# Research Papers — 2025-10 · bundle page 59 of 217

> Full-text markdown of papers #2901–2950 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/59
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/58.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/60.md)

### Learning Coupled Earth System Dynamics with GraphDOP

Authors: Eulalie Boucher, Mihai Alexe, Peter Lean, Ewan Pinnington, Simon Lang, Patrick Laloyaux, Lorenzo Zampieri, Patricia de Rosnay, Niels Bormann, Anthony McNally
Published: 2025-10-23
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.20416v1

Interactions between different components of the Earth System (e.g. ocean, atmosphere, land and cryosphere) are a crucial driver of global weather patterns. Modern Numerical Weather Prediction (NWP) systems typically run separate models of the different components, explicitly coupled across their interfaces to additionally model exchanges between the different components. Accurately representing these coupled interactions remains a major scientific and technical challenge of weather forecasting. GraphDOP is a graph-based machine learning model that learns to forecast weather directly from raw satellite and in-situ observations, without reliance on reanalysis products or traditional physics-based NWP models. GraphDOP simultaneously embeds information from diverse observation sources spanning the full Earth system into a shared latent space. This enables predictions that implicitly capture cross-domain interactions in a single model without the need for any explicit coupling. Here we present a selection of case studies which illustrate the capability of GraphDOP to forecast events where coupled processes play a particularly key role. These include rapid sea-ice freezing in the Arctic, mixing-induced ocean surface cooling during Hurricane Ian and the severe European heat wave of 2022. The results suggest that learning directly from Earth System observations can successfully characterise and propagate cross-component interactions, offering a promising path towards physically consistent end-to-end data-driven Earth System prediction with a single model.

---

### Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processes

Authors: Sishun Liu, Ke Deng, Yongli Ren, Yan Wang, Xiuzhen Zhang
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20414v2

Marked Temporal Point Process (MTPP) has been well studied to model the event distribution in marked event streams, which can be used to predict the mark and arrival time of the next event. However, existing studies overlook that the distribution of event marks is highly imbalanced in many real-world applications, with some marks being frequent but others rare. The imbalance poses a significant challenge to the performance of the next event prediction, especially for events of rare marks. To address this issue, we propose a thresholding method, which learns thresholds to tune the mark probability normalized by the mark's prior probability to optimize mark prediction, rather than predicting the mark directly based on the mark probability as in existing studies. In conjunction with this method, we predict the mark first and then the time. In particular, we develop a novel neural MTPP model to support effective time sampling and estimation of mark probability without computationally expensive numerical improper integration. Extensive experiments on real-world datasets demonstrate the superior performance of our solution against various baselines for the next event mark and time prediction. The code is available at https://github.com/undes1red/IFNMTPP.

---

### Why DPO is a Misspecified Estimator and How to Fix It

Authors: Aditya Gopalan, Sayak Ray Chowdhury, Debangshu Banerjee
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20413v1

Direct alignment algorithms such as Direct Preference Optimization (DPO) fine-tune models based on preference data, using only supervised learning instead of two-stage reinforcement learning with human feedback (RLHF). We show that DPO encodes a statistical estimation problem over reward functions induced by a parametric policy class. When the true reward function that generates preferences cannot be realized via the policy class, DPO becomes misspecified, resulting in failure modes such as preference order reversal, worsening of policy reward, and high sensitivity to the input preference data distribution. On the other hand, we study the local behavior of two-stage RLHF for a parametric class and relate it to a natural gradient step in policy space. Our fine-grained geometric characterization allows us to propose AuxDPO, which introduces additional auxiliary variables in the DPO loss function to help move towards the RLHF solution in a principled manner and mitigate the misspecification in DPO. We empirically demonstrate the superior performance of AuxDPO on didactic bandit settings as well as LLM alignment tasks.

---

### Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction

Authors: Suchir Salhan, Hongyi Gu, Donya Rooein, Diana Galvan-Sosa, Gabrielle Gaudeau, Andrew Caines, Zheng Yuan, Paula Buttery
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20411v1

Multi-turn dialogues between a child and a caregiver are characterized by a property called contingency - that is, prompt, direct, and meaningful exchanges between interlocutors. We introduce ContingentChat, a teacher-student framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M words. Using a novel alignment dataset for post-training, BabyLM generates responses that are more grammatical and cohesive. Experiments with adaptive teacher decoding strategies show limited additional gains. ContingentChat demonstrates the benefits of targeted post-training for dialogue quality and indicates that contingency remains a challenging goal for BabyLMs.

---

### Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control

Authors: Tom Maus, Asma Atamna, Tobias Glasmachers
Published: 2025-10-23
Categories: cs.LG, cs.AI, cs.MA, eess.SY
arXiv: https://arxiv.org/abs/2510.20408v1

Autonomous control of multi-stage industrial processes requires both local specialization and global coordination. Reinforcement learning (RL) offers a promising approach, but its industrial adoption remains limited due to challenges such as reward design, modularity, and action space management. Many academic benchmarks differ markedly from industrial control problems, limiting their transferability to real-world applications. This study introduces an enhanced industry-inspired benchmark environment that combines tasks from two existing benchmarks, SortingEnv and ContainerGym, into a sequential recycling scenario with sorting and pressing operations. We evaluate two control strategies: a modular architecture with specialized agents and a monolithic agent governing the full system, while also analyzing the impact of action masking. Our experiments show that without action masking, agents struggle to learn effective policies, with the modular architecture performing better. When action masking is applied, both architectures improve substantially, and the performance gap narrows considerably. These results highlight the decisive role of action space constraints and suggest that the advantages of specialization diminish as action complexity is reduced. The proposed benchmark thus provides a valuable testbed for exploring practical and robust multi-agent RL solutions in industrial automation, while contributing to the ongoing debate on centralization versus specialization.

---

### PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

Authors: Xiaogang Jia, Qian Wang, Anrui Wang, Han A. Wang, Balázs Gyenes, Emiliyan Gospodinov, Xinkai Jiang, Ge Li, Hongyi Zhou, Weiran Liao, Xi Huang, Maximilian Beck et al.
Published: 2025-10-23
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.20406v3

Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure, while RGB images provide rich semantic context. Current point cloud methods struggle to capture fine-grained detail, especially for complex tasks, which RGB methods lack geometric awareness, which hinders their precision and generalization. We introduce PointMapPolicy, a novel approach that conditions diffusion policies on structured grids of points without downsampling. The resulting data type makes it easier to extract shape and spatial relationships from observations, and can be transformed between reference frames. Yet due to their structure in a regular grid, we enable the use of established computer vision techniques directly to 3D data. Using xLSTM as a backbone, our model efficiently fuses the point maps with RGB data for enhanced multi-modal perception. Through extensive experiments on the RoboCasa and CALVIN benchmarks and real robot evaluations, we demonstrate that our method achieves state-of-the-art performance across diverse manipulation tasks. The overview and demos are available on our project page: https://point-map.github.io/Point-Map/

---

### Identification and Debiased Learning of Causal Effects with General Instrumental Variables

Authors: Shuyuan Chen, Peng Zhang, Yifan Cui
Published: 2025-10-23
Categories: stat.ME, econ.EM, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.20404v2

Instrumental variable methods are fundamental to causal inference when treatment assignment is confounded by unobserved variables. In this article, we develop a general nonparametric causal framework for identification and learning with multi-categorical or continuous instrumental variables. Specifically, the mean potential outcomes and the average treatment effect can be identified via a regular weighting function derived from the proposed framework. Leveraging semiparametric theory, we derive efficient influence functions and construct two consistent, asymptotically normal estimators via debiased machine learning. The first estimator uses a prespecified weighting function, while the second estimator selects the optimal weighting function adaptively. Extensions to longitudinal data, dynamic treatment regimes, and multiplicative instrumental variables are further developed. We demonstrate the proposed method by employing simulation studies and analyzing real data from the Job Training Partnership Act program.

---

### A computational model and tool for generating more novel opportunities in professional innovation processes

Authors: Neil Maiden, Konstantinos Zachos, James Lockerbie, Kostas Petrianakis, Amanda Brown
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20402v1

This paper presents a new computational model of creative outcomes, informed by creativity theories and techniques, which was implemented to generate more novel opportunities for innovation projects. The model implemented five functions that were developed to contribute to the generation of innovation opportunities with higher novelty without loss of usefulness. The model was evaluated using opportunities generated for an innovation project in the hospitality sector. The evaluation revealed that the computational model generated outcomes that were more novel and/or useful than outcomes from Notebook LM and ChatGPT4o. However, not all model functions contributed to the generation of more novel opportunities, leading to new directions for further model development

---

### Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval

Authors: Qing Wang, Chong-Wah Ngo, Yu Cao, Ee-Peng Lim
Published: 2025-10-23
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.20393v1

Existing approaches for image-to-recipe retrieval have the implicit assumption that a food image can fully capture the details textually documented in its recipe. However, a food image only reflects the visual outcome of a cooked dish and not the underlying cooking process. Consequently, learning cross-modal representations to bridge the modality gap between images and recipes tends to ignore subtle, recipe-specific details that are not visually apparent but are crucial for recipe retrieval. Specifically, the representations are biased to capture the dominant visual elements, resulting in difficulty in ranking similar recipes with subtle differences in use of ingredients and cooking methods. The bias in representation learning is expected to be more severe when the training data is mixed of images and recipes sourced from different cuisines. This paper proposes a novel causal approach that predicts the culinary elements potentially overlooked in images, while explicitly injecting these elements into cross-modal representation learning to mitigate biases. Experiments are conducted on the standard monolingual Recipe1M dataset and a newly curated multilingual multicultural cuisine dataset. The results indicate that the proposed causal representation learning is capable of uncovering subtle ingredients and cooking actions and achieves impressive retrieval performance on both monolingual and multilingual multicultural datasets.

---

### FLAS: a combination of proactive and reactive auto-scaling architecture for distributed services

Authors: Víctor Rampérez, Javier Soriano, David Lizcano, Juan A. Lara
Published: 2025-10-23
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2510.20388v1

Cloud computing has established itself as the support for the vast majority of emerging technologies, mainly due to the characteristic of elasticity it offers. Auto-scalers are the systems that enable this elasticity by acquiring and releasing resources on demand to ensure an agreed service level. In this article we present FLAS (Forecasted Load Auto-Scaling), an auto-scaler for distributed services that combines the advantages of proactive and reactive approaches according to the situation to decide the optimal scaling actions in every moment. The main novelties introduced by FLAS are (i) a predictive model of the high-level metrics trend which allows to anticipate changes in the relevant SLA parameters (e.g. performance metrics such as response time or throughput) and (ii) a reactive contingency system based on the estimation of high-level metrics from resource use metrics, reducing the necessary instrumentation (less invasive) and allowing it to be adapted agnostically to different applications. We provide a FLAS implementation for the use case of a content-based publish-subscribe middleware (E-SilboPS) that is the cornerstone of an event-driven architecture. To the best of our knowledge, this is the first auto-scaling system for content-based publish-subscribe distributed systems (although it is generic enough to fit any distributed service). Through an evaluation based on several test cases recreating not only the expected contexts of use, but also the worst possible scenarios (following the Boundary-Value Analysis or BVA test methodology), we have validated our approach and demonstrated the effectiveness of our solution by ensuring compliance with performance requirements over 99% of the time.

---

### Relative-Based Scaling Law for Neural Language Models

Authors: Baoqing Yue, Jinyuan Zhou, Zixi Wei, Jingtao Zhan, Qingyao Ai, Yiqun Liu
Published: 2025-10-23
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.20387v1

Scaling laws aim to accurately predict model performance across different scales. Existing scaling-law studies almost exclusively rely on cross-entropy as the evaluation metric. However, cross-entropy provides only a partial view of performance: it measures the absolute probability assigned to the correct token, but ignores the relative ordering between correct and incorrect tokens. Yet, relative ordering is crucial for language models, such as in greedy-sampling scenario. To address this limitation, we investigate scaling from the perspective of relative ordering. We first propose the Relative-Based Probability (RBP) metric, which quantifies the probability that the correct token is ranked among the top predictions. Building on this metric, we establish the Relative-Based Scaling Law, which characterizes how RBP improves with increasing model size. Through extensive experiments on four datasets and four model families spanning five orders of magnitude, we demonstrate the robustness and accuracy of this law. Finally, we illustrate the broad application of this law with two examples, namely providing a deeper explanation of emergence phenomena and facilitating finding fundamental theories of scaling laws. In summary, the Relative-Based Scaling Law complements the cross-entropy perspective and contributes to a more complete understanding of scaling large language models. Thus, it offers valuable insights for both practical development and theoretical exploration.

---

### NeoDictaBERT: Pushing the Frontier of BERT models for Hebrew

Authors: Shaltiel Shmidman, Avi Shmidman, Moshe Koppel
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20386v1

Since their initial release, BERT models have demonstrated exceptional performance on a variety of tasks, despite their relatively small size (BERT-base has ~100M parameters). Nevertheless, the architectural choices used in these models are outdated compared to newer transformer-based models such as Llama3 and Qwen3. In recent months, several architectures have been proposed to close this gap. ModernBERT and NeoBERT both show strong improvements on English benchmarks and significantly extend the supported context window. Following their successes, we introduce NeoDictaBERT and NeoDictaBERT-bilingual: BERT-style models trained using the same architecture as NeoBERT, with a dedicated focus on Hebrew texts. These models outperform existing ones on almost all Hebrew benchmarks and provide a strong foundation for downstream tasks. Notably, the NeoDictaBERT-bilingual model shows strong results on retrieval tasks, outperforming other multilingual models of similar size. In this paper, we describe the training process and report results across various benchmarks. We release the models to the community as part of our goal to advance research and development in Hebrew NLP.

---

### Positional Encoding Field

Authors: Yunpeng Bai, Haoxiang Li, Qixing Huang
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20385v1

Diffusion Transformers (DiTs) have emerged as the dominant architecture for visual generation, powering state-of-the-art image and video models. By representing images as patch tokens with positional encodings (PEs), DiTs combine Transformer scalability with spatial and temporal inductive biases. In this work, we revisit how DiTs organize visual content and discover that patch tokens exhibit a surprising degree of independence: even when PEs are perturbed, DiTs still produce globally coherent outputs, indicating that spatial coherence is primarily governed by PEs. Motivated by this finding, we introduce the Positional Encoding Field (PE-Field), which extends positional encodings from the 2D plane to a structured 3D field. PE-Field incorporates depth-aware encodings for volumetric reasoning and hierarchical encodings for fine-grained sub-patch control, enabling DiTs to model geometry directly in 3D space. Our PE-Field-augmented DiT achieves state-of-the-art performance on single-image novel view synthesis and generalizes to controllable spatial image editing.

---

### Hierarchical Time Series Forecasting with Robust Reconciliation

Authors: Shuhei Aikawa, Aru Suzuki, Kei Yoshitake, Kanata Teshigawara, Akira Iwabuchi, Ken Kobayashi, Kazuhide Nakata
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20383v2

This paper focuses on forecasting hierarchical time-series data, where each higher-level observation equals the sum of its corresponding lower-level time series. In such contexts, the forecast values should be coherent, meaning that the forecast value of each parent series exactly matches the sum of the forecast values of its child series. Existing hierarchical forecasting methods typically generate base forecasts independently for each series and then apply a reconciliation procedure to adjust them so that the resulting forecast values are coherent across the hierarchy. These methods generally derive an optimal reconciliation, using a covariance matrix of the forecast error. In practice, however, the true covariance matrix is unknown and has to be estimated from finite samples in advance. This gap between the true and estimated covariance matrix may degrade forecast performance. To address this issue, we propose a robust optimization framework for hierarchical reconciliation that accounts for uncertainty in the estimated covariance matrix. We first introduce an uncertainty set for the estimated covariance matrix and formulate a reconciliation problem that minimizes the worst-case average of weighted squared residuals over this uncertainty set. We show that our problem can be cast as a semidefinite optimization problem. Numerical experiments demonstrate that the proposed robust reconciliation method achieved better forecast performance than existing hierarchical forecasting methods, which indicates the effectiveness of integrating uncertainty into the reconciliation process.

---

### VLSP 2025 MLQA-TSR Challenge: Vietnamese Multimodal Legal Question Answering on Traffic Sign Regulation

Authors: Son T. Luu, Trung Vo, Hiep Nguyen, Khanh Quoc Tran, Kiet Van Nguyen, Vu Tran, Ngan Luu-Thuy Nguyen, Le-Minh Nguyen
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20381v1

This paper presents the VLSP 2025 MLQA-TSR - the multimodal legal question answering on traffic sign regulation shared task at VLSP 2025. VLSP 2025 MLQA-TSR comprises two subtasks: multimodal legal retrieval and multimodal question answering. The goal is to advance research on Vietnamese multimodal legal text processing and to provide a benchmark dataset for building and evaluating intelligent systems in multimodal legal domains, with a focus on traffic sign regulation in Vietnam. The best-reported results on VLSP 2025 MLQA-TSR are an F2 score of 64.55% for multimodal legal retrieval and an accuracy of 86.30% for multimodal question answering.

---

### IKnow: Instruction-Knowledge-Aware Continual Pretraining for Effective Domain Adaptation

Authors: Tianyi Zhang, Florian Mai, Lucie Flek
Published: 2025-10-23
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.20377v1

Continual pretraining promises to adapt large language models (LLMs) to new domains using only unlabeled test-time data, but naively applying standard self-supervised objectives to instruction-tuned models is known to degrade their instruction-following capability and semantic representations. Existing fixes assume access to the original base model or rely on knowledge from an external domain-specific database - both of which pose a realistic barrier in settings where the base model weights are withheld for safety reasons or reliable external corpora are unavailable. In this work, we propose Instruction-Knowledge-Aware Continual Adaptation (IKnow), a simple and general framework that formulates novel self-supervised objectives in the instruction-response dialogue format. Rather than depend- ing on external resources, IKnow leverages domain knowledge embedded within the text itself and learns to encode it at a deeper semantic level.

---

### The Impact of Negated Text on Hallucination with Large Language Models

Authors: Jaehyung Seo, Hyeonseok Moon, Heuiseok Lim
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20375v1

Recent studies on hallucination in large language models (LLMs) have been actively progressing in natural language processing. However, the impact of negated text on hallucination with LLMs remains largely unexplored. In this paper, we set three important yet unanswered research questions and aim to address them. To derive the answers, we investigate whether LLMs can recognize contextual shifts caused by negation and still reliably distinguish hallucinations comparable to affirmative cases. We also design the NegHalu dataset by reconstructing existing hallucination detection datasets with negated expressions. Our experiments demonstrate that LLMs struggle to detect hallucinations in negated text effectively, often producing logically inconsistent or unfaithful judgments. Moreover, we trace the internal state of LLMs as they process negated inputs at the token level and reveal the challenges of mitigating their unintended effects.

---

### Testing Most Influential Sets

Authors: Lucas D. Konrad, Nikolas Kuschnig
Published: 2025-10-23
Categories: stat.ML, cs.LG, econ.EM, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2510.20372v4

Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work identifies these most influential sets, there is no formal way to tell when maximum influence is excessive rather than expected under natural random sampling variation. We address this gap by developing a principled framework for most influential sets. Focusing on linear least-squares, we derive a convenient exact influence formula and identify the extreme value distributions of maximal influence - the heavy-tailed Fréchet for constant-size sets and heavy-tailed data, and the well-behaved Gumbel for growing sets or light tails. This allows us to conduct rigorous hypothesis tests for excessive influence. We demonstrate through applications across economics, biology, and machine learning benchmarks, resolving contested findings and replacing ad-hoc heuristics with rigorous inference.

---

### Ask a Strong LLM Judge when Your Reward Model is Uncertain

Authors: Zhenghao Xu, Qin Lu, Qingru Zhang, Liang Qiu, Ilgee Hong, Changlong Yu, Wenlin Yao, Yao Liu, Haoming Jiang, Lihong Li, Hyokun Yun, Tuo Zhao
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20369v1

Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human preferences are vulnerable to reward hacking and generalize poorly to out-of-distribution (OOD) inputs. By contrast, strong LLM judges equipped with reasoning capabilities demonstrate superior generalization, even without additional training, but incur significantly higher inference costs, limiting their applicability in online RLHF. In this work, we propose an uncertainty-based routing framework that efficiently complements a fast RM with a strong but costly LLM judge. Our approach formulates advantage estimation in policy gradient (PG) methods as pairwise preference classification, enabling principled uncertainty quantification to guide routing. Uncertain pairs are forwarded to the LLM judge, while confident ones are evaluated by the RM. Experiments on RM benchmarks demonstrate that our uncertainty-based routing strategy significantly outperforms random judge calling at the same cost, and downstream alignment results showcase its effectiveness in improving online RLHF.

---

### A Transformer Inspired AI-based MIMO receiver

Authors: András Rácz, Tamás Borsos, András Veres, Benedek Csala
Published: 2025-10-23
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2510.20363v1

We present AttDet, a Transformer-inspired MIMO (Multiple Input Multiple Output) detection method that treats each transmit layer as a token and learns inter-stream interference via a lightweight self-attention mechanism. Queries and keys are derived directly from the estimated channel matrix, so attention scores quantify channel correlation. Values are initialized by matched-filter outputs and iteratively refined. The AttDet design combines model-based interpretability with data-driven flexibility. We demonstrate through link-level simulations under realistic 5G channel models and high-order, mixed QAM modulation and coding schemes, that AttDet can approach near-optimal BER/BLER (Bit Error Rate/Block Error Rate) performance while maintaining predictable, polynomial complexity.

---

### ComProScanner: A multi-agent based framework for composition-property structured data extraction from scientific literature

Authors: Aritra Roy, Enrico Grisan, John Buckeridge, Chiara Gattinoni
Published: 2025-10-23
Categories: physics.comp-ph, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2510.20362v1

Since the advent of various pre-trained large language models, extracting structured knowledge from scientific text has experienced a revolutionary change compared with traditional machine learning or natural language processing techniques. Despite these advances, accessible automated tools that allow users to construct, validate, and visualise datasets from scientific literature extraction remain scarce. We therefore developed ComProScanner, an autonomous multi-agent platform that facilitates the extraction, validation, classification, and visualisation of machine-readable chemical compositions and properties, integrated with synthesis data from journal articles for comprehensive database creation. We evaluated our framework using 100 journal articles against 10 different LLMs, including both open-source and proprietary models, to extract highly complex compositions associated with ceramic piezoelectric materials and corresponding piezoelectric strain coefficients (d33), motivated by the lack of a large dataset for such materials. DeepSeek-V3-0324 outperformed all models with a significant overall accuracy of 0.82. This framework provides a simple, user-friendly, readily-usable package for extracting highly complex experimental data buried in the literature to build machine learning or deep learning datasets.

---

### Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning)

Authors: Francesca Padovani, Bastian Bunzeck, Manar Ali, Omar Momen, Arianna Bisazza, Hendrik Buschmeier, Sina Zarrieß
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20358v1

We investigate whether pre-training exclusively on dialogue data results in formally and functionally apt small language models. Based on this pre-trained llamalogue model, we employ a variety of fine-tuning strategies to enforce "more communicative" text generations by our models. Although our models underperform on most standard BabyLM benchmarks, they excel at dialogue continuation prediction in a minimal pair setting. While PPO fine-tuning has mixed to adversarial effects on our models, DPO fine-tuning further improves their performance on our custom dialogue benchmark.

---

### FreeChunker: A Cross-Granularity Chunking Framework

Authors: Wenxuan Zhang, Yuan-Hao Jiang, Yang Cao, Yonghe Wu
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20356v2

Chunking strategies significantly impact the effectiveness of Retrieval-Augmented Generation (RAG) systems. Existing methods operate within fixed-granularity paradigms that rely on static boundary identification, limiting their adaptability to diverse query requirements. This paper presents FreeChunker, a Cross-Granularity Encoding Framework that fundamentally transforms the traditional chunking paradigm: the framework treats sentences as atomic units and shifts from static chunk segmentation to flexible retrieval supporting arbitrary sentence combinations. This paradigm shift not only significantly avoids the computational overhead required for semantic boundary detection, but also enhances adaptability to complex queries. Experimental evaluation on LongBench V2 demonstrates that FreeChunker possesses significant advantages in both retrieval performance and time efficiency compared to existing chunking methods. The pre-trained models and codes are available at https://github.com/mazehart/FreeChunker.

---

### When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets

Authors: Matteo Silvestri, Fabiano Veglianti, Flavio Giorgi, Fabrizio Silvestri, Gabriele Tolomei
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20351v4

Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely unexplored. Existing approaches primarily rely on memorization tests, which are too coarse to detect contamination. In contrast, we propose a framework for assessing contamination in tabular datasets by generating controlled queries and performing comparative evaluation. Given a dataset, we craft multiple-choice aligned queries that preserve task structure while allowing systematic transformations of the underlying data. These transformations are designed to selectively disrupt dataset information while preserving partial knowledge, enabling us to isolate performance attributable to contamination. We complement this setup with non-neural baselines that provide reference performance, and we introduce a statistical testing procedure to formally detect significant deviations indicative of contamination. Empirical results on eight widely used tabular datasets reveal clear evidence of contamination in four cases. These findings suggest that performance on downstream tasks involving such datasets may be substantially inflated, raising concerns about the reliability of current evaluation practices.

---

### What Do AI-Generated Images Want?

Authors: Amanda Wasielewski
Published: 2025-10-23
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.20350v2

W.J.T. Mitchell's influential essay 'What do pictures want?' shifts the theoretical focus away from the interpretative act of understanding pictures and from the motivations of the humans who create them to the possibility that the picture itself is an entity with agency and wants. In this article, I reframe Mitchell's question in light of contemporary AI image generation tools to ask: what do AI-generated images want? Drawing from art historical discourse on the nature of abstraction, I argue that AI-generated images want specificity and concreteness because they are fundamentally abstract. Multimodal text-to-image models, which are the primary subject of this article, are based on the premise that text and image are interchangeable or exchangeable tokens and that there is a commensurability between them, at least as represented mathematically in data. The user pipeline that sees textual input become visual output, however, obscures this representational regress and makes it seem like one form transforms into the other -- as if by magic.

---

### Synthetic Data for Robust Runway Detection

Authors: Estelle Chigot, Dennis G. Wilson, Meriem Ghrib, Fabrice Jimenez, Thomas Oberlin
Published: 2025-10-23
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.20349v1

Deep vision models are now mature enough to be integrated in industrial and possibly critical applications such as autonomous navigation. Yet, data collection and labeling to train such models requires too much efforts and costs for a single company or product. This drawback is more significant in critical applications, where training data must include all possible conditions including rare scenarios. In this perspective, generating synthetic images is an appealing solution, since it allows a cheap yet reliable covering of all the conditions and environments, if the impact of the synthetic-to-real distribution shift is mitigated. In this article, we consider the case of runway detection that is a critical part in autonomous landing systems developed by aircraft manufacturers. We propose an image generation approach based on a commercial flight simulator that complements a few annotated real images. By controlling the image generation and the integration of real and synthetic data, we show that standard object detection models can achieve accurate prediction. We also evaluate their robustness with respect to adverse conditions, in our case nighttime images, that were not represented in the real data, and show the interest of using a customized domain adaptation strategy.

---

### AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

Authors: Seunghoon Lee, Jeongwoo Choi, Byunggwan Son, Jaehyeon Moon, Jeimin Jeon, Bumsub Ham
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20348v1

We present in this paper a novel post-training quantization (PTQ) method, dubbed AccuQuant, for diffusion models. We show analytically and empirically that quantization errors for diffusion models are accumulated over denoising steps in a sampling process. To alleviate the error accumulation problem, AccuQuant minimizes the discrepancies between outputs of a full-precision diffusion model and its quantized version within a couple of denoising steps. That is, it simulates multiple denoising steps of a diffusion sampling process explicitly for quantization, accounting the accumulated errors over multiple denoising steps, which is in contrast to previous approaches to imitating a training process of diffusion models, namely, minimizing the discrepancies independently for each step. We also present an efficient implementation technique for AccuQuant, together with a novel objective, which reduces a memory complexity significantly from $\mathcal{O}(n)$ to $\mathcal{O}(1)$, where $n$ is the number of denoising steps. We demonstrate the efficacy and efficiency of AccuQuant across various tasks and diffusion models on standard benchmarks.

---

### LLM-empowered knowledge graph construction: A survey

Authors: Haonan Bian
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20345v1

Knowledge Graphs (KGs) have long served as a fundamental infrastructure for structured knowledge representation and reasoning. With the advent of Large Language Models (LLMs), the construction of KGs has entered a new paradigm-shifting from rule-based and statistical pipelines to language-driven and generative frameworks. This survey provides a comprehensive overview of recent progress in LLM-empowered knowledge graph construction, systematically analyzing how LLMs reshape the classical three-layered pipeline of ontology engineering, knowledge extraction, and knowledge fusion. We first revisit traditional KG methodologies to establish conceptual foundations, and then review emerging LLM-driven approaches from two complementary perspectives: schema-based paradigms, which emphasize structure, normalization, and consistency; and schema-free paradigms, which highlight flexibility, adaptability, and open discovery. Across each stage, we synthesize representative frameworks, analyze their technical mechanisms, and identify their limitations. Finally, the survey outlines key trends and future research directions, including KG-based reasoning for LLMs, dynamic knowledge memory for agentic systems, and multimodal KG construction. Through this systematic review, we aim to clarify the evolving interplay between LLMs and knowledge graphs, bridging symbolic knowledge engineering and neural semantic understanding toward the development of adaptive, explainable, and intelligent knowledge systems.

---

### Neural Networks for Censored Expectile Regression Based on Data Augmentation

Authors: Wei Cao, Shanshan Wang
Published: 2025-10-23
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.20344v1

Expectile regression neural networks (ERNNs) are powerful tools for capturing heterogeneity and complex nonlinear structures in data. However, most existing research has primarily focused on fully observed data, with limited attention paid to scenarios involving censored observations. In this paper, we propose a data augmentation based ERNNs algorithm, termed DAERNN, for modeling heterogeneous censored data. The proposed DAERNN is fully data driven, requires minimal assumptions, and offers substantial flexibility. Simulation studies and real data applications demonstrate that DAERNN outperforms existing censored ERNNs methods and achieves predictive performance comparable to models trained on fully observed data. Moreover, the algorithm provides a unified framework for handling various censoring mechanisms without requiring explicit parametric model specification, thereby enhancing its applicability to practical censored data analysis.

---

### Teaching Language Models to Reason with Tools

Authors: Chengpeng Li, Zhengyang Tang, Ziniu Li, Mingfeng Xue, Keqin Bao, Tian Ding, Ruoyu Sun, Benyou Wang, Xiang Wang, Junyang Lin, Dayiheng Liu
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20342v1

Large reasoning models (LRMs) like OpenAI-o1 have shown impressive capabilities in natural language reasoning. However, these models frequently demonstrate inefficiencies or inaccuracies when tackling complex mathematical operations. While integrating computational tools such as Code Interpreters (CIs) offers a promising solution, it introduces a critical challenge: a conflict between the model's internal, probabilistic reasoning and the external, deterministic knowledge provided by the CI, which often leads models to unproductive deliberation. To overcome this, we introduce CoRT (Code-Optimized Reasoning Training), a post-training framework designed to teach LRMs to effectively utilize CIs. We propose \emph{Hint-Engineering}, a new data synthesis strategy that strategically injects diverse hints at optimal points within reasoning paths. This approach generates high-quality, code-integrated reasoning data specifically tailored to optimize LRM-CI interaction. Using this method, we have synthesized 30 high-quality samples to post-train models ranging from 1.5B to 32B parameters through supervised fine-tuning. CoRT further refines the multi-round interleaving of external CI usage and internal thinking by employing rejection sampling and reinforcement learning. Our experimental evaluations demonstrate CoRT's effectiveness, yielding absolute improvements of 4\% and 8\% on DeepSeek-R1-Distill-Qwen-32B and DeepSeek-R1-Distill-Qwen-1.5B, respectively, across five challenging mathematical reasoning datasets. Moreover, CoRT significantly enhances efficiency, reducing token usage by approximately 30\% for the 32B model and 50\% for the 1.5B model compared to pure natural language reasoning baselines. The models and code are available at: https://github.com/ChengpengLi1003/CoRT.

---

### Multi-Task Deep Learning for Surface Metrology

Authors: D. Kucharski, A. Gaska, T. Kowaluk, K. Stepien, M. Repalska, B. Gapinski, M. Wieczorowski, M. Nawotka, P. Sobecki, P. Sosinowski, J. Tomasik, A. Wojtowicz
Published: 2025-10-23
Categories: physics.app-ph, cs.AI, cs.LG, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.20339v1

A reproducible deep learning framework is presented for surface metrology to predict surface texture parameters together with their reported standard uncertainties. Using a multi-instrument dataset spanning tactile and optical systems, measurement system type classification is addressed alongside coordinated regression of Ra, Rz, RONt and their uncertainty targets (Ra_uncert, Rz_uncert, RONt_uncert). Uncertainty is modelled via quantile and heteroscedastic heads with post-hoc conformal calibration to yield calibrated intervals. On a held-out set, high fidelity was achieved by single-target regressors (R2: Ra 0.9824, Rz 0.9847, RONt 0.9918), with two uncertainty targets also well modelled (Ra_uncert 0.9899, Rz_uncert 0.9955); RONt_uncert remained difficult (R2 0.4934). The classifier reached 92.85% accuracy and probability calibration was essentially unchanged after temperature scaling (ECE 0.00504 -> 0.00503 on the test split). Negative transfer was observed for naive multi-output trunks, with single-target models performing better. These results provide calibrated predictions suitable to inform instrument selection and acceptance decisions in metrological workflows.

---

### Collateral Damage Assessment Model for AI System Target Engagement in Military Operations

Authors: Clara Maathuis, Kasper Cools
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20337v1

In an era where AI (Artificial Intelligence) systems play an increasing role in the battlefield, ensuring responsible targeting demands rigorous assessment of potential collateral effects. In this context, a novel collateral damage assessment model for target engagement of AI systems in military operations is introduced. The model integrates temporal, spatial, and force dimensions within a unified Knowledge Representation and Reasoning (KRR) architecture following a design science methodological approach. Its layered structure captures the categories and architectural components of the AI systems to be engaged together with corresponding engaging vectors and contextual aspects. At the same time, spreading, severity, likelihood, and evaluation metrics are considered in order to provide a clear representation enhanced by transparent reasoning mechanisms. Further, the model is demonstrated and evaluated through instantiation which serves as a basis for further dedicated efforts that aim at building responsible and trustworthy intelligent systems for assessing the effects produced by engaging AI systems in military operations.

---

### Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parking

Authors: Zixuan Wu, Hengyuan Zhang, Ting-Hsuan Chen, Yuliang Guo, David Paz, Xinyu Huang, Liu Ren
Published: 2025-10-23
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.20335v1

Parking is a critical pillar of driving safety. While recent end-to-end (E2E) approaches have achieved promising in-domain results, robustness under domain shifts (e.g., weather and lighting changes) remains a key challenge. Rather than relying on additional data, in this paper, we propose Dino-Diffusion Parking (DDP), a domain-agnostic autonomous parking pipeline that integrates visual foundation models with diffusion-based planning to enable generalized perception and robust motion planning under distribution shifts. We train our pipeline in CARLA at regular setting and transfer it to more adversarial settings in a zero-shot fashion. Our model consistently achieves a parking success rate above 90% across all tested out-of-distribution (OOD) scenarios, with ablation studies confirming that both the network architecture and algorithmic design significantly enhance cross-domain performance over existing baselines. Furthermore, testing in a 3D Gaussian splatting (3DGS) environment reconstructed from a real-world parking lot demonstrates promising sim-to-real transfer.

---

### Capability of using the normalizing flows for extraction rare gamma events in the TAIGA experiment

Authors: A. P. Kryukov, A. Yu. Razumov, A. P. Demichev, J. J. Dubenskaya, E. O. Gres, S. P. Polyakov, E. B. Postnikov, P. A. Volchugov, D. P. Zhurov
Published: 2025-10-23
Categories: astro-ph.IM, astro-ph.HE, cs.LG
arXiv: https://arxiv.org/abs/2510.20334v1

The objective of this work is to develop a method for detecting rare gamma quanta against the background of charged particles in the fluxes from sources in the Universe with the help of the deep learning and normalizing flows based method designed for anomaly detection. It is shown that the suggested method has a potential for the gamma detection. The method was tested on model data from the TAIGA-IACT experiment. The obtained quantitative performance indicators are still inferior to other approaches, and therefore possible ways to improve the implementation of the method are proposed.

---

### GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?

Authors: Chiyu Chen, Xinhao Song, Yunkai Chai, Yang Yao, Haodong Zhao, Lijun Li, Jie Li, Yan Teng, Gongshen Liu, Yingchun Wang
Published: 2025-10-23
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.20333v3

Vision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile graphical user interfaces (GUIs). Operating in dynamic on-device ecosystems, which include notifications, pop-ups, and inter-app interactions, exposes them to a unique and underexplored threat vector: environmental injection. Unlike prompt-based attacks that manipulate textual instructions, environmental injection corrupts an agent's visual perception by inserting adversarial UI elements (for example, deceptive overlays or spoofed notifications) directly into the GUI. This bypasses textual safeguards and can derail execution, causing privacy leakage, financial loss, or irreversible device compromise. To systematically evaluate this threat, we introduce GhostEI-Bench, the first benchmark for assessing mobile agents under environmental injection attacks within dynamic, executable environments. Moving beyond static image-based assessments, GhostEI-Bench injects adversarial events into realistic application workflows inside fully operational Android emulators and evaluates performance across critical risk scenarios. We further propose a judge-LLM protocol that conducts fine-grained failure analysis by reviewing the agent's action trajectory alongside the corresponding screenshot sequence, pinpointing failure in perception, recognition, or reasoning. Comprehensive experiments on state-of-the-art agents reveal pronounced vulnerability to deceptive environmental cues: current models systematically fail to perceive and reason about manipulated UIs. GhostEI-Bench provides a framework for quantifying and mitigating this emerging threat, paving the way toward more robust and secure embodied agents.

---

### Bias by Design? How Data Practices Shape Fairness in AI Healthcare Systems

Authors: Anna Arias-Duart, Maria Eugenia Cardello, Atia Cortés
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20332v1

Artificial intelligence (AI) holds great promise for transforming healthcare. However, despite significant advances, the integration of AI solutions into real-world clinical practice remains limited. A major barrier is the quality and fairness of training data, which is often compromised by biased data collection practices. This paper draws on insights from the AI4HealthyAging project, part of Spain's national R&D initiative, where our task was to detect biases during clinical data collection. We identify several types of bias across multiple use cases, including historical, representation, and measurement biases. These biases manifest in variables such as sex, gender, age, habitat, socioeconomic status, equipment, and labeling. We conclude with practical recommendations for improving the fairness and robustness of clinical problem design and data collection. We hope that our findings and experience contribute to guiding future projects in the development of fairer AI systems in healthcare.

---

### AnyPcc: Compressing Any Point Cloud with a Single Universal Model

Authors: Kangli Wang, Qianxi Yi, Yuqi Ye, Shihao Li, Wei Gao
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20331v2

Generalization remains a critical challenge in deep learning-based point cloud geometry compression. While existing methods perform well on standard benchmarks, their performance collapses in real-world scenarios due to two fundamental limitations: the lack of context models that are robust across diverse data densities, and the inability to efficiently adapt to out-of-distribution (OOD) data. To overcome both challenges, we introduce AnyPcc, a universal point cloud compression framework. AnyPcc first employs a Universal Context Model that leverages coarse-grained spatial priors with fine-grained channel priors to ensure robust context modeling across the entire density spectrum. Second, our novel Instance-Adaptive Fine-Tuning (IAFT) strategy tackles OOD data by synergizing explicit and implicit compression paradigms. For each instance, it fine-tunes a small subset of network weights and transmits them within the bitstream. The minimal bitrate overhead from these weights is significantly outweighed by the resulting gains in geometry compression. Extensive experiments on a benchmark of 15 diverse datasets confirm that AnyPcc sets a new state-of-the-art in point cloud compression while maintaining low complexity. Our code and datasets have been released to encourage reproducible research.

---

### MemER: Scaling Up Memory for Robot Control via Experience Retrieval

Authors: Ajay Sridhar, Jennifer Pan, Satvik Sharma, Chelsea Finn
Published: 2025-10-23
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20328v1

Humans routinely rely on memory to perform tasks, yet most robot policies lack this capability; our goal is to endow robot policies with the same ability. Naively conditioning on long observation histories is computationally expensive and brittle under covariate shift, while indiscriminate subsampling of history leads to irrelevant or redundant information. We propose a hierarchical policy framework, where the high-level policy is trained to select and track previous relevant keyframes from its experience. The high-level policy uses selected keyframes and the most recent frames when generating text instructions for a low-level policy to execute. This design is compatible with existing vision-language-action (VLA) models and enables the system to efficiently reason over long-horizon dependencies. In our experiments, we finetune Qwen2.5-VL-7B-Instruct and $π_{0.5}$ as the high-level and low-level policies respectively, using demonstrations supplemented with minimal language annotations. Our approach, MemER, outperforms prior methods on three real-world long-horizon robotic manipulation tasks that require minutes of memory. Videos and code can be found at https://jen-pan.github.io/memer/.

---

### LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems

Authors: Fengyuan Yu, Yuyuan Li, Xiaohua Feng, Junjie Fang, Tao Wang, Chaochao Chen
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20327v1

With the growing demand for safeguarding sensitive user information in recommender systems, recommendation attribute unlearning is receiving increasing attention. Existing studies predominantly focus on single-attribute unlearning. However, privacy protection requirements in the real world often involve multiple sensitive attributes and are dynamic. Existing single-attribute unlearning methods cannot meet these real-world requirements due to i) CH1: the inability to handle multiple unlearning requests simultaneously, and ii) CH2: the lack of efficient adaptability to dynamic unlearning needs. To address these challenges, we propose LEGO, a lightweight and efficient multiple-attribute unlearning framework. Specifically, we divide the multiple-attribute unlearning process into two steps: i) Embedding Calibration removes information related to a specific attribute from user embedding, and ii) Flexible Combination combines these embeddings into a single embedding, protecting all sensitive attributes. We frame the unlearning process as a mutual information minimization problem, providing LEGO a theoretical guarantee of simultaneous unlearning, thereby addressing CH1. With the two-step framework, where Embedding Calibration can be performed in parallel and Flexible Combination is flexible and efficient, we address CH2. Extensive experiments on three real-world datasets across three representative recommendation models demonstrate the effectiveness and efficiency of our proposed framework. Our code and appendix are available at https://github.com/anonymifish/lego-rec-multiple-attribute-unlearning.

---

### HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

Authors: Zelin Peng, Zhengqin Xu, Qingyang Liu, Xiaokang Yang, Wei Shen
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20322v3

Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computational resources (e.g., thousands of GPUs) for training to achieve cross-modal alignment at multi-granularity levels. We argue that a key source of this inefficiency lies in the vision encoders they widely equip with, e.g., CLIP and SAM, which lack the alignment with language at multi-granularity levels. To address this issue, in this paper, we leverage hyperbolic space, which inherently models hierarchical levels and thus provides a principled framework for bridging the granularity gap between visual and textual modalities at an arbitrary granularity level. Concretely, we propose an efficient training paradigm for MLLMs, dubbed as HyperET, which can optimize visual representations to align with their textual counterparts at an arbitrary granularity level through dynamic hyperbolic radius adjustment in hyperbolic space. HyperET employs learnable matrices with Möbius multiplication operations, implemented via three effective configurations: diagonal scaling matrices, block-diagonal matrices, and banded matrices, providing a flexible yet efficient parametrization strategy. Comprehensive experiments across multiple MLLM benchmarks demonstrate that HyperET consistently improves both existing pre-training and fine-tuning MLLMs clearly with less than 1\% additional parameters. Code is available at https://github.com/godlin-sjtu/HyperET

---

### Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses

Authors: Wu Yichao, Wang Yirui, Ding Panpan, Wang Hailong, Zhu Bingqian, Liu Chun
Published: 2025-10-23
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20314v1

With the wide application of deep reinforcement learning (DRL) techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research. Especially in the face of adversarial attacks, DRL may suffer serious performance degradation or even make potentially dangerous decisions, so it is crucial to ensure their stability in security-sensitive scenarios. In this paper, we first introduce the basic framework of DRL and analyze the main security challenges faced in complex and changing environments. In addition, this paper proposes an adversarial attack classification framework based on perturbation type and attack target and reviews the mainstream adversarial attack methods against DRL in detail, including various attack methods such as perturbation state space, action space, reward function and model space. To effectively counter the attacks, this paper systematically summarizes various current robustness training strategies, including adversarial training, competitive training, robust learning, adversarial detection, defense distillation and other related defense techniques, we also discuss the advantages and shortcomings of these methods in improving the robustness of DRL. Finally, this paper looks into the future research direction of DRL in adversarial environments, emphasizing the research needs in terms of improving generalization, reducing computational complexity, and enhancing scalability and explainability, aiming to provide valuable references and directions for researchers.

---

### Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation

Authors: Mingliang Zhai, Hansheng Liang, Xiaomeng Fan, Zhi Gao, Chuanhao Li, Che Sun, Xu Bin, Yuwei Wu, Yunde Jia
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20310v2

Embodied Question Answering (EQA) requires agents to explore 3D environments to obtain observations and answer questions related to the scene. Existing methods leverage VLMs to directly explore the environment and answer questions without explicit thinking or planning, which limits their reasoning ability and results in excessive or inefficient exploration as well as ineffective responses. In this paper, we introduce ToolEQA, an agent that integrates external tools with multi-step reasoning, where external tools can provide more useful information for completing the task, helping the model derive better exploration directions in the next step of reasoning and thus obtaining additional effective information. This enables ToolEQA to generate more accurate responses with a shorter exploration distance. To enhance the model's ability for tool-usage and multi-step reasoning, we further design a novel EQA data generation pipeline that automatically constructs large-scale EQA tasks with reasoning trajectories and corresponding answers. Based on the pipeline, we collect the EQA-RT dataset that contains about 18K tasks, divided into a training set EQA-RT-Train, and two test sets EQA-RT-Seen (scenes overlapping with the training set) and EQA-RT-Unseen (novel scenes). Experiments on EQA-RT-Seen and EQA-RT-Unseen show that ToolEQA improves the success rate by 9.2~20.2% over state-of-the-art baselines, while outperforming the zero-shot ToolEQA by 10% in success rate. In addition, ToolEQA also achieves state-of-the-art performance on the HM-EQA, OpenEQA, and EXPRESS-Bench datasets, demonstrating its generality. Our homepage see https://tooleqa.github.io.

---

### Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering

Authors: Lei Tang, Wei Zhou, Mohsen Mesgar
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20304v2

Process reward models (PRMs) enhance complex reasoning in large language models (LLMs) by evaluating candidate solutions step-by-step and selecting answers based on aggregated step scores. While effective in domains such as mathematics, their applicability to tasks involving semi-structured data, like table question answering (TQA), remains unexplored. TQA poses unique challenges for PRMs, including abundant irrelevant information, loosely connected reasoning steps, and domain-specific reasoning. This work presents the first systematic study of PRMs for TQA. We evaluate state-of-the-art generative PRMs on TQA from both answer and step perspectives. Results show that PRMs that combine textual and code verification can aid solution selection but struggle to generalize to out-of-domain data. Analysis reveals a weak correlation between performance in step-level verification and answer accuracy, possibly stemming from weak step dependencies and loose causal links. Our findings highlight limitations of current PRMs on TQA and offer valuable insights for building more robust, process-aware verifiers.

---

### Citation Failure: Definition, Analysis and Efficient Mitigation

Authors: Jan Buchmann, Iryna Gurevych
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20303v3

Citations from LLM-based RAG systems are supposed to simplify response verification. However, this goal is undermined in cases of citation failure, where a model generates a helpful response, but fails to generate citations to complete evidence. In contrast to previous work, we propose to disentangle this from response failure, where the response itself is flawed, and citing complete evidence is impossible. To address citation failure, this work follows a two-step approach: (1) We study when citation failure occurs and (2) how it can be mitigated efficiently. For step 1, we extend prior work by investigating how the relation between response and evidence affects citation quality. We introduce CITECONTROL, a benchmark that systematically varies this relation to enable the analysis of failure modes. Experiments show that failures increase with relational complexity and suggest that combining citation methods could improve performance, motivating step 2. To study the efficient improvement of LLM citation, we propose CITENTION, a framework integrating generative, attention-based, and retrieval-based methods. Results demonstrate substantial citation improvements on CITECONTROL and in transfer settings. We make our data and code publicly available.

---

### InvDec: Inverted Decoder for Multivariate Time Series Forecasting with Separated Temporal and Variate Modeling

Authors: Yuhang Wang
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20302v1

Multivariate time series forecasting requires simultaneously modeling temporal patterns and cross-variate dependencies. Channel-independent methods such as PatchTST excel at temporal modeling but ignore variable correlations, while pure variate-attention approaches such as iTransformer sacrifice temporal encoding. We proposeInvDec (Inverted Decoder), a hybrid architecture that achieves principled separation between temporal encoding and variate-level decoding. InvDec combines a patch-based temporal encoder with an inverted decoder operating on the variate dimension through variate-wise self-attention. We introduce delayed variate embeddings that enrich variable-specific representations only after temporal encoding, preserving temporal feature integrity. An adaptive residual fusion mechanism dynamically balances temporal and variate information across datasets of varying dimensions. Instantiating InvDec with PatchTST yields InvDec-PatchTST. Extensive experiments on seven benchmarks demonstrate significant gains on high-dimensional datasets: 20.9% MSE reduction on Electricity (321 variables), 4.3% improvement on Weather, and 2.7% gain on Traffic compared to PatchTST, while maintaining competitive performance on low-dimensional ETT datasets. Ablation studies validate each component, and analysis reveals that InvDec's advantage grows with dataset dimensionality, confirming that cross-variate modeling becomes critical as the number of variables increases.

---

### DB-FGA-Net: Dual Backbone Frequency Gated Attention Network for Multi-Class Brain Tumor Classification with Grad-CAM Interpretability

Authors: Saraf Anzum Shreya, MD. Abu Ismail Siddique, Sharaf Tasnim
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20299v3

Brain tumors are a challenging problem in neuro-oncology, where early and precise diagnosis is important for successful treatment. Deep learning-based brain tumor classification methods often rely on heavy data augmentation which can limit generalization and trust in clinical applications. In this paper, we propose a double-backbone network integrating VGG16 and Xception with a Frequency-Gated Attention (FGA) Block to capture complementary local and global features. Our model achieves highly competitive performance without augmentation which demonstrates robustness to variably sized and distributed datasets. For further transparency, Grad-CAM is integrated to visualize the tumor regions based on which the model is giving prediction, bridging the gap between model prediction and clinical interpretability. The proposed framework achieves 99.24% accuracy on the 7K-DS dataset for the 4-class setting, along with 98.68% and 99.85% in the 3-class and 2-class settings, respectively. On the independent 3K-DS dataset, the model generalizes with 95.77% accuracy, outperforming several baseline methods under the same experimental setting. To further support clinical usability, we developed a graphical user interface (GUI) that provides real-time classification and Grad-CAM-based tumor localization. These findings suggest that augmentation-free, interpretable, and deployable deep learning models such as DB-FGA-Net hold strong potential for reliable clinical translation in brain tumor diagnosis.

---

### RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective

Authors: Wenqi Jiang
Published: 2025-10-23
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2510.20296v1

Retrieval-augmented generation (RAG) has emerged as one of the most prominent applications of vector databases. By integrating documents retrieved from a database into the prompt of a large language model (LLM), RAG enables more reliable and informative content generation. While there has been extensive research on vector databases, many open research problems remain once they are considered in the wider context of end-to-end RAG pipelines. One practical yet challenging problem is how to jointly optimize both system performance and generation quality in RAG, which is significantly more complex than it appears due to the numerous knobs on both the algorithmic side (spanning models and databases) and the systems side (from software to hardware). In this paper, we present RAG-Stack, a three-pillar blueprint for quality-performance co-optimization in RAG systems. RAG-Stack comprises: (1) RAG-IR, an intermediate representation that serves as an abstraction layer to decouple quality and performance aspects; (2) RAG-CM, a cost model for estimating system performance given an RAG-IR; and (3) RAG-PE, a plan exploration algorithm that searches for high-quality, high-performance RAG configurations. We believe this three-pillar blueprint will become the de facto paradigm for RAG quality-performance co-optimization in the years to come.

---

### Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization

Authors: Yang Qiu, Yixiong Zou, Jun Wang, Wei Liu, Xiangyu Fu, Ruixuan Li
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20295v1

Out-of-distribution generalization under distributional shifts remains a critical challenge for graph neural networks. Existing methods generally adopt the Invariant Risk Minimization (IRM) framework, requiring costly environment annotations or heuristically generated synthetic splits. To circumvent these limitations, in this work, we aim to develop an IRM-free method for capturing causal subgraphs. We first identify that causal subgraphs exhibit substantially smaller distributional variations than non-causal components across diverse environments, which we formalize as the Invariant Distribution Criterion and theoretically prove in this paper. Building on this criterion, we systematically uncover the quantitative relationship between distributional shift and representation norm for identifying the causal subgraph, and investigate its underlying mechanisms in depth. Finally, we propose an IRM-free method by introducing a norm-guided invariant distribution objective for causal subgraph discovery and prediction. Extensive experiments on two widely used benchmarks demonstrate that our method consistently outperforms state-of-the-art methods in graph generalization.

---

### A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization

Authors: LinFeng Li, Jian Zhao, Zepeng Yang, Yuhang Song, Bojun Lin, Tianle Zhang, Yuchen Yuan, Chi Zhang, Xuelong Li
Published: 2025-10-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.20291v1

We present a winning solution to RoboSense 2025 Track 4: Cross-Modal Drone Navigation. The task retrieves the most relevant geo-referenced image from a large multi-platform corpus (satellite/drone/ground) given a natural-language query. Two obstacles are severe inter-platform heterogeneity and a domain gap between generic training descriptions and platform-specific test queries. We mitigate these with a domain-aligned preprocessing pipeline and a Mixture-of-Experts (MoE) framework: (i) platform-wise partitioning, satellite augmentation, and removal of orientation words; (ii) an LLM-based caption refinement pipeline to align textual semantics with the distinct visual characteristics of each platform. Using BGE-M3 (text) and EVA-CLIP (image), we train three platform experts using a progressive two-stage, hard-negative mining strategy to enhance discriminative power, and fuse their scores at inference. The system tops the official leaderboard, demonstrating robust cross-modal geo-localization under heterogeneous viewpoints.

---

### Breakdance Video classification in the age of Generative AI

Authors: Sauptik Dhar, Naveen Ramakrishnan, Michelle Munson
Published: 2025-10-23
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20287v1

Large Vision Language models have seen huge application in several sports use-cases recently. Most of these works have been targeted towards a limited subset of popular sports like soccer, cricket, basketball etc; focusing on generative tasks like visual question answering, highlight generation. This work analyzes the applicability of the modern video foundation models (both encoder and decoder) for a very niche but hugely popular dance sports - breakdance. Our results show that Video Encoder models continue to outperform state-of-the-art Video Language Models for prediction tasks. We provide insights on how to choose the encoder model and provide a thorough analysis into the workings of a finetuned decoder model for breakdance video classification.

---