# Research Papers — 2025-10 · bundle page 3 of 217

> Full-text markdown of papers #101–150 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/3
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/2.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/4.md)

### PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting

Authors: Danyal Maqbool, Changhee Lee, Zachary Huemann, Samuel D. Church, Matthew E. Larson, Scott B. Perlman, Tomas A. Romero, Joshua D. Warner, Meghan Lubner, Xin Tie, Jameson Merkow, Junjie Hu et al.
Published: 2025-10-31
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.27680v2

Generating automated reports for 3D positron emission tomography (PET) is an important and challenging task in medical imaging. PET plays a vital role in oncology, but automating report generation is difficult due to the complexity of whole-body 3D volumes, the wide range of potential clinical findings, and the limited availability of annotated datasets. To address these challenges, we introduce PETARSeg-11K, the first large-scale, publicly available dataset that provides lesion-level correspondence between 3D PET/CT volumes and free-text radiological findings. It comprises 11,356 lesion descriptions paired with 3D segmentations. Second, we propose PETAR-4B, a 3D vision-language model designed for mask-aware, spatially grounded PET/CT reporting. PETAR-4B jointly encodes PET, CT, and 3D lesion segmentation masks, using a 3D focal prompt to capture fine-grained details of lesions that normally comprise less than 0.1% of the volume. Evaluations using automated metrics show PETAR-4B substantially outperforming all 2D and 3D baselines. A human study involving five physicians -- the first of its kind for automated PET reporting -- confirms the model's clinical utility and establishes correlations between automated metrics and expert judgment. This work provides a foundational dataset and a novel architecture, advancing 3D medical vision-language understanding in PET.

---

### Dark-Field X-Ray Imaging Significantly Improves Deep-Learning based Detection of Synthetic Early-Stage Lung Tumors in Preclinical Models

Authors: Joyoni Dey, Hunter C. Meyer, Murtuza S. Taqi
Published: 2025-10-31
Categories: physics.med-ph, cs.CV, cs.LG, eess.IV, physics.optics
arXiv: https://arxiv.org/abs/2510.27679v1

Low-dose computed tomography (LDCT) is the current standard for lung cancer screening, yet its adoption and accessibility remain limited. Many regions lack LDCT infrastructure, and even among those screened, early-stage cancer detection often yield false positives, as shown in the National Lung Screening Trial (NLST) with a sensitivity of 93.8 percent and a false-positive rate of 26.6 percent. We aim to investigate whether X-ray dark-field imaging (DFI) radiograph, a technique sensitive to small-angle scatter from alveolar microstructure and less susceptible to organ shadowing, can significantly improve early-stage lung tumor detection when coupled with deep-learning segmentation. Using paired attenuation (ATTN) and DFI radiograph images of euthanized mouse lungs, we generated realistic synthetic tumors with irregular boundaries and intensity profiles consistent with physical lung contrast. A U-Net segmentation network was trained on small patches using either ATTN, DFI, or a combination of ATTN and DFI channels. Results show that the DFI-only model achieved a true-positive detection rate of 83.7 percent, compared with 51 percent for ATTN-only, while maintaining comparable specificity (90.5 versus 92.9 percent). The combined ATTN and DFI input achieved 79.6 percent sensitivity and 97.6 percent specificity. In conclusion, DFI substantially improves early-tumor detectability in comparison to standard attenuation radiography and shows potential as an accessible, low-cost, low-dose alternative for pre-clinical or limited-resource screening where LDCT is unavailable.

---

### Vision Transformer for Robust Occluded Person Reidentification in Complex Surveillance Scenes

Authors: Bo Li, Duyuan Zheng, Xinyang Liu, Qingwen Li, Hong Li, Hongyan Cui, Ge Gao, Chen Liu
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27677v1

Person re-identification (ReID) in surveillance is challenged by occlusion, viewpoint distortion, and poor image quality. Most existing methods rely on complex modules or perform well only on clear frontal images. We propose Sh-ViT (Shuffling Vision Transformer), a lightweight and robust model for occluded person ReID. Built on ViT-Base, Sh-ViT introduces three components: First, a Shuffle module in the final Transformer layer to break spatial correlations and enhance robustness to occlusion and blur; Second, scenario-adapted augmentation (geometric transforms, erasing, blur, and color adjustment) to simulate surveillance conditions; Third, DeiT-based knowledge distillation to improve learning with limited labels.To support real-world evaluation, we construct the MyTT dataset, containing over 10,000 pedestrians and 30,000+ images from base station inspections, with frequent equipment occlusion and camera variations. Experiments show that Sh-ViT achieves 83.2% Rank-1 and 80.1% mAP on MyTT, outperforming CNN and ViT baselines, and 94.6% Rank-1 and 87.5% mAP on Market1501, surpassing state-of-the-art methods.In summary, Sh-ViT improves robustness to occlusion and blur without external modules, offering a practical solution for surveillance-based personnel monitoring.

---

### On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection

Authors: Md Abdul Hannan, Ronghao Ni, Chi Zhang, Limin Jia, Ravi Mangal, Corina S. Pasareanu
Published: 2025-10-31
Categories: cs.SE, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.27675v2

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of coding tasks, including summarization, translation, completion, and code generation. Despite these advances, detecting code vulnerabilities remains a challenging problem for LLMs. In-context learning (ICL) has emerged as an effective mechanism for improving model performance by providing a small number of labeled examples within the prompt. Prior work has shown, however, that the effectiveness of ICL depends critically on how these few-shot examples are selected. In this paper, we study two intuitive criteria for selecting few-shot examples for ICL in the context of code vulnerability detection. The first criterion leverages model behavior by prioritizing samples on which the LLM consistently makes mistakes, motivated by the intuition that such samples can expose and correct systematic model weaknesses. The second criterion selects examples based on semantic similarity to the query program, using k-nearest-neighbor retrieval to identify relevant contexts. We conduct extensive evaluations using open-source LLMs and datasets spanning multiple programming languages. Our results show that for Python and JavaScript, careful selection of few-shot examples can lead to measurable performance improvements in vulnerability detection. In contrast, for C and C++ programs, few-shot example selection has limited impact, suggesting that more powerful but also more expensive approaches, such as re-training or fine-tuning, may be required to substantially improve model performance.

---

### Culture Cartography: Mapping the Landscape of Cultural Knowledge

Authors: Caleb Ziems, William Held, Jane Yu, Amir Goldberg, David Grusky, Diyi Yang
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27672v1

To serve global users safely and productively, LLMs need culture-specific knowledge that might not be learned during pre-training. How do we find such knowledge that is (1) salient to in-group users, but (2) unknown to LLMs? The most common solutions are single-initiative: either researchers define challenging questions that users passively answer (traditional annotation), or users actively produce data that researchers structure as benchmarks (knowledge extraction). The process would benefit from mixed-initiative collaboration, where users guide the process to meaningfully reflect their cultures, and LLMs steer the process towards more challenging questions that meet the researcher's goals. We propose a mixed-initiative methodology called CultureCartography. Here, an LLM initializes annotation with questions for which it has low-confidence answers, making explicit both its prior knowledge and the gaps therein. This allows a human respondent to fill these gaps and steer the model towards salient topics through direct edits. We implement this methodology as a tool called CultureExplorer. Compared to a baseline where humans answer LLM-proposed questions, we find that CultureExplorer more effectively produces knowledge that leading models like DeepSeek R1 and GPT-4o are missing, even with web search. Fine-tuning on this data boosts the accuracy of Llama-3.1-8B by up to 19.2% on related culture benchmarks.

---

### MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design

Authors: Wei Zhang, Zekun Guo, Yingce Xia, Peiran Jin, Shufang Xie, Tao Qin, Xiang-Yang Li
Published: 2025-10-31
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.27671v1

Structure-based drug design (SBDD), which maps target proteins to candidate molecular ligands, is a fundamental task in drug discovery. Effectively aligning protein structural representations with molecular representations, and ensuring alignment between generated drugs and their pharmacological properties, remains a critical challenge. To address these challenges, we propose MolChord, which integrates two key techniques: (1) to align protein and molecule structures with their textual descriptions and sequential representations (e.g., FASTA for proteins and SMILES for molecules), we leverage NatureLM, an autoregressive model unifying text, small molecules, and proteins, as the molecule generator, alongside a diffusion-based structure encoder; and (2) to guide molecules toward desired properties, we curate a property-aware dataset by integrating preference data and refine the alignment process using Direct Preference Optimization (DPO). Experimental results on CrossDocked2020 demonstrate that our approach achieves state-of-the-art performance on key evaluation metrics, highlighting its potential as a practical tool for SBDD.

---

### Deep learning denoising unlocks quantitative insights in operando materials microscopy

Authors: Samuel Degnan-Morgenstern, Alexander E. Cohen, Rajeev Gopal, Megan Gober, George J. Nelson, Peng Bai, Martin Z. Bazant
Published: 2025-10-31
Categories: cs.CV, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2510.27667v1

Operando microscopy provides direct insight into the dynamic chemical and physical processes that govern functional materials, yet measurement noise limits the effective resolution and undermines quantitative analysis. Here, we present a general framework for integrating unsupervised deep learning-based denoising into quantitative microscopy workflows across modalities and length scales. Using simulated data, we demonstrate that deep denoising preserves physical fidelity, introduces minimal bias, and reduces uncertainty in model learning with partial differential equation (PDE)-constrained optimization. Applied to experiments, denoising reveals nanoscale chemical and structural heterogeneity in scanning transmission X-ray microscopy (STXM) of lithium iron phosphate (LFP), enables automated particle segmentation and phase classification in optical microscopy of graphite electrodes, and reduces noise-induced variability by nearly 80% in neutron radiography to resolve heterogeneous lithium transport. Collectively, these results establish deep denoising as a powerful, modality-agnostic enhancement that advances quantitative operando imaging and extends the reach of previously noise-limited techniques.

---

### Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements

Authors: Tom Sprunck, Marcelo Pereyra, Tobias Liaudat
Published: 2025-10-31
Categories: eess.IV, cs.LG, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.27663v3

Modern imaging techniques heavily rely on Bayesian statistical models to address difficult image reconstruction and restoration tasks. This paper addresses the objective evaluation of such models in settings where ground truth is unavailable, with a focus on model selection and misspecification diagnosis. Existing unsupervised model evaluation methods are often unsuitable for computational imaging due to their high computational cost and incompatibility with modern image priors defined implicitly via machine learning models. We herein propose a general methodology for unsupervised model selection and misspecification detection in Bayesian imaging sciences, based on a novel combination of Bayesian cross-validation and data fission, a randomized measurement splitting technique. The approach is compatible with any Bayesian imaging sampler, including diffusion and plug-and-play samplers. We demonstrate the methodology through experiments involving various scoring rules and types of model misspecification, where we achieve excellent selection and detection accuracy with a low computational cost.

---

### Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systems

Authors: Alireza Saleh Abadi, Leen-Kiat Soh
Published: 2025-10-31
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.27659v1

In the rapidly evolving field of multi-agent reinforcement learning (MARL), understanding the dynamics of open systems is crucial. Openness in MARL refers to the dynam-ic nature of agent populations, tasks, and agent types with-in a system. Specifically, there are three types of openness as reported in (Eck et al. 2023) (2): agent openness, where agents can enter or leave the system at any time; task openness, where new tasks emerge, and existing ones evolve or disappear; and type openness, where the capabil-ities and behaviors of agents change over time. This report provides a conceptual and empirical review, focusing on the interplay between openness and the credit assignment problem (CAP). CAP involves determining the contribution of individual agents to the overall system performance, a task that becomes increasingly complex in open environ-ments. Traditional credit assignment (CA) methods often assume static agent populations, fixed and pre-defined tasks, and stationary types, making them inadequate for open systems. We first conduct a conceptual analysis, in-troducing new sub-categories of openness to detail how events like agent turnover or task cancellation break the assumptions of environmental stationarity and fixed team composition that underpin existing CAP methods. We then present an empirical study using representative temporal and structural algorithms in an open environment. The results demonstrate that openness directly causes credit misattribution, evidenced by unstable loss functions and significant performance degradation.

---

### Community Detection on Model Explanation Graphs for Explainable AI

Authors: Ehsan Moradi
Published: 2025-10-31
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2510.27655v1

Feature-attribution methods (e.g., SHAP, LIME) explain individual predictions but often miss higher-order structure: sets of features that act in concert. We propose Modules of Influence (MoI), a framework that (i) constructs a model explanation graph from per-instance attributions, (ii) applies community detection to find feature modules that jointly affect predictions, and (iii) quantifies how these modules relate to bias, redundancy, and causality patterns. Across synthetic and real datasets, MoI uncovers correlated feature groups, improves model debugging via module-level ablations, and localizes bias exposure to specific modules. We release stability and synergy metrics, a reference implementation, and evaluation protocols to benchmark module discovery in XAI.

---

### Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition

Authors: Shuyan Lyu, Zhanzimo Wu, Junliang Du
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27651v1

Modern deep neural networks (DNNs) are typically trained with a global cross-entropy loss in a supervised end-to-end manner: neurons need to store their outgoing weights; training alternates between a forward pass (computation) and a top-down backward pass (learning) which is biologically implausible. Alternatively, greedy layer-wise training eliminates the need for cross-entropy loss and backpropagation. By avoiding the computation of intermediate gradients and the storage of intermediate outputs, it reduces memory usage and helps mitigate issues such as vanishing or exploding gradients. However, most existing layer-wise training approaches have been evaluated only on relatively small datasets with simple deep architectures. In this paper, we first systematically analyze the training dynamics of popular convolutional neural networks (CNNs) trained by stochastic gradient descent (SGD) through an information-theoretic lens. Our findings reveal that networks converge layer-by-layer from bottom to top and that the flow of information adheres to a Markov information bottleneck principle. Building on these observations, we propose a novel layer-wise training approach based on the recently developed deterministic information bottleneck (DIB) and the matrix-based Rényi's $α$-order entropy functional. Specifically, each layer is trained jointly with an auxiliary classifier that connects directly to the output layer, enabling the learning of minimal sufficient task-relevant representations. We empirically validate the effectiveness of our training procedure on CIFAR-10 and CIFAR-100 using modern deep CNNs and further demonstrate its applicability to a practical task involving traffic sign recognition. Our approach not only outperforms existing layer-wise training baselines but also achieves performance comparable to SGD.

---

### Imbalanced Classification through the Lens of Spurious Correlations

Authors: Jakob Hackstein, Sidney Bender
Published: 2025-10-31
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.27650v1

Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighting schemes, we view imbalance as a data condition that amplifies Clever Hans (CH) effects by underspecification of minority classes. In a counterfactual explanations-based approach, we propose to leverage Explainable AI to jointly identify and eliminate CH effects emerging under imbalance. Our method achieves competitive classification performance on three datasets and demonstrates how CH effects emerge under imbalance, a perspective largely overlooked by existing approaches.

---

### Gaussian Combined Distance: A Generic Metric for Object Detection

Authors: Ziqian Guan, Xieyi Fu, Pengjun Huang, Hengyuan Zhang, Hubin Du, Yongtao Liu, Yinglin Wang, Qang Ma
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27649v1

In object detection, a well-defined similarity metric can significantly enhance model performance. Currently, the IoU-based similarity metric is the most commonly preferred choice for detectors. However, detectors using IoU as a similarity metric often perform poorly when detecting small objects because of their sensitivity to minor positional deviations. To address this issue, recent studies have proposed the Wasserstein Distance as an alternative to IoU for measuring the similarity of Gaussian-distributed bounding boxes. However, we have observed that the Wasserstein Distance lacks scale invariance, which negatively impacts the model's generalization capability. Additionally, when used as a loss function, its independent optimization of the center attributes leads to slow model convergence and unsatisfactory detection precision. To address these challenges, we introduce the Gaussian Combined Distance (GCD). Through analytical examination of GCD and its gradient, we demonstrate that GCD not only possesses scale invariance but also facilitates joint optimization, which enhances model localization performance. Extensive experiments on the AI-TOD-v2 dataset for tiny object detection show that GCD, as a bounding box regression loss function and label assignment metric, achieves state-of-the-art performance across various detectors. We further validated the generalizability of GCD on the MS-COCO-2017 and Visdrone-2019 datasets, where it outperforms the Wasserstein Distance across diverse scales of datasets. Code is available at https://github.com/MArKkwanGuan/mmdet-GCD.

---

### NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception

Authors: Congzhang Shao, Quan Yuan, Guiyang Luo, Yue Hu, Danni Wang, Yilin Liu, Rui Pan, Bo Chen, Jinglin Li
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27647v3

Collaborative perception improves task performance by expanding the perception range through information sharing among agents. . Immutable heterogeneity poses a significant challenge in collaborative perception, as participating agents may employ different and fixed perception models. This leads to domain gaps in the intermediate features shared among agents, consequently degrading collaborative performance. Aligning the features of all agents to a common representation can eliminate domain gaps with low training cost. However, in existing methods, the common representation is designated as the representation of a specific agent, making it difficult for agents with significant domain discrepancies from this specific agent to achieve proper alignment. This paper proposes NegoCollab, a heterogeneous collaboration method based on the negotiated common representation. It introduces a negotiator during training to derive the common representation from the local representations of each modality's agent, effectively reducing the inherent domain gap with the various local representations. In NegoCollab, the mutual transformation of features between the local representation space and the common representation space is achieved by a pair of sender and receiver. To better align local representations to the common representation containing multimodal information, we introduce structural alignment loss and pragmatic alignment loss in addition to the distribution alignment loss to supervise the training. This enables the knowledge in the common representation to be fully distilled into the sender.

---

### VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images

Authors: Cesar H. Comin, Wesley N. Galvão
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27646v1

Semantic segmentation of blood vessels is an important task in medical image analysis, but its progress is often hindered by the scarcity of large annotated datasets and the poor generalization of models across different imaging modalities. A key aspect is the tendency of Convolutional Neural Networks (CNNs) to learn texture-based features, which limits their performance when applied to new domains with different visual characteristics. We hypothesize that leveraging geometric priors of vessel shapes, such as their tubular and branching nature, can lead to more robust and data-efficient models. To investigate this, we introduce VessShape, a methodology for generating large-scale 2D synthetic datasets designed to instill a shape bias in segmentation models. VessShape images contain procedurally generated tubular geometries combined with a wide variety of foreground and background textures, encouraging models to learn shape cues rather than textures. We demonstrate that a model pre-trained on VessShape images achieves strong few-shot segmentation performance on two real-world datasets from different domains, requiring only four to ten samples for fine-tuning. Furthermore, the model exhibits notable zero-shot capabilities, effectively segmenting vessels in unseen domains without any target-specific training. Our results indicate that pre-training with a strong shape bias can be an effective strategy to overcome data scarcity and improve model generalization in blood vessel segmentation.

---

### Bayesian Optimization on Networks

Authors: Wenwen Li, Daniel Sanz-Alonso, Ruiyi Yang
Published: 2025-10-31
Categories: stat.ML, cs.LG, math.NA, math.OC, stat.CO
arXiv: https://arxiv.org/abs/2510.27643v2

This paper studies optimization on networks modeled as metric graphs. Motivated by applications where the objective function is expensive to evaluate or only available as a black box, we develop Bayesian optimization algorithms that sequentially update a Gaussian process surrogate model of the objective to guide the acquisition of query points. To ensure that the surrogates are tailored to the network's geometry, we adopt Whittle-Matérn Gaussian process prior models defined via stochastic partial differential equations on metric graphs. In addition to establishing regret bounds for optimizing sufficiently smooth objective functions, we analyze the practical case in which the smoothness of the objective is unknown and the Whittle-Matérn prior is represented using finite elements. Numerical results demonstrate the effectiveness of our algorithms for optimizing benchmark objective functions on a synthetic metric graph and for Bayesian inversion via maximum a posteriori estimation on a telecommunication network.

---

### SpecAttn: Speculating Sparse Attention

Authors: Harsh Shah
Published: 2025-10-31
Categories: cs.CL, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.27641v1

Large Language Models (LLMs) face significant computational bottlenecks during inference due to the quadratic complexity of self-attention mechanisms, particularly as context lengths increase. We introduce SpecAttn, a novel training-free approach that seamlessly integrates with existing speculative decoding techniques to enable efficient sparse attention in pre-trained transformers. Our key insight is to exploit the attention weights already computed by the draft model during speculative decoding to identify important tokens for the target model, eliminating redundant computation while maintaining output quality. SpecAttn employs three core techniques: KL divergence-based layer alignment between draft and target models, a GPU-optimized sorting-free algorithm for top-p token selection from draft attention patterns, and dynamic key-value cache pruning guided by these predictions. By leveraging the computational work already performed in standard speculative decoding pipelines, SpecAttn achieves over 75% reduction in key-value cache accesses with a mere 15.29% increase in perplexity on the PG-19 dataset, significantly outperforming existing sparse attention methods. Our approach demonstrates that speculative execution can be enhanced to provide approximate verification without significant performance degradation.

---

### Enhancing software product lines with machine learning components

Authors: Luz-Viviana Cobaleda, Julián Carvajal, Paola Vallejo, Andrés López, Raúl Mazo
Published: 2025-10-31
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2510.27640v1

Modern software systems increasingly integrate machine learning (ML) due to its advancements and ability to enhance data-driven decision-making. However, this integration introduces significant challenges for software engineering, especially in software product lines (SPLs), where managing variability and reuse becomes more complex with the inclusion of ML components. Although existing approaches have addressed variability management in SPLs and the integration of ML components in isolated systems, few have explored the intersection of both domains. Specifically, there is limited support for modeling and managing variability in SPLs that incorporate ML components. To bridge this gap, this article proposes a structured framework designed to extend Software Product Line engineering, facilitating the integration of ML components. It facilitates the design of SPLs with ML capabilities by enabling systematic modeling of variability and reuse. The proposal has been partially implemented with the VariaMos tool.

---

### Panprediction: Optimal Predictions for Any Downstream Task and Loss

Authors: Sivaraman Balakrishnan, Nika Haghtalab, Daniel Hsu, Brian Lee, Eric Zhao
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27638v1

Supervised learning is classically formulated as training a model to minimize a fixed loss function over a fixed distribution, or task. However, an emerging paradigm instead views model training as extracting enough information from data so that the model can be used to minimize many losses on many downstream tasks. We formalize a mathematical framework for this paradigm, which we call panprediction, and study its statistical complexity. Formally, panprediction generalizes omniprediction and sits upstream from multi-group learning, which respectively focus on predictions that generalize to many downstream losses or many downstream tasks, but not both. Concretely, we design algorithms that learn deterministic and randomized panpredictors with $\tilde{O}(1/\varepsilon^3)$ and $\tilde{O}(1/\varepsilon^2)$ samples, respectively. Our results demonstrate that under mild assumptions, simultaneously minimizing infinitely many losses on infinitely many tasks can be as statistically easy as minimizing one loss on one task. Along the way, we improve the best known sample complexity guarantee of deterministic omniprediction by a factor of $1/\varepsilon$, and match all other known sample complexity guarantees of omniprediction and multi-group learning. Our key technical ingredient is a nearly lossless reduction from panprediction to a statistically efficient notion of calibration, called step calibration.

---

### Sketch-to-Layout: Sketch-Guided Multimodal Layout Generation

Authors: Riccardo Brioschi, Aleksandr Alekseev, Emanuele Nevali, Berkay Döner, Omar El Malki, Blagoj Mitrevski, Leandro Kieliger, Mark Collier, Andrii Maksai, Jesse Berent, Claudiu Musat, Efi Kokiopoulou
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27632v1

Graphic layout generation is a growing research area focusing on generating aesthetically pleasing layouts ranging from poster designs to documents. While recent research has explored ways to incorporate user constraints to guide the layout generation, these constraints often require complex specifications which reduce usability. We introduce an innovative approach exploiting user-provided sketches as intuitive constraints and we demonstrate empirically the effectiveness of this new guidance method, establishing the sketch-to-layout problem as a promising research direction, which is currently under-explored. To tackle the sketch-to-layout problem, we propose a multimodal transformer-based solution using the sketch and the content assets as inputs to produce high quality layouts. Since collecting sketch training data from human annotators to train our model is very costly, we introduce a novel and efficient method to synthetically generate training sketches at scale. We train and evaluate our model on three publicly available datasets: PubLayNet, DocLayNet and SlidesVQA, demonstrating that it outperforms state-of-the-art constraint-based methods, while offering a more intuitive design experience. In order to facilitate future sketch-to-layout research, we release O(200k) synthetically-generated sketches for the public datasets above. The datasets are available at https://github.com/google-deepmind/sketch_to_layout.

---

### Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training

Authors: Dayuan Fu, Yunze Wu, Xiaojie Cai, Lyumanshan Ye, Shijie Xia, Zhen Huang, Weiye Si, Tianze Xu, Jie Sun, Keyu Li, Mohan Jiang, Junfei Wang et al.
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27630v2

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, training them to succeed on long-horizon, domain-specialized tasks remains challenging. Current methods primarily fall into two categories. The first relies on dense human annotations through behavior cloning, which is prohibitively expensive for long-horizon tasks that can take days or months. The second depends on outcome-driven sampling, which often collapses due to the rarity of valid positive trajectories on domain-specialized tasks. We introduce Apollo, a sampling framework that integrates asynchronous human guidance with action-level data filtering. Instead of requiring annotators to shadow every step, Apollo allows them to intervene only when the agent drifts from a promising trajectory, by providing prior knowledge, strategic advice, etc. This lightweight design makes it possible to sustain interactions for over 30 hours and produces valuable trajectories at a lower cost. Apollo then applies supervision control to filter out sub-optimal actions and prevent error propagation. Together, these components enable reliable and effective data collection in long-horizon environments. To demonstrate the effectiveness of Apollo, we evaluate it using InnovatorBench. Our experiments show that when applied to train the GLM-4.5 model on InnovatorBench, Apollo achieves more than a 50% improvement over the untrained baseline and a 28% improvement over a variant trained without human interaction. These results highlight the critical role of human-in-the-loop sampling and the robustness of Apollo's design in handling long-horizon, domain-specialized tasks.

---

### Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models

Authors: Boyi Wei, Zora Che, Nathaniel Li, Udari Madhushani Sehwag, Jasper Götting, Samira Nedungadi, Julian Michael, Summer Yue, Dan Hendrycks, Peter Henderson, Zifan Wang, Seth Donoughe et al.
Published: 2025-10-31
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.27629v4

Open-weight bio-foundation models present a dual-use dilemma. While holding great promise for accelerating scientific research and drug development, they could also enable bad actors to develop more deadly bioweapons. To mitigate the risk posed by these models, current approaches focus on filtering biohazardous data during pre-training. However, the effectiveness of such an approach remains unclear, particularly against determined actors who might fine-tune these models for malicious use. To address this gap, we propose BioRiskEval, a framework to evaluate the robustness of procedures that are intended to reduce the dual-use capabilities of bio-foundation models. BioRiskEval assesses models' virus understanding through three lenses, including sequence modeling, mutational effects prediction, and virulence prediction. Our results show that current filtering practices may not be particularly effective: Excluded knowledge can be rapidly recovered in some cases via fine-tuning, and exhibits broader generalizability in sequence modeling. Furthermore, dual-use signals may already reside in the pretrained representations, and can be elicited via simple linear probing. These findings highlight the challenges of data filtering as a standalone procedure, underscoring the need for further research into robust safety and security strategies for open-weight bio-foundation models.

---

### Validity Is What You Need

Authors: Sebastian Benthall, Andrew Clark
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27628v1

While AI agents have long been discussed and studied in computer science, today's Agentic AI systems are something new. We consider other definitions of Agentic AI and propose a new realist definition. Agentic AI is a software delivery mechanism, comparable to software as a service (SaaS), which puts an application to work autonomously in a complex enterprise setting. Recent advances in large language models (LLMs) as foundation models have driven excitement in Agentic AI. We note, however, that Agentic AI systems are primarily applications, not foundations, and so their success depends on validation by end users and principal stakeholders. The tools and techniques needed by the principal users to validate their applications are quite different from the tools and techniques used to evaluate foundation models. Ironically, with good validation measures in place, in many cases the foundation models can be replaced with much simpler, faster, and more interpretable models that handle core logic. When it comes to Agentic AI, validity is what you need. LLMs are one option that might achieve it.

---

### BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

Authors: Qiusi Zhan, Hyeonjeong Ha, Rui Yang, Sirui Xu, Hanyang Chen, Liang-Yan Gui, Yu-Xiong Wang, Huan Zhang, Heng Ji, Daniel Kang
Published: 2025-10-31
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.27623v3

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack surface: visual backdoor attacks, where the agent behaves normally until a visual trigger appears in the scene, then persistently executes an attacker-specified multi-step policy. We introduce BEAT, the first framework to inject such visual backdoors into VLM-based embodied agents using objects in the environments as triggers. Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably. BEAT addresses this challenge by (1) constructing a training set that spans diverse scenes, tasks, and trigger placements to expose agents to trigger variability, and (2) introducing a two-stage training scheme that first applies supervised fine-tuning (SFT) and then our novel Contrastive Trigger Learning (CTL). CTL formulates trigger discrimination as preference learning between trigger-present and trigger-free inputs, explicitly sharpening the decision boundaries to ensure precise backdoor activation. Across various embodied agent benchmarks and VLMs, BEAT achieves attack success rates up to 80%, while maintaining strong benign task performance, and generalizes reliably to out-of-distribution trigger placements. Notably, compared to naive SFT, CTL boosts backdoor activation accuracy up to 39% under limited backdoor data. These findings expose a critical yet unexplored security risk in VLM-based embodied agents, underscoring the need for robust defenses before real-world deployment.

---

### VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation

Authors: Heng Ping, Arijit Bhattacharjee, Peiyu Zhang, Shixuan Li, Wei Yang, Anzhe Cheng, Xiaole Zhang, Jesse Thomason, Ali Jannesari, Nesreen Ahmed, Paul Bogdan
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27617v2

Automation of Register Transfer Level (RTL) design can help developers meet increasing computational demands. Large Language Models (LLMs) show promise for Hardware Description Language (HDL) generation, but face challenges due to limited parametric knowledge and domain-specific constraints. While prompt engineering and fine-tuning have limitations in knowledge coverage and training costs, multi-agent architectures offer a training-free paradigm to enhance reasoning through collaborative generation. However, current multi-agent approaches suffer from two critical deficiencies: susceptibility to noise propagation and constrained reasoning space exploration. We propose VeriMoA, a training-free mixture-of-agents (MoA) framework with two synergistic innovations. First, a quality-guided caching mechanism to maintain all intermediate HDL outputs and enables quality-based ranking and selection across the entire generation process, encouraging knowledge accumulation over layers of reasoning. Second, a multi-path generation strategy that leverages C++ and Python as intermediate representations, decomposing specification-to-HDL translation into two-stage processes that exploit LLM fluency in high-resource languages while promoting solution diversity. Comprehensive experiments on VerilogEval 2.0 and RTLLM 2.0 benchmarks demonstrate that VeriMoA achieves 15--30% improvements in Pass@1 across diverse LLM backbones, especially enabling smaller models to match larger models and fine-tuned alternatives without requiring costly training.

---

### ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modeling

Authors: Zhuohan Wang, Ziwei Zhu, Ziniu Li, Congliang Chen, Yizhou Han, Yufeng Lin, Zhihang Lin, Angyang Gu, Xinglin Hu, Ruoyu Sun, Tian Ding
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27610v1

Formulating optimization problems for industrial applications demands significant manual effort and domain expertise. While Large Language Models (LLMs) show promise in automating this process, evaluating their performance remains difficult due to the absence of robust metrics. Existing solver-based approaches often face inconsistency, infeasibility issues, and high computational costs. To address these issues, we propose ORGEval, a graph-theoretic evaluation framework for assessing LLMs' capabilities in formulating linear and mixed-integer linear programs. ORGEval represents optimization models as graphs, reducing equivalence detection to graph isomorphism testing. We identify and prove a sufficient condition, when the tested graphs are symmetric decomposable (SD), under which the Weisfeiler-Lehman (WL) test is guaranteed to correctly detect isomorphism. Building on this, ORGEval integrates a tailored variant of the WL-test with an SD detection algorithm to evaluate model equivalence. By focusing on structural equivalence rather than instance-level configurations, ORGEval is robust to numerical variations. Experimental results show that our method can successfully detect model equivalence and produce 100\% consistent results across random parameter configurations, while significantly outperforming solver-based methods in runtime, especially on difficult problems. Leveraging ORGEval, we construct the Bench4Opt dataset and benchmark state-of-the-art LLMs on optimization modeling. Our results reveal that although optimization modeling remains challenging for all LLMs, DeepSeek-V3 and Claude-Opus-4 achieve the highest accuracies under direct prompting, outperforming even leading reasoning models.

---

### Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model

Authors: John Won, Kyungmin Lee, Huiwon Jang, Dongyoung Kim, Jinwoo Shin
Published: 2025-10-31
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.27607v3

Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predicting states and actions due to the modality gap. To address this, we propose DUal-STream diffusion (DUST), a world-model augmented VLA framework featuring a multimodal diffusion transformer that maintains separate modality streams while enabling cross-modal knowledge sharing. In addition, DUST utilizes independent noise perturbations and a decoupled flow matching loss to learn cross-modal causal relationships. We further introduce an asynchronous sampling method for action and vision tokens that enhances performance through inference-time scaling. Experimental results on simulated benchmarks like RoboCasa and GR-1 show that DUST achieves up to 6% gains over state-of-the-art VLA and world-modeling baselines, with inference-time scaling providing an additional 2-5% improvement. In real-world tasks using the Franka Research 3, DUST outperforms baselines by 10% in success rate. Finally, we demonstrate that DUST enables effective transfer learning through both pretraining on action-free videos and joint-training with heterogeneous robot and human datasets.

---

### Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning

Authors: Yuhong Liu, Beichen Zhang, Yuhang Zang, Yuhang Cao, Long Xing, Xiaoyi Dong, Haodong Duan, Dahua Lin, Jiaqi Wang
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27606v2

Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (RLVR) pipelines depend on costly supervision, specialized tools, or constrained environments that limit scale. We introduce Spatial-SSRL, a self-supervised RL paradigm that derives verifiable signals directly from ordinary RGB or RGB-D images. Spatial-SSRL automatically formulates five pretext tasks that capture 2D and 3D spatial structure: shuffled patch reordering, flipped patch recognition, cropped patch inpainting, regional depth ordering, and relative 3D position prediction. These tasks provide ground-truth answers that are easy to verify and require no human or LVLM annotation. Training on our tasks substantially improves spatial reasoning while preserving general visual capabilities. On seven spatial understanding benchmarks in both image and video settings, Spatial-SSRL delivers average accuracy gains of 4.63% (3B) and 3.89% (7B) over the Qwen2.5-VL baselines. Our results show that simple, intrinsic supervision enables RLVR at scale and provides a practical route to stronger spatial intelligence in LVLMs.

---

### Who Made This? Fake Detection and Source Attribution with Diffusion Features

Authors: Simone Bonechi, Paolo Andreini, Barbara Toniella Corradini
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27602v2

The rapid rise of generative models has yielded synthetic images of striking realism, blurring the line between real and fake content. As novel models proliferate, detectors must go beyond mere fake identification to robustly generalise across unseen generators and synthetic content. We introduce FRIDA (Fake image Recognition and source Identification via Diffusion features Analysis), a lightweight, data-efficient framework that uses features from a pre-trained Stable Diffusion Model to detect and attribute AI-generated images. Through an in-depth analysis of how data from different generators are encoded across diffusion U-Net layers, we propose a method that (i) detects synthetic images using a training-free $k$-Nearest Neighbour approach and (ii) performs source model attribution via a compact neural classifier. On the GenImage benchmark, FRIDA achieves state-of-the-art cross-generator detection with limited data while maintaining robust source model attribution capabilities. These results establish diffusion features as a reliable framework for AI-generated image forensics.

---

### ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning

Authors: Samarup Bhattacharya, Anubhab Bhattacharya, Abir Chakraborty
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27599v1

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives them their strength, yet it also opens the door to a hidden flaw. The very gradients that help a model learn can also be used to produce small, imperceptible tweaks that cause the model to completely alter its decision. Such tweaks are called adversarial attacks. These attacks exploit this vulnerability by adding tiny, imperceptible changes to images that, while leaving them identical to the human eye, cause the model to make wrong predictions. In this work, we propose Adversarially-trained Contrastive Hard-mining for Optimized Robustness (ANCHOR), a framework that leverages the power of supervised contrastive learning with explicit hard positive mining to enable the model to learn representations for images such that the embeddings for the images, their augmentations, and their perturbed versions cluster together in the embedding space along with those for other images of the same class while being separated from images of other classes. This alignment helps the model focus on stable, meaningful patterns rather than fragile gradient cues. On CIFAR-10, our approach achieves impressive results for both clean and robust accuracy under PGD-20 (epsilon = 0.031), outperforming standard adversarial training methods. Our results indicate that combining adversarial guidance with hard-mined contrastive supervision helps models learn more structured and robust representations, narrowing the gap between accuracy and robustness.

---

### InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research

Authors: Yunze Wu, Dayuan Fu, Weiye Si, Zhen Huang, Mohan Jiang, Keyu Li, Shijie Xia, Jie Sun, Tianze Xu, Xiangkun Hu, Pengrui Lu, Xiaojie Cai et al.
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27598v2

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research. It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction, which require runnable artifacts and assessment of correctness, performance, output quality, and uncertainty. To support agent operation, we develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving. We also implement a lightweight ReAct agent that couples explicit reasoning with executable planning using frontier models such as Claude-4, GPT-5, GLM-4.5, and Kimi-K2. Our experiments demonstrate that while frontier models show promise in code-driven research tasks, they struggle with fragile algorithm-related tasks and long-horizon decision making, such as impatience, poor resource management, and overreliance on template-based reasoning. Furthermore, agents require over 11 hours to achieve their best performance on InnovatorBench, underscoring the benchmark's difficulty and showing the potential of InnovatorBench to be the next generation of code-based research benchmark.

---

### Learned Static Function Data Structures

Authors: Stefan Hermann, Hans-Peter Lehmann, Giorgio Vinciguerra, Stefan Walzer
Published: 2025-10-31
Categories: cs.DS, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2510.27588v3

We consider the task of constructing a data structure for associating a static set of keys with values, while allowing arbitrary output values for queries involving keys outside the set. Compared to hash tables, these so-called static function data structures do not need to store the key set and thus use significantly less memory. Several techniques are known, with compressed static functions approaching the zero-order empirical entropy of the value sequence. In this paper, we introduce learned static functions, which use machine learning to capture correlations between keys and values. For each key, a model predicts a probability distribution over the values, from which we derive a key-specific prefix code to compactly encode the true value. The resulting codeword is stored in a classic static function data structure. This design allows learned static functions to break the zero-order entropy barrier while still supporting point queries. Our experiments show substantial space savings: up to one order of magnitude on real data, and up to three orders of magnitude on synthetic data.

---

### Image Hashing via Cross-View Code Alignment in the Age of Foundation Models

Authors: Ilyass Moummad, Kawtar Zaher, Hervé Goëau, Alexis Joly
Published: 2025-10-31
Categories: cs.CV, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.27584v3

Efficient large-scale retrieval requires representations that are both compact and discriminative. Foundation models provide powerful visual and multimodal embeddings, but nearest neighbor search in these high-dimensional spaces is computationally expensive. Hashing offers an efficient alternative by enabling fast Hamming distance search with binary codes, yet existing approaches often rely on complex pipelines, multi-term objectives, designs specialized for a single learning paradigm, and long training times. We introduce CroVCA (Cross-View Code Alignment), a simple and unified principle for learning binary codes that remain consistent across semantically aligned views. A single binary cross-entropy loss enforces alignment, while coding-rate maximization serves as an anti-collapse regularizer to promote balanced and diverse codes. To implement this, we design HashCoder, a lightweight MLP hashing network with a final batch normalization layer to enforce balanced codes. HashCoder can be used as a probing head on frozen embeddings or to adapt encoders efficiently via LoRA fine-tuning. Across benchmarks, CroVCA achieves state-of-the-art results in just 5 training epochs. At 16 bits, it performs particularly well; for instance, unsupervised hashing on COCO completes in under 2 minutes and supervised hashing on ImageNet100 in about 3 minutes on a single GPU. These results highlight CroVCA's efficiency, adaptability, and broad applicability.

---

### Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum

Authors: Zhuoning Guo, Mingxin Li, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Xiaowen Chu
Published: 2025-10-31
Categories: cs.CV, cs.AI, cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.27571v1

The prevailing video retrieval paradigm is structurally misaligned, as narrow benchmarks incentivize correspondingly limited data and single-task training. Therefore, universal capability is suppressed due to the absence of a diagnostic evaluation that defines and demands multi-dimensional generalization. To break this cycle, we introduce a framework built on the co-design of evaluation, data, and modeling. First, we establish the Universal Video Retrieval Benchmark (UVRB), a suite of 16 datasets designed not only to measure performance but also to diagnose critical capability gaps across tasks and domains. Second, guided by UVRB's diagnostics, we introduce a scalable synthesis workflow that generates 1.55 million high-quality pairs to populate the semantic space required for universality. Finally, we devise the Modality Pyramid, a curriculum that trains our General Video Embedder (GVE) by explicitly leveraging the latent interconnections within our diverse data. Extensive experiments show GVE achieves state-of-the-art zero-shot generalization on UVRB. In particular, our analysis reveals that popular benchmarks are poor predictors of general ability and that partially relevant retrieval is a dominant but overlooked scenario. Overall, our co-designed framework provides a practical path to escape the limited scope and advance toward truly universal video retrieval.

---

### MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval

Authors: Qi Luo, Xiaonan Li, Yuxin Wang, Tingshuo Fan, Yuan Li, Xinchi Chen, Xipeng Qiu
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27569v1

Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new information. Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge; However, the effectiveness of RAG critically depends on whether the model can adequately access relevant information. Existing RAG systems rely on a single retriever with fixed top-k selection, restricting access to a narrow and static subset of the corpus. As a result, this single-retriever paradigm has become the primary bottleneck for comprehensive external information acquisition, especially in tasks requiring corpus-level reasoning. To overcome this limitation, we propose MARAG-R1, a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms for broader and more precise information access. MARAG-R1 equips the model with four retrieval tools -- semantic search, keyword search, filtering, and aggregation -- and learns both how and when to use them through a two-stage training process: supervised fine-tuning followed by reinforcement learning. This design allows the model to interleave reasoning and retrieval, progressively gathering sufficient evidence for corpus-level synthesis. Experiments on GlobalQA, HotpotQA, and 2WikiMultiHopQA demonstrate that MARAG-R1 substantially outperforms strong baselines and achieves new state-of-the-art results in corpus-level reasoning tasks.

---

### SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning

Authors: Ali Asgarov, Umid Suleymanov, Aadyant Khatri
Published: 2025-10-31
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.27568v2

Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search strategies, and struggle to effectively combine information from multiple sources. We introduce SIGMA (Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning), a unified framework that orchestrates specialized agents to independently reason, perform targeted searches, and synthesize findings through a moderator mechanism. Each agent generates hypothetical passages to optimize retrieval for its analytic perspective, ensuring knowledge integration is both context-sensitive and computation-efficient. When evaluated on challenging benchmarks such as MATH500, AIME, and PhD-level science QA GPQA, SIGMA consistently outperforms both open- and closed-source systems, achieving an absolute performance improvement of 7.4%. Our results demonstrate that multi-agent, on-demand knowledge integration significantly enhances both reasoning accuracy and efficiency, offering a scalable approach for complex, knowledge-intensive problem-solving. We will release the code upon publication.

---

### CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments

Authors: Forough Mehralian, Ryan Shar, James R. Rae, Alireza Hashemi
Published: 2025-10-31
Categories: cs.SE, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.27565v1

As large language models become increasingly capable of generating code, evaluating their performance remains a complex and evolving challenge. Existing benchmarks primarily focus on functional correctness, overlooking the diversity of real-world coding tasks and developer expectations. To this end, we introduce a multi-language benchmark that evaluates LLM instruction-following capabilities and is extensible to operate on any set of standalone coding problems. Our benchmark evaluates instruction following in two key settings: adherence to pre-defined constraints specified with the initial problem, and the ability to perform refinements based on follow-up instructions. For this paper's analysis, we empirically evaluated our benchmarking pipeline with programming tasks from LiveBench, that are also automatically translated from Python into Java and JavaScript. Our automated benchmark reveals that models exhibit differing levels of performance across multiple dimensions of instruction-following. Our benchmarking pipeline provides a more comprehensive evaluation of code generation models, highlighting their strengths and limitations across languages and generation goals.

---

### Optimal Convergence Analysis of DDPM for General Distributions

Authors: Yuchen Jiao, Yuchen Zhou, Gen Li
Published: 2025-10-31
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.27562v2

Score-based diffusion models have achieved remarkable empirical success in generating high-quality samples from target data distributions. Among them, the Denoising Diffusion Probabilistic Model (DDPM) is one of the most widely used samplers, generating samples via estimated score functions. Despite its empirical success, a tight theoretical understanding of DDPM -- especially its convergence properties -- remains limited. In this paper, we provide a refined convergence analysis of the DDPM sampler and establish near-optimal convergence rates under general distributional assumptions. Specifically, we introduce a relaxed smoothness condition parameterized by a constant $L$, which is small for many practical distributions (e.g., Gaussian mixture models). We prove that the DDPM sampler with accurate score estimates achieves a convergence rate of $$\widetilde{O}\left(\frac{d\min\{d,L^2\}}{T^2}\right)~\text{in Kullback-Leibler divergence},$$ where $d$ is the data dimension, $T$ is the number of iterations, and $\widetilde{O}$ hides polylogarithmic factors in $T$. This result substantially improves upon the best-known $d^2/T^2$ rate when $L < \sqrt{d}$. By establishing a matching lower bound, we show that our convergence analysis is tight for a wide array of target distributions. Moreover, it reveals that DDPM and DDIM share the same dependence on $d$, raising an interesting question of why DDIM often appears empirically faster.

---

### Toward Accurate Long-Horizon Robotic Manipulation: Language-to-Action with Foundation Models via Scene Graphs

Authors: Sushil Samuel Dinesh, Shinkyu Park
Published: 2025-10-31
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.27558v1

This paper presents a framework that leverages pre-trained foundation models for robotic manipulation without domain-specific training. The framework integrates off-the-shelf models, combining multimodal perception from foundation models with a general-purpose reasoning model capable of robust task sequencing. Scene graphs, dynamically maintained within the framework, provide spatial awareness and enable consistent reasoning about the environment. The framework is evaluated through a series of tabletop robotic manipulation experiments, and the results highlight its potential for building robotic manipulation systems directly on top of off-the-shelf foundation models.

---

### Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization

Authors: Inacio Vieira, Antonio Castaldo, James O'Doherty, Sheila Castilho
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27556v1

LLMs often require adaptation to domain-specific requirements, a process that can be expensive when relying solely on SFT. We present an empirical study on applying CPO to simulate a post-editing workflow for data-efficient domain adaptation. Our approach synthesizes preference pairs by treating the base model's own raw output as the 'rejected' translation and the human-approved TM entry as the 'chosen' one. This method provides direct feedback on the model's current knowledge, guiding it to align with domain-specific standards. Experiments in English-Brazilian Portuguese and English-Korean show that, by using just 14.7k preference pairs, the model achieves performance close to that of a model trained on 160k+ samples with SFT, demonstrating significant data efficiency. Although we showcase its effectiveness in MT, this application of CPO naturally generalizes to other generative tasks where a model's initial drafts can serve as a contrastive signal against a golden reference.

---

### Sybil-Resistant Service Discovery for Agent Economies

Authors: David Shi, Kevin Joo
Published: 2025-10-31
Categories: cs.CR, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2510.27554v1

x402 enables Hypertext Transfer Protocol (HTTP) services like application programming interfaces (APIs), data feeds, and inference providers to accept cryptocurrency payments for access. As agents increasingly consume these services, discovery becomes critical: which swap interface should an agent trust? Which data provider is the most reliable? We introduce TraceRank, a reputation-weighted ranking algorithm where payment transactions serve as endorsements. TraceRank seeds addresses with precomputed reputation metrics and propagates reputation through payment flows weighted by transaction value and temporal recency. Applied to x402's payment graph, this surfaces services preferred by high-reputation users rather than those with high transaction volume. Our system combines TraceRank with semantic search to respond to natural language queries with high quality results. We argue that reputation propagation resists Sybil attacks by making spam services with many low-reputation payers rank below legitimate services with few high-reputation payers. Ultimately, we aim to construct a search method for x402 enabled services that avoids infrastructure bias and has better performance than purely volume based or semantic methods.

---

### Multilingual BERT language model for medical tasks: Evaluation on domain-specific adaptation and cross-linguality

Authors: Yinghao Luo, Lang Zhou, Amrish Jhingoer, Klaske Vliegenthart Jongbloed, Carlijn Jordans, Ben Werkhoven, Tom Seinen, Erik van Mulligen, Casper Rokx, Yunlei Li
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27552v1

In multilingual healthcare applications, the availability of domain-specific natural language processing(NLP) tools is limited, especially for low-resource languages. Although multilingual bidirectional encoder representations from transformers (BERT) offers a promising motivation to mitigate the language gap, the medical NLP tasks in low-resource languages are still underexplored. Therefore, this study investigates how further pre-training on domain-specific corpora affects model performance on medical tasks, focusing on three languages: Dutch, Romanian and Spanish. In terms of further pre-training, we conducted four experiments to create medical domain models. Then, these models were fine-tuned on three downstream tasks: Automated patient screening in Dutch clinical notes, named entity recognition in Romanian and Spanish clinical notes. Results show that domain adaptation significantly enhanced task performance. Furthermore, further differentiation of domains, e.g. clinical and general biomedical domains, resulted in diverse performances. The clinical domain-adapted model outperformed the more general biomedical domain-adapted model. Moreover, we observed evidence of cross-lingual transferability. Moreover, we also conducted further investigations to explore potential reasons contributing to these performance differences. These findings highlight the feasibility of domain adaptation and cross-lingual ability in medical NLP. Within the low-resource language settings, these findings can provide meaningful guidance for developing multilingual medical NLP systems to mitigate the lack of training data and thereby improve the model performance.

---

### MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series

Authors: Xue Xia, Randall Balestriero, Tao Zhang, Yixin Zhou, Andrew Ding, Dev Saini, Lorenz Hurni
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27547v1

Historical maps are unique and valuable archives that document geographic features across different time periods. However, automated analysis of historical map images remains a significant challenge due to their wide stylistic variability and the scarcity of annotated training data. Constructing linked spatio-temporal datasets from historical map time series is even more time-consuming and labor-intensive, as it requires synthesizing information from multiple maps. Such datasets are essential for applications such as dating buildings, analyzing the development of road networks and settlements, studying environmental changes etc. We present MapSAM2, a unified framework for automatically segmenting both historical map images and time series. Built on a visual foundation model, MapSAM2 adapts to diverse segmentation tasks with few-shot fine-tuning. Our key innovation is to treat both historical map images and time series as videos. For images, we process a set of tiles as a video, enabling the memory attention mechanism to incorporate contextual cues from similar tiles, leading to improved geometric accuracy, particularly for areal features. For time series, we introduce the annotated Siegfried Building Time Series Dataset and, to reduce annotation costs, propose generating pseudo time series from single-year maps by simulating common temporal transformations. Experimental results show that MapSAM2 learns temporal associations effectively and can accurately segment and link buildings in time series under limited supervision or using pseudo videos. We will release both our dataset and code to support future research.

---

### EBT-Policy: Energy Unlocks Emergent Physical Reasoning Capabilities

Authors: Travis Davies, Yiqi Huang, Alexi Gladstone, Yunxin Liu, Xiang Chen, Heng Ji, Huxian Liu, Luhui Hu
Published: 2025-10-31
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.27545v1

Implicit policies parameterized by generative models, such as Diffusion Policy, have become the standard for policy learning and Vision-Language-Action (VLA) models in robotics. However, these approaches often suffer from high computational cost, exposure bias, and unstable inference dynamics, which lead to divergence under distribution shifts. Energy-Based Models (EBMs) address these issues by learning energy landscapes end-to-end and modeling equilibrium dynamics, offering improved robustness and reduced exposure bias. Yet, policies parameterized by EBMs have historically struggled to scale effectively. Recent work on Energy-Based Transformers (EBTs) demonstrates the scalability of EBMs to high-dimensional spaces, but their potential for solving core challenges in physically embodied models remains underexplored. We introduce a new energy-based architecture, EBT-Policy, that solves core issues in robotic and real-world settings. Across simulated and real-world tasks, EBT-Policy consistently outperforms diffusion-based policies, while requiring less training and inference computation. Remarkably, on some tasks it converges within just two inference steps, a 50x reduction compared to Diffusion Policy's 100. Moreover, EBT-Policy exhibits emergent capabilities not seen in prior models, such as zero-shot recovery from failed action sequences using only behavior cloning and without explicit retry training. By leveraging its scalar energy for uncertainty-aware inference and dynamic compute allocation, EBT-Policy offers a promising path toward robust, generalizable robot behavior under distribution shifts.

---

### TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation

Authors: Nikolaus Holzer, William Fishell, Baishakhi Ray, Mark Santolucito
Published: 2025-10-31
Categories: cs.AI, cs.FL
arXiv: https://arxiv.org/abs/2510.27544v3

Current training paradigms, optimized for long-horizon reasoning trace execution, have made Large Language Models (LLMs) excel at pattern matching and forward simulation of reasoning, but underperform at counterfactual causal understanding and reasoning. We introduce TempoBench, the first formally verifiable temporal benchmark that isolates counterfactual causal attribution over execution trajectories, and we show that LLMs categorically fall back to brute-force simulation-based reasoning to solve causal reasoning problems. Built from synthesized deterministic Mealy machines, TempoBench provides an infinitely scalable corpus of trajectory-based causal reasoning problems with controllable complexity and provably correct causal labels. Frontier models reach 96% step accuracy simulating a system forward, and fall to 32% when asked which inputs were necessary for an observed output, displaying what we call the SIM/MIN gap. Our findings show that LLMs cannot reliably identify minimal necessary causes, often confusing ``possible inputs'' with ``necessary causes,'' demonstrating an inability to understand which inputs were not needed. This failure is critical for deployment in causal inference tasks such as debugging, root cause analysis, and task planning where agents must use counterfactual reasoning to plan for specific desired outcomes. We show that training on TempoBench yields a targeted gain on causal benchmarks in open-source models while matching general-purpose, math, and code reasoning datasets on standard benchmarks. This indicates counterfactual causal reasoning is a learnable, architecturally distinct capability that sits on top of existing reasoning competencies.

---

### DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models

Authors: Malik H. Altakrori, Nizar Habash, Abed Alhakim Freihat, Younes Samih, Kirill Chirkunov, Muhammed AbuOdeh, Radu Florian, Teresa Lynn, Preslav Nakov, Alham Fikri Aji
Published: 2025-10-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.27543v2

We present DialectalArabicMMLU, a new benchmark for evaluating the performance of large language models (LLMs) across Arabic dialects. While recently developed Arabic and multilingual benchmarks have advanced LLM evaluation for Modern Standard Arabic (MSA), dialectal varieties remain underrepresented despite their prevalence in everyday communication. DialectalArabicMMLU extends the MMLU-Redux framework through manual translation and adaptation of 3K multiple-choice question-answer pairs into five major dialects (Syrian, Egyptian, Emirati, Saudi, and Moroccan), yielding a total of 15K QA pairs across 32 academic and professional domains (22K QA pairs when also including English and MSA). The benchmark enables systematic assessment of LLM reasoning and comprehension beyond MSA, supporting both task-based and linguistic analysis. We evaluate 19 open-weight Arabic and multilingual LLMs (1B-13B parameters) and report substantial performance variation across dialects, revealing persistent gaps in dialectal generalization. DialectalArabicMMLU provides the first unified, human-curated resource for measuring dialectal understanding in Arabic, thus promoting more inclusive evaluation and future model development.

---

### AstuteRAG-FQA: Task-Aware Retrieval-Augmented Generation Framework for Proprietary Data Challenges in Financial Question Answering

Authors: Mohammad Zahangir Alam, Khandoker Ashik Uz Zaman, Mahdi H. Miraz
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27537v1

Retrieval-Augmented Generation (RAG) shows significant promise in knowledge-intensive tasks by improving domain specificity, enhancing temporal relevance, and reducing hallucinations. However, applying RAG to finance encounters critical challenges: restricted access to proprietary datasets, limited retrieval accuracy, regulatory constraints, and sensitive data interpretation. We introduce AstuteRAG-FQA, an adaptive RAG framework tailored for Financial Question Answering (FQA), leveraging task-aware prompt engineering to address these challenges. The framework uses a hybrid retrieval strategy integrating both open-source and proprietary financial data while maintaining strict security protocols and regulatory compliance. A dynamic prompt framework adapts in real time to query complexity, improving precision and contextual relevance. To systematically address diverse financial queries, we propose a four-tier task classification: explicit factual, implicit factual, interpretable rationale, and hidden rationale involving implicit causal reasoning. For each category, we identify key challenges, datasets, and optimization techniques within the retrieval and generation process. The framework incorporates multi-layered security mechanisms including differential privacy, data anonymization, and role-based access controls to protect sensitive financial information. Additionally, AstuteRAG-FQA implements real-time compliance monitoring through automated regulatory validation systems that verify responses against industry standards and legal obligations. We evaluate three data integration techniques - contextual embedding, small model augmentation, and targeted fine-tuning - analyzing their efficiency and feasibility across varied financial environments.

---

### Patient-Centered Summarization Framework for AI Clinical Summarization: A Mixed-Methods Design

Authors: Maria Lizarazo Jimenez, Ana Gabriela Claros, Kieran Green, David Toro-Tobon, Felipe Larios, Sheena Asthana, Camila Wenczenovicz, Kerly Guevara Maldonado, Luis Vilatuna-Andrango, Cristina Proano-Velez, Satya Sai Sri Bandi, Shubhangi Bagewadi et al.
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27535v1

Large Language Models (LLMs) are increasingly demonstrating the potential to reach human-level performance in generating clinical summaries from patient-clinician conversations. However, these summaries often focus on patients' biology rather than their preferences, values, wishes, and concerns. To achieve patient-centered care, we propose a new standard for Artificial Intelligence (AI) clinical summarization tasks: Patient-Centered Summaries (PCS). Our objective was to develop a framework to generate PCS that capture patient values and ensure clinical utility and to assess whether current open-source LLMs can achieve human-level performance in this task. We used a mixed-methods process. Two Patient and Public Involvement groups (10 patients and 8 clinicians) in the United Kingdom participated in semi-structured interviews exploring what personal and contextual information should be included in clinical summaries and how it should be structured for clinical use. Findings informed annotation guidelines used by eight clinicians to create gold-standard PCS from 88 atrial fibrillation consultations. Sixteen consultations were used to refine a prompt aligned with the guidelines. Five open-source LLMs (Llama-3.2-3B, Llama-3.1-8B, Mistral-8B, Gemma-3-4B, and Qwen3-8B) generated summaries for 72 consultations using zero-shot and few-shot prompting, evaluated with ROUGE-L, BERTScore, and qualitative metrics. Patients emphasized lifestyle routines, social support, recent stressors, and care values. Clinicians sought concise functional, psychosocial, and emotional context. The best zero-shot performance was achieved by Mistral-8B (ROUGE-L 0.189) and Llama-3.1-8B (BERTScore 0.673); the best few-shot by Llama-3.1-8B (ROUGE-L 0.206, BERTScore 0.683). Completeness and fluency were similar between experts and models, while correctness and patient-centeredness favored human PCS.

---

### Deep Neural Watermarking for Robust Copyright Protection in 3D Point Clouds

Authors: Khandoker Ashik Uz Zaman, Mohammad Zahangir Alam, Mohammed N. M. Ali, Mahdi H. Miraz
Published: 2025-10-31
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.27533v1

The protection of intellectual property has become critical due to the rapid growth of three-dimensional content in digital media. Unlike traditional images or videos, 3D point clouds present unique challenges for copyright enforcement, as they are especially vulnerable to a range of geometric and non-geometric attacks that can easily degrade or remove conventional watermark signals. In this paper, we address these challenges by proposing a robust deep neural watermarking framework for 3D point cloud copyright protection and ownership verification. Our approach embeds binary watermarks into the singular values of 3D point cloud blocks using spectral decomposition, i.e. Singular Value Decomposition (SVD), and leverages the extraction capabilities of Deep Learning using PointNet++ neural network architecture. The network is trained to reliably extract watermarks even after the data undergoes various attacks such as rotation, scaling, noise, cropping and signal distortions. We validated our method using the publicly available ModelNet40 dataset, demonstrating that deep learning-based extraction significantly outperforms traditional SVD-based techniques under challenging conditions. Our experimental evaluation demonstrates that the deep learning-based extraction approach significantly outperforms existing SVD-based methods with deep learning achieving bitwise accuracy up to 0.83 and Intersection over Union (IoU) of 0.80, compared to SVD achieving a bitwise accuracy of 0.58 and IoU of 0.26 for the Crop (70%) attack, which is the most severe geometric distortion in our experiment. This demonstrates our method's ability to achieve superior watermark recovery and maintain high fidelity even under severe distortions.

---

### SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps

Authors: Neha Srikanth, Victor Bursztyn, Puneet Mathur, Ani Nenkova
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27532v1

We introduce SQLSpace, a human-interpretable, generalizable, compact representation for text-to-SQL examples derived with minimal human intervention. We demonstrate the utility of these representations in evaluation with three use cases: (i) closely comparing and contrasting the composition of popular text-to-SQL benchmarks to identify unique dimensions of examples they evaluate, (ii) understanding model performance at a granular level beyond overall accuracy scores, and (iii) improving model performance through targeted query rewriting based on learned correctness estimation. We show that SQLSpace enables analysis that would be difficult with raw examples alone: it reveals compositional differences between benchmarks, exposes performance patterns obscured by accuracy alone, and supports modeling of query success.

---