# Research Papers — 2025-11 · bundle page 151 of 197

> Full-text markdown of papers #7501–7550 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/151
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/150.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/152.md)

### Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees

Authors: Mohammad Shirzadi, Ali Safarpoor Dehkordi, Ahad N. Zehmakan
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06598v1

Message passing is the core operation in graph neural networks, where each node updates its embeddings by aggregating information from its neighbors. However, in deep architectures, this process often leads to diminished expressiveness. A popular solution is to use residual connections, where the input from the current (or initial) layer is added to aggregated neighbor information to preserve embeddings across layers. Following a recent line of research, we investigate an adaptive residual scheme in which different nodes have varying residual strengths. We prove that this approach prevents oversmoothing; particularly, we show that the Dirichlet energy of the embeddings remains bounded away from zero. This is the first theoretical guarantee not only for the adaptive setting, but also for static residual connections (where residual strengths are shared across nodes) with activation functions. Furthermore, extensive experiments show that this adaptive approach outperforms standard and state-of-the-art message passing mechanisms, especially on heterophilic graphs. To improve the time complexity of our approach, we introduce a variant in which residual strengths are not learned but instead set heuristically, a choice that performs as well as the learnable version.

---

### Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality

Authors: Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
Published: 2025-11-10
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2511.06597v1

In this work, we study offline convex optimization with smooth objectives, where the classical Nesterov's Accelerated Gradient (NAG) method achieves the optimal accelerated convergence. Extensive research has aimed to understand NAG from various perspectives, and a recent line of work approaches this from the viewpoint of online learning and online-to-batch conversion, emphasizing the role of optimistic online algorithms for acceleration. In this work, we contribute to this perspective by proposing novel optimistic online-to-batch conversions that incorporate optimism theoretically into the analysis, thereby significantly simplifying the online algorithm design while preserving the optimal convergence rates. Specifically, we demonstrate the effectiveness of our conversions through the following results: (i) when combined with simple online gradient descent, our optimistic conversion achieves the optimal accelerated convergence; (ii) our conversion also applies to strongly convex objectives, and by leveraging both optimistic online-to-batch conversion and optimistic online algorithms, we achieve the optimal accelerated convergence rate for strongly convex and smooth objectives, for the first time through the lens of online-to-batch conversion; (iii) our optimistic conversion can achieve universality to smoothness -- applicable to both smooth and non-smooth objectives without requiring knowledge of the smoothness coefficient -- and remains efficient as non-universal methods by using only one gradient query in each iteration. Finally, we highlight the effectiveness of our optimistic online-to-batch conversions by a precise correspondence with NAG.

---

### Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion

Authors: Hui Sun, Long Lv, Pingping Zhang, Tongdan Tang, Feng Tian, Weibing Sun, Huchuan Lu
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06593v1

Multi-Modal Image Fusion (MMIF) aims to integrate complementary image information from different modalities to produce informative images. Previous deep learning-based MMIF methods generally adopt Convolutional Neural Networks (CNNs) or Transformers for feature extraction. However, these methods deliver unsatisfactory performances due to the limited receptive field of CNNs and the high computational cost of Transformers. Recently, Mamba has demonstrated a powerful potential for modeling long-range dependencies with linear complexity, providing a promising solution to MMIF. Unfortunately, Mamba lacks full spatial and frequency perceptions, which are very important for MMIF. Moreover, employing Image Reconstruction (IR) as an auxiliary task has been proven beneficial for MMIF. However, a primary challenge is how to leverage IR efficiently and effectively. To address the above issues, we propose a novel framework named Spatial-Frequency Enhanced Mamba Fusion (SFMFusion) for MMIF. More specifically, we first propose a three-branch structure to couple MMIF and IR, which can retain complete contents from source images. Then, we propose the Spatial-Frequency Enhanced Mamba Block (SFMB), which can enhance Mamba in both spatial and frequency domains for comprehensive feature extraction. Finally, we propose the Dynamic Fusion Mamba Block (DFMB), which can be deployed across different branches for dynamic feature fusion. Extensive experiments show that our method achieves better results than most state-of-the-art methods on six MMIF datasets. The source code is available at https://github.com/SunHui1216/SFMFusion.

---

### MedVoiceBias: A Controlled Study of Audio LLM Behavior in Clinical Decision-Making

Authors: Zhi Rui Tam, Yun-Nung Chen
Published: 2025-11-10
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2511.06592v1

As large language models transition from text-based interfaces to audio interactions in clinical settings, they might introduce new vulnerabilities through paralinguistic cues in audio. We evaluated these models on 170 clinical cases, each synthesized into speech from 36 distinct voice profiles spanning variations in age, gender, and emotion. Our findings reveal a severe modality bias: surgical recommendations for audio inputs varied by as much as 35% compared to identical text-based inputs, with one model providing 80% fewer recommendations. Further analysis uncovered age disparities of up to 12% between young and elderly voices, which persisted in most models despite chain-of-thought prompting. While explicit reasoning successfully eliminated gender bias, the impact of emotion was not detected due to poor recognition performance. These results demonstrate that audio LLMs are susceptible to making clinical decisions based on a patient's voice characteristics rather than medical evidence, a flaw that risks perpetuating healthcare disparities. We conclude that bias-aware architectures are essential and urgently needed before the clinical deployment of these models.

---

### Learning Biomolecular Motion: The Physics-Informed Machine Learning Paradigm

Authors: Aaryesh Deshpande
Published: 2025-11-10
Categories: q-bio.BM, cs.LG, physics.comp-ph, stat.ML
arXiv: https://arxiv.org/abs/2511.06585v1

The convergence of statistical learning and molecular physics is transforming our approach to modeling biomolecular systems. Physics-informed machine learning (PIML) offers a systematic framework that integrates data-driven inference with physical constraints, resulting in models that are accurate, mechanistic, generalizable, and able to extrapolate beyond observed domains. This review surveys recent advances in physics-informed neural networks and operator learning, differentiable molecular simulation, and hybrid physics-ML potentials, with emphasis on long-timescale kinetics, rare events, and free-energy estimation. We frame these approaches as solutions to the "biomolecular closure problem", recovering unresolved interactions beyond classical force fields while preserving thermodynamic consistency and mechanistic interpretability. We examine theoretical foundations, tools and frameworks, computational trade-offs, and unresolved issues, including model expressiveness and stability. We outline prospective research avenues at the intersection of machine learning, statistical physics, and computational chemistry, contending that future advancements will depend on mechanistic inductive biases, and integrated differentiable physical learning frameworks for biomolecular simulation and discovery.

---

### TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations

Authors: Jacob Si, Mike Qu, Michelle Lee, Marek Rei, Yingzhen Li
Published: 2025-11-10
Categories: cs.CL, cs.AI, cs.CV, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2511.06582v2

Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While effective for text-based documents, question answering on tabular documents often fails to generate plausible responses. Standard parsing techniques lose the two-dimensional structural semantics critical for cell interpretation. In this work, we present TabRAG, a parsing-based RAG framework designed to improve tabular document question answering via structured representations. Our framework consists of layout segmentation that decomposes the document inputs into a series of components, enabling fine-grained extraction. Subsequently, a vision language model parses and extracts the document tables into a hierarchically structured representation. In order to cater various table styles and formats, we integrate a self-generated in-context learning module that guides the table extraction process. Experimental results demonstrate that TabRAG outperforms existing popular parsing techniques across a broad suite of evaluation and ablation benchmarks. Code is available at: https://github.com/jacobyhsi/TabRAG.

---

### Evaluating Large Language Models on Quantum Mechanics: A Comparative Study Across Diverse Models and Tasks

Authors: S. K. Rithvik
Published: 2025-11-09
Categories: cs.AI, quant-ph
arXiv: https://arxiv.org/abs/2602.19006v1

We present a systematic evaluation of large language models on quantum mechanics problem-solving. Our study evaluates 15 models from five providers (OpenAI, Anthropic, Google, Alibaba, DeepSeek) spanning three capability tiers on 20 tasks covering derivations, creative problems, non-standard concepts, and numerical computation, comprising 900 baseline and 75 tool-augmented assessments. Results reveal clear tier stratification: flagship models achieve 81\% average accuracy, outperforming mid-tier (77\%) and fast models (67\%) by 4pp and 14pp respectively. Task difficulty patterns emerge distinctly: derivations show highest performance (92\% average, 100\% for flagship models), while numerical computation remains most challenging (42\%). Tool augmentation on numerical tasks yields task-dependent effects: modest overall improvement (+4.4pp) at 3x token cost masks dramatic heterogeneity ranging from +29pp gains to -16pp degradation. Reproducibility analysis across three runs quantifies 6.3pp average variance, with flagship models demonstrating exceptional stability (GPT-5 achieves zero variance) while specialized models require multi-run evaluation. This work contributes: (i) a benchmark for quantum mechanics with automatic verification, (ii) systematic evaluation quantifying tier-based performance hierarchies, (iii) empirical analysis of tool augmentation trade-offs, and (iv) reproducibility characterization. All tasks, verifiers, and results are publicly released.

---

### Evo* 2025 -- Late-Breaking Abstracts Volume

Authors: A. M. Mora, A. I. Esparcia-Alcázar, M. S. Cruz
Published: 2025-11-09
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2511.17543v1

Volume containing the Late-Breaking Abstracts submitted to the Evo* 2025 Conference, held in Trieste (Italy) from April 23rd to 25th. These extended abstracts showcase ongoing research and preliminary findings exploring the application of various Bioinspired Methods (primarily Evolutionary Computation) to a range of problems, many of which address real-world scenarios.

---

### Leibniz's Monadology as Foundation for the Artificial Age Score: A Formal Architecture for Al Memory Evaluation

Authors: Seyma Yaman Kayadibi
Published: 2025-11-09
Categories: cs.AI, cs.IT, cs.LO
arXiv: https://arxiv.org/abs/2511.17541v1

This paper develops a mathematically rigorous, philosophically grounded framework for evaluating artificial memory systems, rooted in the metaphysical structure of Leibniz's Monadology. Building on a previously formalized metric, the Artificial Age Score (AAS), the study maps twenty core propositions from the Monadology to an information-theoretic architecture. In this design, each monad functions as a modular unit defined by a truth score, a redundancy parameter, and a weighted contribution to a global memory penalty function. Smooth logarithmic transformations operationalize these quantities and yield interpretable, bounded metrics for memory aging, representational stability, and salience. Classical metaphysical notions of perception, apperception, and appetition are reformulated as entropy, gradient dynamics, and internal representation fidelity. Logical principles, including the laws of non-contradiction and sufficient reason, are encoded as regularization constraints guiding memory evolution. A central contribution is a set of first principles proofs establishing refinement invariance, structural decomposability, and monotonicity under scale transformation, aligned with the metaphysical structure of monads. The framework's formal organization is structured into six thematic bundles derived from Monadology, aligning each mathematical proof with its corresponding philosophical domain. Beyond evaluation, the framework offers a principled blueprint for building Al memory architectures that are modular, interpretable, and provably sound.

---

### EcoSpa: Efficient Transformer Training with Coupled Sparsity

Authors: Jinqi Xiao, Cheng Luo, Lingyi Huang, Cheng Yang, Yang Sui, Huy Phan, Xiao Zang, Yibiao Ying, Zhexiang Tang, Anima Anandkumar, Bo Yuan
Published: 2025-11-09
Categories: cs.LG, cs.AI, cs.PF
arXiv: https://arxiv.org/abs/2511.11641v1

Transformers have become the backbone of modern AI, yet their high computational demands pose critical system challenges. While sparse training offers efficiency gains, existing methods fail to preserve critical structural relationships between weight matrices that interact multiplicatively in attention and feed-forward layers. This oversight leads to performance degradation at high sparsity levels. We introduce EcoSpa, an efficient structured sparse training method that jointly evaluates and sparsifies coupled weight matrix pairs, preserving their interaction patterns through aligned row/column removal. EcoSpa introduces a new granularity for calibrating structural component importance and performs coupled estimation and sparsification across both pre-training and fine-tuning scenarios. Evaluations demonstrate substantial improvements: EcoSpa enables efficient training of LLaMA-1B with 50\% memory reduction and 21\% faster training, achieves $2.2\times$ model compression on GPT-2-Medium with $2.4$ lower perplexity, and delivers $1.6\times$ inference speedup. The approach uses standard PyTorch operations, requiring no custom hardware or kernels, making efficient transformer training accessible on commodity hardware.

---

### Exploring Parallelism in FPGA-Based Accelerators for Machine Learning Applications

Authors: Sed Centeno, Christopher Sprague, Arnab A Purkayastha, Ray Simar, Neeraj Magotra
Published: 2025-11-09
Categories: cs.DC, cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2511.11640v1

Speculative backpropagation has emerged as a promising technique to accelerate the training of neural networks by overlapping the forward and backward passes. Leveraging speculative weight updates when error gradients fall within a specific threshold reduces training time without substantially compromising accuracy. In this work, we implement speculative backpropagation on the MNIST dataset using OpenMP as the parallel programming platform. OpenMP's multi-threading capabilities enable simultaneous execution of forward and speculative backpropagation steps, significantly improving training speed. The application is planned for synthesis on a state-of-the-art FPGA to demonstrate its potential for hardware acceleration. Our CPU-based experimental results demonstrate that speculative backpropagation achieves a maximum speedup of 24% in execution time when using a threshold of 0.25, and accuracy remaining within 3-4% of the baseline across various epochs. Additionally, when comparing individual step execution time, speculative backpropagation yields a maximum speedup of 35% over the baseline, demonstrating the effectiveness of overlapping forward and backward passes.

---

### Image-based Morphological Characterization of Filamentous Biological Structures with Non-constant Curvature Shape Feature

Authors: Jie Fan, Francesco Visentin, Barbara Mazzolai, Emanuela Del Dottore
Published: 2025-11-09
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2511.11639v1

Tendrils coil their shape to anchor the plant to supporting structures, allowing vertical growth toward light. Although climbing plants have been studied for a long time, extracting information regarding the relationship between the temporal shape change, the event that triggers it, and the contact location is still challenging. To help build this relation, we propose an image-based method by which it is possible to analyze shape changes over time in tendrils when mechano-stimulated in different portions of their body. We employ a geometric approach using a 3D Piece-Wise Clothoid-based model to reconstruct the configuration taken by a tendril after mechanical rubbing. The reconstruction shows high robustness and reliability with an accuracy of R2 > 0.99. This method demonstrates distinct advantages over deep learning-based approaches, including reduced data requirements, lower computational costs, and interpretability. Our analysis reveals higher responsiveness in the apical segment of tendrils, which might correspond to higher sensitivity and tissue flexibility in that region of the organs. Our study provides a methodology for gaining new insights into plant biomechanics and offers a foundation for designing and developing novel intelligent robotic systems inspired by climbing plants.

---

### Grounded Visual Factualization: Factual Anchor-Based Finetuning for Enhancing MLLM Factual Consistency

Authors: Filippo Morbiato, Luca Romano, Alessandro Persona
Published: 2025-11-09
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.10671v1

Visual hallucination, where Multimodal Large Language Models fabricate details inconsistent with image content, critically undermines their reliability. Existing fine-tuning methods offer limited improvement, failing to deeply intervene in factual reasoning. This paper introduces Grounded Visual Factualization (GVF) Finetuning, a novel approach to systematically enhance MLLM visual factual consistency. GVF integrates explicit factual signals via three core mechanisms: Factual Anchor Data Augmentation, enriching training data with structured factual anchors and counter-factual prompts; Fact-Aware Instruction Tuning, embedding these cues into explicit instructions; and a Factual Consistency Loss function, specifically penalizing factual inaccuracies. Evaluated on LLaVA-1.5-13B, GVF Finetuning significantly outperforms standard fine-tuning on the VHTest benchmark for both Open-Ended Question (OEQ) and Yes/No Question (YNQ) formats. Crucially, GVF maintains or even slightly improves performance on general multimodal benchmarks like MME and POPE, demonstrating effective mitigation of visual hallucinations without compromising general understanding and reasoning abilities.

---

### Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment

Authors: Yan Gao, Yazheng Yang, Zhibin Lan, Yidong Chen, Min Zhang, Daimeng Wei, Derek F. Wong, Jinsong Su
Published: 2025-11-09
Categories: cs.CL, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2511.10670v2

Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing significant challenges due to the complexity of semantic modeling and the scarcity of CS data. Previous studies mainly rely on the models themselves to implicitly learn semantic representations and resort to costly manual annotations. To mitigate these limitations, we propose enhancing Large Language Models (LLMs) with a Mixture-of-Experts (MoE) speech projector composed of language expert groups, where each group specializes in the semantic space of a specific language for fine-grained speech feature modeling. A language-specific loss and an intra-group load balancing loss are jointly introduced to guide efficient token routing across and within expert groups. Furthermore, we introduce a multi-stage training paradigm that utilizes readily available automatic speech recognition (ASR) and monolingual ST data, facilitating speech-text alignment and improving translation performance. To bridge the data gap for smooth domain transfer, a transition loss is employed to improve adaptation to CS scenarios. Extensive experiments on widely used datasets demonstrate the effectiveness and generality of our approach, achieving average improvements of $0.86$ BLEU and $0.93$ COMET over SeamlessM4T, with maximum improvements of $1.49$ BLEU and $1.41$ COMET across different test sets.

---

### Forecasting Spoken Language Development in Children with Cochlear Implants Using Preimplantation MRI

Authors: Yanlin Wang, Di Yuan, Shani Dettman, Dawn Choo, Emily Shimeng Xu, Denise Thomas, Maura E Ryan, Patrick C M Wong, Nancy M Young
Published: 2025-11-09
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.10669v1

Cochlear implants (CI) significantly improve spoken language in children with severe-to-profound sensorineural hearing loss (SNHL), yet outcomes remain more variable than in children with normal hearing. This variability cannot be reliably predicted for individual children using age at implantation or residual hearing. This study aims to compare the accuracy of traditional machine learning (ML) to deep transfer learning (DTL) algorithms to predict post-CI spoken language development of children with bilateral SNHL using a binary classification model of high versus low language improvers. A total of 278 implanted children enrolled from three centers. The accuracy, sensitivity and specificity of prediction models based upon brain neuroanatomic features using traditional ML and DTL learning. DTL prediction models using bilinear attention-based fusion strategy achieved: accuracy of 92.39% (95% CI, 90.70%-94.07%), sensitivity of 91.22% (95% CI, 89.98%-92.47%), specificity of 93.56% (95% CI, 90.91%-96.21%), and area under the curve (AUC) of 0.977 (95% CI, 0.969-0.986). DTL outperformed traditional ML models in all outcome measures. DTL was significantly improved by direct capture of discriminative and task-specific information that are advantages of representation learning enabled by this approach over ML. The results support the feasibility of a single DTL prediction model for language prediction of children served by CI programs worldwide.

---

### Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising

Authors: Assaf Singer, Noam Rotstein, Amir Mann, Ron Kimmel, Or Litany
Published: 2025-11-09
Categories: cs.CV, cs.AI, cs.GR, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2511.08633v1

Diffusion-based video generation can create realistic videos, yet existing image- and text-based conditioning fails to offer precise motion control. Prior methods for motion-conditioned synthesis typically require model-specific fine-tuning, which is computationally expensive and restrictive. We introduce Time-to-Move (TTM), a training-free, plug-and-play framework for motion- and appearance-controlled video generation with image-to-video (I2V) diffusion models. Our key insight is to use crude reference animations obtained through user-friendly manipulations such as cut-and-drag or depth-based reprojection. Motivated by SDEdit's use of coarse layout cues for image editing, we treat the crude animations as coarse motion cues and adapt the mechanism to the video domain. We preserve appearance with image conditioning and introduce dual-clock denoising, a region-dependent strategy that enforces strong alignment in motion-specified regions while allowing flexibility elsewhere, balancing fidelity to user intent with natural dynamics. This lightweight modification of the sampling process incurs no additional training or runtime cost and is compatible with any backbone. Extensive experiments on object and camera motion benchmarks show that TTM matches or exceeds existing training-based baselines in realism and motion control. Beyond this, TTM introduces a unique capability: precise appearance control through pixel-level conditioning, exceeding the limits of text-only prompting. Visit our project page for video examples and code: https://time-to-move.github.io/.

---

### Hope, Aspirations, and the Impact of LLMs on Female Programming Learners in Afghanistan

Authors: Hamayoon Behmanush, Freshta Akhtari, Roghieh Nooripour, Ingmar Weber, Vikram Kamath Cannanure
Published: 2025-11-09
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2511.08630v1

Designing impactful educational technologies in contexts of socio-political instability requires a nuanced understanding of educational aspirations. Currently, scalable metrics for measuring aspirations are limited. This study adapts, translates, and evaluates Snyder's Hope Scale as a metric for measuring aspirations among 136 women learning programming online during a period of systemic educational restrictions in Afghanistan. The adapted scale demonstrated good reliability (Cronbach's α = 0.78) and participants rated it as understandable and relevant. While overall aspiration-related scores did not differ significantly by access to Large Language Models (LLMs), those with access reported marginally higher scores on the Avenues subscale (p = .056), suggesting broader perceived pathways to achieving educational aspirations. These findings support the use of the adapted scale as a metric for aspirations in contexts of socio-political instability. More broadly, the adapted scale can be used to evaluate the impact of aspiration-driven design of educational technologies.

---

### Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network

Authors: Xuan Yu, Tianyang Xu
Published: 2025-11-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.08628v3

Grassmannian manifold offers a powerful carrier for geometric representation learning by modelling high-dimensional data as low-dimensional subspaces. However, existing approaches predominantly rely on static single-subspace representations, neglecting the dynamic interplay between multiple subspaces critical for capturing complex geometric structures. To address this limitation, we propose a topology-driven multi-subspace fusion framework that enables adaptive subspace collaboration on the Grassmannian. Our solution introduces two key innovations: (1) Inspired by the Kolmogorov-Arnold representation theorem, an adaptive multi-subspace modelling mechanism is proposed that dynamically selects and weights task-relevant subspaces via topological convergence analysis, and (2) a multi-subspace interaction block that fuses heterogeneous geometric representations through Fréchet mean optimisation on the manifold. Theoretically, we establish the convergence guarantees of adaptive subspaces under a projection metric topology, ensuring stable gradient-based optimisation. Practically, we integrate Riemannian batch normalisation and mutual information regularisation to enhance discriminability and robustness. Extensive experiments on 3D action recognition (HDM05, FPHA), EEG classification (MAMEM-SSVEPII), and graph tasks demonstrate state-of-the-art performance. Our work not only advances geometric deep learning but also successfully adapts the proven multi-channel interaction philosophy of Euclidean networks to non-Euclidean domains, achieving superior discriminability and interpretability.

---

### SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images

Authors: Shuhang Chen, Hangjie Yuan, Pengwei Liu, Hanxue Gu, Tao Feng, Dong Ni
Published: 2025-11-09
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.08626v1

The Segment Anything Model (SAM) has demonstrated significant potential in medical image segmentation. Yet, its performance is limited when only a small amount of labeled data is available, while there is abundant valuable yet often overlooked hierarchical information in medical data. To address this limitation, we draw inspiration from self-supervised learning and propose SAMora, an innovative framework that captures hierarchical medical knowledge by applying complementary self-supervised learning objectives at the image, patch, and pixel levels. To fully exploit the complementarity of hierarchical knowledge within LoRAs, we introduce HL-Attn, a hierarchical fusion module that integrates multi-scale features while maintaining their distinct characteristics. SAMora is compatible with various SAM variants, including SAM2, SAMed, and H-SAM. Experimental results on the Synapse, LA, and PROMISE12 datasets demonstrate that SAMora outperforms existing SAM variants. It achieves state-of-the-art performance in both few-shot and fully supervised settings while reducing fine-tuning epochs by 90%. The code is available at https://github.com/ShChen233/SAMora.

---

### Cross-Field Interface-Aware Neural Operators for Multiphase Flow Simulation

Authors: Zhenzhong Wang, Xin Zhang, Jun Liao, Min Jiang
Published: 2025-11-09
Categories: physics.flu-dyn, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08625v2

Multiphase flow simulation is critical in science and engineering but incurs high computational costs due to complex field discontinuities and the need for high-resolution numerical meshes. While Neural Operators (NOs) offer an efficient alternative for solving Partial Differential Equations (PDEs), they struggle with two core challenges unique to multiphase systems: spectral bias caused by spatial heterogeneity at phase interfaces, and the persistent scarcity of expensive, high-resolution field data. This work introduces the Interface Information Aware Neural Operator (IANO), a novel architecture that mitigates these issues by leveraging readily obtainable interface data (e.g., topology and position). Interface data inherently contains the high-frequency features not only necessary to complement the physical field data, but also help with spectral bias. IANO incorporates an interface-aware function encoding mechanism to capture dynamic coupling, and a geometry-aware positional encoding method to enhance spatial fidelity for pointwise super-resolution. Empirical results across multiple multiphase flow cases demonstrate that IANO achieves significant accuracy improvements (up to $\sim$10\%) over existing NO baselines. Furthermore, IANO exhibits superior generalization capabilities in low-data and noisy settings, confirming its utility for practical, data-efficient $\text{AI}$-based multiphase flow simulations.

---

### When Are Learning Biases Equivalent? A Unifying Framework for Fairness, Robustness, and Distribution Shift

Authors: Sushant Mehta
Published: 2025-11-09
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.07485v1

Machine learning systems exhibit diverse failure modes: unfairness toward protected groups, brittleness to spurious correlations, poor performance on minority sub-populations, which are typically studied in isolation by distinct research communities. We propose a unifying theoretical framework that characterizes when different bias mechanisms produce quantitatively equivalent effects on model performance. By formalizing biases as violations of conditional independence through information-theoretic measures, we prove formal equivalence conditions relating spurious correlations, subpopulation shift, class imbalance, and fairness violations. Our theory predicts that a spurious correlation of strength $α$ produces equivalent worst-group accuracy degradation as a sub-population imbalance ratio $r \approx (1+α)/(1-α)$ under feature overlap assumptions. Empirical validation in six datasets and three architectures confirms that predicted equivalences hold within the accuracy of the worst group 3\%, enabling the principled transfer of debiasing methods across problem domains. This work bridges the literature on fairness, robustness, and distribution shifts under a common perspective.

---

### Counterfactual Forecasting of Human Behavior using Generative AI and Causal Graphs

Authors: Dharmateja Priyadarshi Uddandarao, Ravi Kiran Vadlamani
Published: 2025-11-09
Categories: cs.LG, cs.CE, stat.ME
arXiv: https://arxiv.org/abs/2511.07484v1

This study presents a novel framework for counterfactual user behavior forecasting that combines structural causal models with transformer-based generative artificial intelligence. To model fictitious situations, the method creates causal graphs that map the connections between user interactions, adoption metrics, and product features. The framework generates realistic behavioral trajectories under counterfactual conditions by using generative models that are conditioned on causal variables. Tested on datasets from web interactions, mobile applications, and e-commerce, the methodology outperforms conventional forecasting and uplift modeling techniques. Product teams can effectively simulate and assess possible interventions prior to deployment thanks to the framework improved interpretability through causal path visualization.

---

### Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning

Authors: Qianxi He, Qingyu Ren, Shanzhe Lei, Xuhong Wang, Yingchun Wang
Published: 2025-11-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07483v1

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However, numerous technical reports indicate that purely rule-based reward RL frequently results in poor-quality reasoning chains or inconsistencies between reasoning processes and final answers, particularly when the base model is of smaller scale. During the RL exploration process, models might employ low-quality reasoning chains due to the lack of knowledge, occasionally producing correct answers randomly and receiving rewards based on established rule-based judges. This constrains the potential for resource-limited organizations to conduct direct reinforcement learning training on smaller-scale models. We propose a novel confidence-based reward model tailored for enhancing STEM reasoning capabilities. Unlike conventional approaches, our model penalizes not only incorrect answers but also low-confidence correct responses, thereby promoting more robust and logically consistent reasoning. We validate the effectiveness of our approach through static evaluations, Best-of-N inference tests, and PPO-based RL training. Our method outperforms several state-of-the-art open-source reward models across diverse STEM benchmarks. We release our codes and model in https://github.com/qianxiHe147/C2RM.

---

### Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits

Authors: Dev Patel, Gabrielle Gervacio, Diekola Raimi, Kevin Zhu, Ryan Lagasse, Gabriel Grand, Ashwinee Panda, Maheep Chaudhary
Published: 2025-11-09
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.07482v1

Large Language Models require substantial computational resources for inference, posing deployment challenges. While dynamic pruning offers superior efficiency over static methods through adaptive circuit selection, it exacerbates alignment degradation by retaining only input-dependent safety-critical circuit preservation across diverse inputs. As a result, addressing these heightened alignment vulnerabilities remains critical. We introduce Alignment-Aware Probe Pruning (AAPP), a dynamic structured pruning method that adaptively preserves alignment-relevant circuits during inference, building upon Probe Pruning. Experiments on LLaMA 2-7B, Qwen2.5-14B-Instruct, and Gemma-3-12B-IT show AAPP improves refusal rates by 50\% at matched compute, enabling efficient yet safety-preserving LLM deployment.

---

### Comparing Reconstruction Attacks on Pretrained Versus Full Fine-tuned Large Language Model Embeddings on Homo Sapiens Splice Sites Genomic Data

Authors: Reem Al-Saidi, Erman Ayday, Ziad Kobti
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07481v1

This study investigates embedding reconstruction attacks in large language models (LLMs) applied to genomic sequences, with a specific focus on how fine-tuning affects vulnerability to these attacks. Building upon Pan et al.'s seminal work demonstrating that embeddings from pretrained language models can leak sensitive information, we conduct a comprehensive analysis using the HS3D genomic dataset to determine whether task-specific optimization strengthens or weakens privacy protections. Our research extends Pan et al.'s work in three significant dimensions. First, we apply their reconstruction attack pipeline to pretrained and fine-tuned model embeddings, addressing a critical gap in their methodology that did not specify embedding types. Second, we implement specialized tokenization mechanisms tailored specifically for DNA sequences, enhancing the model's ability to process genomic data, as these models are pretrained on natural language and not DNA. Third, we perform a detailed comparative analysis examining position-specific, nucleotide-type, and privacy changes between pretrained and fine-tuned embeddings. We assess embeddings vulnerabilities across different types and dimensions, providing deeper insights into how task adaptation shifts privacy risks throughout genomic sequences. Our findings show a clear distinction in reconstruction vulnerability between pretrained and fine-tuned embeddings. Notably, fine-tuning strengthens resistance to reconstruction attacks in multiple architectures -- XLNet (+19.8\%), GPT-2 (+9.8\%), and BERT (+7.8\%) -- pointing to task-specific optimization as a potential privacy enhancement mechanism. These results highlight the need for advanced protective mechanisms for language models processing sensitive genomic data, while highlighting fine-tuning as a potential privacy-enhancing technique worth further exploration.

---

### KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs

Authors: Shuyuan Liu, Jiawei Chen, Xiao Yang, Hang Su, Zhaoxia Yin
Published: 2025-11-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.07480v1

With the widespread application of large language models (LLMs) in various fields, the security challenges they face have become increasingly prominent, especially the issue of jailbreak. These attacks induce the model to generate erroneous or uncontrolled outputs through crafted inputs, threatening the generality and security of the model. Although existing defense methods have shown some effectiveness, they often struggle to strike a balance between model generality and security. Excessive defense may limit the normal use of the model, while insufficient defense may lead to security vulnerabilities. In response to this problem, we propose a Knowledge Graph Defense Framework (KG-DF). Specifically, because of its structured knowledge representation and semantic association capabilities, Knowledge Graph(KG) can be searched by associating input content with safe knowledge in the knowledge base, thus identifying potentially harmful intentions and providing safe reasoning paths. However, traditional KG methods encounter significant challenges in keyword extraction, particularly when confronted with diverse and evolving attack strategies. To address this issue, we introduce an extensible semantic parsing module, whose core task is to transform the input query into a set of structured and secure concept representations, thereby enhancing the relevance of the matching process. Experimental results show that our framework enhances defense performance against various jailbreak attack methods, while also improving the response quality of the LLM in general QA scenarios by incorporating domain-general knowledge.

---

### Modulo Video Recovery via Selective Spatiotemporal Vision Transformer

Authors: Tianyu Geng, Feng Ji, Wee Peng Tay
Published: 2025-11-09
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2511.07479v1

Conventional image sensors have limited dynamic range, causing saturation in high-dynamic-range (HDR) scenes. Modulo cameras address this by folding incident irradiance into a bounded range, yet require specialized unwrapping algorithms to reconstruct the underlying signal. Unlike HDR recovery, which extends dynamic range from conventional sampling, modulo recovery restores actual values from folded samples. Despite being introduced over a decade ago, progress in modulo image recovery has been slow, especially in the use of modern deep learning techniques. In this work, we demonstrate that standard HDR methods are unsuitable for modulo recovery. Transformers, however, can capture global dependencies and spatial-temporal relationships crucial for resolving folded video frames. Still, adapting existing Transformer architectures for modulo recovery demands novel techniques. To this end, we present Selective Spatiotemporal Vision Transformer (SSViT), the first deep learning framework for modulo video reconstruction. SSViT employs a token selection strategy to improve efficiency and concentrate on the most critical regions. Experiments confirm that SSViT produces high-quality reconstructions from 8-bit folded videos and achieves state-of-the-art performance in modulo video recovery.

---

### CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning

Authors: Jun Wang, Yevgeniy Vorobeychik, Yiannis Kantaros
Published: 2025-11-09
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.06575v1

Large Language Models (LLMs) have recently emerged as planners for language-instructed agents, generating sequences of actions to accomplish natural language tasks. However, their reliability remains a challenge, especially in long-horizon tasks, since they often produce overconfident yet wrong outputs. Conformal Prediction (CP) has been leveraged to address this issue by wrapping LLM outputs into prediction sets that contain the correct action with a user-defined confidence. When the prediction set is a singleton, the planner executes that action; otherwise, it requests help from a user. This has led to LLM-based planners that can ensure plan correctness with a user-defined probability. However, as LLMs are trained in an uncertainty-agnostic manner, without awareness of prediction sets, they tend to produce unnecessarily large sets, particularly at higher confidence levels, resulting in frequent human interventions limiting autonomous deployment. To address this, we introduce CoFineLLM (Conformal Finetuning for LLMs), the first CP-aware finetuning framework for LLM-based planners that explicitly reduces prediction-set size and, in turn, the need for user interventions. We evaluate our approach on multiple language-instructed robot planning problems and show consistent improvements over uncertainty-aware and uncertainty-agnostic finetuning baselines in terms of prediction-set size, and help rates. Finally, we demonstrate robustness of our method to out-of-distribution scenarios in hardware experiments.

---

### SteganoSNN: SNN-Based Audio-in-Image Steganography with Encryption

Authors: Biswajit Kumar Sahoo, Pedro Machado, Isibor Kennedy Ihianle, Andreas Oikonomou, Srinivas Boppu
Published: 2025-11-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.06573v1

Secure data hiding remains a fundamental challenge in digital communication, requiring a careful balance between computational efficiency and perceptual transparency. The balance between security and performance is increasingly fragile with the emergence of generative AI systems capable of autonomously generating and optimising sophisticated cryptanalysis and steganalysis algorithms, thereby accelerating the exposure of vulnerabilities in conventional data-hiding schemes. This work introduces SteganoSNN, a neuromorphic steganographic framework that exploits spiking neural networks (SNNs) to achieve secure, low-power, and high-capacity multimedia data hiding. Digitised audio samples are converted into spike trains using leaky integrate-and-fire (LIF) neurons, encrypted via a modulo-based mapping scheme, and embedded into the least significant bits of RGBA image channels using a dithering mechanism to minimise perceptual distortion. Implemented in Python using NEST and realised on a PYNQ-Z2 FPGA, SteganoSNN attains real-time operation with an embedding capacity of 8 bits per pixel. Experimental evaluations on the DIV2K 2017 dataset demonstrate image fidelity between 40.4 dB and 41.35 dB in PSNR and SSIM values consistently above 0.97, surpassing SteganoGAN in computational efficiency and robustness. SteganoSNN establishes a foundation for neuromorphic steganography, enabling secure, energy-efficient communication for Edge-AI, IoT, and biomedical applications.

---

### Rep2Text: Decoding Full Text from a Single LLM Token Representation

Authors: Haiyan Zhao, Zirui He, Yiming Tang, Fan Yang, Ali Payani, Dianbo Liu, Mengnan Du
Published: 2025-11-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.06571v3

Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their internal mechanisms remain largely opaque. In this work, we investigate a fundamental question: to what extent can the original input text be recovered from a single last-token representation in an LLM? To this end, we propose Rep2Text, a novel framework for decoding text from last-token representations. Rep2Text employs a trainable adapter that maps a target model's last-token representation into the token embedding space of a decoding language model, which then autoregressively reconstructs the input text. Experiments across various model combinations (Llama-3.1-8B, Gemma-7B, Mistral-7B-v0.1, Llama-3.2-3B, etc.) show that, on average, roughly half of the tokens in 16-token sequences can be recovered from this compressed representation while preserving strong semantic coherence. Further analysis reveals a clear information bottleneck effect: as sequence length increases, token-level recovery declines, while semantic information remains relatively well preserved. We also find that scaling effects are less pronounced in inversion tasks. Finally, our framework demonstrates robust generalization to out-of-distribution clinical data.

---

### Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity

Authors: João Mattos, Debolina Halder Lina, Arlei Silva
Published: 2025-11-09
Categories: cs.LG, cs.AI, cs.SI, stat.ML
arXiv: https://arxiv.org/abs/2511.06568v2

Link prediction is a fundamental task in graph machine learning with applications, ranging from social recommendation to knowledge graph completion. Fairness in this setting is critical, as biased predictions can exacerbate societal inequalities. Prior work adopts a dyadic definition of fairness, enforcing fairness through demographic parity between intra-group and inter-group link predictions. However, we show that this dyadic framing can obscure underlying disparities across subgroups, allowing systemic biases to go undetected. Moreover, we argue that demographic parity does not meet desired properties for fairness assessment in ranking-based tasks such as link prediction. We formalize the limitations of existing fairness evaluations and propose a framework that enables a more expressive assessment. Additionally, we propose a lightweight post-processing method combined with decoupled link predictors that effectively mitigates bias and achieves state-of-the-art fairness-utility trade-offs.

---

### FPGA or GPU? Analyzing comparative research for application-specific guidance

Authors: Arnab A Purkayastha, Jay Tharwani, Shobhit Aggarwal
Published: 2025-11-09
Categories: cs.AR, cs.CL, cs.DC, cs.PL
arXiv: https://arxiv.org/abs/2511.06565v1

The growing complexity of computational workloads has amplified the need for efficient and specialized hardware accelerators. Field Programmable Gate Arrays (FPGAs) and Graphics Processing Units (GPUs) have emerged as prominent solutions, each excelling in specific domains. Although there is substantial research comparing FPGAs and GPUs, most of the work focuses primarily on performance metrics, offering limited insight into the specific types of applications that each accelerator benefits the most. This paper aims to bridge this gap by synthesizing insights from various research articles to guide users in selecting the appropriate accelerator for domain-specific applications. By categorizing the reviewed studies and analyzing key performance metrics, this work highlights the strengths, limitations, and ideal use cases for FPGAs and GPUs. The findings offer actionable recommendations, helping researchers and practitioners navigate trade-offs in performance, energy efficiency, and programmability.

---

### Practical Policy Distillation for Reinforcement Learning in Radio Access Networks

Authors: Sara Khosravi, Burak Demirel, Linghui Zhou, Javier Rasines, Pablo Soldati
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06563v2

Adopting artificial intelligence (AI) in radio access networks (RANs) presents several challenges, including limited availability of link-level measurements (e.g., CQI reports), stringent real-time processing constraints (e.g., sub-1 ms per TTI), and network heterogeneity (different spectrum bands, cell types, and vendor equipment). A critical yet often overlooked barrier lies in the computational and memory limitations of RAN baseband hardware, particularly in legacy 4th Generation (4G) systems, which typically lack on-chip neural accelerators. As a result, only lightweight AI models (under 1 Mb and sub-100~μs inference time) can be effectively deployed, limiting both their performance and applicability. However, achieving strong generalization across diverse network conditions often requires large-scale models with substantial resource demands. To address this trade-off, this paper investigates policy distillation in the context of a reinforcement learning-based link adaptation task. We explore two strategies: single-policy distillation, where a scenario-agnostic teacher model is compressed into one generalized student model; and multi-policy distillation, where multiple scenario-specific teachers are consolidated into a single generalist student. Experimental evaluations in a high-fidelity, 5th Generation (5G)-compliant simulator demonstrate that both strategies produce compact student models that preserve the teachers' generalization capabilities while complying with the computational and memory limitations of existing RAN hardware.

---

### LLM For Loop Invariant Generation and Fixing: How Far Are We?

Authors: Mostafijur Rahman Akhond, Saikat Chakraborty, Gias Uddin
Published: 2025-11-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.06552v1

A loop invariant is a property of a loop that remains true before and after each execution of the loop. The identification of loop invariants is a critical step to support automated program safety assessment. Recent advancements in Large Language Models (LLMs) have demonstrated potential in diverse software engineering (SE) and formal verification tasks. However, we are not aware of the performance of LLMs to infer loop invariants. We report an empirical study of both open-source and closed-source LLMs of varying sizes to assess their proficiency in inferring inductive loop invariants for programs and in fixing incorrect invariants. Our findings reveal that while LLMs exhibit some utility in inferring and repairing loop invariants, their performance is substantially enhanced when supplemented with auxiliary information such as domain knowledge and illustrative examples. LLMs achieve a maximum success rate of 78\% in generating, but are limited to 16\% in repairing the invariant.

---

### Video Dataset for Surgical Phase, Keypoint, and Instrument Recognition in Laparoscopic Surgery (PhaKIR)

Authors: Tobias Rueckert, Raphaela Maerkl, David Rauber, Leonard Klausmann, Max Gutbrod, Daniel Rueckert, Hubertus Feussner, Dirk Wilhelm, Christoph Palm
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06549v1

Robotic- and computer-assisted minimally invasive surgery (RAMIS) is increasingly relying on computer vision methods for reliable instrument recognition and surgical workflow understanding. Developing such systems often requires large, well-annotated datasets, but existing resources often address isolated tasks, neglect temporal dependencies, or lack multi-center variability. We present the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) dataset, comprising eight complete laparoscopic cholecystectomy videos recorded at three medical centers. The dataset provides frame-level annotations for three interconnected tasks: surgical phase recognition (485,875 frames), instrument keypoint estimation (19,435 frames), and instrument instance segmentation (19,435 frames). PhaKIR is, to our knowledge, the first multi-institutional dataset to jointly provide phase labels, instrument pose information, and pixel-accurate instrument segmentations, while also enabling the exploitation of temporal context since full surgical procedure sequences are available. It served as the basis for the PhaKIR Challenge as part of the Endoscopic Vision (EndoVis) Challenge at MICCAI 2024 to benchmark methods in surgical scene understanding, thereby further validating the dataset's quality and relevance. The dataset is publicly available upon request via the Zenodo platform.

---

### Bayesian Uncertainty Quantification with Anchored Ensembles for Robust EV Power Consumption Prediction

Authors: Ghazal Farhani, Taufiq Rahman, Kieran Humphries
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06538v1

Accurate EV power estimation underpins range prediction and energy management, yet practitioners need both point accuracy and trustworthy uncertainty. We propose an anchored-ensemble Long Short-Term Memory (LSTM) with a Student-t likelihood that jointly captures epistemic (model) and aleatoric (data) uncertainty. Anchoring imposes a Gaussian weight prior (MAP training), yielding posterior-like diversity without test-time sampling, while the t-head provides heavy-tailed robustness and closed-form prediction intervals. Using vehicle-kinematic time series (e.g., speed, motor RPM), our model attains strong accuracy: RMSE 3.36 +/- 1.10, MAE 2.21 +/- 0.89, R-squared = 0.93 +/- 0.02, explained variance 0.93 +/- 0.02, and delivers well-calibrated uncertainty bands with near-nominal coverage. Against competitive baselines (Student-t MC dropout; quantile regression with/without anchoring), our method matches or improves log-scores while producing sharper intervals at the same coverage. Crucially for real-time deployment, inference is a single deterministic pass per ensemble member (or a weight-averaged collapse), eliminating Monte Carlo latency. The result is a compact, theoretically grounded estimator that couples accuracy, calibration, and systems efficiency, enabling reliable range estimation and decision-making for production EV energy management.

---

### Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languages

Authors: Oluwadara Kalejaiye, Luel Hagos Beyene, David Ifeoluwa Adelani, Mmekut-Mfon Gabriel Edet, Aniefon Daniel Akpan, Eno-Abasi Urua, Anietie Andy
Published: 2025-11-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.06531v1

Nigeria is the most populous country in Africa with a population of more than 200 million people. More than 500 languages are spoken in Nigeria and it is one of the most linguistically diverse countries in the world. Despite this, natural language processing (NLP) research has mostly focused on the following four languages: Hausa, Igbo, Nigerian-Pidgin, and Yoruba (i.e <1% of the languages spoken in Nigeria). This is in part due to the unavailability of textual data in these languages to train and apply NLP algorithms. In this work, we introduce ibom -- a dataset for machine translation and topic classification in four Coastal Nigerian languages from the Akwa Ibom State region: Anaang, Efik, Ibibio, and Oro. These languages are not represented in Google Translate or in major benchmarks such as Flores-200 or SIB-200. We focus on extending Flores-200 benchmark to these languages, and further align the translated texts with topic labels based on SIB-200 classification dataset. Our evaluation shows that current LLMs perform poorly on machine translation for these languages in both zero-and-few shot settings. However, we find the few-shot samples to steadily improve topic classification with more shots.

---

### Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement

Authors: Xiaonan Luo, Yue Huang, Ping He, Xiangliang Zhang
Published: 2025-11-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.06530v1

High-quality Question-Answer (QA) datasets are foundational for reliable Large Language Model (LLM) evaluation, yet even expert-crafted datasets exhibit persistent gaps in domain coverage, misaligned difficulty distributions, and factual inconsistencies. The recent surge in generative model-powered datasets has compounded these quality challenges. In this work, we introduce RefineLab, the first LLM-driven framework that automatically refines raw QA textual data into high-quality datasets under a controllable token-budget constraint. RefineLab takes a set of target quality attributes (such as coverage and difficulty balance) as refinement objectives, and performs selective edits within a predefined token budget to ensure practicality and efficiency. In essence, RefineLab addresses a constrained optimization problem: improving the quality of QA samples as much as possible while respecting resource limitations. With a set of available refinement operations (e.g., rephrasing, distractor replacement), RefineLab takes as input the original dataset, a specified set of target quality dimensions, and a token budget, and determines which refinement operations should be applied to each QA sample. This process is guided by an assignment module that selects optimal refinement strategies to maximize overall dataset quality while adhering to the budget constraint. Experiments demonstrate that RefineLab consistently narrows divergence from expert datasets across coverage, difficulty alignment, factual fidelity, and distractor quality. RefineLab pioneers a scalable, customizable path to reproducible dataset design, with broad implications for LLM evaluation.

---

### TriShGAN: Enhancing Sparsity and Robustness in Multivariate Time Series Counterfactuals Explanation

Authors: Hongnan Ma, Yiwei Shi, Guanxiong Sun, Mengyue Yang, Weiru Liu
Published: 2025-11-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.06529v1

In decision-making processes, stakeholders often rely on counterfactual explanations, which provide suggestions about what should be changed in the queried instance to alter the outcome of an AI system. However, generating these explanations for multivariate time series presents challenges due to their complex, multi-dimensional nature. Traditional Nearest Unlike Neighbor-based methods typically substitute subsequences in a queried time series with influential subsequences from an NUN, which is not always realistic in real-world scenarios due to the rigid direct substitution. Counterfactual with Residual Generative Adversarial Networks-based methods aim to address this by learning from the distribution of observed data to generate synthetic counterfactual explanations. However, these methods primarily focus on minimizing the cost from the queried time series to the counterfactual explanations and often neglect the importance of distancing the counterfactual explanation from the decision boundary. This oversight can result in explanations that no longer qualify as counterfactual if minor changes occur within the model. To generate a more robust counterfactual explanation, we introduce TriShGAN, under the CounteRGAN framework enhanced by the incorporation of triplet loss. This unsupervised learning approach uses distance metric learning to encourage the counterfactual explanations not only to remain close to the queried time series but also to capture the feature distribution of the instance with the desired outcome, thereby achieving a better balance between minimal cost and robustness. Additionally, we integrate a Shapelet Extractor that strategically selects the most discriminative parts of the high-dimensional queried time series to enhance the sparsity of counterfactual explanation and efficiency of the training process.

---

### Efficient Approximation of Volterra Series for High-Dimensional Systems

Authors: Navin Khoshnan, Claudia K Petritsch, Bryce-Allen Bagley
Published: 2025-11-09
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.06527v1

The identification of high-dimensional nonlinear dynamical systems via the Volterra series has significant potential, but has been severely hindered by the curse of dimensionality. Tensor Network (TN) methods such as the Modified Alternating Linear Scheme (MVMALS) have been a breakthrough for the field, offering a tractable approach by exploiting the low-rank structure in Volterra kernels. However, these techniques still encounter prohibitive computational and memory bottlenecks due to high-order polynomial scaling with respect to input dimension. To overcome this barrier, we introduce the Tensor Head Averaging (THA) algorithm, which significantly reduces complexity by constructing an ensemble of localized MVMALS models trained on small subsets of the input space. In this paper, we present a theoretical foundation for the THA algorithm. We establish observable, finite-sample bounds on the error between the THA ensemble and a full MVMALS model, and we derive an exact decomposition of the squared error. This decomposition is used to analyze the manner in which subset models implicitly compensate for omitted dynamics. We quantify this effect, and prove that correlation between the included and omitted dynamics creates an optimization incentive which drives THA's performance toward accuracy superior to a simple truncation of a full MVMALS model. THA thus offers a scalable and theoretically grounded approach for identifying previously intractable high-dimensional systems.

---

### FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis

Authors: Jan Ondras, Marek Šuppa
Published: 2025-11-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.06522v1

Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benchmark evaluating fractal program synthesis from images. Fractals provide ideal test cases: Iterated Function Systems with only a few contraction maps generate complex self-similar patterns through simple recursive rules, requiring models to bridge visual perception with mathematical abstraction. We evaluate four leading MLLMs -- GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Flash, and Qwen 2.5-VL -- on 12 canonical fractals. Models must generate executable Python code reproducing the fractal, enabling objective evaluation. Results reveal a striking disconnect: 76% generate syntactically valid code but only 4% capture mathematical structure. Success varies systematically -- models handle geometric transformations (Koch curves: 17-21%) but fail at branching recursion (trees: <2%), revealing fundamental gaps in mathematical abstraction. FractalBench provides a contamination-resistant diagnostic for visual-mathematical reasoning and is available at https://github.com/NaiveNeuron/FractalBench

---

### On the Analogy between Human Brain and LLMs: Spotting Key Neurons in Grammar Perception

Authors: Sanaz Saki Norouzi, Mohammad Masjedi, Pascal Hitzler
Published: 2025-11-09
Categories: q-bio.NC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.06519v1

Artificial Neural Networks, the building blocks of AI, were inspired by the human brain's network of neurons. Over the years, these networks have evolved to replicate the complex capabilities of the brain, allowing them to handle tasks such as image and language processing. In the realm of Large Language Models, there has been a keen interest in making the language learning process more akin to that of humans. While neuroscientific research has shown that different grammatical categories are processed by different neurons in the brain, we show that LLMs operate in a similar way. Utilizing Llama 3, we identify the most important neurons associated with the prediction of words belonging to different part-of-speech tags. Using the achieved knowledge, we train a classifier on a dataset, which shows that the activation patterns of these key neurons can reliably predict part-of-speech tags on fresh data. The results suggest the presence of a subspace in LLMs focused on capturing part-of-speech tag concepts, resembling patterns observed in lesion studies of the brain in neuroscience.

---

### You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

Authors: Amit LeVi, Raz Lapid, Rom Himelstein, Chaim Baskin, Ravid Shwartz Ziv, Avi Mendelson
Published: 2025-11-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.06516v4

Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste bits on layers that are less relevant to the task signal while over-compressing layers that are critical for downstream behavior. We propose Task-Aware Quantization (TAQ), a training-free, weight-only mixed-precision PTQ framework that uses a small set of unlabeled task calibration prompts to allocate higher precision to task-relevant transformer layers under a fixed bit budget. TAQ estimates layer importance from hidden representations and output sensitivity, and we instantiate it with three scoring rules: TAQ-IS, based on activation information and stability; TAQ-KL, based on output-distribution sensitivity under a quantization-noise proxy; and TAQ-O, a label-informed oracle diagnostic for analyzing layer sensitivity. Across several benchmarks, TAQ outperforms task-agnostic baselines such in most settings, with especially strong gains in the accuracy--memory ratio. We further validate that these gains translate to real deployment behavior through hardware throughput and latency measurements, and analyze calibration robustness and residual-stream error propagation. Overall, TAQ turns mixed-precision PTQ from a model-centric compression step into a task-conditioned precision-allocation problem. A reference implementation is available at \href{https://anonymous.4open.science/r/TAQ-9217/README.md}{\includegraphics(height=1em){imgs/github-mark.png}}.

---

### EASE: Practical and Efficient Safety Alignment for Small Language Models

Authors: Haonan Shi, Guoli Wang, Tu Ouyang, An Wang
Published: 2025-11-09
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.06512v1

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While deliberative safety reasoning alignment offers deeper alignment for defending against sophisticated attacks, effectively implanting such reasoning capability in SLMs with limited capabilities remains an open challenge. Moreover, safety reasoning incurs significant computational overhead as models apply reasoning to nearly all queries, making it impractical for resource-constrained edge deployment scenarios that demand rapid responses. We propose EASE, a novel framework that enables practical and Efficient safety Alignment for Small languagE models. Our approach first identifies the optimal safety reasoning teacher that can effectively distill safety reasoning capabilities to SLMs. We then align models to selectively activate safety reasoning for dangerous adversarial jailbreak queries while providing direct responses to straightforward malicious queries and general helpful tasks. This selective mechanism enables small models to maintain robust safety guarantees against sophisticated attacks while preserving computational efficiency for benign interactions. Experimental results demonstrate that EASE reduces jailbreak attack success rates by up to 17% compared to shallow alignment methods while reducing inference overhead by up to 90% compared to deliberative safety reasoning alignment, making it practical for SLMs real-world edge deployments.

---

### SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports

Authors: Haotian Xia, Haonan Ge, Junbo Zou, Hyun Woo Choi, Xuebin Zhang, Danny Suradja, Botao Rui, Ethan Tran, Wendy Jin, Zhen Ye, Xiyang Lin, Christopher Lai et al.
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06499v3

Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models. To succeed, models must master three critical capabilities: perceiving nuanced visual details, applying abstract sport rule knowledge, and grounding that knowledge in specific visual evidence. Current sports benchmarks either cover single sports or lack the detailed reasoning chains and precise visual grounding needed to robustly evaluate these core capabilities in a multi-sport context. To address this gap, we introduce SportR, the first multi-sports large-scale benchmark designed to train and evaluate MLLMs on the fundamental reasoning required for sports intelligence. Our benchmark provides a dataset of 4,789 images and 2,052 videos. To enable granular evaluation, we structure our benchmark around a progressive hierarchy of question-answer pairs designed to probe reasoning at increasing depths - from simple infraction identification to complex penalty prediction. For the most advanced tasks requiring multi-step reasoning, such as determining penalties or explaining tactics, we provide 6,841 high-quality, human-authored Chain of Thought annotations. In addition, our benchmark incorporates both image and video modalities and provides manual bounding box annotations to test visual grounding in the image part directly. Extensive experiments demonstrate the profound difficulty of our benchmark. State-of-the-art baseline models perform poorly on our most challenging tasks. While training on our data via Supervised Fine-Tuning and Reinforcement Learning improves these scores, they remain relatively low, highlighting a significant gap in current model capabilities. SportR presents a new challenge for the community, providing a critical resource to drive future research in multimodal sports reasoning.

---

### Rethinking what Matters: Effective and Robust Multilingual Realignment for Low-Resource Languages

Authors: Quang Phuoc Nguyen, David Anugraha, Felix Gaschi, Jun Bin Cheng, En-Shiun Annie Lee
Published: 2025-11-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.06497v1

Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for typologically distant or low-resource languages (LRLs) compared to English. Moreover, word realignment tools often rely on high-quality parallel data, which can be scarce or noisy for many LRLs. In this work, we conduct an extensive empirical study to investigate whether realignment truly benefits from using all available languages, or if strategically selected subsets can offer comparable or even improved cross-lingual transfer, and study the impact on LRLs. Our controlled experiments show that realignment can be particularly effective for LRLs and that using carefully selected, linguistically diverse subsets can match full multilingual alignment, and even outperform it for unseen LRLs. This indicates that effective realignment does not require exhaustive language coverage and can reduce data collection overhead, while remaining both efficient and robust when guided by informed language selection.

---

### A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving

Authors: Keke Long, Jiacheng Guo, Tianyun Zhang, Hongkai Yu, Xiaopeng Li
Published: 2025-11-09
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.06496v1

Vision Language Models (VLMs) are increasingly used in autonomous driving to help understand traffic scenes, but they sometimes produce hallucinations, which are false details not grounded in the visual input. Detecting and mitigating hallucinations is challenging when ground-truth references are unavailable and model internals are inaccessible. This paper proposes a novel self-contained low-rank approach to automatically rank multiple candidate captions generated by multiple VLMs based on their hallucination levels, using only the captions themselves without requiring external references or model access. By constructing a sentence-embedding matrix and decomposing it into a low-rank consensus component and a sparse residual, we use the residual magnitude to rank captions: selecting the one with the smallest residual as the most hallucination-free. Experiments on the NuScenes dataset demonstrate that our approach achieves 87% selection accuracy in identifying hallucination-free captions, representing a 19% improvement over the unfiltered baseline and a 6-10% improvement over multi-agent debate method. The sorting produced by sparse error magnitudes shows strong correlation with human judgments of hallucinations, validating our scoring mechanism. Additionally, our method, which can be easily parallelized, reduces inference time by 51-67% compared to debate approaches, making it practical for real-time autonomous driving applications.

---

### Probably Approximately Global Robustness Certification

Authors: Peter Blohm, Patrick Indri, Thomas Gärtner, Sagar Malhotra
Published: 2025-11-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.06495v1

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approaches do not provide formal guarantees, our approach is able to efficiently certify a probabilistic relaxation of robustness. The key idea is to sample an $ε$-net and invoke a local robustness oracle on the sample. Remarkably, the size of the sample needed to achieve probably approximately global robustness guarantees is independent of the input dimensionality, the number of classes, and the learning algorithm itself. Our approach can, therefore, be applied even to large neural networks that are beyond the scope of traditional formal verification. Experiments empirically confirm that it characterizes robustness better than state-of-the-art sampling-based approaches and scales better than formal methods.

---

### Route Experts by Sequence, not by Token

Authors: Tiansheng Wen, Yifei Wang, Aosong Feng, Long Ma, Xinyang Liu, Yifan Wang, Lixuan Guo, Bo Chen, Stefanie Jegelka, Chenyu You
Published: 2025-11-09
Categories: cs.LG, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2511.06494v2

Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token, but the standard TopK routing assigns the same fixed number of experts to all tokens, ignoring their varying complexity. Prior adaptive routing methods introduce additional modules and hyperparameters, often requiring costly retraining from scratch. We propose Sequence-level TopK (SeqTopK), a minimal modification that shifts the expert budget from the token level to the sequence level. By selecting the top $T \cdot K$ experts across all $T$ tokens, SeqTopK enables end-to-end learned dynamic allocation -- assigning more experts to difficult tokens and fewer to easy ones -- while preserving the same overall budget. SeqTopK requires only a few lines of code, adds less than 1% overhead, and remains fully compatible with pretrained MoE models. Experiments across math, coding, law, and writing show consistent improvements over TopK and prior parameter-free adaptive methods, with gains that become substantially larger under higher sparsity (up to 16.9%). These results highlight SeqTopK as a simple, efficient, and scalable routing strategy, particularly well-suited for the extreme sparsity regimes of next-generation LLMs. Code is available at https://github.com/Y-Research-SBU/SeqTopK.

---

### Learning Time-Varying Graph Signals via Koopman

Authors: Sivaram Krishnan, Jinho Choi, Jihong Park
Published: 2025-11-09
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.06493v1

A wide variety of real-world data, such as sea measurements, e.g., temperatures collected by distributed sensors and multiple unmanned aerial vehicles (UAV) trajectories, can be naturally represented as graphs, often exhibiting non-Euclidean structures. These graph representations may evolve over time, forming time-varying graphs. Effectively modeling and analyzing such dynamic graph data is critical for tasks like predicting graph evolution and reconstructing missing graph data. In this paper, we propose a framework based on the Koopman autoencoder (KAE) to handle time-varying graph data. Specifically, we assume the existence of a hidden non-linear dynamical system, where the state vector corresponds to the graph embedding of the time-varying graph signals. To capture the evolving graph structures, the graph data is first converted into a vector time series through graph embedding, representing the structural information in a finite-dimensional latent space. In this latent space, the KAE is applied to learn the underlying non-linear dynamics governing the temporal evolution of graph features, enabling both prediction and reconstruction tasks.

---