinforcement learning (RL) framework that integrates bias mitigation and automated feature selection within a single learning process. Unlike traditional heuristic-driven filter or wrapper approaches, our RL agent adaptively selects features using a reward signal that explicitly integrates predictive performance with fairness considerations. This dynamic formulation allows the model to balance generalization, accuracy, and equity throughout the training process, rather than rely exclusively on pre-processing adjustments or post hoc correction mechanisms. In this paper, we describe the construction of a multi-component reward function, the specification of the agents action space over feature subsets, and the integration of this system with ensemble learning. We aim to provide a flexible and generalizable way to select features in environments where predictors are correlated and biases can inadvertently re-emerge.

---

### Operator Learning for Power Systems Simulation

Authors: Matthew Schlegel, Matthew E. Taylor, Mostafa Farrokhabadi
Published: 2025-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09704v1

Time domain simulation, i.e., modeling the system's evolution over time, is a crucial tool for studying and enhancing power system stability and dynamic performance. However, these simulations become computationally intractable for renewable-penetrated grids, due to the small simulation time step required to capture renewable energy resources' ultra-fast dynamic phenomena in the range of 1-50 microseconds. This creates a critical need for solutions that are both fast and scalable, posing a major barrier for the stable integration of renewable energy resources and thus climate change mitigation. This paper explores operator learning, a family of machine learning methods that learn mappings between functions, as a surrogate model for these costly simulations. The paper investigates, for the first time, the fundamental concept of simulation time step-invariance, which enables models trained on coarse time steps to generalize to fine-resolution dynamics. Three operator learning methods are benchmarked on a simple test system that, while not incorporating practical complexities of renewable-penetrated grids, serves as a first proof-of-concept to demonstrate the viability of time step-invariance. Models are evaluated on (i) zero-shot super-resolution, where training is performed on a coarse simulation time step and inference is performed at super-resolution, and (ii) generalization between stable and unstable dynamic regimes. This work addresses a key challenge in the integration of renewable energy for the mitigation of climate change by benchmarking operator learning methods to model physical systems.

---

### VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands

Authors: Aofan Liu, Lulu Tang
Published: 2025-10-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.09699v1

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge. Unlike text-only models, VLMs integrate additional modalities, introducing novel vulnerabilities such as image hijacking, which can manipulate the model into producing inappropriate or harmful responses. Drawing inspiration from text-based jailbreaks like the "Do Anything Now" (DAN) command, this work introduces VisualDAN, a single adversarial image embedded with DAN-style commands. Specifically, we prepend harmful corpora with affirmative prefixes (e.g., "Sure, I can provide the guidance you need") to trick the model into responding positively to malicious queries. The adversarial image is then trained on these DAN-inspired harmful texts and transformed into the text domain to elicit malicious outputs. Extensive experiments on models such as MiniGPT-4, MiniGPT-v2, InstructBLIP, and LLaVA reveal that VisualDAN effectively bypasses the safeguards of aligned VLMs, forcing them to execute a broad range of harmful instructions that severely violate ethical standards. Our results further demonstrate that even a small amount of toxic content can significantly amplify harmful outputs once the model's defenses are compromised. These findings highlight the urgent need for robust defenses against image-based attacks and offer critical insights for future research into the alignment and security of VLMs.

---

### Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression

Authors: Lorenzo Nikiforos, Luciano Prono, Charalampos Antoniadis, Fabio Pareschi, Riccardo Rovatti, Gianluca Setti
Published: 2025-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09696v3

The increasing scale of Deep Neural Networks (DNNs) introduces the need for compression techniques such as pruning, quantization, and low-rank decomposition. While these methods are very effective at reducing memory, computation, and energy consumption, they may introduce severe accuracy degradation, which is often mitigated by using iterative, gradual compression. However, different compression techniques require distinct iterative approaches, and some result in unstable, discontinuous model fine-tuning. We introduce Vanishing Contributions (VCON), a unified framework for the smooth, iterative transition of DNNs into a compressed form. Rather than replacing the original network directly with its compressed version, VCON executes both in parallel during fine-tuning. The contribution of the original (uncompressed) model is progressively reduced, while that of the compressed model is gradually increased. This affine combination allows the network to slowly adapt, improving stability and mitigating accuracy degradation. We evaluate VCON on computer vision and natural language processing benchmarks, using multiple compression strategies. In most settings, our framework improves accuracy over post-shot and iterative baselines. Typical gains exceed 1%, while some configuration exhibits improvements above 15%. VCON is thus compatible with existing compression techniques and consistently improves performance across diverse tasks.

---

### Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detection

Authors: Yanran Chen, Lynn Greschner, Roman Klinger, Michael Klenk, Steffen Eger
Published: 2025-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09695v3

Logical fallacies are common in public communication and can mislead audiences; fallacious arguments may still appear convincing despite lacking soundness, because convincingness is inherently subjective. We present the first computational study of how emotional framing interacts with fallacies and convincingness, using large language models (LLMs) to systematically change emotional appeals in fallacious arguments. We benchmark eight LLMs on injecting emotional appeal into fallacious arguments while preserving their logical structures, then use the best models to generate stimuli for a human study. Our results show that LLM-driven emotional framing reduces human fallacy detection in F1 by 14.5% on average. Humans perform better in fallacy detection when perceiving enjoyment than fear or sadness, and these three emotions also correlate with significantly higher convincingness compared to neutral or other emotion states. Our work has implications for AI-driven emotional manipulation in the context of fallacious argumentation.

---

### Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection

Authors: Xiaodan Li, Mengjie Wu, Yao Zhu, Yunna Lv, YueFeng Chen, Cen Chen, Jianmei Guo, Hui Xue
Published: 2025-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09694v1

Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrails mostly perform post-hoc detection that may expose unsafe content before it is caught, and the latency constraints further push them toward lightweight models, limiting detection accuracy. In this work, we propose Kelp, a novel plug-in framework that enables streaming risk detection within the LM generation pipeline. Kelp leverages intermediate LM hidden states through a Streaming Latent Dynamics Head (SLD), which models the temporal evolution of risk across the generated sequence for more accurate real-time risk detection. To ensure reliable streaming moderation in real applications, we introduce an Anchored Temporal Consistency (ATC) loss to enforce monotonic harm predictions by embedding a benign-then-harmful temporal prior. Besides, for a rigorous evaluation of streaming guardrails, we also present StreamGuardBench-a model-grounded benchmark featuring on-the-fly responses from each protected model, reflecting real-world streaming scenarios in both text and vision-language tasks. Across diverse models and datasets, Kelp consistently outperforms state-of-the-art post-hoc guardrails and prior plug-in probes (15.61% higher average F1), while using only 20M parameters and adding less than 0.5 ms of per-token latency.

---

### Neural PDE Solvers with Physics Constraints: A Comparative Study of PINNs, DRM, and WANs

Authors: Jiakang Chen
Published: 2025-10-09
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2510.09693v1

Partial differential equations (PDEs) underpin models across science and engineering, yet analytical solutions are atypical and classical mesh-based solvers can be costly in high dimensions. This dissertation presents a unified comparison of three mesh-free neural PDE solvers, physics-informed neural networks (PINNs), the deep Ritz method (DRM), and weak adversarial networks (WANs), on Poisson problems (up to 5D) and the time-independent Schrödinger equation in 1D/2D (infinite well and harmonic oscillator), and extends the study to a laser-driven case of Schrödinger's equation via the Kramers-Henneberger (KH) transformation. Under a common protocol, all methods achieve low $L_2$ errors ($10^{-6}$-$10^{-9}$) when paired with forced boundary conditions (FBCs), forced nodes (FNs), and orthogonality regularization (OG). Across tasks, PINNs are the most reliable for accuracy and recovery of excited spectra; DRM offers the best accuracy-runtime trade-off on stationary problems; WAN is more sensitive but competitive when weak-form constraints and FN/OG are used effectively. Sensitivity analyses show that FBC removes boundary-loss tuning, network width matters more than depth for single-network solvers, and most gains occur within 5000-10,000 epochs. The same toolkit solves the KH case, indicating transfer beyond canonical benchmarks. We provide practical guidelines for method selection and outline the following extensions: time-dependent formulations for DRM and WAN, adaptive residual-driven sampling, parallel multi-state training, and neural domain decomposition. These results support physics-guided neural solvers as credible, scalable tools for solving complex PDEs.

---

### Evaluation of Differential Privacy Mechanisms on Federated Learning

Authors: Tejash Varsani
Published: 2025-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09691v1

Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding noise to model updates, usually controlled by a fixed privacy budget. However, this approach can introduce excessive noise, particularly when the model converges, which compromises performance. To address this problem, adaptive privacy budgets have been investigated as a potential solution. This work implements DP methods using Laplace and Gaussian mechanisms with an adaptive privacy budget, extending the SelecEval simulator. We introduce an adaptive clipping approach in the Gaussian mechanism, ensuring that gradients of the model are dynamically updated rather than using a fixed sensitivity. We conduct extensive experiments with various privacy budgets, IID and non-IID datasets, and different numbers of selected clients per round. While our experiments were limited to 200 training rounds, the results suggest that adaptive privacy budgets and adaptive clipping can help maintain model accuracy while preserving privacy.

---

### When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models

Authors: Haoran Ou, Kangjie Chen, Xingshuo Han, Gelei Deng, Jie Zhang, Han Qiu, Tianwei Zhang
Published: 2025-10-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.09689v3

Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Internet. While this integration enhances model capability, it also introduces a distinct safety threat surface: the retrieval and citation process has the potential risk of exposing users to harmful or low-credibility web content. Existing red-teaming methods are largely designed for standalone LLMs as they primarily focus on unsafe generation, ignoring risks emerging from the complex search workflow. To address this gap, we propose CREST-Search, a pioneering red-teaming framework for LLMs with web search. The cornerstone of CREST-Search is three novel attack strategies that generate seemingly benign search queries yet induce unsafe citations. It also employs an iterative in-context refinement mechanism to strengthen adversarial effectiveness under black-box constraints. In addition, we construct a search-specific harmful dataset, WebSearch-Harm, which enables fine-tuning a specialized red-teaming model to improve query quality. Our experiments demonstrate that CREST-Search can effectively bypass safety filters and systematically expose vulnerabilities in web search-based LLM systems, underscoring the necessity of the development of robust search models.

---

### On the Occurence of Critical Learning Periods in Neural Networks

Authors: Stanisław Pawlak
Published: 2025-10-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.09687v1

This study delves into the plasticity of neural networks, offering empirical support for the notion that critical learning periods and warm-starting performance loss can be avoided through simple adjustments to learning hyperparameters. The critical learning phenomenon emerges when training is initiated with deficit data. Subsequently, after numerous deficit epochs, the network's plasticity wanes, impeding its capacity to achieve parity in accuracy with models trained from scratch, even when extensive clean data training follows deficit epochs. Building upon seminal research introducing critical learning periods, we replicate key findings and broaden the experimental scope of the main experiment from the original work. In addition, we consider a warm-starting approach and show that it can be seen as a form of deficit pretraining. In particular, we demonstrate that these problems can be averted by employing a cyclic learning rate schedule. Our findings not only impact neural network training practices but also establish a vital link between critical learning periods and ongoing research on warm-starting neural network training.

---

### Stop DDoS Attacking the Research Community with AI-Generated Survey Papers

Authors: Jianghao Lin, Rong Shan, Jiachen Zhu, Yunjia Xi, Yong Yu, Weinan Zhang
Published: 2025-10-09
Categories: cs.CY, cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.09686v1

Survey papers are foundational to the scholarly progress of research communities, offering structured overviews that guide both novices and experts across disciplines. However, the recent surge of AI-generated surveys, especially enabled by large language models (LLMs), has transformed this traditionally labor-intensive genre into a low-effort, high-volume output. While such automation lowers entry barriers, it also introduces a critical threat: the phenomenon we term the "survey paper DDoS attack" to the research community. This refers to the unchecked proliferation of superficially comprehensive but often redundant, low-quality, or even hallucinated survey manuscripts, which floods preprint platforms, overwhelms researchers, and erodes trust in the scientific record. In this position paper, we argue that we must stop uploading massive amounts of AI-generated survey papers (i.e., survey paper DDoS attack) to the research community, by instituting strong norms for AI-assisted review writing. We call for restoring expert oversight and transparency in AI usage and, moreover, developing new infrastructures such as Dynamic Live Surveys, community-maintained, version-controlled repositories that blend automated updates with human curation. Through quantitative trend analysis, quality audits, and cultural impact discussion, we show that safeguarding the integrity of surveys is no longer optional but imperative to the research community.

---

### Deep Neural Networks Inspired by Differential Equations

Authors: Yongshuai Liu, Lianfang Wang, Kuilin Qin, Qinghua Zhang, Faqiang Wang, Li Cui, Jun Liu, Yuping Duan, Tieyong Zeng
Published: 2025-10-09
Categories: cs.LG, cs.AI, cs.CV, math.NA
arXiv: https://arxiv.org/abs/2510.09685v2

Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challenges related to theoretical understanding, interpretability, and generalization. To address these issues, researchers are increasingly adopting a differential equations perspective to propose a unified theoretical framework and systematic design methodologies for neural networks. In this paper, we provide an extensive review of deep neural network architectures and dynamic modeling methods inspired by differential equations. We specifically examine deep neural network models and deterministic dynamical network constructs based on ordinary differential equations (ODEs), as well as regularization techniques and stochastic dynamical network models informed by stochastic differential equations (SDEs). We present numerical comparisons of these models to illustrate their characteristics and performance. Finally, we explore promising research directions in integrating differential equations with deep learning to offer new insights for developing intelligent computational methods that boast enhanced interpretability and generalization capabilities.

---

### Using LLMs to Directly Guess Conditional Expectations Can Improve Efficiency in Causal Estimation

Authors: Chris Engh, P. M. Aronow
Published: 2025-10-09
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.09684v1

We propose a simple yet effective use of LLM-powered AI tools to improve causal estimation. In double machine learning, the accuracy of causal estimates of the effect of a treatment on an outcome in the presence of a high-dimensional confounder depends on the performance of estimators of conditional expectation functions. We show that predictions made by generative models trained on historical data can be used to improve the performance of these estimators relative to approaches that solely rely on adjusting for embeddings extracted from these models. We argue that the historical knowledge and reasoning capacities associated with these generative models can help overcome curse-of-dimensionality problems in causal inference problems. We consider a case study using a small dataset of online jewelry auctions, and demonstrate that inclusion of LLM-generated guesses as predictors can improve efficiency in estimation.

---

### ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review

Authors: Gaurav Sahu, Hugo Larochelle, Laurent Charlin, Christopher Pal
Published: 2025-10-09
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.08867v1

Peer review is the cornerstone of scientific publishing, yet it suffers from inconsistencies, reviewer subjectivity, and scalability challenges. We introduce ReviewerToo, a modular framework for studying and deploying AI-assisted peer review to complement human judgment with systematic and consistent assessments. ReviewerToo supports systematic experiments with specialized reviewer personas and structured evaluation criteria, and can be partially or fully integrated into real conference workflows. We validate ReviewerToo on a carefully curated dataset of 1,963 paper submissions from ICLR 2025, where our experiments with the gpt-oss-120b model achieves 81.8% accuracy for the task of categorizing a paper as accept/reject compared to 83.9% for the average human reviewer. Additionally, ReviewerToo-generated reviews are rated as higher quality than the human average by an LLM judge, though still trailing the strongest expert contributions. Our analysis highlights domains where AI reviewers excel (e.g., fact-checking, literature coverage) and where they struggle (e.g., assessing methodological novelty and theoretical contributions), underscoring the continued need for human expertise. Based on these findings, we propose guidelines for integrating AI into peer-review pipelines, showing how AI can enhance consistency, coverage, and fairness while leaving complex evaluative judgments to domain experts. Our work provides a foundation for systematic, hybrid peer-review systems that scale with the growth of scientific publishing.

---

### Multi-fidelity Batch Active Learning for Gaussian Process Classifiers

Authors: Murray Cutforth, Yiming Yang, Tiffany Fan, Serge Guillas, Eric Darve
Published: 2025-10-09
Categories: cs.LG, cs.CE, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.08865v1

Many science and engineering problems rely on expensive computational simulations, where a multi-fidelity approach can accelerate the exploration of a parameter space. We study efficient allocation of a simulation budget using a Gaussian Process (GP) model in the binary simulation output case. This paper introduces Bernoulli Parameter Mutual Information (BPMI), a batch active learning algorithm for multi-fidelity GP classifiers. BPMI circumvents the intractability of calculating mutual information in the probability space by employing a first-order Taylor expansion of the link function. We evaluate BPMI against several baselines on two synthetic test cases and a complex, real-world application involving the simulation of a laser-ignited rocket combustor. In all experiments, BPMI demonstrates superior performance, achieving higher predictive accuracy for a fixed computational budget.

---

### Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models

Authors: Ragib Amin Nihal, Rui Wen, Kazuhiro Nakadai, Jun Sakuma
Published: 2025-10-09
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.08859v2

Large language models (LLMs) remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories through distinct conversational approaches. Existing multi-turn methods often rely on heuristic or ad hoc exploration strategies, providing limited insight into underlying model weaknesses. The relationship between conversation patterns and model vulnerabilities across harm categories remains poorly understood. We propose Pattern Enhanced Chain of Attack (PE-CoA), a framework of five conversation patterns to construct multi-turn jailbreaks through natural dialogue. Evaluating PE-CoA on twelve LLMs spanning ten harm categories, we achieve state-of-the-art performance, uncovering pattern-specific vulnerabilities and LLM behavioral characteristics: models exhibit distinct weakness profiles, defense to one pattern does not generalize to others, and model families share similar failure modes. These findings highlight limitations of safety training and indicate the need for pattern-aware defenses. Code available on: https://github.com/Ragib-Amin-Nihal/PE-CoA

---

### Sparse components distinguish visual pathways & their alignment to neural networks

Authors: Ammar I Marvi, Nancy G Kanwisher, Meenakshi Khosla
Published: 2025-10-09
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.08858v1

The ventral, dorsal, and lateral streams in high-level human visual cortex are implicated in distinct functional processes. Yet, deep neural networks (DNNs) trained on a single task model the entire visual system surprisingly well, hinting at common computational principles across these pathways. To explore this inconsistency, we applied a novel sparse decomposition approach to identify the dominant components of visual representations within each stream. Consistent with traditional neuroscience research, we find a clear difference in component response profiles across the three visual streams -- identifying components selective for faces, places, bodies, text, and food in the ventral stream; social interactions, implied motion, and hand actions in the lateral stream; and some less interpretable components in the dorsal stream. Building on this, we introduce Sparse Component Alignment (SCA), a new method for measuring representational alignment between brains and machines that better captures the latent neural tuning of these two visual systems. Using SCA, we find that standard visual DNNs are more aligned with the ventral than either dorsal or lateral representations. SCA reveals these distinctions with greater resolution than conventional population-level geometry, offering a measure of representational alignment that is sensitive to a system's underlying axes of neural tuning.

---

### Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training

Authors: T. Ed Li, Junyu Ren
Published: 2025-10-09
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.08855v1

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training methods face feature absorption, where features (or neurons) are absorbed into each other to minimize $L_1$ penalty, making it difficult to consistently identify and analyze model behaviors. We introduce Adaptive Temporal Masking (ATM), a novel training approach that dynamically adjusts feature selection by tracking activation magnitudes, frequencies, and reconstruction contributions to compute importance scores that evolve over time. ATM applies a probabilistic masking mechanism based on statistical thresholding of these importance scores, creating a more natural feature selection process. Through extensive experiments on the Gemma-2-2b model, we demonstrate that ATM achieves substantially lower absorption scores compared to existing methods like TopK and JumpReLU SAEs, while maintaining excellent reconstruction quality. These results establish ATM as a principled solution for learning stable, interpretable features in neural networks, providing a foundation for more reliable model analysis.

---

### On the Alignment Between Supervised and Self-Supervised Contrastive Learning

Authors: Achleshwar Luthra, Priyadarsi Mishra, Tomer Galanti
Published: 2025-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.08852v1

Self-supervised contrastive learning (CL) has achieved remarkable empirical success, often producing representations that rival supervised pre-training on downstream tasks. Recent theory explains this by showing that the CL loss closely approximates a supervised surrogate, Negatives-Only Supervised Contrastive Learning (NSCL) loss, as the number of classes grows. Yet this loss-level similarity leaves an open question: {\em Do CL and NSCL also remain aligned at the representation level throughout training, not just in their objectives?} We address this by analyzing the representation alignment of CL and NSCL models trained under shared randomness (same initialization, batches, and augmentations). First, we show that their induced representations remain similar: specifically, we prove that the similarity matrices of CL and NSCL stay close under realistic conditions. Our bounds provide high-probability guarantees on alignment metrics such as centered kernel alignment (CKA) and representational similarity analysis (RSA), and they clarify how alignment improves with more classes, higher temperatures, and its dependence on batch size. In contrast, we demonstrate that parameter-space coupling is inherently unstable: divergence between CL and NSCL weights can grow exponentially with training time. Finally, we validate these predictions empirically, showing that CL-NSCL alignment strengthens with scale and temperature, and that NSCL tracks CL more closely than other supervised objectives. This positions NSCL as a principled bridge between self-supervised and supervised learning. Our code and project page are available at (\href{https://github.com/DLFundamentals/understanding_ssl_v2}{code}, \href{https://dlfundamentals.github.io/cl-nscl-representation-alignment/}{project page}).

---

### Repository-Aware File Path Retrieval via Fine-Tuned LLMs

Authors: Vasudha Yanuganti, Ishaan Puri, Swapnil Chhatre, Mantinder Singh, Ashok Jallepalli, Hritvik Shrivastava, Pradeep Kumar Sharma
Published: 2025-10-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.08850v1

Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the bug introduced?" Traditional code search (keyword or IR based) often misses semantic context and cross file links, while large language models (LLMs) understand natural language but lack repository specific detail. We present a method for file path retrieval that fine tunes a strong LLM (Qwen3-8B) with QLoRA and Unsloth optimizations to predict relevant file paths directly from a natural language query. To build training data, we introduce six code aware strategies that use abstract syntax tree (AST) structure and repository content to generate realistic question-answer pairs, where answers are sets of file paths. The strategies range from single file prompts to hierarchical repository summaries, providing broad coverage. We fine tune on Python projects including Flask, Click, Jinja, FastAPI, and PyTorch, and obtain high retrieval accuracy: up to 91\% exact match and 93\% recall on held out queries, clearly beating single strategy training. On a large codebase like PyTorch (about 4,000 Python files), the model reaches 59\% recall, showing scalability. We analyze how multi level code signals help the LLM reason over cross file context and discuss dataset design, limits (for example, context length in very large repos), and future integration of retrieval with LLM based code intelligence.

---

### FOLK: Fast Open-Vocabulary 3D Instance Segmentation via Label-guided Knowledge Distillation

Authors: Hongrui Wu, Zhicheng Gao, Jin Cao, Kelu Yao, Wen Shen, Zhihua Wei
Published: 2025-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.08849v1

Open-vocabulary 3D instance segmentation seeks to segment and classify instances beyond the annotated label space. Existing methods typically map 3D instances to 2D RGB-D images, and then employ vision-language models (VLMs) for classification. However, such a mapping strategy usually introduces noise from 2D occlusions and incurs substantial computational and memory costs during inference, slowing down the inference speed. To address the above problems, we propose a Fast Open-vocabulary 3D instance segmentation method via Label-guided Knowledge distillation (FOLK). Our core idea is to design a teacher model that extracts high-quality instance embeddings and distills its open-vocabulary knowledge into a 3D student model. In this way, during inference, the distilled 3D model can directly classify instances from the 3D point cloud, avoiding noise caused by occlusions and significantly accelerating the inference process. Specifically, we first design a teacher model to generate a 2D CLIP embedding for each 3D instance, incorporating both visibility and viewpoint diversity, which serves as the learning target for distillation. We then develop a 3D student model that directly produces a 3D embedding for each 3D instance. During training, we propose a label-guided distillation algorithm to distill open-vocabulary knowledge from label-consistent 2D embeddings into the student model. FOLK conducted experiments on the ScanNet200 and Replica datasets, achieving state-of-the-art performance on the ScanNet200 dataset with an AP50 score of 35.7, while running approximately 6.0x to 152.2x faster than previous methods. All codes will be released after the paper is accepted.

---

### What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment

Authors: Allison Sihan Jia, Daniel Huang, Nikhil Vytla, Seung Won Wilson Yoo, Nirvika Choudhury, Shayak Sen, John C. Mitchell, Anupam Datta
Published: 2025-10-09
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.08847v2

We introduce the Agent GPA (Goal-Plan-Action) framework, driven by the fundamental insight that critical agent failures emerge at the intersections of setting goals, devising plans, and executing actions. We operationalize the framework with a factorized suite of LLM judges designed to measure distinct elements of Goal-Plan-Act alignment. To make this methodology scalable and generalizable across diverse agent architectures and datasets, we use state-of-the-art automated prompt optimization techniques to systematically generate domain-specific evaluation criteria. We validate this approach across three benchmarks: a multi-agent research setting (TRAIL/GAIA), a single coding agent setting (TRAIL/SWE-bench), and a private, enterprise data-agent setting (Snowflake Intelligence). Extensive evaluation on TRAIL/GAIA demonstrates the core validity of the framework, which identifies a broad range of agent failures (95% of human-annotated errors), localizes errors to enable targeted debugging (86% of human-annotated errors), and exhibits strong agreement with human evaluators. Crucially, by applying our automated methodology to both public datasets, we demonstrate that our GPA judges generally achieve the highest error coverage (ranging from 76% to 86%) in comparison to manual prompting approaches. We also leverage an evolutionary coding agent to improve judge consistency by up to 38% through iterative refinement of evaluation rubrics. Overall, Agent GPA provides a rigorous and generalizable paradigm for targeted agent evaluation.

---

### The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective

Authors: Thai-Hoang Pham, Jiayuan Chen, Seungyeon Lee, Yuanlong Wang, Sayoko Moroi, Xueru Zhang, Ping Zhang
Published: 2025-10-09
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.08840v1

As machine learning (ML) algorithms are increasingly used in medical image analysis, concerns have emerged about their potential biases against certain social groups. Although many approaches have been proposed to ensure the fairness of ML models, most existing works focus only on medical image diagnosis tasks, such as image classification and segmentation, and overlooked prognosis scenarios, which involve predicting the likely outcome or progression of a medical condition over time. To address this gap, we introduce FairTTE, the first comprehensive framework for assessing fairness in time-to-event (TTE) prediction in medical imaging. FairTTE encompasses a diverse range of imaging modalities and TTE outcomes, integrating cutting-edge TTE prediction and fairness algorithms to enable systematic and fine-grained analysis of fairness in medical image prognosis. Leveraging causal analysis techniques, FairTTE uncovers and quantifies distinct sources of bias embedded within medical imaging datasets. Our large-scale evaluation reveals that bias is pervasive across different imaging modalities and that current fairness methods offer limited mitigation. We further demonstrate a strong association between underlying bias sources and model disparities, emphasizing the need for holistic approaches that target all forms of bias. Notably, we find that fairness becomes increasingly difficult to maintain under distribution shifts, underscoring the limitations of existing solutions and the pressing need for more robust, equitable prognostic models.

---

### Reinforcement Learning-Driven Edge Management for Reliable Multi-view 3D Reconstruction

Authors: Motahare Mounesan, Sourya Saha, Houchao Gan, Md. Nurul Absur, Saptarshi Debroy
Published: 2025-10-09
Categories: cs.LG, cs.AI, cs.CV, cs.DC, cs.GR, cs.MM
arXiv: https://arxiv.org/abs/2510.08839v1

Real-time multi-view 3D reconstruction is a mission-critical application for key edge-native use cases, such as fire rescue, where timely and accurate 3D scene modeling enables situational awareness and informed decision-making. However, the dynamic and unpredictable nature of edge resource availability introduces disruptions, such as degraded image quality, unstable network links, and fluctuating server loads, which challenge the reliability of the reconstruction pipeline. In this work, we present a reinforcement learning (RL)-based edge resource management framework for reliable 3D reconstruction to ensure high quality reconstruction within a reasonable amount of time, despite the system operating under a resource-constrained and disruption-prone environment. In particular, the framework adopts two cooperative Q-learning agents, one for camera selection and one for server selection, both of which operate entirely online, learning policies through interactions with the edge environment. To support learning under realistic constraints and evaluate system performance, we implement a distributed testbed comprising lab-hosted end devices and FABRIC infrastructure-hosted edge servers to emulate smart city edge infrastructure under realistic disruption scenarios. Results show that the proposed framework improves application reliability by effectively balancing end-to-end latency and reconstruction quality in dynamic environments.

---

### Long-Tailed Recognition via Information-Preservable Two-Stage Learning

Authors: Fudong Lin, Xu Yuan
Published: 2025-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.08836v1

The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper, we propose a novel two-stage learning approach to mitigate such a majority-biased tendency while preserving valuable information within datasets. Specifically, the first stage proposes a new representation learning technique from the information theory perspective. This approach is theoretically equivalent to minimizing intra-class distance, yielding an effective and well-separated feature space. The second stage develops a novel sampling strategy that selects mathematically informative instances, able to rectify majority-biased decision boundaries without compromising a model's overall performance. As a result, our approach achieves the state-of-the-art performance across various long-tailed benchmark datasets, validated via extensive experiments. Our code is available at https://github.com/fudong03/BNS_IPDPP.

---

### The human-authorship halo: attribution bias in literary style evaluation by humans and AI

Authors: Wouter Haverals, Meredith Martin
Published: 2025-10-09
Categories: cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2510.08831v2

As AI writing tools become widespread, we need to understand how both humans and machines evaluate literary style, a domain where objective standards are elusive and judgments are inherently subjective. We conducted controlled experiments using Raymond Queneau's Exercises in Style (1947) to measure attribution bias across evaluators. Study 1 compared human participants (N=556) and AI models (N=13) evaluating literary passages from Queneau versus GPT-4-generated versions under three conditions: blind, accurately labeled, and counterfactually labeled. Study 2 tested bias generalization across a 14x14 matrix of AI evaluators and creators. Both studies revealed systematic pro-human attribution bias. Humans showed +13.7 percentage point (pp) bias (Cohen's h = 0.28, 95% CI: 0.19-0.37), while AI models showed +34.3 percentage point bias (h = 0.70, 95% CI: 0.62-0.78), a 2.5-fold stronger effect (P<0.001). Study 2 confirmed this bias operates across AI architectures (+25.8pp, 95% CI: 24.1-27.6%), demonstrating that AI systems systematically devalue creative content when labeled as "AI-generated" regardless of which AI created it. We also find that attribution labels lead evaluators to invert assessment criteria, with identical features receiving opposing evaluations based solely on perceived authorship. This suggests AI models have absorbed human cultural biases against artificial creativity during training, including through the preference signals on which they are aligned. Our study represents the first controlled comparison of attribution bias between human and artificial evaluators in aesthetic judgment, revealing that AI systems not only replicate but amplify this human tendency.

---

### CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization

Authors: Debeshee Das, Luca Beurer-Kellner, Marc Fischer, Maximilian Baader
Published: 2025-10-09
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.08829v1

The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are often ill-calibrated as they cannot reliably differentiate malicious and benign instructions, leading to high false positive rates that prevent their real-world adoption. To address this, we present a novel approach inspired by the fundamental principle of computer security: data should not contain executable instructions. Instead of sample-level classification, we propose a token-level sanitization process, which surgically removes any instructions directed at AI systems from tool outputs, capturing malicious instructions as a byproduct. In contrast to existing safety classifiers, this approach is non-blocking, does not require calibration, and is agnostic to the context of tool outputs. Further, we can train such token-level predictors with readily available instruction-tuning data only, and don't have to rely on unrealistic prompt injection examples from challenges or of other synthetic origin. In our experiments, we find that this approach generalizes well across a wide range of attacks and benchmarks like AgentDojo, BIPIA, InjecAgent, ASB and SEP, achieving a 7-10x reduction of attack success rate (ASR) (34% to 3% on AgentDojo), without impairing agent utility in both benign and malicious settings.

---

### McMining: Automated Discovery of Misconceptions in Student Code

Authors: Erfan Al-Hossami, Razvan Bunescu
Published: 2025-10-09
Categories: cs.SE, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.08827v1

When learning to code, students often develop misconceptions about various programming language concepts. These can not only lead to bugs or inefficient code, but also slow down the learning of related concepts. In this paper, we introduce McMining, the task of mining programming misconceptions from samples of code from a student. To enable the training and evaluation of McMining systems, we develop an extensible benchmark dataset of misconceptions together with a large set of code samples where these misconceptions are manifested. We then introduce two LLM-based McMiner approaches and through extensive evaluations show that models from the Gemini, Claude, and GPT families are effective at discovering misconceptions in student code.

---

### Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs

Authors: Jia Ao Sun, Hao Yu, Fabrizio Gotti, Fengran Mo, Yihong Wu, Yuchen Hui, Zhan Su, Lingfeng Xiao, Jian-Yun Nie
Published: 2025-10-09
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.08825v2

Large language models (LLMs) augmented with knowledge graphs (KGs) offer a promising approach for knowledge-intensive reasoning. Central to this approach is the selection of appropriate reasoning paths in the KG. Yet, existing methods face a common limitation: reasoning path selection is often performed by separate modules using criteria that are only weakly connected to the reasoning requirements. This often results in selecting incorrect relations or premature pruning of relevant paths. We propose Search-on-Graph (SoG), a method that strengthens the connection between path selection and reasoning by having the LLM itself select which relations to follow, informed by both the available KG structure and the complete reasoning history. SoG follows an \textit{observe-think-navigate} paradigm: at each step, the LLM observes the relational connections available at the current entity, reasons about which path best advances toward answering the question, and navigates accordingly. This context-aware navigation fully exploits the LLM's reasoning capabilities rather than relying on independent selection modules with surrogate criteria. Experiments on six knowledge graph question answering (KGQA) benchmarks demonstrate that SoG outperforms state-of-the-art methods while requiring no task-specific fine-tuning and generalizing across different KG schemas.

---

### D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition

Authors: Yiyang Huang, Yizhou Wang, Yun Fu
Published: 2025-10-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.08818v1

Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). However, this adaptation remains challenging, as it requires processing dense and temporally extended visual inputs that exceed the capacity of image-based models. This paper identifies the perception bottleneck and token overload as key challenges in extending image-based VLMs to the video domain. To address these issues, we propose D-CoDe, a training-free adaptation framework that incorporates dynamic compression and question decomposition. Specifically, dynamic compression alleviates the perception bottleneck through adaptive selection of representative frames and content-aware aggregation of spatial tokens, thereby reducing redundancy while preserving informative content. In parallel, question decomposition mitigates token overload by reformulating the original query into sub-questions, guiding the model to focus on distinct aspects of the video and enabling more comprehensive understanding. Experiments demonstrate that D-CoDe effectively improves video understanding across various benchmarks. Furthermore, strong performance on the challenging long-video benchmark highlights the potential of D-CoDe in handling complex video-language tasks. Code is available at https://github.com/hukcc/D-CoDe.

---

### A Quantale-Weakness Route to $P \neq NP$ via CD Evidence Normalization and Gauge-Buffered Locked Ensembles

Authors: Ben Goertzel
Published: 2025-10-09
Categories: cs.CC, cs.AI
arXiv: https://arxiv.org/abs/2510.08814v2

We present a proof architecture for \(P \neq NP\) based on an upper--lower clash in polytime-capped conditional description length. We construct an efficiently samplable family of SAT instances \(Y\) such that every satisfying witness for \(Y\) yields the same global message \(M(Y)\). If \(P=NP\), then a standard polynomial-time SAT self-reduction recovers \(M(Y)\) from \(Y\), so \( K_{\mathrm{poly}}(M(Y)\mid Y)=O(1). \) The lower-bound side shows the opposite. For the same ensemble, no fixed polynomial-time observer can gain substantial predictive advantage on a linear number of selected message coordinates. The argument treats computation as an evidence-producing process: predictive advantage is converted into constructible-dual evidence skew and then into pairwise distinctions between message-opposite worlds. A normalization theorem shows that every target-relevant non-neutral evidence leaf is either a safe-buffer observation or a hidden-gauge observation. Safe-buffer observations have negligible leakage, while hidden-gauge observations are limited by gauge-rank accounting. This yields an atomic evidence budget implying that total message-resolving advantage is \(o(t)\) across \(t\) selected coordinates. Boundary-law mixing gives the near-random baseline for the visible surface. Combining this with the evidence budget gives product small-success and then, by Compression-from-Success, \( K_{\mathrm{poly}}(M(Y)\mid Y)\ge Ω(t) \) with high probability. This contradicts the constant upper bound from \(P=NP\). Therefore \(P \neq NP\).

---

### The Model's Language Matters: A Comparative Privacy Analysis of LLMs

Authors: Abhishek K. Mishra, Antoine Boutet, Lucas Magnana
Published: 2025-10-09
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2510.08813v1

Large Language Models (LLMs) are increasingly deployed across multilingual applications that handle sensitive data, yet their scale and linguistic variability introduce major privacy risks. Mostly evaluated for English, this paper investigates how language structure affects privacy leakage in LLMs trained on English, Spanish, French, and Italian medical corpora. We quantify six linguistic indicators and evaluate three attack vectors: extraction, counterfactual memorization, and membership inference. Results show that privacy vulnerability scales with linguistic redundancy and tokenization granularity: Italian exhibits the strongest leakage, while English shows higher membership separability. In contrast, French and Spanish display greater resilience due to higher morphological complexity. Overall, our findings provide the first quantitative evidence that language matters in privacy leakage, underscoring the need for language-aware privacy-preserving mechanisms in LLM deployments.

---

### Adaptive Science Operations in Deep Space Missions Using Offline Belief State Planning

Authors: Grace Ra Kim, Hailey Warner, Duncan Eddy, Evan Astle, Zachary Booth, Edward Balaban, Mykel J. Kochenderfer
Published: 2025-10-09
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.08812v2

Deep space missions face extreme communication delays and environmental uncertainty that prevent real-time ground operations. To support autonomous science operations in communication-constrained environments, we present a partially observable Markov decision process (POMDP) framework that adaptively sequences spacecraft science instruments. We integrate a Bayesian network into the POMDP observation space to manage the high-dimensional and uncertain measurements typical of astrobiology missions. This network compactly encodes dependencies among measurements and improves the interpretability and computational tractability of science data. Instrument operation policies are computed offline, allowing resource-aware plans to be generated and thoroughly validated prior to launch. We use the Enceladus Orbilander's proposed Life Detection Suite (LDS) as a case study, demonstrating how Bayesian network structure and reward shaping influence system performance. We compare our method against the mission's baseline Concept of Operations (ConOps), evaluating both misclassification rates and performance in off-nominal sample accumulation scenarios. Our approach reduces sample identification errors by nearly 40%

---

### TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference

Authors: Michal Podstawski
Published: 2025-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.08808v4

Graphs provide a universal framework for representing complex relational systems, and inferring their structural properties is a core challenge in graph analysis and reasoning. While large language models have recently demonstrated emerging abilities to perform symbolic and numerical reasoning, the potential of smaller, resource-efficient models in this context remains largely unexplored. This paper investigates whether compact transformer-based language models can infer graph-theoretic parameters directly from graph representations. To enable systematic evaluation, we introduce the TinyGraphEstimator dataset - a balanced collection of connected graphs generated from multiple random graph models and annotated with detailed structural metadata. We evaluate several small open models on their ability to predict key graph parameters such as density, clustering, and chromatic number. Furthermore, we apply lightweight fine-tuning using the Low-Rank Adaptation (LoRA) technique, achieving consistent improvements across all evaluated metrics. The results demonstrate that small language models possess non-trivial reasoning capacity over graph-structured data and can be effectively adapted for structural inference tasks through efficient parameter tuning.

---

### Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation

Authors: Zhenyu Zhao, Hongyi Jing, Xiawei Liu, Jiageng Mao, Abha Jha, Hanwen Yang, Rong Xue, Sergey Zakharov, Vitor Guizilini, Yue Wang
Published: 2025-10-09
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.08807v3

From loco-motion to dextrous manipulation, humanoid robots have made remarkable strides in demonstrating complex full-body capabilities. However, the majority of current robot learning datasets and benchmarks mainly focus on stationary robot arms, and the few existing humanoid datasets are either confined to fixed environments or limited in task diversity, often lacking human-humanoid interaction and lower-body locomotion. Moreover, there are a few standardized evaluation platforms for benchmarking learning-based policies on humanoid data. In this work, we present Humanoid Everyday, a large-scale and diverse humanoid manipulation dataset characterized by extensive task variety involving dextrous object manipulation, human-humanoid interaction, locomotion-integrated actions, and more. Leveraging a highly efficient human-supervised teleoperation pipeline, Humanoid Everyday aggregates high-quality multimodal sensory data, including RGB, depth, LiDAR, and tactile inputs, together with natural language annotations, comprising 10.3k trajectories and over 3 million frames of data across 260 tasks across 7 broad categories. In addition, we conduct an analysis of representative policy learning methods on our dataset, providing insights into their strengths and limitations across different task categories. For standardized evaluation, we introduce a cloud-based evaluation platform that allows researchers to seamlessly deploy their policies in our controlled setting and receive performance feedback. By releasing Humanoid Everyday along with our policy learning analysis and a standardized cloud-based evaluation platform, we intend to advance research in general-purpose humanoid manipulation and lay the groundwork for more capable and embodied robotic agents in real-world scenarios. Our dataset, data collection code, and cloud evaluation website are made publicly available on our project website.

---

### MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding

Authors: Siddeshwar Raghavan, Tanwi Mallick
Published: 2025-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08804v3

We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require algorithms that are rigorous, interconnected with deep domain knowledge, and incorporate domain-specific reasoning, as well as algorithm iteration without requiring I/O test cases. Many scientific problems also require a sequence of subproblems to be solved, leading to the final desired result. MOSAIC is designed as a training-free framework with specially designed agents to self-reflect, create the rationale, code, and debug within a student-teacher paradigm to address the challenges of scientific code generation. This design facilitates stepwise problem decomposition, targeted error correction, and, when combined with our Consolidated Context Window (CCW), mitigates LLM hallucinations when solving complex scientific tasks involving chained subproblems. We evaluate MOSAIC on scientific coding benchmarks and demonstrate that our specialized agentic framework outperforms existing approaches in terms of accuracy, robustness, and interpretability.

---

### Man-Made Heuristics Are Dead. Long Live Code Generators!

Authors: Rohit Dwivedula, Divyanshu Saxena, Aditya Akella, Swarat Chaudhuri, Daehyeok Kim
Published: 2025-10-09
Categories: cs.OS, cs.DC, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.08803v1

Policy design for various systems controllers has conventionally been a manual process, with domain experts carefully tailoring heuristics for the specific instance in which the policy will be deployed. In this paper, we re-imagine policy design via a novel automated search technique fueled by recent advances in generative models, specifically Large Language Model (LLM)-driven code generation. We outline the design and implementation of PolicySmith, a framework that applies LLMs to synthesize instance-optimal heuristics. We apply PolicySmith to two long-standing systems policies - web caching and congestion control, highlighting the opportunities unraveled by this LLM-driven heuristic search. For caching, PolicySmith discovers heuristics that outperform established baselines on standard open-source traces. For congestion control, we show that PolicySmith can generate safe policies that integrate directly into the Linux kernel.

---

### Edu-EmotionNet: Cross-Modality Attention Alignment with Temporal Feedback Loops

Authors: S M Rafiuddin
Published: 2025-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.08802v1

Understanding learner emotions in online education is critical for improving engagement and personalized instruction. While prior work in emotion recognition has explored multimodal fusion and temporal modeling, existing methods often rely on static fusion strategies and assume that modality inputs are consistently reliable, which is rarely the case in real-world learning environments. We introduce Edu-EmotionNet, a novel framework that jointly models temporal emotion evolution and modality reliability for robust affect recognition. Our model incorporates three key components: a Cross-Modality Attention Alignment (CMAA) module for dynamic cross-modal context sharing, a Modality Importance Estimator (MIE) that assigns confidence-based weights to each modality at every time step, and a Temporal Feedback Loop (TFL) that leverages previous predictions to enforce temporal consistency. Evaluated on educational subsets of IEMOCAP and MOSEI, re-annotated for confusion, curiosity, boredom, and frustration, Edu-EmotionNet achieves state-of-the-art performance and demonstrates strong robustness to missing or noisy modalities. Visualizations confirm its ability to capture emotional transitions and adaptively prioritize reliable signals, making it well suited for deployment in real-time learning systems

---

### Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective

Authors: Wangjie You, Xusheng Wang, Xing Wang, Wenxiang Jiao, Chao Feng, Juntao Li, Min Zhang
Published: 2025-10-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.08800v1

While Large Language Models (LLMs) have demonstrated advanced reasoning capabilities, their comprehensive evaluation in general Chinese-language contexts remains understudied. To bridge this gap, we propose Chinese Commonsense Multi-hop Reasoning (CCMOR), a novel benchmark designed to evaluate LLMs' ability to integrate Chinese-specific factual knowledge with multi-step logical reasoning. Specifically, we first construct a domain-balanced seed set from existing QA datasets, then develop an LLM-powered pipeline to generate multi-hop questions anchored on factual unit chains. To ensure the quality of resulting dataset, we implement a human-in-the-loop verification system, where domain experts systematically validate and refine the generated questions. Using CCMOR, we evaluate state-of-the-art LLMs, demonstrating persistent limitations in LLMs' ability to process long-tail knowledge and execute knowledge-intensive reasoning. Notably, retrieval-augmented generation substantially mitigates these knowledge gaps, yielding significant performance gains.

---

### SkipSR: Faster Super Resolution with Token Skipping

Authors: Rohan Choudhury, Shanchuan Lin, Jianyi Wang, Hao Chen, Qi Zhao, Feng Cheng, Lu Jiang, Kris Kitani, Laszlo A. Jeni
Published: 2025-10-09
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.08799v1

Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer videos. Our key insight is that many regions in video are inherently low-detail and gain little from refinement, yet current methods process all pixels uniformly. To take advantage of this, we propose SkipSR, a simple framework for accelerating video SR by identifying low-detail regions directly from low-resolution input, then skipping computation on them entirely, only super-resolving the areas that require refinement. This simple yet effective strategy preserves perceptual quality in both standard and one-step diffusion SR models while significantly reducing computation. In standard SR benchmarks, our method achieves up to 60% faster end-to-end latency than prior models on 720p videos with no perceptible loss in quality. Video demos are available at https://rccchoudhury.github.io/skipsr/

---

### Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models

Authors: S M Rafiuddin, Muntaha Nujat Khan
Published: 2025-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08798v1

Transformer attention scales quadratically with sequence length O(n^2), limiting long-context use. We propose Adaptive Retention, a probabilistic, layer-wise token selection mechanism that learns which representations to keep under a strict global budget M. Retention is modeled with Bernoulli gates trained via a Hard-Concrete/variational relaxation and enforced with a simple top-M rule at inference, making the method differentiable and drop-in for standard encoders. Across classification, extractive QA, and long-document summarization, keeping only 30-50% of tokens preserves >= 95% of full-model performance while cutting peak memory by ~35-45% and improving throughput by up to ~1.8x. This architecture-agnostic approach delivers practical long-context efficiency without modifying base attention or task heads.

---

### TAPAS: Datasets for Learning the Learning with Errors Problem

Authors: Eshika Saxena, Alberto Alfarano, François Charton, Emily Wenger, Kristin Lauter
Published: 2025-10-09
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2510.08797v2

AI-powered attacks on Learning with Errors (LWE), an important hard math problem in post-quantum cryptography, rival or outperform "classical" attacks on LWE under certain parameter settings. Despite the promise of this approach, a dearth of accessible data limits AI practitioners' ability to study and improve these attacks. Creating LWE data for AI model training is time- and compute-intensive and requires significant domain expertise. To fill this gap and accelerate AI research on LWE attacks, we propose the TAPAS datasets, a Toolkit for Analysis of Post-quantum cryptography using AI Systems. These datasets cover several LWE settings and can be used off-the-shelf by AI practitioners to prototype new approaches to cracking LWE. This work documents TAPAS dataset creation, establishes attack performance baselines, and lays out directions for future work.

---

### PO-CKAN:Physics Informed Deep Operator Kolmogorov Arnold Networks with Chunk Rational Structure

Authors: Junyi Wu, Guang Lin
Published: 2025-10-09
Categories: cs.LG, math-ph
arXiv: https://arxiv.org/abs/2510.08795v2

We propose PO-CKAN, a physics-informed deep operator framework based on Chunkwise Rational Kolmogorov--Arnold Networks (KANs), for approximating the solution operators of partial differential equations. This framework leverages a Deep Operator Network (DeepONet) architecture that incorporates Chunkwise Rational Kolmogorov-Arnold Network (CKAN) sub-networks for enhanced function approximation. The principles of Physics-Informed Neural Networks (PINNs) are integrated into the operator learning framework to enforce physical consistency. This design enables the efficient learning of physically consistent spatio-temporal solution operators and allows for rapid prediction for parametric time-dependent PDEs with varying inputs (e.g., parameters, initial/boundary conditions) after training. Validated on challenging benchmark problems, PO-CKAN demonstrates accurate operator learning with results closely matching high-fidelity solutions. PO-CKAN adopts a DeepONet-style branch--trunk architecture with its sub-networks instantiated as rational KAN modules, and enforces physical consistency via a PDE residual (PINN-style) loss. On Burgers' equation with $ν=0.01$, PO-CKAN reduces the mean relative $L^2$ error by approximately 48\% compared to PI-DeepONet, and achieves competitive accuracy on the Eikonal and diffusion--reaction benchmarks.

---