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

> Full-text markdown of papers #451–500 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/10
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/9.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/11.md)

### On Purely Private Covariance Estimation

Authors: Tommaso d'Orsi, Gleb Novikov
Published: 2025-10-30
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2510.26717v2

We present a simple perturbation mechanism for the release of $d$-dimensional covariance matrices $Σ$ under pure differential privacy. For large datasets with at least $n\geq d^2/\varepsilon$ elements, our mechanism recovers the provably optimal Frobenius norm error guarantees of \cite{nikolov2023private}, while simultaneously achieving best known error for all other $p$-Schatten norms, with $p\in (1,\infty)$. Our error is information-theoretically optimal for all $p\ge 2$, in particular, our mechanism is the first purely private covariance estimator that achieves optimal error in spectral norm. For small datasets $n< d^2/\varepsilon$, we further show that by projecting the output onto the nuclear norm ball of appropriate radius, our algorithm achieves the optimal Frobenius norm error $O(\sqrt{d\;\text{Tr}(Σ) /n})$, improving over the known bounds of $O(\sqrt{d/n})$ of \cite{nikolov2023private} and ${O}\big(d^{3/4}\sqrt{\text{Tr}(Σ)/n}\big)$ of \cite{dong2022differentially}.

---

### LSM-MS2: A Foundation Model Bridging Spectral Identification and Biological Interpretation

Authors: Gabriel Asher, Devesh Shah, Amy A. Caudy, Luke Ferro, Lea Amar, Ana S. H. Costa, Thomas Patton, Niall O'Connor, Jennifer M. Campbell, Jack Geremia
Published: 2025-10-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26715v1

A vast majority of mass spectrometry data remains uncharacterized, leaving much of its biological and chemical information untapped. Recent advances in machine learning have begun to address this gap, particularly for tasks such as spectral identification in tandem mass spectrometry data. Here, we present the latest generation of LSM-MS2, a large-scale deep learning foundation model trained on millions of spectra to learn a semantic chemical space. LSM-MS2 achieves state-of-the-art performance in spectral identification, improving on existing methods by 30% in accuracy of identifying challenging isomeric compounds, yielding 42% more correct identifications in complex biological samples, and maintaining robustness under low-concentration conditions. Furthermore, LSM-MS2 produces rich spectral embeddings that enable direct biological interpretation from minimal downstream data, successfully differentiating disease states and predicting clinical outcomes across diverse translational applications.

---

### On the importance of multiple training seeds for evaluating machine unlearning

Authors: Jamie Lanyon, Axel Finke, Petros Andreou, Georgina Cosma
Published: 2025-10-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.26714v5

Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining. Most practical unlearning algorithms are only approximate and their performance can only be assessed empirically. Common practice is to run unlearning algorithms multiple times independently (i.e., using multiple unlearning seeds) starting from the same trained model (i.e., using only a single training seed ). In image-classification experiments, this practice can give non-representative results as unlearning performance can be sensitive to the choice of training seed. This is particularly relevant for deterministic unlearning methods which always produce the same result when started from the same trained model. Further experiments on federated learning-to-rank, and large language models confirm that this issue extends beyond image classification. We also explain why increasing the number of unlearning seeds cannot generally compensate for the lack of multiple training seeds. Finally, we give guidance on how to select the number of training and unlearning seeds.

---

### An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning

Authors: Chuyan Chen, Chenyang Ma, Zhangxin Li, Yutong He, Yanjie Dong, Kun Yuan
Published: 2025-10-30
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2510.26709v3

Communication remains a central bottleneck in large-scale distributed machine learning, and gradient sparsification has emerged as a promising strategy to alleviate this challenge. However, existing gradient compressors face notable limitations: Rand-$K$ discards structural information and performs poorly in practice, while Top-$K$ preserves informative entries but loses the contraction property and requires costly All-Gather operations. In this paper, we propose ARC-Top-$K$, an {All-Reduce}-Compatible Top-$K$ compressor that aligns sparsity patterns across nodes using a lightweight sketch of the gradient, enabling index-free All-Reduce while preserving globally significant information. ARC-Top-$K$ is provably contractive and, when combined with momentum error feedback (EF21M), achieves linear speedup and sharper convergence rates than the original EF21M under standard assumptions. Empirically, ARC-Top-$K$ matches the accuracy of Top-$K$ while reducing wall-clock training time by up to 60.7\%, offering an efficient and scalable solution that combines the robustness of Rand-$K$ with the strong performance of Top-$K$.

---

### Value Drifts: Tracing Value Alignment During LLM Post-Training

Authors: Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Stańczak, Vered Shwartz, Siva Reddy
Published: 2025-10-30
Categories: cs.CL, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.26707v2

As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems. Therefore, studying the alignment of LLMs with human values has become a crucial field of inquiry. Prior work, however, mostly focuses on evaluating the alignment of fully trained models, overlooking the training dynamics by which models learn to express human values. In this work, we investigate how and at which stage value alignment arises during the course of a model's post-training. Our analysis disentangles the effects of post-training algorithms and datasets, measuring both the magnitude and time of value drifts during training. Experimenting with Llama-3 and Qwen-3 models of different sizes and popular supervised fine-tuning (SFT) and preference optimization datasets and algorithms, we find that the SFT phase generally establishes a model's values, and subsequent preference optimization rarely re-aligns these values. Furthermore, using a synthetic preference dataset that enables controlled manipulation of values, we find that different preference optimization algorithms lead to different value alignment outcomes, even when preference data is held constant. Our findings provide actionable insights into how values are learned during post-training and help to inform data curation, as well as the selection of models and algorithms for preference optimization to improve model alignment to human values.

---

### Budgeted Multiple-Expert Deferral

Authors: Giulia DeSalvo, Clara Mohri, Mehryar Mohri, Yutao Zhong
Published: 2025-10-30
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.26706v1

Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard training procedures for deferral algorithms typically require querying all experts for every training instance, an approach that becomes prohibitively expensive when expert queries incur significant computational or resource costs. This undermines the core goal of deferral: to limit unnecessary expert usage. To overcome this challenge, we introduce the budgeted deferral framework, which aims to train effective deferral algorithms while minimizing expert query costs during training. We propose new algorithms for both two-stage and single-stage multiple-expert deferral settings that selectively query only a subset of experts per training example. While inspired by active learning, our setting is fundamentally different: labels are already known, and the core challenge is to decide which experts to query in order to balance cost and predictive performance. We establish theoretical guarantees for both of our algorithms, including generalization bounds and label complexity analyses. Empirical results across several domains show that our algorithms substantially reduce training costs without sacrificing prediction accuracy, demonstrating the practical value of our budget-aware deferral algorithms.

---

### How Regularization Terms Make Invertible Neural Networks Bayesian Point Estimators

Authors: Nick Heilenkötter
Published: 2025-10-30
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.26704v1

Can regularization terms in the training of invertible neural networks lead to known Bayesian point estimators in reconstruction? Invertible networks are attractive for inverse problems due to their inherent stability and interpretability. Recently, optimization strategies for invertible neural networks that approximate either a reconstruction map or the forward operator have been studied from a Bayesian perspective, but each has limitations. To address this, we introduce and analyze two regularization terms for the network training that, upon inversion of the network, recover properties of classical Bayesian point estimators: while the first can be connected to the posterior mean, the second resembles the MAP estimator. Our theoretical analysis characterizes how each loss shapes both the learned forward operator and its inverse reconstruction map. Numerical experiments support our findings and demonstrate how these loss-term regularizers introduce data-dependence in a stable and interpretable way.

---

### ProstNFound+: A Prospective Study using Medical Foundation Models for Prostate Cancer Detection

Authors: Paul F. R. Wilson, Mohamed Harmanani, Minh Nguyen Nhat To, Amoon Jamzad, Tarek Elghareb, Zhuoxin Guo, Adam Kinnaird, Brian Wodlinger, Purang Abolmaesumi, Parvin Mousavi
Published: 2025-10-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.26703v1

Purpose: Medical foundation models (FMs) offer a path to build high-performance diagnostic systems. However, their application to prostate cancer (PCa) detection from micro-ultrasound (μUS) remains untested in clinical settings. We present ProstNFound+, an adaptation of FMs for PCa detection from μUS, along with its first prospective validation. Methods: ProstNFound+ incorporates a medical FM, adapter tuning, and a custom prompt encoder that embeds PCa-specific clinical biomarkers. The model generates a cancer heatmap and a risk score for clinically significant PCa. Following training on multi-center retrospective data, the model is prospectively evaluated on data acquired five years later from a new clinical site. Model predictions are benchmarked against standard clinical scoring protocols (PRI-MUS and PI-RADS). Results: ProstNFound+ shows strong generalization to the prospective data, with no performance degradation compared to retrospective evaluation. It aligns closely with clinical scores and produces interpretable heatmaps consistent with biopsy-confirmed lesions. Conclusion: The results highlight its potential for clinical deployment, offering a scalable and interpretable alternative to expert-driven protocols.

---

### Delegated Authorization for Agents Constrained to Semantic Task-to-Scope Matching

Authors: Majed El Helou, Chiara Troiani, Benjamin Ryder, Jean Diaconu, Hervé Muyal, Marcelo Yannuzzi
Published: 2025-10-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.26702v1

Authorizing Large Language Model driven agents to dynamically invoke tools and access protected resources introduces significant risks, since current methods for delegating authorization grant overly broad permissions and give access to tools allowing agents to operate beyond the intended task scope. We introduce and assess a delegated authorization model enabling authorization servers to semantically inspect access requests to protected resources, and issue access tokens constrained to the minimal set of scopes necessary for the agents' assigned tasks. Given the unavailability of datasets centered on delegated authorization flows, particularly including both semantically appropriate and inappropriate scope requests for a given task, we introduce ASTRA, a dataset and data generation pipeline for benchmarking semantic matching between tasks and scopes. Our experiments show both the potential and current limitations of model-based matching, particularly as the number of scopes needed for task completion increases. Our results highlight the need for further research into semantic matching techniques enabling intent-aware authorization for multi-agent and tool-augmented applications, including fine-grained control, such as Task-Based Access Control (TBAC).

---

### Assessment of the conditional exchangeability assumption in causal machine learning models: a simulation study

Authors: Gerard T. Portela, Jason B. Gibbons, Sebastian Schneeweiss, Rishi J. Desai
Published: 2025-10-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.26700v1

Observational studies developing causal machine learning (ML) models for the prediction of individualized treatment effects (ITEs) seldom conduct empirical evaluations to assess the conditional exchangeability assumption. We aimed to evaluate the performance of these models under conditional exchangeability violations and the utility of negative control outcomes (NCOs) as a diagnostic. We conducted a simulation study to examine confounding bias in ITE estimates generated by causal forest and X-learner models under varying conditions, including the presence or absence of true heterogeneity. We simulated data to reflect real-world scenarios with differing levels of confounding, sample size, and NCO confounding structures. We then estimated and compared subgroup-level treatment effects on the primary outcome and NCOs across settings with and without unmeasured confounding. When conditional exchangeability was violated, causal forest and X-learner models failed to recover true treatment effect heterogeneity and, in some cases, falsely indicated heterogeneity when there was none. NCOs successfully identified subgroups affected by unmeasured confounding. Even when NCOs did not perfectly satisfy its ideal assumptions, it remained informative, flagging potential bias in subgroup level estimates, though not always pinpointing the subgroup with the largest confounding. Violations of conditional exchangeability substantially limit the validity of ITE estimates from causal ML models in routinely collected observational data. NCOs serve a useful empirical diagnostic tool for detecting subgroup-specific unmeasured confounding and should be incorporated into causal ML workflows to support the credibility of individualized inference.

---

### The End of Manual Decoding: Towards Truly End-to-End Language Models

Authors: Zhichao Wang, Dongyang Ma, Xinting Huang, Deng Cai, Tian Lan, Jiahao Xu, Haitao Mi, Xiaoying Tang, Yan Wang
Published: 2025-10-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.26697v2

The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temperature and top-p. This paper introduces AutoDeco, a novel architecture that enables truly "end-to-end" generation by learning to control its own decoding strategy. We augment the standard transformer with lightweight heads that, at each step, dynamically predict context-specific temperature and top-p values alongside the next-token logits. This approach transforms decoding into a parametric, token-level process, allowing the model to self-regulate its sampling strategy within a single forward pass. Through extensive experiments on eight benchmarks, we demonstrate that AutoDeco not only significantly outperforms default decoding strategies but also achieves performance comparable to an oracle-tuned baseline derived from "hacking the test set"-a practical upper bound for any static method. Crucially, we uncover an emergent capability for instruction-based decoding control: the model learns to interpret natural language commands (e.g., "generate with low randomness") and adjusts its predicted temperature and top-p on a token-by-token basis, opening a new paradigm for steerable and interactive LLM decoding.

---

### The Impact and Outlook of 3D Gaussian Splatting

Authors: Bernhard Kerbl
Published: 2025-10-30
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.26694v1

Since its introduction, 3D Gaussian Splatting (3DGS) has rapidly transformed the landscape of 3D scene representations, inspiring an extensive body of associated research. Follow-up work includes analyses and contributions that enhance the efficiency, scalability, and real-world applicability of 3DGS. In this summary, we present an overview of several key directions that have emerged in the wake of 3DGS. We highlight advances enabling resource-efficient training and rendering, the evolution toward dynamic (or four-dimensional, 4DGS) representations, and deeper exploration of the mathematical foundations underlying its appearance modeling and rendering process. Furthermore, we examine efforts to bring 3DGS to mobile and virtual reality platforms, its extension to massive-scale environments, and recent progress toward near-instant radiance field reconstruction via feed-forward or distributed computation. Collectively, these developments illustrate how 3DGS has evolved from a breakthrough representation into a versatile and foundational tool for 3D vision and graphics.

---

### Kimi Linear: An Expressive, Efficient Attention Architecture

Authors: Kimi Team, Yu Zhang, Zongyu Lin, Xingcheng Yao, Jiaxi Hu, Fanqing Meng, Chengyin Liu, Xin Men, Songlin Yang, Zhiyuan Li, Wentao Li, Enzhe Lu et al.
Published: 2025-10-30
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.26692v2

We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL) scaling regimes. At its core lies Kimi Delta Attention (KDA), an expressive linear attention module that extends Gated DeltaNet with a finer-grained gating mechanism, enabling more effective use of limited finite-state RNN memory. Our bespoke chunkwise algorithm achieves high hardware efficiency through a specialized variant of the Diagonal-Plus-Low-Rank (DPLR) transition matrices, which substantially reduces computation compared to the general DPLR formulation while remaining more consistent with the classical delta rule. We pretrain a Kimi Linear model with 3B activated parameters and 48B total parameters, based on a layerwise hybrid of KDA and Multi-Head Latent Attention (MLA). Our experiments show that with an identical training recipe, Kimi Linear outperforms full MLA with a sizeable margin across all evaluated tasks, while reducing KV cache usage by up to 75% and achieving up to 6 times decoding throughput for a 1M context. These results demonstrate that Kimi Linear can be a drop-in replacement for full attention architectures with superior performance and efficiency, including tasks with longer input and output lengths. To support further research, we open-source the KDA kernel and vLLM implementations, and release the pre-trained and instruction-tuned model checkpoints.

---

### LoRAQuant: Mixed-Precision Quantization of LoRA to Ultra-Low Bits

Authors: Amir Reza Mirzaei, Yuqiao Wen, Yanshuai Cao, Lili Mou
Published: 2025-10-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26690v3

Low-Rank Adaptation (LoRA) has become a popular technique for parameter-efficient fine-tuning of large language models (LLMs). In many real-world scenarios, multiple adapters are loaded simultaneously to enable LLM customization for personalized user experiences or to support a diverse range of tasks. Although each adapter is lightweight in isolation, their aggregate cost becomes substantial at scale. To address this, we propose LoRAQuant, a mixed-precision post-training quantization method tailored to LoRA. Specifically, LoRAQuant reparameterizes each adapter by singular value decomposition (SVD) to concentrate the most important information into specific rows and columns. This makes it possible to quantize the important components to higher precision, while quantizing the rest to ultra-low bitwidth. We conduct comprehensive experiments with LLaMA 2-7B, LLaMA 2-13B, and Mistral 7B models on mathematical reasoning, coding, and summarization tasks. Results show that our LoRAQuant uses significantly lower bits than other quantization methods, but achieves comparable or even higher performance.

---

### FlowQ-Net: A Generative Framework for Automated Quantum Circuit Design

Authors: Jun Dai, Michael Rizvi-Martel, Guillaume Rabusseau
Published: 2025-10-30
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.26688v1

Designing efficient quantum circuits is a central bottleneck to exploring the potential of quantum computing, particularly for noisy intermediate-scale quantum (NISQ) devices, where circuit efficiency and resilience to errors are paramount. The search space of gate sequences grows combinatorially, and handcrafted templates often waste scarce qubit and depth budgets. We introduce \textsc{FlowQ-Net} (Flow-based Quantum design Network), a generative framework for automated quantum circuit synthesis based on Generative Flow Networks (GFlowNets). This framework learns a stochastic policy to construct circuits sequentially, sampling them in proportion to a flexible, user-defined reward function that can encode multiple design objectives such as performance, depth, and gate count. This approach uniquely enables the generation of a diverse ensemble of high-quality circuits, moving beyond single-solution optimization. We demonstrate the efficacy of \textsc{FlowQ-Net} through an extensive set of simulations. We apply our method to Variational Quantum Algorithm (VQA) ansatz design for molecular ground state estimation, Max-Cut, and image classification, key challenges in near-term quantum computing. Circuits designed by \textsc{FlowQ-Net} achieve significant improvements, yielding circuits that are 10$\times$-30$\times$ more compact in terms of parameters, gates, and depth compared to commonly used unitary baselines, without compromising accuracy. This trend holds even when subjected to error profiles from real-world quantum devices. Our results underline the potential of generative models as a general-purpose methodology for automated quantum circuit design, offering a promising path towards more efficient quantum algorithms and accelerating scientific discovery in the quantum domain.

---

### Process Integrated Computer Vision for Real-Time Failure Prediction in Steel Rolling Mill

Authors: Vaibhav Kurrey, Sivakalyan Pujari, Gagan Raj Gupta
Published: 2025-10-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.26684v1

We present a long-term deployment study of a machine vision-based anomaly detection system for failure prediction in a steel rolling mill. The system integrates industrial cameras to monitor equipment operation, alignment, and hot bar motion in real time along the process line. Live video streams are processed on a centralized video server using deep learning models, enabling early prediction of equipment failures and process interruptions, thereby reducing unplanned breakdown costs. Server-based inference minimizes the computational load on industrial process control systems (PLCs), supporting scalable deployment across production lines with minimal additional resources. By jointly analyzing sensor data from data acquisition systems and visual inputs, the system identifies the location and probable root causes of failures, providing actionable insights for proactive maintenance. This integrated approach enhances operational reliability, productivity, and profitability in industrial manufacturing environments.

---

### Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models

Authors: Mingchen Tu, Zhiqiang Liu, Juan Li, Liangyurui Liu, Junjie Wang, Lei Liang, Wen Zhang
Published: 2025-10-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.26683v2

Although Large Language Models (LLMs) perform exceptionally well in general domains, the problem of hallucinations poses significant risks in specialized fields such as healthcare and law, where high interpretability is essential. Existing fine-tuning methods depend heavily on large-scale professional datasets, which are often hard to obtain due to the privacy regulations. Moreover, existing self-evolution methods are primarily designed for general domains, which may struggle to adapt to knowledge-intensive domains due to the lack of knowledge constraints. In this paper, we propose an ontology rule guided method Evontree to enable self-evolution of LLMs in low-resource specialized domains. Specifically, Evontree first extracts domain ontology knowledge from raw models, then detects knowledge inconsistencies using two core ontology rules, and finally reinforces gap knowledge into model via self-distilled fine-tuning. Extensive evaluations on medical QA benchmarks using Llama3-8B-Instruct and Med42-V2 demonstrate the effectiveness of Evontree, which outperforms both the base models and strong baselines, achieving up to a 3.7\% improvement in accuracy. Detailed ablation studies further validate the robustness of our approach.

---

### Improving Classification of Occluded Objects through Scene Context

Authors: Courtney M. King, Daniel D. Leeds, Damian Lyons, George Kalaitzis
Published: 2025-10-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26681v1

The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to aid in object recognition in biological vision. In this work, we attempt to add robustness into existing Region Proposal Network-Deep Convolutional Neural Network (RPN-DCNN) object detection networks through two distinct scene-based information fusion techniques. We present one algorithm under each methodology: the first operates prior to prediction, selecting a custom object network to use based on the identified background scene, and the second operates after detection, fusing scene knowledge into initial object scores output by the RPN. We demonstrate our algorithms on challenging datasets featuring partial occlusions, which show overall improvement in both recall and precision against baseline methods. In addition, our experiments contrast multiple training methodologies for occlusion handling, finding that training on a combination of both occluded and unoccluded images demonstrates an improvement over the others. Our method is interpretable and can easily be adapted to other datasets, offering many future directions for research and practical applications.

---

### Tight Differentially Private PCA via Matrix Coherence

Authors: Tommaso d'Orsi, Gleb Novikov
Published: 2025-10-30
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2510.26679v1

We revisit the task of computing the span of the top $r$ singular vectors $u_1, \ldots, u_r$ of a matrix under differential privacy. We show that a simple and efficient algorithm -- based on singular value decomposition and standard perturbation mechanisms -- returns a private rank-$r$ approximation whose error depends only on the \emph{rank-$r$ coherence} of $u_1, \ldots, u_r$ and the spectral gap $σ_r - σ_{r+1}$. This resolves a question posed by Hardt and Roth~\cite{hardt2013beyond}. Our estimator outperforms the state of the art -- significantly so in some regimes. In particular, we show that in the dense setting, it achieves the same guarantees for single-spike PCA in the Wishart model as those attained by optimal non-private algorithms, whereas prior private algorithms failed to do so. In addition, we prove that (rank-$r$) coherence does not increase under Gaussian perturbations. This implies that any estimator based on the Gaussian mechanism -- including ours -- preserves the coherence of the input. We conjecture that similar behavior holds for other structured models, including planted problems in graphs. We also explore applications of coherence to graph problems. In particular, we present a differentially private algorithm for Max-Cut and other constraint satisfaction problems under low coherence assumptions.

---

### Action-Driven Processes for Continuous-Time Control

Authors: Ruimin He, Shaowei Lin
Published: 2025-10-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.26672v3

At the heart of reinforcement learning are actions -- decisions made in response to observations of the environment. Actions are equally fundamental in the modeling of stochastic processes, as they trigger discontinuous state transitions and enable the flow of information through large, complex systems. In this paper, we unify the perspectives of stochastic processes and reinforcement learning through action-driven processes, and illustrate their application to spiking neural networks. Leveraging ideas from control-as-inference, we show that minimizing the Kullback-Leibler divergence between a policy-driven true distribution and a reward-driven model distribution for a suitably defined action-driven process is equivalent to maximum entropy reinforcement learning.

---

### BRIQA: Balanced Reweighting in Image Quality Assessment of Pediatric Brain MRI

Authors: Alya Almsouti, Ainur Khamitova, Darya Taratynova, Mohammad Yaqub
Published: 2025-10-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.26661v1

Assessing the severity of artifacts in pediatric brain Magnetic Resonance Imaging (MRI) is critical for diagnostic accuracy, especially in low-field systems where the signal-to-noise ratio is reduced. Manual quality assessment is time-consuming and subjective, motivating the need for robust automated solutions. In this work, we propose BRIQA (Balanced Reweighting in Image Quality Assessment), which addresses class imbalance in artifact severity levels. BRIQA uses gradient-based loss reweighting to dynamically adjust per-class contributions and employs a rotating batching scheme to ensure consistent exposure to underrepresented classes. Through experiments, no single architecture performs best across all artifact types, emphasizing the importance of architectural diversity. The rotating batching configuration improves performance across metrics by promoting balanced learning when combined with cross-entropy loss. BRIQA improves average macro F1 score from 0.659 to 0.706, with notable gains in Noise (0.430), Zipper (0.098), Positioning (0.097), Contrast (0.217), Motion (0.022), and Banding (0.012) artifact severity classification. The code is available at https://github.com/BioMedIA-MBZUAI/BRIQA.

---

### The Era of Agentic Organization: Learning to Organize with Language Models

Authors: Zewen Chi, Li Dong, Qingxiu Dong, Yaru Hao, Xun Wu, Shaohan Huang, Furu Wei
Published: 2025-10-30
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.26658v1

We envision a new era of AI, termed agentic organization, where agents solve complex problems by working collaboratively and concurrently, enabling outcomes beyond individual intelligence. To realize this vision, we introduce asynchronous thinking (AsyncThink) as a new paradigm of reasoning with large language models, which organizes the internal thinking process into concurrently executable structures. Specifically, we propose a thinking protocol where an organizer dynamically assigns sub-queries to workers, merges intermediate knowledge, and produces coherent solutions. More importantly, the thinking structure in this protocol can be further optimized through reinforcement learning. Experiments demonstrate that AsyncThink achieves 28% lower inference latency compared to parallel thinking while improving accuracy on mathematical reasoning. Moreover, AsyncThink generalizes its learned asynchronous thinking capabilities, effectively tackling unseen tasks without additional training.

---

### Posterior-driven Heuristic Support Adaptation in a Probabilistic Treatment of Real2Sim2Real for Vision-Driven Deformable Linear Object Manipulation

Authors: Georgios Kamaras, Craig Innes, Subramanian Ramamoorthy
Published: 2025-10-30
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.26656v4

Likelihood-free inference (LFI) enables system identification in complex tasks via black-box modelling, abstracting nonlinearity and stochasticity, and infers a domain distribution for adapting agents to parametric deployment conditions. LFI assumes an arbitrary support for sampling, which remains fixed as the initial generic prior is refined to increasingly descriptive posteriors. Misspecified support can therefore yield suboptimal yet overconfident posteriors. We address this issue by using the posterior of an inference step to guide the adaptation of the support using three illustrative heuristics: EDGE, MODE, and CENTRE. Each heuristic interprets the updated belief and enables support adaptation alongside posterior inference. For illustrative purposes, we first study misspecified support in LFI and evaluate the utility of our heuristics using stochastic dynamical benchmarks. We then evaluate posterior-driven heuristic support adaptation for parameter inference and policy learning in a dynamic deformable linear object (DLO) manipulation task. Inference results in a finer length and stiffness classification for a parametric set of DLOs. When the resulting posteriors are used as domain distributions for sim-based policy learning, they lead to more robust object-centric agent performance.

---

### Towards Reliable Sea Ice Drift Estimation in the Arctic Deep Learning Optical Flow on RADARSAT-2

Authors: Daniela Martin, Joseph Gallego
Published: 2025-10-30
Categories: cs.CV, physics.geo-ph
arXiv: https://arxiv.org/abs/2510.26653v1

Accurate estimation of sea ice drift is critical for Arctic navigation, climate research, and operational forecasting. While optical flow, a computer vision technique for estimating pixel wise motion between consecutive images, has advanced rapidly in computer vision, its applicability to geophysical problems and to satellite SAR imagery remains underexplored. Classical optical flow methods rely on mathematical models and strong assumptions about motion, which limit their accuracy in complex scenarios. Recent deep learning based approaches have substantially improved performance and are now the standard in computer vision, motivating their application to sea ice drift estimation. We present the first large scale benchmark of 48 deep learning optical flow models on RADARSAT 2 ScanSAR sea ice imagery, evaluated with endpoint error (EPE) and Fl all metrics against GNSS tracked buoys. Several models achieve sub kilometer accuracy (EPE 6 to 8 pixels, 300 to 400 m), a small error relative to the spatial scales of sea ice motion and typical navigation requirements in the Arctic. Our results demonstrate that the models are capable of capturing consistent regional drift patterns and that recent deep learning based optical flow methods, which have substantially improved motion estimation accuracy compared to classical methods, can be effectively transferred to polar remote sensing. Optical flow produces spatially continuous drift fields, providing motion estimates for every image pixel rather than at sparse buoy locations, offering new opportunities for navigation and climate modeling.

---

### Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments

Authors: Xiaoyi He, Danggui Chen, Zhenshuo Zhang, Zimeng Bai
Published: 2025-10-30
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.26646v1

This paper presents a hierarchical path-planning and control framework that combines a high-level Deep Q-Network (DQN) for discrete sub-goal selection with a low-level Twin Delayed Deep Deterministic Policy Gradient (TD3) controller for continuous actuation. The high-level module selects behaviors and sub-goals; the low-level module executes smooth velocity commands. We design a practical reward shaping scheme (direction, distance, obstacle avoidance, action smoothness, collision penalty, time penalty, and progress), together with a LiDAR-based safety gate that prevents unsafe motions. The system is implemented in ROS + Gazebo (TurtleBot3) and evaluated with PathBench metrics, including success rate, collision rate, path efficiency, and re-planning efficiency, in dynamic and partially observable environments. Experiments show improved success rate and sample efficiency over single-algorithm baselines (DQN or TD3 alone) and rule-based planners, with better generalization to unseen obstacle configurations and reduced abrupt control changes. Code and evaluation scripts are available at the project repository.

---

### Curly Flow Matching for Learning Non-gradient Field Dynamics

Authors: Katarina Petrović, Lazar Atanackovic, Viggo Moro, Kacper Kapuśniak, İsmail İlkan Ceylan, Michael Bronstein, Avishek Joey Bose, Alexander Tong
Published: 2025-10-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26645v1

Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural sciences. Such models rely on key assumptions about the underlying process in order to enable faithful learning of governing dynamics that mimic the actual system behavior. The de facto assumption in current approaches relies on the principle of least action that results in gradient field dynamics and leads to trajectories minimizing an energy functional between two probability measures. However, many real-world systems, such as cell cycles in single-cell RNA, are known to exhibit non-gradient, periodic behavior, which fundamentally cannot be captured by current state-of-the-art methods such as flow and bridge matching. In this paper, we introduce Curly Flow Matching (Curly-FM), a novel approach that is capable of learning non-gradient field dynamics by designing and solving a Schrödinger bridge problem with a non-zero drift reference process -- in stark contrast to typical zero-drift reference processes -- which is constructed using inferred velocities in addition to population snapshot data. We showcase Curly-FM by solving the trajectory inference problems for single cells, computational fluid dynamics, and ocean currents with approximate velocities. We demonstrate that Curly-FM can learn trajectories that better match both the reference process and population marginals. Curly-FM expands flow matching models beyond the modeling of populations and towards the modeling of known periodic behavior in physical systems. Our code repository is accessible at: https://github.com/kpetrovicc/curly-flow-matching.git

---

### MSAD: A Deep Dive into Model Selection for Time series Anomaly Detection

Authors: Emmanouil Sylligardos, John Paparrizos, Themis Palpanas, Pierre Senellart, Paul Boniol
Published: 2025-10-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26643v2

Anomaly detection is a fundamental task for time series analytics with important implications for the downstream performance of many applications. Despite increasing academic interest and the large number of methods proposed in the literature, recent benchmarks and evaluation studies demonstrated that no overall best anomaly detection methods exist when applied to very heterogeneous time series datasets. Therefore, the only scalable and viable solution to solve anomaly detection over very different time series collected from diverse domains is to propose a model selection method that will select, based on time series characteristics, the best anomaly detection methods to run. Existing AutoML solutions are, unfortunately, not directly applicable to time series anomaly detection, and no evaluation of time series-based approaches for model selection exists. Towards that direction, this paper studies the performance of time series classification methods used as model selection for anomaly detection. In total, we evaluate 234 model configurations derived from 16 base classifiers across more than 1980 time series, and we propose the first extensive experimental evaluation of time series classification as model selection for anomaly detection. Our results demonstrate that model selection methods outperform every single anomaly detection method while being in the same order of magnitude regarding execution time. This evaluation is the first step to demonstrate the accuracy and efficiency of time series classification algorithms for anomaly detection, and represents a strong baseline that can then be used to guide the model selection step in general AutoML pipelines. Preprint version of an article accepted at the VLDB Journal.

---

### All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles

Authors: Sayed Pedram Haeri Boroujeni, Niloufar Mehrabi, Hazim Alzorgan, Mahlagha Fazeli, Abolfazl Razi
Published: 2025-10-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26641v4

Autonomous Vehicles (AVs) are transforming the future of transportation through advances in intelligent perception, decision-making, and control systems. However, their success is tied to one core capability, reliable object detection in complex and multimodal environments. While recent breakthroughs in Computer Vision (CV) and Artificial Intelligence (AI) have driven remarkable progress, the field still faces a critical challenge as knowledge remains fragmented across multimodal perception, contextual reasoning, and cooperative intelligence. This survey bridges that gap by delivering a forward-looking analysis of object detection in AVs, emphasizing emerging paradigms such as Vision-Language Models (VLMs), Large Language Models (LLMs), and Generative AI rather than re-examining outdated techniques. We begin by systematically reviewing the fundamental spectrum of AV sensors (camera, ultrasonic, LiDAR, and Radar) and their fusion strategies, highlighting not only their capabilities and limitations in dynamic driving environments but also their potential to integrate with recent advances in LLM/VLM-driven perception frameworks. Next, we introduce a structured categorization of AV datasets that moves beyond simple collections, positioning ego-vehicle, infrastructure-based, and cooperative datasets (e.g., V2V, V2I, V2X, I2I), followed by a cross-analysis of data structures and characteristics. Ultimately, we analyze cutting-edge detection methodologies, ranging from 2D and 3D pipelines to hybrid sensor fusion, with particular attention to emerging transformer-driven approaches powered by Vision Transformers (ViTs), Large and Small Language Models (SLMs), and VLMs. By synthesizing these perspectives, our survey delivers a clear roadmap of current capabilities, open challenges, and future opportunities.

---

### SAMRI: Segment Any MRI

Authors: Zhao Wang, Wei Dai, Thuy Thanh Dao, Steffen Bollmann, Hongfu Sun, Craig Engstrom, Shekhar S. Chandra
Published: 2025-10-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.26635v3

Summary: SAMRI is an MRI-specialized adaptation of the Segment Anything Model achieving superior whole-body MRI segmentation, particularly for small and clinically critical structures, through box and point prompts for rapid annotation. Purpose: Existing SAM adaptations treat MRI as a generic modality, overlooking variable tissue contrast, intensity inhomogeneity, and clinically important small structures. We propose an MRI-specialized foundation model with strong whole-body segmentation and zero-shot generalization for direct use on any MRI annotation task. Methods: SAMRI fine-tunes only the mask decoder of SAM (ViT-B/16), keeping encoders frozen to preserve pretrained representations and eliminate redundant passes-reducing training time by 94%, trainable parameters by 96%, and FLOPs by ~99% versus full-model retraining. Training used 1.1 million 2D slice-mask pairs from 30 datasets spanning 47 targets, T1/T2/FLAIR/DWI contrasts, and whole-body anatomy, with focal-Dice loss and bounding-box (with optional point) prompts. Sizes were stratified by mask area (small: <0.5%; medium: 0.5-3.5%; large: >3.5%), and significance assessed by the Wilcoxon signed-rank test. Results: SAMRI with box+point prompts achieved mean DSC 0.87 +/- 0.11 across 47 targets, outperforming MedSAM (0.74 +/- 0.24) by 17.6% (p < 0.05), with largest gains for small (+42.4%) and medium (+26.9%) structures. On six zero-shot datasets, SAMRI achieved mean DSC 0.85, outperforming baselines. Inference requires only ~4.5 GB VRAM through an interactive interface on standard hardware. Conclusion: Decoder-only fine-tuning on a large, MRI-specific corpus delivers superior whole-body segmentation with strong zero-shot generalization, particularly for small and clinically salient structures. Public code, pretrained models, and an interactive interface make SAMRI deployable for MRI segmentation research and clinical workflows.

---

### Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization

Authors: Colin Doumont, Victor Picheny, Viacheslav Borovitskiy, Henry Moss
Published: 2025-10-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26633v1

Bayesian Optimization (BO) has the potential to solve various combinatorial tasks, ranging from materials science to neural architecture search. However, BO requires specialized kernels to effectively model combinatorial domains. Recent efforts have introduced several combinatorial kernels, but the relationships among them are not well understood. To bridge this gap, we develop a unifying framework based on heat kernels, which we derive in a systematic way and express as simple closed-form expressions. Using this framework, we prove that many successful combinatorial kernels are either related or equivalent to heat kernels, and validate this theoretical claim in our experiments. Moreover, our analysis confirms and extends the results presented in Bounce: certain algorithms' performance decreases substantially when the unknown optima of the function do not have a certain structure. In contrast, heat kernels are not sensitive to the location of the optima. Lastly, we show that a fast and simple pipeline, relying on heat kernels, is able to achieve state-of-the-art results, matching or even outperforming certain slow or complex algorithms.

---

### PT-DETR: Small Target Detection Based on Partially-Aware Detail Focus

Authors: Bingcong Huo, Zhiming Wang
Published: 2025-10-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26630v1

To address the challenges in UAV object detection, such as complex backgrounds, severe occlusion, dense small objects, and varying lighting conditions,this paper proposes PT-DETR based on RT-DETR, a novel detection algorithm specifically designed for small objects in UAV imagery. In the backbone network, we introduce the Partially-Aware Detail Focus (PADF) Module to enhance feature extraction for small objects. Additionally,we design the Median-Frequency Feature Fusion (MFFF) module,which effectively improves the model's ability to capture small-object details and contextual information. Furthermore,we incorporate Focaler-SIoU to strengthen the model's bounding box matching capability and increase its sensitivity to small-object features, thereby further enhancing detection accuracy and robustness. Compared with RT-DETR, our PT-DETR achieves mAP improvements of 1.6% and 1.7% on the VisDrone2019 dataset with lower computational complexity and fewer parameters, demonstrating its robustness and feasibility for small-object detection tasks.

---

### Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model

Authors: Biao Zhang, Yong Cheng, Siamak Shakeri, Xinyi Wang, Min Ma, Orhan Firat
Published: 2025-10-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.26622v1

Recent large language model (LLM) research has undergone an architectural shift from encoder-decoder modeling to nowadays the dominant decoder-only modeling. This rapid transition, however, comes without a rigorous comparative analysis especially \textit{from the scaling perspective}, raising concerns that the potential of encoder-decoder models may have been overlooked. To fill this gap, we revisit encoder-decoder LLM (RedLLM), enhancing it with recent recipes from decoder-only LLM (DecLLM). We conduct a comprehensive comparison between RedLLM, pretrained with prefix language modeling (LM), and DecLLM, pretrained with causal LM, at different model scales, ranging from $\sim$150M to $\sim$8B. Using RedPajama V1 (1.6T tokens) for pretraining and FLAN for instruction tuning, our experiments show that RedLLM produces compelling scaling properties and surprisingly strong performance. While DecLLM is overall more compute-optimal during pretraining, RedLLM demonstrates comparable scaling and context length extrapolation capabilities. After instruction tuning, RedLLM achieves comparable and even better results on various downstream tasks while enjoying substantially better inference efficiency. We hope our findings could inspire more efforts on re-examining RedLLM, unlocking its potential for developing powerful and efficient LLMs.

---

### Aeolus: A Multi-structural Flight Delay Dataset

Authors: Lin Xu, Xinyun Yuan, Yuxuan Liang, Suwan Yin, Yuankai Wu
Published: 2025-10-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.26616v2

We introduce Aeolus, a large-scale Multi-modal Flight Delay Dataset designed to advance research on flight delay prediction and support the development of foundation models for tabular data. Existing datasets in this domain are typically limited to flat tabular structures and fail to capture the spatiotemporal dynamics inherent in delay propagation. Aeolus addresses this limitation by providing three aligned modalities: (i) a tabular dataset with rich operational, meteorological, and airportlevel features for over 50 million flights; (ii) a flight chain module that models delay propagation along sequential flight legs, capturing upstream and downstream dependencies; and (iii) a flight network graph that encodes shared aircraft, crew, and airport resource connections, enabling cross-flight relational reasoning. The dataset is carefully constructed with temporal splits, comprehensive features, and strict leakage prevention to support realistic and reproducible machine learning evaluation. Aeolus supports a broad range of tasks, including regression, classification, temporal structure modeling, and graph learning, serving as a unified benchmark across tabular, sequential, and graph modalities. We release baseline experiments and preprocessing tools to facilitate adoption. Aeolus fills a key gap for both domain-specific modeling and general-purpose structured data research.Our source code and data can be accessed at https://github.com/Flnny/Delay-data

---

### SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding

Authors: Yiqiao Jin, Rachneet Kaur, Zhen Zeng, Sumitra Ganesh, Srijan Kumar
Published: 2025-10-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.26615v4

Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While multimodal large language models (MLLMs) offer opportunities in document understanding, current systems struggle with complex, multi-page visual documents, particularly in fine-grained reasoning over elements and pages. We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents, especially slide decks. SlideAgent employs specialized agents and decomposes reasoning into three specialized levels--global, page, and element--to construct a structured, query-agnostic representation that captures both overarching themes and detailed visual or textual cues. During inference, SlideAgent selectively activates specialized agents for multi-level reasoning and integrates their outputs into coherent, context-aware answers. Extensive experiments show that SlideAgent significantly improves accuracy over both proprietary (+7.9%) and open-source models (+9.8%).

---

### Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras

Authors: Christoffer Koo Øhrstrøm, Ronja Güldenring, Lazaros Nalpantidis
Published: 2025-10-30
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.26614v2

We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous and spatially sparse events, our goal is to discover an event representation that preserves these properties. Prior works have represented events as frames or as voxels. However, while these representations yield high accuracy, both frames and voxels are synchronous and decrease the spatial sparsity. Spiking Patches gives the means to preserve the unique properties of event cameras and we show in our experiments that this comes without sacrificing accuracy. We evaluate our tokenizer using a GNN, PCN, and a Transformer on gesture recognition and object detection. Tokens from Spiking Patches yield inference times that are up to 3.4x faster than voxel-based tokens and up to 10.4x faster than frames. We achieve this while matching their accuracy and even surpassing in some cases with absolute improvements up to 3.8 for gesture recognition and up to 1.4 for object detection. Thus, tokenization constitutes a novel direction in event-based vision and marks a step towards methods that preserve the properties of event cameras.

---

### FARM: Fine-Tuning Geospatial Foundation Models for Intra-Field Crop Yield Regression

Authors: Shayan Nejadshamsi, Yuanyuan Zhang, Shadi Zaki, Brock Porth, Lysa Porth, Vahab Khoshdel
Published: 2025-10-30
Categories: cs.CV, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2510.26609v2

Accurate and timely crop yield prediction is crucial for global food security and modern agricultural management. Traditional methods often lack the scalability and granularity required for precision farming. This paper introduces FARM: Fine-tuning Agricultural Regression Models, a deep learning framework designed for high-resolution, intra-field canola yield prediction. FARM leverages a pre-trained, large-scale geospatial foundation model (Prithvi-EO-2.0-600M) and adapts it for a continuous regression task, transforming multi-temporal satellite imagery into dense, pixel-level (30 m) yield maps. Evaluated on a comprehensive dataset from the Canadian Prairies, FARM achieves a Root Mean Squared Error (RMSE) of 0.44 and an R^2 of 0.81. Using an independent high-resolution yield monitor dataset, we further show that fine-tuning FARM on limited ground-truth labels outperforms training the same architecture from scratch, confirming the benefit of pre-training on large, upsampled county-level data for data-scarce precision agriculture. These results represent improvement over baseline architectures like 3D-CNN and DeepYield, which highlight the effectiveness of fine-tuning foundation models for specialized agricultural applications. By providing a continuous, high-resolution output, FARM offers a more actionable tool for precision agriculture than conventional classification or county-level aggregation methods. This work validates a novel approach that bridges the gap between large-scale Earth observation and on-farm decision-making, offering a scalable solution for detailed agricultural monitoring.

---

### Wasserstein Regression as a Variational Approximation of Probabilistic Trajectories through the Bernstein Basis

Authors: Maksim Maslov, Alexander Kugaevskikh, Matthew Ivanov
Published: 2025-10-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.26607v1

This paper considers the problem of regression over distributions, which is becoming increasingly important in machine learning. Existing approaches often ignore the geometry of the probability space or are computationally expensive. To overcome these limitations, a new method is proposed that combines the parameterization of probability trajectories using a Bernstein basis and the minimization of the Wasserstein distance between distributions. The key idea is to model a conditional distribution as a smooth probability trajectory defined by a weighted sum of Gaussian components whose parameters -- the mean and covariance -- are functions of the input variable constructed using Bernstein polynomials. The loss function is the averaged squared Wasserstein distance between the predicted Gaussian distributions and the empirical data, which takes into account the geometry of the distributions. An autodiff-based optimization method is used to train the model. Experiments on synthetic datasets that include complex trajectories demonstrated that the proposed method provides competitive approximation quality in terms of the Wasserstein distance, Energy Distance, and RMSE metrics, especially in cases of pronounced nonlinearity. The model demonstrates trajectory smoothness that is better than or comparable to alternatives and robustness to changes in data structure, while maintaining high interpretability due to explicit parameterization via control points. The developed approach represents a balanced solution that combines geometric accuracy, computational practicality, and interpretability. Prospects for further research include extending the method to non-Gaussian distributions, applying entropy regularization to speed up computations, and adapting the approach to working with high-dimensional data for approximating surfaces and more complex structures.

---

### Normative Reasoning in Large Language Models: A Comparative Benchmark from Logical and Modal Perspectives

Authors: Kentaro Ozeki, Risako Ando, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, Mitsuhiro Okada
Published: 2025-10-30
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.26606v2

Normative reasoning is a type of reasoning that involves normative or deontic modality, such as obligation and permission. While large language models (LLMs) have demonstrated remarkable performance across various reasoning tasks, their ability to handle normative reasoning remains underexplored. In this paper, we systematically evaluate LLMs' reasoning capabilities in the normative domain from both logical and modal perspectives. Specifically, to assess how well LLMs reason with normative modals, we make a comparison between their reasoning with normative modals and their reasoning with epistemic modals, which share a common formal structure. To this end, we introduce a new dataset covering a wide range of formal patterns of reasoning in both normative and epistemic domains, while also incorporating non-formal cognitive factors that influence human reasoning. Our results indicate that, although LLMs generally adhere to valid reasoning patterns, they exhibit notable inconsistencies in specific types of normative reasoning and display cognitive biases similar to those observed in psychological studies of human reasoning. These findings highlight challenges in achieving logical consistency in LLMs' normative reasoning and provide insights for enhancing their reliability. All data and code are released publicly at https://github.com/kmineshima/NeuBAROCO.

---

### Agentic AI Home Energy Management System: A Large Language Model Framework for Residential Load Scheduling

Authors: Reda El Makroum, Sebastian Zwickl-Bernhard, Lukas Kranzl
Published: 2025-10-30
Categories: cs.AI, cs.MA, eess.SY
arXiv: https://arxiv.org/abs/2510.26603v1

The electricity sector transition requires substantial increases in residential demand response capacity, yet Home Energy Management Systems (HEMS) adoption remains limited by user interaction barriers requiring translation of everyday preferences into technical parameters. While large language models have been applied to energy systems as code generators and parameter extractors, no existing implementation deploys LLMs as autonomous coordinators managing the complete workflow from natural language input to multi-appliance scheduling. This paper presents an agentic AI HEMS where LLMs autonomously coordinate multi-appliance scheduling from natural language requests to device control, achieving optimal scheduling without example demonstrations. A hierarchical architecture combining one orchestrator with three specialist agents uses the ReAct pattern for iterative reasoning, enabling dynamic coordination without hardcoded workflows while integrating Google Calendar for context-aware deadline extraction. Evaluation across three open-source models using real Austrian day-ahead electricity prices reveals substantial capability differences. Llama-3.3-70B successfully coordinates all appliances across all scenarios to match cost-optimal benchmarks computed via mixed-integer linear programming, while other models achieve perfect single-appliance performance but struggle to coordinate all appliances simultaneously. Progressive prompt engineering experiments demonstrate that analytical query handling without explicit guidance remains unreliable despite models' general reasoning capabilities. We open-source the complete system including orchestration logic, agent prompts, tools, and web interfaces to enable reproducibility, extension, and future research.

---

### ResMatching: Noise-Resilient Computational Super-Resolution via Guided Conditional Flow Matching

Authors: Anirban Ray, Vera Galinova, Florian Jug
Published: 2025-10-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.26601v3

Computational Super-Resolution (CSR) in fluorescence microscopy has, despite being an ill-posed problem, a long history. At its very core, CSR is about finding a prior that can be used to extrapolate frequencies in a micrograph that have never been imaged by the image-generating microscope. It stands to reason that, with the advent of better data-driven machine learning techniques, stronger prior can be learned and hence CSR can lead to better results. Here, we present ResMatching, a novel CSR method that uses guided conditional flow matching to learn such improved data-priors. We evaluate ResMatching on 4 diverse biological structures from the BioSR dataset and compare its results against 7 baselines. ResMatching consistently achieves competitive results, demonstrating in all cases the best trade-off between data fidelity and perceptual realism. We observe that CSR using ResMatching is particularly effective in cases where a strong prior is hard to learn, e.g. when the given low-resolution images contain a lot of noise. Additionally, we show that ResMatching can be used to sample from an implicitly learned posterior distribution and that this distribution is calibrated for all tested use-cases, enabling our method to deliver a pixel-wise data-uncertainty term that can guide future users to reject uncertain predictions.

---

### Hybrid Physical-Neural Simulator for Fast Cosmological Hydrodynamics

Authors: Arne Thomsen, Tilman Tröster, François Lanusse
Published: 2025-10-30
Categories: astro-ph.CO, cs.LG
arXiv: https://arxiv.org/abs/2510.26593v1

Cosmological field-level inference requires differentiable forward models that solve the challenging dynamics of gas and dark matter under hydrodynamics and gravity. We propose a hybrid approach where gravitational forces are computed using a differentiable particle-mesh solver, while the hydrodynamics are parametrized by a neural network that maps local quantities to an effective pressure field. We demonstrate that our method improves upon alternative approaches, such as an Enthalpy Gradient Descent baseline, both at the field and summary-statistic level. The approach is furthermore highly data efficient, with a single reference simulation of cosmological structure formation being sufficient to constrain the neural pressure model. This opens the door for future applications where the model is fit directly to observational data, rather than a training set of simulations.

---

### Physics-Informed Mixture Models and Surrogate Models for Precision Additive Manufacturing

Authors: Sebastian Basterrech, Shuo Shan, Debabrata Adhikari, Sankhya Mohanty
Published: 2025-10-30
Categories: math-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.26586v2

In this study, we leverage a mixture model learning approach to identify defects in laser-based Additive Manufacturing (AM) processes. By incorporating physics based principles, we also ensure that the model is sensitive to meaningful physical parameter variations. The empirical evaluation was conducted by analyzing real-world data from two AM processes: Directed Energy Deposition and Laser Powder Bed Fusion. In addition, we also studied the performance of the developed framework over public datasets with different alloy type and experimental parameter information. The results show the potential of physics-guided mixture models to examine the underlying physical behavior of an AM system.

---

### Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

Authors: Fulin Lin, Shaowen Chen, Ruishan Fang, Hongwei Wang, Tao Lin
Published: 2025-10-30
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2510.26585v2

While Multi-Agent Systems (MAS) excel at complex tasks, their growing autonomy with operational complexity often leads to critical inefficiencies, such as excessive token consumption and failures arising from misinformation. Existing methods primarily focus on post-hoc failure attribution, lacking proactive, real-time interventions to enhance robustness and efficiency. To this end, we introduce SupervisorAgent, a lightweight and modular framework for runtime, adaptive supervision that operates without altering the base agent's architecture. Triggered by an LLM-free adaptive filter, SupervisorAgent intervenes at critical junctures to proactively correct errors, guide inefficient behaviors, and purify observations. On the challenging GAIA benchmark, SupervisorAgent reduces the token consumption of the Smolagent framework by an average of 29.68% without compromising its success rate. Extensive experiments across five additional benchmarks (math reasoning, code generation, and question answering) and various SoTA foundation models validate the broad applicability and robustness of our approach.

---

### Emu3.5: Native Multimodal Models are World Learners

Authors: Yufeng Cui, Honghao Chen, Haoge Deng, Xu Huang, Xinghang Li, Jirong Liu, Yang Liu, Zhuoyan Luo, Jinsheng Wang, Wenxuan Wang, Yueze Wang, Chengyuan Wang et al.
Published: 2025-10-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26583v1

We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.

---

### CATCH: A Modular Cross-domain Adaptive Template with Hook

Authors: Xinjin Li, Yulie Lu, Jinghan Cao, Yu Ma, Zhenglin Li, Yeyang Zhou
Published: 2025-10-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26582v1

Recent advances in Visual Question Answering (VQA) have demonstrated impressive performance in natural image domains, with models like LLaVA leveraging large language models (LLMs) for open-ended reasoning. However, their generalization degrades significantly when transferred to out-of-domain scenarios such as remote sensing, medical imaging, or math diagrams, due to large distributional shifts and the lack of effective domain adaptation mechanisms. Existing approaches typically rely on per-domain fine-tuning or bespoke pipelines, which are costly, inflexible, and not scalable across diverse tasks. In this paper, we propose CATCH, a plug-and-play framework for cross-domain adaptation that improves the generalization of VQA models while requiring minimal changes to their core architecture. Our key idea is to decouple visual and linguistic adaptation by introducing two lightweight modules: a domain classifier to identify the input image type, and a dual adapter mechanism comprising a Prompt Adapter for language modulation and a Visual Adapter for vision feature adjustment. Both modules are dynamically injected via a unified hook interface, requiring no retraining of the backbone model. Experimental results across four domain-specific VQA benchmarks demonstrate that our framework achieves consistent performance gains without retraining the backbone model, including +2.3 BLEU on MathVQA, +2.6 VQA on MedVQA-RAD, and +3.1 ROUGE on ChartQA. These results highlight that CATCH provides a scalable and extensible approach to multi-domain VQA, enabling practical deployment across diverse application domains.

---

### Dynamic Context-Aware Scene Reasoning Using Vision-Language Alignment in Zero-Shot Real-World Scenarios

Authors: Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi
Published: 2025-10-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.26580v1

In real-world environments, AI systems often face unfamiliar scenarios without labeled data, creating a major challenge for conventional scene understanding models. The inability to generalize across unseen contexts limits the deployment of vision-based applications in dynamic, unstructured settings. This work introduces a Dynamic Context-Aware Scene Reasoning framework that leverages Vision-Language Alignment to address zero-shot real-world scenarios. The goal is to enable intelligent systems to infer and adapt to new environments without prior task-specific training. The proposed approach integrates pre-trained vision transformers and large language models to align visual semantics with natural language descriptions, enhancing contextual comprehension. A dynamic reasoning module refines predictions by combining global scene cues and object-level interactions guided by linguistic priors. Extensive experiments on zero-shot benchmarks such as COCO, Visual Genome, and Open Images demonstrate up to 18% improvement in scene understanding accuracy over baseline models in complex and unseen environments. Results also show robust performance in ambiguous or cluttered scenes due to the synergistic fusion of vision and language. This framework offers a scalable and interpretable approach for context-aware reasoning, advancing zero-shot generalization in dynamic real-world settings.

---

### Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models

Authors: Yinrong Hong, Zhiquan Tan, Kai Hu
Published: 2025-10-30
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.26577v2

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and validation of multiple tokens. While recent approaches like EAGLE-2 and EAGLE-3 improve speculative decoding using dynamic tree structures, they often neglect the impact of crucial system variables such as GPU devices and batch sizes. Therefore, we introduce a new dynamic tree decoding approach called CAST that takes into account inference costs, including factors such as GPU configurations and batch sizes, to dynamically refine the tree structure. Through comprehensive experimentation across six diverse tasks and utilizing six distinct LLMs, our methodology demonstrates remarkable results, achieving speeds up to 5.2 times faster than conventional decoding methods. Moreover, it generally outperforms existing state-of-the-art techniques from 5 % to 20%. The code is available at https://github.com/EAGLE-Research/sglang-eagle4.

---

### InfoFlow: Reinforcing Search Agent Via Reward Density Optimization

Authors: Kun Luo, Hongjin Qian, Zheng Liu, Ziyi Xia, Shitao Xiao, Siqi Bao, Jun Zhao, Kang Liu
Published: 2025-10-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.26575v1

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward Density} in deep search scenarios, where agents expend significant exploratory costs for infrequent and often null final rewards. In this paper, we formalize this challenge as the \textbf{Reward Density Optimization} problem, which aims to improve the reward obtained per unit of exploration cost. This paper introduce \textbf{InfoFlow}, a systematic framework that tackles this problem from three aspects. 1) \textbf{Subproblem decomposition}: breaking down long-range tasks to assign process rewards, thereby providing denser learning signals. 2) \textbf{Failure-guided hints}: injecting corrective guidance into stalled trajectories to increase the probability of successful outcomes. 3) \textbf{Dual-agent refinement}: employing a dual-agent architecture to offload the cognitive burden of deep exploration. A refiner agent synthesizes the search history, which effectively compresses the researcher's perceived trajectory, thereby reducing exploration cost and increasing the overall reward density. We evaluate InfoFlow on multiple agentic search benchmarks, where it significantly outperforms strong baselines, enabling lightweight LLMs to achieve performance comparable to advanced proprietary LLMs.

---

### Comparative Analysis of Deep Learning Models for Olive Tree Crown and Shadow Segmentation Towards Biovolume Estimation

Authors: Wondimagegn Abebe Demissie, Stefano Roccella, Rudy Rossetto, Antonio Minnocci, Andrea Vannini, Luca Sebastiani
Published: 2025-10-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.26573v1

Olive tree biovolume estimation is a key task in precision agriculture, supporting yield prediction and resource management, especially in Mediterranean regions severely impacted by climate-induced stress. This study presents a comparative analysis of three deep learning models U-Net, YOLOv11m-seg, and Mask RCNN for segmenting olive tree crowns and their shadows in ultra-high resolution UAV imagery. The UAV dataset, acquired over Vicopisano, Italy, includes manually annotated crown and shadow masks. Building on these annotations, the methodology emphasizes spatial feature extraction and robust segmentation; per-tree biovolume is then estimated by combining crown projected area with shadow-derived height using solar geometry. In testing, Mask R-CNN achieved the best overall accuracy (F1 = 0.86; mIoU = 0.72), while YOLOv11m-seg provided the fastest throughput (0.12 second per image). The estimated biovolumes spanned from approximately 4 to 24 cubic meters, reflecting clear structural differences among trees. These results indicate Mask R-CNN is preferable when biovolume accuracy is paramount, whereas YOLOv11m-seg suits large-area deployments where speed is critical; U-Net remains a lightweight, high-sensitivity option. The framework enables accurate, scalable orchard monitoring and can be further strengthened with DEM or DSM integration and field calibration for operational decision support.

---

### AdSum: Two-stream Audio-visual Summarization for Automated Video Advertisement Clipping

Authors: Wen Xie, Yanjun Zhu, Gijs Overgoor, Yakov Bart, Agata Lapedriza Garcia, Sarah Ostadabbas
Published: 2025-10-30
Categories: cs.CV, cs.IR, cs.MM
arXiv: https://arxiv.org/abs/2510.26569v2

Advertisers commonly need multiple versions of the same advertisement (ad) at varying durations for a single campaign. The traditional approach involves manually selecting and re-editing shots from longer video ads to create shorter versions, which is labor-intensive and time-consuming. In this paper, we introduce a framework for automated video ad clipping using video summarization techniques. We are the first to frame video clipping as a shot selection problem, tailored specifically for advertising. Unlike existing general video summarization methods that primarily focus on visual content, our approach emphasizes the critical role of audio in advertising. To achieve this, we develop a two-stream audio-visual fusion model that predicts the importance of video frames, where importance is defined as the likelihood of a frame being selected in the firm-produced short ad. To address the lack of ad-specific datasets, we present AdSum204, a novel dataset comprising 102 pairs of 30-second and 15-second ads from real advertising campaigns. Extensive experiments demonstrate that our model outperforms state-of-the-art methods across various metrics, including Average Precision, Area Under Curve, Spearman, and Kendall. The dataset and code are available at https://github.com/ostadabbas/AdSum204.

---