# Research Papers — 2025-10 · bundle page 21 of 217

> Full-text markdown of papers #1001–1050 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/21
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/20.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/22.md)

### Bridging the Divide: End-to-End Sequence-Graph Learning

Authors: Yuen Chen, Yulun Wu, Samuel Sharpe, Igor Melnyk, Nam H. Nguyen, Furong Huang, C. Bayan Bruss, Rizal Fathony
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.25126v2

Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its own sequence of events while simultaneously engaging in relationships with others. Existing methods in sequence and graph modeling often overlook one modality in favor of the other. We argue that these two facets should instead be integrated and learned jointly. We introduce BRIDGE, a unified end-to-end architecture that couples a sequence model with a graph module under a single objective, allowing gradients to flow across both components to learn task-aligned representations. To enable fine-grained interaction, we propose TOKENXATTN, a token-level cross-attention layer that facilitates message passing between specific events in neighboring sequences. Across two settings, relationship prediction and fraud detection, BRIDGE consistently outperforms static graph models, temporal graph methods, as well as sequence-only baselines on both ranking and classification metrics.

---

### Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data

Authors: Woojin Cho, Kookjin Lee, Noseong Park, Donsub Rim, Gerrit Welper
Published: 2025-10-29
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2510.25123v2

We present a data-driven dimensionality reduction method that is well-suited for physics-based data representing hyperbolic wave propagation. The method utilizes a specialized neural network architecture called low rank neural representation (LRNR) inside a hypernetwork framework. The architecture is motivated by theoretical results that rigorously prove the existence of efficient representations for this wave class. We illustrate through archetypal examples that such an efficient low-dimensional representation of propagating waves can be learned directly from data through a combination of deep learning techniques. We observe that a low rank tensor representation arises naturally in the trained LRNRs, and that this reveals a new decomposition of wave propagation where each decomposed mode corresponds to interpretable physical features. Furthermore, we demonstrate that the LRNR architecture enables efficient inference via a compression scheme, which is a potentially important feature when deploying LRNRs in demanding performance regimes.

---

### Bilevel Models for Adversarial Learning and A Case Study

Authors: Yutong Zheng, Qingna Li
Published: 2025-10-29
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.25121v2

Adversarial learning has been attracting more and more attention thanks to the fast development of machine learning and artificial intelligence. However, due to the complicated structure of most machine learning models, the mechanism of adversarial attacks is not well interpreted. How to measure the effect of attacks is still not quite clear. In this paper, we investigate the adversarial learning from the perturbation analysis point of view. We characterize the robustness of learning models through the calmness of the solution mapping. In the case of convex clustering models, we identify the conditions under which the clustering results remain the same under perturbations. When the noise level is large, it leads to an attack. Therefore, we propose two bilevel models for adversarial learning where the effect of adversarial learning is measured by some deviation function. Specifically, we systematically study the so-called $δ$-measure and show that under certain conditions, it can be used as a deviation function in adversarial learning for convex clustering models. Finally, we conduct numerical tests to verify the above theoretical results as well as the efficiency of the two proposed bilevel models.

---

### A Survey on Unlearning in Large Language Models

Authors: Ruichen Qiu, Jiajun Tan, Jiayue Pu, Honglin Wang, Xiao-Shan Gao, Fei Sun
Published: 2025-10-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.25117v2

Large Language Models (LLMs) demonstrate remarkable capabilities, but their training on massive corpora poses significant risks from memorized sensitive information. To mitigate these issues and align with legal standards, unlearning has emerged as a critical technique to selectively erase specific knowledge from LLMs without compromising their overall performance. This survey provides a systematic review of over 180 papers on LLM unlearning published since 2021. First, it introduces a novel taxonomy that categorizes unlearning methods based on the phase in the LLM pipeline of the intervention. This framework further distinguishes between parameter modification and parameter selection strategies, thus enabling deeper insights and more informed comparative analysis. Second, it offers a multidimensional analysis of evaluation paradigms. For datasets, we compare 18 existing benchmarks from the perspectives of task format, content, and experimental paradigms to offer actionable guidance. For metrics, we move beyond mere enumeration by dividing knowledge memorization metrics into 10 categories to analyze their advantages and applicability, while also reviewing metrics for model utility, robustness, and efficiency. By discussing current challenges and future directions, this survey aims to advance the field of LLM unlearning and the development of secure AI systems.

---

### Pretraining Strategies using Monolingual and Parallel Data for Low-Resource Machine Translation

Authors: Idriss Nguepi Nguefack, Mara Finkelstein, Toadoum Sari Sakayo
Published: 2025-10-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.25116v1

This research article examines the effectiveness of various pretraining strategies for developing machine translation models tailored to low-resource languages. Although this work considers several low-resource languages, including Afrikaans, Swahili, and Zulu, the translation model is specifically developed for Lingala, an under-resourced African language, building upon the pretraining approach introduced by Reid and Artetxe (2021), originally designed for high-resource languages. Through a series of comprehensive experiments, we explore different pretraining methodologies, including the integration of multiple languages and the use of both monolingual and parallel data during the pretraining phase. Our findings indicate that pretraining on multiple languages and leveraging both monolingual and parallel data significantly enhance translation quality. This study offers valuable insights into effective pretraining strategies for low-resource machine translation, helping to bridge the performance gap between high-resource and low-resource languages. The results contribute to the broader goal of developing more inclusive and accurate NLP models for marginalized communities and underrepresented populations. The code and datasets used in this study are publicly available to facilitate further research and ensure reproducibility, with the exception of certain data that may no longer be accessible due to changes in public availability.

---

### Energy Approach from $\varepsilon$-Graph to Continuum Diffusion Model with Connectivity Functional

Authors: Yahong Yang, Sun Lee, Jeff Calder, Wenrui Hao
Published: 2025-10-29
Categories: math.NA, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.25114v2

We derive an energy-based continuum limit for $\varepsilon$-graphs endowed with a general connectivity functional. We prove that the discrete energy and its continuum counterpart differ by at most $O(\varepsilon)$; the prefactor involves only the $W^{1,1}$-norm of the connectivity density as $\varepsilon\to0$, so the error bound remains valid even when that density has strong local fluctuations. As an application, we introduce a neural-network procedure that reconstructs the connectivity density from edge-weight data and then embeds the resulting continuum model into a brain-dynamics framework. In this setting, the usual constant diffusion coefficient is replaced by the spatially varying coefficient produced by the learned density, yielding dynamics that differ significantly from those obtained with conventional constant-diffusion models.

---

### The Neural Differential Manifold: An Architecture with Explicit Geometric Structure

Authors: Di Zhang
Published: 2025-10-29
Categories: cs.LG, cs.AI, math.DG, math.OC
arXiv: https://arxiv.org/abs/2510.25113v1

This paper introduces the Neural Differential Manifold (NDM), a novel neural network architecture that explicitly incorporates geometric structure into its fundamental design. Departing from conventional Euclidean parameter spaces, the NDM re-conceptualizes a neural network as a differentiable manifold where each layer functions as a local coordinate chart, and the network parameters directly parameterize a Riemannian metric tensor at every point. The architecture is organized into three synergistic layers: a Coordinate Layer implementing smooth chart transitions via invertible transformations inspired by normalizing flows, a Geometric Layer that dynamically generates the manifold's metric through auxiliary sub-networks, and an Evolution Layer that optimizes both task performance and geometric simplicity through a dual-objective loss function. This geometric regularization penalizes excessive curvature and volume distortion, providing intrinsic regularization that enhances generalization and robustness. The framework enables natural gradient descent optimization aligned with the learned manifold geometry and offers unprecedented interpretability by endowing internal representations with clear geometric meaning. We analyze the theoretical advantages of this approach, including its potential for more efficient optimization, enhanced continual learning, and applications in scientific discovery and controllable generative modeling. While significant computational challenges remain, the Neural Differential Manifold represents a fundamental shift towards geometrically structured, interpretable, and efficient deep learning systems.

---

### DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

Authors: Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai, You Li, Smit Vasani, Binwei Yao, Michael Henry Tessler, Sijia Yang, Dhavan Shah, Robert Hawkins, Junjie Hu, Timothy T. Rogers
Published: 2025-10-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.25110v6

Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior, such as premature convergence, and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a large-scale benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages and private Likert-scale beliefs from U.S.-based participants across 107 topics; the cleaned benchmark used in our experiments contains 2,788 participants in 697 groups, enabling evaluation at the utterance and group levels and supporting future individual-level analyses. We instantiate "digital twin" RPLAs with seven LLMs and evaluate across two settings: next-message prediction and full dynamics simulation, using stance-based opinion-dynamics metrics. In zero-shot settings, RPLA groups exhibit strong opinion convergence relative to human groups. On the held-out group split, supervised fine-tuning (SFT) for Llama-3.1-8B-Instruct improves auxiliary stance alignment and reduces group-level convergence error, though discrepancies in opinion change and belief updating remain. DEBATE enables rigorous benchmarking of simulated opinion dynamics and supports future research on aligning multi-agent RPLAs with realistic human interactions.

---

### Shift is Good: Mismatched Data Mixing Improves Test Performance

Authors: Marko Medvedev, Kaifeng Lyu, Zhiyuan Li, Nathan Srebro
Published: 2025-10-29
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.25108v2

We consider training and testing on mixture distributions with different training and test proportions. We show that in many settings, and in some sense generically, distribution shift can be beneficial, and test performance can improve due to mismatched training proportions, even if the components are unrelated and with no transfer between components. In a variety of scenarios, we identify the optimal training proportions and the extent to which such distribution shift can be beneficial. We show how the same analysis applies also to a compositional setting with differing distribution of component "skills'' at training and test.

---

### KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA

Authors: Zhuo Chen, Fei Wang, Zixuan Li, Zhao Zhang, Weiwei Ding, Chuanguang Yang, Yongjun Xu, Xiaolong Jin, Jiafeng Guo
Published: 2025-10-29
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.25101v2

Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB). Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Models (LLMs) iteratively decompose a question, generate its corresponding logical queries, and interact with the KB to derive the answer. However, these methods typically fine-tune LLMs on reasoning trajectories synthesized via process supervision, which offers weak incentives for exploration and thus fails to strengthen the agentic reasoning ability. In this paper, we propose KnowCoder-A1, an LLM that can autonomously perform agentic reasoning on KBs to obtain answers. To incentivize autonomous exploration, KnowCoder-A1 trains the LLM under outcome-only supervision via a multi-stage curriculum reinforcement learning with an easy-to-hard curriculum. To establish foundational agentic capabilities, KnowCoder-A1 first fine-tunes the LLM on a small set of high-quality trajectories obtained through outcome-based rejection sampling. Then, to alleviate the reward sparsity inherent in outcome-only supervision, it applies multi-stage curriculum RL with reward schedules that progress from easy to hard. Trained with outcome-only supervision, KnowCoder-A1 exhibits powerful reasoning behaviors and consistently outperforms prior approaches across three mainstream datasets. Notably, on the zero-shot subset of GrailQA, KnowCoder-A1 achieves up to an 11.1% relative improvement while using only one-twelfth of the training data, demonstrating strong agentic reasoning capabilities.

---

### Learning Fair Graph Representations with Multi-view Information Bottleneck

Authors: Chuxun Liu, Debo Cheng, Qingfeng Chen, Jiangzhang Gan, Jiuyong Li, Lin Liu
Published: 2025-10-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.25096v1

Graph neural networks (GNNs) excel on relational data by passing messages over node features and structure, but they can amplify training data biases, propagating discriminatory attributes and structural imbalances into unfair outcomes. Many fairness methods treat bias as a single source, ignoring distinct attribute and structure effects and leading to suboptimal fairness and utility trade-offs. To overcome this challenge, we propose FairMIB, a multi-view information bottleneck framework designed to decompose graphs into feature, structural, and diffusion views for mitigating complexity biases in GNNs. Especially, the proposed FairMIB employs contrastive learning to maximize cross-view mutual information for bias-free representation learning. It further integrates multi-perspective conditional information bottleneck objectives to balance task utility and fairness by minimizing mutual information with sensitive attributes. Additionally, FairMIB introduces an inverse probability-weighted (IPW) adjacency correction in the diffusion view, which reduces the spread of bias propagation during message passing. Experiments on five real-world benchmark datasets demonstrate that FairMIB achieves state-of-the-art performance across both utility and fairness metrics.

---

### Socio-cognitive agent-oriented evolutionary algorithm with trust-based optimization

Authors: Aleksandra Urbańczyk, Krzysztof Czech, Piotr Urbańczyk, Marek Kisiel-Dorohinicki, Aleksander Byrski
Published: 2025-10-29
Categories: cs.NE, math.OC
arXiv: https://arxiv.org/abs/2510.25095v1

This paper introduces the Trust-Based Optimization (TBO), a novel extension of the island model in evolutionary computation that replaces conventional periodic migrations with a flexible, agent-driven interaction mechanism based on trust or reputation. Experimental results demonstrate that TBO generally outperforms the standard island model evolutionary algorithm across various optimization problems. Nevertheless, algorithm performance varies depending on the problem type, with certain configurations being more effective for specific landscapes or dimensions. The findings suggest that trust and reputation mechanisms provide a flexible and adaptive approach to evolutionary optimization, improving solution quality in many cases.

---

### Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection

Authors: Chanhyeong Yang, Taehoon Song, Jihwan Park, Hyunwoo J. Kim
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.25094v1

Zero-shot Human-Object Interaction detection aims to localize humans and objects in an image and recognize their interaction, even when specific verb-object pairs are unseen during training. Recent works have shown promising results using prompt learning with pretrained vision-language models such as CLIP, which align natural language prompts with visual features in a shared embedding space. However, existing approaches still fail to handle the visual complexity of interaction, including (1) intra-class visual diversity, where instances of the same verb appear in diverse poses and contexts, and (2) inter-class visual entanglement, where distinct verbs yield visually similar patterns. To address these challenges, we propose VDRP, a framework for Visual Diversity and Region-aware Prompt learning. First, we introduce a visual diversity-aware prompt learning strategy that injects group-wise visual variance into the context embedding. We further apply Gaussian perturbation to encourage the prompts to capture diverse visual variations of a verb. Second, we retrieve region-specific concepts from the human, object, and union regions. These are used to augment the diversity-aware prompt embeddings, yielding region-aware prompts that enhance verb-level discrimination. Experiments on the HICO-DET benchmark demonstrate that our method achieves state-of-the-art performance under four zero-shot evaluation settings, effectively addressing both intra-class diversity and inter-class visual entanglement. Code is available at https://github.com/mlvlab/VDRP.

---

### Continual Low-Rank Adapters for LLM-based Generative Recommender Systems

Authors: Hyunsik Yoo, Ting-Wei Li, SeongKu Kang, Zhining Liu, Charlie Xu, Qilin Qi, Hanghang Tong
Published: 2025-10-29
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2510.25093v3

While large language models (LLMs) achieve strong performance in recommendation, they face challenges in continual learning as users, items, and user preferences evolve over time. Existing LoRA-based continual methods primarily focus on preserving performance on previous tasks, but this overlooks the unique nature of recommendation: the goal is not to predict past preferences, and outdated preferences can even harm performance when current interests shift significantly. To address this, we propose PESO (Proximally rEgularized Single evolving lOra, a continual adaptation method for LoRA in recommendation. PESO introduces a proximal regularizer that anchors the current adapter to its most recent frozen state, enabling the model to flexibly balance adaptation and preservation, and to better capture recent user behaviors. Theoretically, we show that this proximal design provides data-aware, direction-wise guidance in the LoRA subspace. Empirically, PESO consistently outperforms existing LoRA-based continual learning methods.

---

### H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Experts

Authors: Peilin Tan, Liang Xie, Churan Zhi, Dian Tu, Chuanqi Shi
Published: 2025-10-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.25091v1

Stock movement prediction remains fundamentally challenging due to complex temporal dependencies, heterogeneous modalities, and dynamically evolving inter-stock relationships. Existing approaches often fail to unify structural, semantic, and regime-adaptive modeling within a scalable framework. This work introduces H3M-SSMoEs, a novel Hypergraph-based MultiModal architecture with LLM reasoning and Style-Structured Mixture of Experts, integrating three key innovations: (1) a Multi-Context Multimodal Hypergraph that hierarchically captures fine-grained spatiotemporal dynamics via a Local Context Hypergraph (LCH) and persistent inter-stock dependencies through a Global Context Hypergraph (GCH), employing shared cross-modal hyperedges and Jensen-Shannon Divergence weighting mechanism for adaptive relational learning and cross-modal alignment; (2) a LLM-enhanced reasoning module, which leverages a frozen large language model with lightweight adapters to semantically fuse and align quantitative and textual modalities, enriching representations with domain-specific financial knowledge; and (3) a Style-Structured Mixture of Experts (SSMoEs) that combines shared market experts and industry-specialized experts, each parameterized by learnable style vectors enabling regime-aware specialization under sparse activation. Extensive experiments on three major stock markets demonstrate that H3M-SSMoEs surpasses state-of-the-art methods in both superior predictive accuracy and investment performance, while exhibiting effective risk control. Datasets, source code, and model weights are available at our GitHub repository: https://github.com/PeilinTime/H3M-SSMoEs.

---

### BioCoref: Benchmarking Biomedical Coreference Resolution with LLMs

Authors: Nourah M Salem, Elizabeth White, Michael Bada, Lawrence Hunter
Published: 2025-10-29
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.25087v1

Coreference resolution in biomedical texts presents unique challenges due to complex domain-specific terminology, high ambiguity in mention forms, and long-distance dependencies between coreferring expressions. In this work, we present a comprehensive evaluation of generative large language models (LLMs) for coreference resolution in the biomedical domain. Using the CRAFT corpus as our benchmark, we assess the LLMs' performance with four prompting experiments that vary in their use of local, contextual enrichment, and domain-specific cues such as abbreviations and entity dictionaries. We benchmark these approaches against a discriminative span-based encoder, SpanBERT, to compare the efficacy of generative versus discriminative methods. Our results demonstrate that while LLMs exhibit strong surface-level coreference capabilities, especially when supplemented with domain-grounding prompts, their performance remains sensitive to long-range context and mentions ambiguity. Notably, the LLaMA 8B and 17B models show superior precision and F1 scores under entity-augmented prompting, highlighting the potential of lightweight prompt engineering for enhancing LLM utility in biomedical NLP tasks.

---

### PSTF-AttControl: Per-Subject-Tuning-Free Personalized Image Generation with Controllable Face Attributes

Authors: Xiang liu, Zhaoxiang Liu, Huan Hu, Zipeng Wang, Ping Chen, Zezhou Chen, Kai Wang, Shiguo Lian
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.25084v1

Recent advancements in personalized image generation have significantly improved facial identity preservation, particularly in fields such as entertainment and social media. However, existing methods still struggle to achieve precise control over facial attributes in a per-subject-tuning-free (PSTF) way. Tuning-based techniques like PreciseControl have shown promise by providing fine-grained control over facial features, but they often require extensive technical expertise and additional training data, limiting their accessibility. In contrast, PSTF approaches simplify the process by enabling image generation from a single facial input, but they lack precise control over facial attributes. In this paper, we introduce a novel, PSTF method that enables both precise control over facial attributes and high-fidelity preservation of facial identity. Our approach utilizes a face recognition model to extract facial identity features, which are then mapped into the $W^+$ latent space of StyleGAN2 using the e4e encoder. We further enhance the model with a Triplet-Decoupled Cross-Attention module, which integrates facial identity, attribute features, and text embeddings into the UNet architecture, ensuring clean separation of identity and attribute information. Trained on the FFHQ dataset, our method allows for the generation of personalized images with fine-grained control over facial attributes, while without requiring additional fine-tuning or training data for individual identities. We demonstrate that our approach successfully balances personalization with precise facial attribute control, offering a more efficient and user-friendly solution for high-quality, adaptable facial image synthesis. The code is publicly available at https://github.com/UnicomAI/PSTF-AttControl.

---

### Monopoly Deal: A Benchmark Environment for Bounded One-Sided Response Games

Authors: Will Wolf
Published: 2025-10-29
Categories: cs.GT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.25080v2

Card games are widely used to study sequential decision-making under uncertainty, with real-world analogues in negotiation, finance, and cybersecurity. These games typically fall into three categories based on the flow of control: strictly sequential (players alternate single actions), deterministic response (some actions trigger a fixed outcome), and unbounded reciprocal response (alternating counterplays are permitted). A less-explored but strategically rich structure is the bounded one-sided response, where a player's action briefly transfers control to the opponent, who must satisfy a fixed condition through one or more moves before the turn resolves. We term games featuring this mechanism Bounded One-Sided Response Games (BORGs). We introduce a modified version of Monopoly Deal as a benchmark environment that isolates this dynamic, where a Rent action forces the opponent to choose payment assets. The gold-standard algorithm, Counterfactual Regret Minimization (CFR), converges on effective strategies without novel algorithmic extensions. A lightweight full-stack research platform unifies the environment, a parallelized CFR runtime, and a human-playable web interface. The trained CFR agent and source code are available at https://monopolydeal.ai.

---

### Neighborhood Feature Pooling for Remote Sensing Image Classification

Authors: Fahimeh Orvati Nia, Amirmohammad Mohammadi, Salim Al Kharsa, Pragati Naikare, Zigfried Hampel-Arias, Joshua Peeples
Published: 2025-10-29
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2510.25077v3

In this work, we introduce Neighborhood Feature Pooling (NFP), a novel pooling layer designed to enhance texture-aware representation learning for remote sensing image classification. The proposed NFP layer captures relationships between neighboring spatial features by aggregating local similarity patterns across feature dimensions. Implemented using standard convolutional operations, NFP can be seamlessly integrated into existing neural network architectures with minimal additional parameters. Extensive experiments across multiple benchmark datasets and backbone models demonstrate that NFP consistently improves classification performance compared to conventional pooling strategies, while maintaining computational efficiency. These results highlight the effectiveness of neighborhood-based feature aggregation for capturing discriminative texture information in remote sensing imagery.

---

### BOND: License to Train with Black-Box Functions

Authors: Andrew Clark, Jack Moursounidis, Osmaan Rasouli, William Gan, Cooper Doyle, Anna Leontjeva
Published: 2025-10-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.25074v2

We introduce Bounded Numerical Differentiation (BOND), a perturbative method for estimating the gradients of black-box functions. BOND is distinguished by its formulation, which adaptively bounds perturbations to ensure accurate sign estimation, and by its implementation, which operates at black-box interfaces. This enables BOND to be more accurate and scalable compared to existing methods, facilitating end-to-end training of architectures that incorporate non-autodifferentiable modules. We observe that these modules, implemented in our experiments as frozen networks, can enhance model performance without increasing the number of trainable parameters. Our findings highlight the potential of leveraging fixed transformations to expand model capacity, pointing to hybrid analogue - digital devices as a path to scaling networks, and provides insights into the dynamics of adaptive optimizers.

---

### Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments

Authors: Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.25070v1

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work proposes a vision-language integration framework that unifies pre-trained visual encoders (e.g., CLIP, ViT) and large language models (e.g., GPT-based architectures) to achieve semantic alignment between visual and textual modalities. The goal is to enable robust zero-shot comprehension of scenes by leveraging natural language as a bridge to generalize over unseen categories and contexts. Our approach develops a unified model that embeds visual inputs and textual prompts into a shared space, followed by multimodal fusion and reasoning layers for contextual interpretation. Experiments on Visual Genome, COCO, ADE20K, and custom real-world datasets demonstrate significant gains over state-of-the-art zero-shot models in object recognition, activity detection, and scene captioning. The proposed system achieves up to 18% improvement in top-1 accuracy and notable gains in semantic coherence metrics, highlighting the effectiveness of cross-modal alignment and language grounding in enhancing generalization for real-world scene understanding.

---

### TOPol: Capturing and Explaining Multidimensional Semantic Polarity Fields and Vectors

Authors: Gabin Taibi, Lucia Gomez
Published: 2025-10-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.25069v2

Traditional approaches to semantic polarity in computational linguistics treat sentiment as a unidimensional scale, overlooking the multidimensional structure of language. This work introduces TOPol (Topic-Orientation POLarity), a semi-unsupervised framework for reconstructing and interpreting multidimensional narrative polarity fields under human-on-the-loop (HoTL) defined contextual boundaries (CBs). The framework embeds documents using a transformer-based large language model (tLLM), applies neighbor-tuned UMAP projection, and segments topics via Leiden partitioning. Given a CB between discourse regimes A and B, TOPol computes directional vectors between corresponding topic-boundary centroids, yielding a polarity field that quantifies fine-grained semantic displacement during regime shifts. This vectorial representation enables assessing CB quality and detecting polarity changes, guiding HoTL CB refinement. To interpret identified polarity vectors, the tLLM compares their extreme points and produces contrastive labels with estimated coverage. Robustness analyses show that only CB definitions (the main HoTL-tunable parameter) significantly affect results, confirming methodological stability. We evaluate TOPol on two corpora: (i) U.S. Central Bank speeches around a macroeconomic breakpoint, capturing non-affective semantic shifts, and (ii) Amazon product reviews across rating strata, where affective polarity aligns with NRC valence. Results demonstrate that TOPol consistently captures both affective and non-affective polarity transitions, providing a scalable, generalizable, and interpretable framework for context-sensitive multidimensional discourse analysis.

---

### DRIP: Dynamic patch Reduction via Interpretable Pooling

Authors: Yusen Peng, Sachin Kumar
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.25067v2

Recently, the advances in vision-language models, including contrastive pretraining and instruction tuning, have greatly pushed the frontier of multimodal AI. However, owing to the large-scale and hence expensive pretraining, the efficiency concern has discouraged researchers from attempting to pretrain a vision language model from scratch. In this work, we propose Dynamic patch Reduction via Interpretable Pooling (DRIP), which adapts to the input images and dynamically merges tokens in the deeper layers of a visual encoder. Our results on both ImageNet training from scratch and CLIP contrastive pretraining demonstrate a significant GFLOP reduction while maintaining comparable classification/zero-shot performance. To further validate our proposed method, we conduct continual pretraining on a large biology dataset, extending its impact into scientific domains.

---

### Rewarding Structural Conformance of Reasoning using Process Mining

Authors: Yongjae Lee, Taekhyun Park, Sunghyun Sim, Hyerim Bae
Published: 2025-10-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.25065v3

Recent advances in sparse reward policy gradient methods have enabled effective reinforcement learning (RL)-based language model post-training. However, for reasoning tasks such as mathematical problem solving, binarized outcome rewards provide limited feedback on intermediate reasoning steps. While some studies have attempted to address this issue by estimating overall reasoning quality, it remains unclear whether these rewards are reliable proxies for the quality of stepwise reasoning. In this study, we consider reasoning as a structured process and propose TACReward, the reward model that can be seamlessly integrated into sparse reward policy gradient methods without additional human annotation costs or architectural modifications. TACReward aggregates stepwise structural deviations between teacher and policy reasoning using process mining techniques, producing a scalar output reward range of (0, 1) to indicate reasoning quality. Experiments on multiple mathematical reasoning benchmarks demonstrate that integrating the TACReward into sparse reward frameworks encourages the policy model to improve the structural quality of reasoning. Consequently, this leads to consistent performance improvements over existing sparse reward frameworks. Our code and checkpoints are publicly available at https://github.com/Thrillcrazyer/TACReward and https://huggingface.co/Thrillcrazyer/TACReward7B.

---

### Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?

Authors: Seonjeong Hwang, Hyounghun Kim, Gary Geunbae Lee
Published: 2025-10-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.25064v2

Estimating the cognitive complexity of reading comprehension (RC) items is crucial for assessing item difficulty before it is administered to learners. Unlike syntactic and semantic features, such as passage length or semantic similarity between options, cognitive features that arise during answer reasoning are not readily extractable using existing NLP tools and have traditionally relied on human annotation. In this study, we examine whether large language models (LLMs) can estimate the cognitive complexity of RC items by focusing on two dimensions-Evidence Scope and Transformation Level-that indicate the degree of cognitive burden involved in reasoning about the answer. Our experimental results demonstrate that LLMs can approximate the cognitive complexity of items, indicating their potential as tools for prior difficulty analysis. Further analysis reveals a gap between LLMs' reasoning ability and their metacognitive awareness: even when they produce correct answers, they sometimes fail to correctly identify the features underlying their own reasoning process.

---

### Nonlinear Dynamics In Optimization Landscape of Shallow Neural Networks with Tunable Leaky ReLU

Authors: Jingzhou Liu
Published: 2025-10-29
Categories: math.OC, cs.LG, math.DS
arXiv: https://arxiv.org/abs/2510.25060v2

In this work, we study the nonlinear dynamics of a shallow neural network trained with mean-squared loss and leaky ReLU activation. Under Gaussian inputs and equal layer width k, (1) we establish, based on the equivariant gradient degree, a theoretical framework, applicable to any number of neurons k>= 4, to detect bifurcation of critical points with associated symmetries from global minimum as leaky parameter $α$ varies. Typically, our analysis reveals that a multi-mode degeneracy consistently occurs at the critical number 0, independent of k. (2) As a by-product, we further show that such bifurcations are width-independent, arise only for nonnegative $α$ and that the global minimum undergoes no further symmetry-breaking instability throughout the engineering regime $α$ in range (0,1). An explicit example with k=5 is presented to illustrate the framework and exhibit the resulting bifurcation together with their symmetries.

---

### Auto3DSeg for Brain Tumor Segmentation from 3D MRI in BraTS 2023 Challenge

Authors: Andriy Myronenko, Dong Yang, Yufan He, Daguang Xu
Published: 2025-10-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.25058v1

In this work, we describe our solution to the BraTS 2023 cluster of challenges using Auto3DSeg from MONAI. We participated in all 5 segmentation challenges, and achieved the 1st place results in three of them: Brain Metastasis, Brain Meningioma, BraTS-Africa challenges, and the 2nd place results in the remaining two: Adult and Pediatic Glioma challenges.

---

### GAPMAP: Mapping Scientific Knowledge Gaps in Biomedical Literature Using Large Language Models

Authors: Nourah M Salem, Elizabeth White, Michael Bada, Lawrence Hunter
Published: 2025-10-29
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.25055v1

Scientific progress is driven by the deliberate articulation of what remains unknown. This study investigates the ability of large language models (LLMs) to identify research knowledge gaps in the biomedical literature. We define two categories of knowledge gaps: explicit gaps, clear declarations of missing knowledge; and implicit gaps, context-inferred missing knowledge. While prior work has focused mainly on explicit gap detection, we extend this line of research by addressing the novel task of inferring implicit gaps. We conducted two experiments on almost 1500 documents across four datasets, including a manually annotated corpus of biomedical articles. We benchmarked both closed-weight models (from OpenAI) and open-weight models (Llama and Gemma 2) under paragraph-level and full-paper settings. To address the reasoning of implicit gaps inference, we introduce \textbf{\small TABI}, a Toulmin-Abductive Bucketed Inference scheme that structures reasoning and buckets inferred conclusion candidates for validation. Our results highlight the robust capability of LLMs in identifying both explicit and implicit knowledge gaps. This is true for both open- and closed-weight models, with larger variants often performing better. This suggests a strong ability of LLMs for systematically identifying candidate knowledge gaps, which can support early-stage research formulation, policymakers, and funding decisions. We also report observed failure modes and outline directions for robust deployment, including domain adaptation, human-in-the-loop verification, and benchmarking across open- and closed-weight models.

---

### Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech

Authors: Pedro Corrêa, João Lima, Victor Moreno, Lucas Ueda, Paula Dornhofer Paro Costa
Published: 2025-10-29
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2510.25054v2

Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks. Although promising results have been achieved, there is growing discussion regarding these models' generalization capabilities and the extent to which they truly integrate audio and text modalities in their internal representations. In this work, we evaluate four SLMs on the task of speech emotion recognition using a dataset of emotionally incongruent speech samples, a condition under which the semantic content of the spoken utterance conveys one emotion while speech expressiveness conveys another. Our results indicate that SLMs rely predominantly on textual semantics rather than speech emotion to perform the task, indicating that text-related representations largely dominate over acoustic representations. We release both the code and the Emotionally Incongruent Synthetic Speech dataset (EMIS) to the community.

---

### Scalable predictive processing framework for multitask caregiving robots

Authors: Hayato Idei, Tamon Miyake, Tetsuya Ogata, Yuichi Yamashita
Published: 2025-10-29
Categories: cs.RO, cs.AI, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2510.25053v1

The rapid aging of societies is intensifying demand for autonomous care robots; however, most existing systems are task-specific and rely on handcrafted preprocessing, limiting their ability to generalize across diverse scenarios. A prevailing theory in cognitive neuroscience proposes that the human brain operates through hierarchical predictive processing, which underlies flexible cognition and behavior by integrating multimodal sensory signals. Inspired by this principle, we introduce a hierarchical multimodal recurrent neural network grounded in predictive processing under the free-energy principle, capable of directly integrating over 30,000-dimensional visuo-proprioceptive inputs without dimensionality reduction. The model was able to learn two representative caregiving tasks, rigid-body repositioning and flexible-towel wiping, without task-specific feature engineering. We demonstrate three key properties: (i) self-organization of hierarchical latent dynamics that regulate task transitions, capture variability in uncertainty, and infer occluded states; (ii) robustness to degraded vision through visuo-proprioceptive integration; and (iii) asymmetric interference in multitask learning, where the more variable wiping task had little influence on repositioning, whereas learning the repositioning task led to a modest reduction in wiping performance, while the model maintained overall robustness. Although the evaluation was limited to simulation, these results establish predictive processing as a universal and scalable computational principle, pointing toward robust, flexible, and autonomous caregiving robots while offering theoretical insight into the human brain's ability to achieve flexible adaptation in uncertain real-world environments.

---

### Breast Cancer VLMs: Clinically Practical Vision-Language Train-Inference Models

Authors: Shunjie-Fabian Zheng, Hyeonjun Lee, Thijs Kooi, Ali Diba
Published: 2025-10-29
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.25051v1

Breast cancer remains the most commonly diagnosed malignancy among women in the developed world. Early detection through mammography screening plays a pivotal role in reducing mortality rates. While computer-aided diagnosis (CAD) systems have shown promise in assisting radiologists, existing approaches face critical limitations in clinical deployment - particularly in handling the nuanced interpretation of multi-modal data and feasibility due to the requirement of prior clinical history. This study introduces a novel framework that synergistically combines visual features from 2D mammograms with structured textual descriptors derived from easily accessible clinical metadata and synthesized radiological reports through innovative tokenization modules. Our proposed methods in this study demonstrate that strategic integration of convolutional neural networks (ConvNets) with language representations achieves superior performance to vision transformer-based models while handling high-resolution images and enabling practical deployment across diverse populations. By evaluating it on multi-national cohort screening mammograms, our multi-modal approach achieves superior performance in cancer detection and calcification identification compared to unimodal baselines, with particular improvements. The proposed method establishes a new paradigm for developing clinically viable VLM-based CAD systems that effectively leverage imaging data and contextual patient information through effective fusion mechanisms.

---

### Dynamically Weighted Momentum with Adaptive Step Sizes for Efficient Deep Network Training

Authors: Zhifeng Wang, Longlong Li, Chunyan Zeng
Published: 2025-10-29
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.25042v1

Within the current sphere of deep learning research, despite the extensive application of optimization algorithms such as Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (Adam), there remains a pronounced inadequacy in their capability to address fluctuations in learning efficiency, meet the demands of complex models, and tackle non-convex optimization issues. These challenges primarily arise from the algorithms' limitations in handling complex data structures and models, for instance, difficulties in selecting an appropriate learning rate, avoiding local optima, and navigating through high-dimensional spaces. To address these issues, this paper introduces a novel optimization algorithm named DWMGrad. This algorithm, building on the foundations of traditional methods, incorporates a dynamic guidance mechanism reliant on historical data to dynamically update momentum and learning rates. This allows the optimizer to flexibly adjust its reliance on historical information, adapting to various training scenarios. This strategy not only enables the optimizer to better adapt to changing environments and task complexities but also, as validated through extensive experimentation, demonstrates DWMGrad's ability to achieve faster convergence rates and higher accuracies under a multitude of scenarios.

---

### Improving User Experience with Personalized Review Ranking and Summarization

Authors: Muhammad Jawad Mufti, Omar Hammad, MD. Mahfuzur Rahman
Published: 2025-10-28
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.05261v2

Online consumer reviews are important decision-support resources in e-commerce, yet the increasing volume of reviews often creates information overload and makes it difficult for users to identify content that matches their individual preferences. Existing review-ranking approaches commonly rely on aggregate signals such as star ratings, helpfulness votes, or recency, which may not reflect user-specific interests. This paper proposes a personalized review ranking and summarization framework that integrates user preference modeling, hybrid sentiment estimation, aspect-level review matching, and Large Language Model (LLM)-based summarization. The framework first extracts aspect-level preferences and sentiment signals from historical reviews. It then incorporates user-selected product aspects and written review input to build a personalized user profile. Candidate reviews are ranked by comparing this profile with review-level aspect and sentiment representations. The top-ranked reviews are then summarized to provide concise, preference-aligned information. The proposed method was evaluated using an Amazon Mobile Electronics review dataset and a structured user study involving 70 participants across common consumer electronics categories. Results show that the proposed ranking method outperformed random ordering, star-rating-based ranking, helpfulness-vote ranking, recency-based ranking, and semantic-similarity-based ranking. User-study results further indicate improvements in satisfaction, perceived relevance, decision-making confidence, ease of finding information, and reading efficiency. The findings suggest that combining aspect-level personalization, sentiment-aware ranking, and LLM-based summarization can reduce review overload and support more efficient user-centered decision-making.

---

### A Comprehensive Survey on Surgical Digital Twin

Authors: Afsah Sharaf Khan, Falong Fan, Doohwan DH Kim, Abdurrahman Alshareef, Dong Chen, Justin Kim, Ernest Carter, Bo Liu, Jerzy W. Rozenblit, Bernard Zeigler
Published: 2025-10-28
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2512.00019v1

With the accelerating availability of multimodal surgical data and real-time computation, Surgical Digital Twins (SDTs) have emerged as virtual counterparts that mirror, predict, and inform decisions across pre-, intra-, and postoperative care. Despite promising demonstrations, SDTs face persistent challenges: fusing heterogeneous imaging, kinematics, and physiology under strict latency budgets; balancing model fidelity with computational efficiency; ensuring robustness, interpretability, and calibrated uncertainty; and achieving interoperability, privacy, and regulatory compliance in clinical environments. This survey offers a critical, structured review of SDTs. We clarify terminology and scope, propose a taxonomy by purpose, model fidelity, and data sources, and synthesize state-of-the-art achievements in deformable registration and tracking, real-time simulation and co-simulation, AR/VR guidance, edge-cloud orchestration, and AI for scene understanding and prediction. We contrast non-robotic twins with robot-in-the-loop architectures for shared control and autonomy, and identify open problems in validation and benchmarking, safety assurance and human factors, lifecycle "digital thread" integration, and scalable data governance. We conclude with a research agenda toward trustworthy, standards-aligned SDTs that deliver measurable clinical benefit. By unifying vocabulary, organizing capabilities, and highlighting gaps, this work aims to guide SDT design and deployment and catalyze translation from laboratory prototypes to routine surgical care.

---

### Evaluating Device-First Continuum AI (DFC-AI) for Autonomous Operations in the Energy Sector

Authors: Siavash M. Alamouti, Fay Arjomandi, Michel Burger, Bashar Altakrouri
Published: 2025-10-28
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2511.17528v2

Industrial automation in the energy sector requires AI systems that can operate autonomously regardless of network availability, a requirement that cloud-centric architectures cannot meet. This paper evaluates the application of Device-First Continuum AI (DFC-AI) to critical energy sector operations. DFC-AI, a specialized architecture within the Hybrid Edge Cloud paradigm, implements intelligent agents using a microservices architecture that originates at end devices and extends across the computational continuum. Through comprehensive simulations of energy sector scenarios including drone inspections, sensor networks, and worker safety systems, we demonstrate that DFC-AI maintains full operational capability during network outages while cloud and gateway-based systems experience complete or partial failure. Our analysis reveals that zero-configuration GPU discovery and heterogeneous device clustering are particularly well-suited for energy sector deployments, where specialized nodes can handle intensive AI workloads for entire fleets of inspection drones or sensor networks. The evaluation shows that DFC-AI achieves significant latency reduction and energy savings compared to cloud architectures. Additionally, we find that gateway based edge solutions can paradoxically cost more than cloud solutions for certain energy sector workloads due to infrastructure overhead, while DFC-AI can consistently provide cost savings by leveraging enterprise-owned devices. These findings, validated through rigorous statistical analysis, establish that DFC-AI addresses the unique challenges of energy sector operations, ensuring intelligent agents remain available and functional in remote oil fields, offshore platforms, and other challenging environments characteristic of the industry.

---

### Decision-Making Amid Information-Based Threats in Sociotechnical Systems: A Review

Authors: Aaron R. Allred, Erin E. Richardson, Sarah R. Bostrom, James Crum, Cara Spencer, Chad Tossell, Richard E. Niemeyer, Leanne Hirshfield, Allison P. A. Hayman
Published: 2025-10-28
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2511.11595v1

Technological systems increasingly mediate human information exchange, spanning interactions among humans as well as between humans and artificial agents. The unprecedented scale and reliance on information disseminated through these systems substantially expand the scope of information-based influence that can both enable and undermine sound decision-making. Consequently, understanding and protecting decision-making today faces growing challenges, as individuals and organizations must navigate evolving opportunities and information-based threats across varied domains and information environments. While these risks are widely recognized, research remains fragmented: work evaluating information-based threat phenomena has progressed largely in isolation from foundational studies of human information processing. In this review, we synthesize insights from both domains to identify shared cognitive mechanisms that mediate vulnerability to information-based threats and shape behavioral outcomes. Finally, we outline directions for future research aimed at integrating these perspectives, emphasizing the importance of such integration for mitigating human vulnerabilities and aligning human-machine representations.

---

### Where did you get that? Towards Summarization Attribution for Analysts

Authors: Violet B, John M. Conroy, Sean Lynch, Danielle M, Neil P. Molino, Aaron Wiechmann, Julia S. Yang
Published: 2025-10-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.08589v1

Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.

---

### Explainable Federated Learning for U.S. State-Level Financial Distress Modeling

Authors: Lorenzo Carta, Fernando Spadea, Oshani Seneviratne
Published: 2025-10-28
Categories: q-fin.ST, cs.LG
arXiv: https://arxiv.org/abs/2511.08588v1

We present the first application of federated learning (FL) to the U.S. National Financial Capability Study, introducing an interpretable framework for predicting consumer financial distress across all 50 states and the District of Columbia without centralizing sensitive data. Our cross-silo FL setup treats each state as a distinct data silo, simulating real-world governance in nationwide financial systems. Unlike prior work, our approach integrates two complementary explainable AI techniques to identify both global (nationwide) and local (state-specific) predictors of financial hardship, such as contact from debt collection agencies. We develop a machine learning model specifically suited for highly categorical, imbalanced survey data. This work delivers a scalable, regulation-compliant blueprint for early warning systems in finance, demonstrating how FL can power socially responsible AI applications in consumer credit risk and financial inclusion.

---

### Evidence-Bound Autonomous Research (EviBound): A Governance Framework for Eliminating False Claims

Authors: Ruiying Chen
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.05524v1

LLM-based autonomous research agents report false claims: tasks marked "complete" despite missing artifacts, contradictory metrics, or failed executions. EviBound is an evidence-bound execution framework that eliminates false claims through dual governance gates requiring machine-checkable evidence. Two complementary gates enforce evidence requirements. The pre-execution Approval Gate validates acceptance criteria schemas before code runs, catching structural violations proactively. The post-execution Verification Gate validates artifacts via MLflow API queries (with recursive path checking) and optionally validates metrics when specified by acceptance criteria. Claims propagate only when backed by a queryable run ID, required artifacts, and FINISHED status. Bounded, confidence-gated retries (typically 1-2 attempts) recover from transient failures without unbounded loops. The framework was evaluated on 8 benchmark tasks spanning infrastructure validation, ML capabilities, and governance stress tests. Baseline A (Prompt-Level Only) yields 100% hallucination (8/8 claimed, 0/8 verified). Baseline B (Verification-Only) reduces hallucination to 25% (2/8 fail verification). EviBound (Dual Gates) achieves 0% hallucination: 7/8 tasks verified and 1 task correctly blocked at the approval gate, all with only approximately 8.3% execution overhead. This package includes execution trajectories, MLflow run IDs for all verified tasks, and a 4-step verification protocol. Research integrity is an architectural property, achieved through governance gates rather than emergent from model scale.

---

### The Evolution of Probabilistic Price Forecasting Techniques: A Review of the Day-Ahead, Intra-Day, and Balancing Markets

Authors: Ciaran O'Connor, Mohamed Bahloul, Steven Prestwich, Andrea Visentin
Published: 2025-10-28
Categories: q-fin.ST, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2511.05523v1

Electricity price forecasting has become a critical tool for decision-making in energy markets, particularly as the increasing penetration of renewable energy introduces greater volatility and uncertainty. Historically, research in this field has been dominated by point forecasting methods, which provide single-value predictions but fail to quantify uncertainty. However, as power markets evolve due to renewable integration, smart grids, and regulatory changes, the need for probabilistic forecasting has become more pronounced, offering a more comprehensive approach to risk assessment and market participation. This paper presents a review of probabilistic forecasting methods, tracing their evolution from Bayesian and distribution based approaches, through quantile regression techniques, to recent developments in conformal prediction. Particular emphasis is placed on advancements in probabilistic forecasting, including validity-focused methods which address key limitations in uncertainty estimation. Additionally, this review extends beyond the Day-Ahead Market to include the Intra-Day and Balancing Markets, where forecasting challenges are intensified by higher temporal granularity and real-time operational constraints. We examine state of the art methodologies, key evaluation metrics, and ongoing challenges, such as forecast validity, model selection, and the absence of standardised benchmarks, providing researchers and practitioners with a comprehensive and timely resource for navigating the complexities of modern electricity markets.

---

### AIRMap: AI-Generated Radio Maps for Wireless Digital Twins

Authors: Ali Saeizadeh, Miead Tehrani-Moayyed, Davide Villa, J. Gordon Beattie, Pedram Johari, Stefano Basagni, Tommaso Melodia
Published: 2025-10-28
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2511.05522v4

Accurate, low-latency channel modeling is essential for real-time wireless network simulation and digital-twin applications. Traditional modeling methods like ray tracing are however computationally demanding and unsuited to model dynamic conditions. In this paper, we propose AIRMap, a deep-learning framework for ultra-fast radio-map estimation, along with an automated pipeline for creating the largest radio-map dataset to date. AIRMap uses a single-input U-Net autoencoder that processes only a 2D elevation map of terrain and building heights. Trained on 1.2M Boston-area samples and validated across four distinct urban and rural environments with varying terrain and building density, AIRMap predicts path gain with under 4 dB RMSE in 4 ms per inference on an NVIDIA L40S-over 100x faster than GPU-accelerated ray tracing based radio maps. A lightweight calibration using just 20% of field measurements reduces the median error to approximately 5%, significantly outperforming traditional simulators, which exceed 50% error. Integration into the Colosseum emulator and the Sionna SYS platform demonstrate near-zero error in spectral efficiency and block-error rate compared to measurement-based channels. These findings validate AIRMap's potential for scalable, accurate, and real-time radio map estimation in wireless digital twins.

---

### SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection

Authors: Jingqing Wang, Jiaxing Shang, Rong Xu, Fei Hao, Tianjin Huang, Geyong Min
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.04692v1

Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

---

### A Penny for Your Thoughts: Decoding Speech from Inexpensive Brain Signals

Authors: Quentin Auster, Kateryna Shapovalenko, Chuang Ma, Demaio Sun
Published: 2025-10-28
Categories: cs.SD, cs.AI, cs.CL, cs.HC, eess.AS, q-bio.NC
arXiv: https://arxiv.org/abs/2511.04691v1

We explore whether neural networks can decode brain activity into speech by mapping EEG recordings to audio representations. Using EEG data recorded as subjects listened to natural speech, we train a model with a contrastive CLIP loss to align EEG-derived embeddings with embeddings from a pre-trained transformer-based speech model. Building on the state-of-the-art EEG decoder from Meta, we introduce three architectural modifications: (i) subject-specific attention layers (+0.15% WER improvement), (ii) personalized spatial attention (+0.45%), and (iii) a dual-path RNN with attention (-1.87%). Two of the three modifications improved performance, highlighting the promise of personalized architectures for brain-to-speech decoding and applications in brain-computer interfaces.

---

### World Simulation with Video Foundation Models for Physical AI

Authors: NVIDIA, :, Arslan Ali, Junjie Bai, Maciej Bala, Yogesh Balaji, Aaron Blakeman, Tiffany Cai, Jiaxin Cao, Tianshi Cao, Elizabeth Cha, Yu-Wei Chao et al.
Published: 2025-10-28
Categories: cs.CV, cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2511.00062v2

We introduce (Cosmos-Predict2.5), the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, (Cosmos-Predict2.5) unifies Text2World, Image2World, and Video2World generation in a single model and leverages (Cosmos-Reason1), a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, (Cosmos-Predict2.5) achieves substantial improvements over (Cosmos-Predict1) in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with (Cosmos-Transfer2.5), a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5$\times$ smaller than (Cosmos-Transfer1), it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish (Cosmos-Predict2.5) and (Cosmos-Transfer2.5) as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.

---

### Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?

Authors: Zhiqi Qi, Runxin Zhao, Hanyang Zhuang, Chunxiang Wang, Ming Yang
Published: 2025-10-28
Categories: cs.CV, cs.RO, eess.IV
arXiv: https://arxiv.org/abs/2511.00060v1

LiDAR-based roadside perception is a cornerstone of advanced Intelligent Transportation Systems (ITS). While considerable research has addressed optimal LiDAR placement for infrastructure, the profound impact of differing LiDAR scanning patterns on perceptual performance remains comparatively under-investigated. The inherent nature of various scanning modes - such as traditional repetitive (mechanical/solid-state) versus emerging non-repetitive (e.g. prism-based) systems - leads to distinct point cloud distributions at varying distances, critically dictating the efficacy of object detection and overall environmental understanding. To systematically investigate these differences in infrastructure-based contexts, we introduce the "InfraLiDARs' Benchmark," a novel dataset meticulously collected in the CARLA simulation environment using concurrently operating infrastructure-based LiDARs exhibiting both scanning paradigms. Leveraging this benchmark, we conduct a comprehensive statistical analysis of the respective LiDAR scanning abilities and evaluate the impact of these distinct patterns on the performance of various leading 3D object detection algorithms. Our findings reveal that non-repetitive scanning LiDAR and the 128-line repetitive LiDAR were found to exhibit comparable detection performance across various scenarios. Despite non-repetitive LiDAR's limited perception range, it's a cost-effective option considering its low price. Ultimately, this study provides insights for setting up roadside perception system with optimal LiDAR scanning patterns and compatible algorithms for diverse roadside applications, and publicly releases the "InfraLiDARs' Benchmark" dataset to foster further research.

---

### Automatically Finding Rule-Based Neurons in OthelloGPT

Authors: Aditya Singh, Zihang Wen, Srujananjali Medicherla, Adam Karvonen, Can Rager
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00059v1

OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computational patterns, yet grounded in rule-based game logic that enables meaningful reverse-engineering. We present an automated approach based on decision trees to identify and interpret MLP neurons that encode rule-based game logic. Our method trains regression decision trees to map board states to neuron activations, then extracts decision paths where neurons are highly active to convert them into human-readable logical forms. These descriptions reveal highly interpretable patterns; for instance, neurons that specifically detect when diagonal moves become legal. Our findings suggest that roughly half of the neurons in layer 5 can be accurately described by compact, rule-based decision trees ($R^2 > 0.7$ for 913 of 2,048 neurons), while the remainder likely participate in more distributed or non-rule-based computations. We verify the causal relevance of patterns identified by our decision trees through targeted interventions. For a specific square, for specific game patterns, we ablate neurons corresponding to those patterns and find an approximately 5-10 fold stronger degradation in the model's ability to predict legal moves along those patterns compared to control patterns. To facilitate future work, we provide a Python tool that maps rule-based game behaviors to their implementing neurons, serving as a resource for researchers to test whether their interpretability methods recover meaningful computational structures.

---

### MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

Authors: Yuxi Liu, Renjia Deng, Yutong He, Xue Wang, Tao Yao, Kun Yuan
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00056v3

The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise optimization, which treats each transformer block as a single layer and optimizes it sequentially, while freezing the other layers to save optimizer states and activations. Although effective, these methods ignore the varying importance of the modules within each layer, leading to suboptimal performance. Moreover, layer-wise sampling provides only limited memory savings, as at least one full layer must remain active during optimization. To overcome these limitations, we propose Module-wise Importance SAmpling (MISA), a novel method that divides each layer into smaller modules and assigns importance scores to each module. MISA uses a weighted random sampling mechanism to activate modules, provably reducing gradient variance compared to layer-wise sampling. Additionally, we establish an \(\mathcal{O}(1/\sqrt{K})\) convergence rate under non-convex and stochastic conditions, where $K$ is the total number of block updates, and provide a detailed memory analysis showcasing MISA's superiority over existing baseline methods. Experiments on diverse learning tasks validate the effectiveness of MISA. Source code is available at https://github.com/pkumelon/MISA.

---

### Exploring Federated Learning for Thermal Urban Feature Segmentation -- A Comparison of Centralized and Decentralized Approaches

Authors: Leonhard Duda, Khadijeh Alibabaei, Elena Vollmer, Leon Klug, Valentin Kozlov, Lisana Berberi, Mishal Benz, Rebekka Volk, Juan Pedro Gutiérrez Hermosillo Muriedas, Markus Götz, Judith Sáínz-Pardo Díaz, Álvaro López García et al.
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00055v2

Federated Learning (FL) is an approach for training a shared Machine Learning (ML) model with distributed training data and multiple participants. FL allows bypassing limitations of the traditional Centralized Machine Learning CL if data cannot be shared or stored centrally due to privacy or technical restrictions -- the participants train the model locally with their training data and do not need to share it among the other participants. This paper investigates the practical implementation and effectiveness of FL in a real-world scenario, specifically focusing on unmanned aerial vehicle (UAV)-based thermal images for common thermal feature detection in urban environments. The distributed nature of the data arises naturally and makes it suitable for FL applications, as images captured in two German cities are available. This application presents unique challenges due to non-identical distribution and feature characteristics of data captured at both locations. The study makes several key contributions by evaluating FL algorithms in real deployment scenarios rather than simulation. We compare several FL approaches with a centralized learning baseline across key performance metrics such as model accuracy, training time, communication overhead, and energy usage. This paper also explores various FL workflows, comparing client-controlled workflows and server-controlled workflows. The findings of this work serve as a valuable reference for understanding the practical application and limitations of the FL methods in segmentation tasks in UAV-based imaging.

---

### SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation

Authors: Gio Huh, Dhruv Sheth, Rayhan Zirvi, Frank Xiao
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00054v1

While Vision-Language Models (VLMs) excel in many areas, they struggle with complex spatial reasoning, which requires problem decomposition and strategic tool use. Fine-tuning smaller, more deployable models offers an efficient path to strong performance, but this is hampered by a major bottleneck: the absence of high-quality, step-by-step reasoning data. To address this data-efficiency gap, we introduce SpatialTraceGen, a framework to distill the reasoning processes of a large teacher model into a high-quality dataset of multi-hop, multi-tool reasoning traces. A key innovation is our automated Verifier, which scalably ensures the fidelity of each reasoning step, providing a cost-effective alternative to manual human annotation. On the CLEVR-Humans benchmark, this verifier-guided process improves the average quality score of traces by 17\% while reducing quality variance by over 40\%. SpatialTraceGen delivers a dataset of expert traces, providing the structured, step-by-step examples of tool use necessary for effective fine-tuning and sample-efficient offline reinforcement learning.

---

### Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

Authors: Hao Wang, Licheng Pan, Yuan Lu, Zhichao Chen, Tianqiao Liu, Shuting He, Zhixuan Chu, Qingsong Wen, Haoxuan Li, Zhouchen Lin
Published: 2025-10-28
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.00053v2

The design of learning objectives is central to training time-series forecasting models. Existing learning objectives such as mean squared error mostly treat each future step as an independent, equally weighted task, which leads to the following two challenges: (1) they overlook the label autocorrelation effect among future steps, leading to biased learning objectives; (2) they fail to set heterogeneous task weights for different forecasting tasks corresponding to varying future steps, limiting the forecasting performance. To fill this gap, we propose a novel quadratic-form weighted learning objective, addressing both issues simultaneously. Specifically, the off-diagonal elements of the weighting matrix account for the label autocorrelation effect, whereas the non-uniform diagonals are expected to match the preferred weights of the forecasting tasks with varying future steps. On this basis, we propose a Quadratic Direct Forecast (QDF) learning algorithm, which trains the forecast model using the adaptively updated quadratic-form weighting matrix. Experiments show that our QDF effectively improves the performance of various forecast models, achieving state-of-the-art results. Code is available at https://github.com/Master-PLC/QDF.

---