# Research Papers — 2025-11 · bundle page 124 of 197 > Full-text markdown of papers #6151–6200 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/124 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/123.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/125.md) ### Beyond empirical models: Discovering new constitutive laws in solids with graph-based equation discovery Authors: Hao Xu, Yuntian Chen, Dongxiao Zhang Published: 2025-11-13 Categories: cond-mat.mtrl-sci, cs.LG, physics.app-ph, physics.data-an arXiv: https://arxiv.org/abs/2511.09906v1 Constitutive models are fundamental to solid mechanics and materials science, underpinning the quantitative description and prediction of material responses under diverse loading conditions. Traditional phenomenological models, which are derived through empirical fitting, often lack generalizability and rely heavily on expert intuition and predefined functional forms. In this work, we propose a graph-based equation discovery framework for the automated discovery of constitutive laws directly from multisource experimental data. This framework expresses equations as directed graphs, where nodes represent operators and variables, edges denote computational relations, and edge features encode parametric dependencies. This enables the generation and optimization of free-form symbolic expressions with undetermined material-specific parameters. Through the proposed framework, we have discovered new constitutive models for strain-rate effects in alloy steel materials and the deformation behavior of lithium metal. Compared with conventional empirical models, these new models exhibit compact analytical structures and achieve higher accuracy. The proposed graph-based equation discovery framework provides a generalizable and interpretable approach for data-driven scientific modelling, particularly in contexts where traditional empirical formulations are inadequate for representing complex physical phenomena. --- ### PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors Authors: Brian B. Moser, Shalini Sarode, Federico Raue, Stanislav Frolov, Krzysztof Adamkiewicz, Arundhati Shanbhag, Joachim Folz, Tobias C. Nauen, Andreas Dengel Published: 2025-11-13 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.09905v2 Dataset distillation (DD) promises compact yet faithful synthetic data, but existing approaches often inherit the inductive bias of a single teacher model. As dataset size increases, this bias drives generation toward overly smooth, homogeneous samples, reducing intra-class diversity and limiting generalization. We present PRISM (PRIors from diverse Source Models), a framework that disentangles architectural priors during synthesis. PRISM decouples the logit-matching and regularization objectives, supervising them with different teacher architectures: a primary model for logits and a stochastic subset for batch-normalization (BN) alignment. On ImageNet-1K, PRISM consistently and reproducibly outperforms single-teacher methods (e.g., SRe2L) and recent multi-teacher variants (e.g., G-VBSM) at low- and mid-IPC regimes. The generated data also show significantly richer intra-class diversity, as reflected by a notable drop in cosine similarity between features. We further analyze teacher selection strategies (pre- vs. intra-distillation) and introduce a scalable cross-class batch formation scheme for fast parallel synthesis. Code will be released after the review period. --- ### CTRL-ALT-DECEIT: Sabotage Evaluations for Automated AI R&D Authors: Francis Rhys Ward, Teun van der Weij, Hanna Gábor, Sam Martin, Raja Mehta Moreno, Harel Lidar, Louis Makower, Thomas Jodrell, Lauren Robson Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.09904v2 AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI systems may be deployed in safety-critical settings, including to help ensure the safety of future systems. Unfortunately, frontier and future systems may not be sufficiently trustworthy, and there is evidence that these systems may even be misaligned with their developers or users. Therefore, we investigate the capabilities of AI agents to act against the interests of their users when conducting ML engineering, by sabotaging ML models, sandbagging their performance, and subverting oversight mechanisms. First, we extend MLE-Bench, a benchmark for realistic ML tasks, with code-sabotage tasks such as implanting backdoors and purposefully causing generalisation failures. Frontier agents make meaningful progress on our sabotage tasks. In addition, we study agent capabilities to sandbag on MLE-Bench. Agents can calibrate their performance to specified target levels below their actual capability. To mitigate sabotage, we use LM monitors to detect suspicious agent behaviour, and we measure model capability to sabotage and sandbag without being detected by these monitors. Overall, monitors are capable at detecting code-sabotage attempts but our results suggest that detecting sandbagging is more difficult. Additionally, aggregating multiple monitor predictions works well, but monitoring may not be sufficiently reliable to mitigate sabotage in high-stakes domains. Our benchmark is implemented in the UK AISI's Inspect framework and we make our code publicly available at https://github.com/TeunvdWeij/ctrl-alt-deceit --- ### Autonomous-Flow-Based Generation Authors: Hossein Rouhvarzi, Anastasis Kratsios Published: 2025-11-13 Categories: cs.LG, math.CA, math.DS, math.NA, stat.ML arXiv: https://arxiv.org/abs/2511.09902v3 We show that using autonomous-flow-based generation, one can universally approximate orientation-preserving diffeomorphisms defined on the cube by Neural ODEs with rate $\mathcal{O}(P^{-1/d})$ with $P$ parameters. On the other hand, we show that by using only a single autonomous flow, the class of Neural ODEs is nowhere dense on the cube in dimension $d \ge 2$ . Under a compact-support$_\mathrm{id}$ condition on $(0,1)^d$, we show that using autonomous-flow-based generation, one can universally approximate compactly supported$_\mathrm{id}$ diffeomorphisms on $(0,1)^d$ for any dimension with rate $\mathcal{O}((\frac{P}{\log P})^{-2/d})$ with $P$ parameters and for compactly supported$_\mathrm{id}$ homeomorphisms on $(0,1)^d$ in dimension $d \geq 5$ with rate $\mathcal{O}(P^{-1/(d+1)})$ with $P$ parameters and by a composition of at most $I_d$ autonomous Neural ODEs with the same support$_\mathrm{id}$, where $I_d$ depends only on the dimension. Moreover, we show that the class of single autonomous flows compactly supported$_\mathrm{id}$ on $(0,1)^d$ is meagre in the space of compactly supported$_\mathrm{id}$ homeomorphisms on $(0,1)^d$ for $d\ge 2$. By linearly lifting the domain into one higher dimension, we obtain a universal approximation result for Lipschitz functions compactly supported on $(0,1)^d$ with rate $\mathcal{O}(P^{-1/(d+1)})$ with $P$ parameters. --- ### Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training Authors: Weilin Wan, Fan Yi, Weizhong Zhang, Quan Zhou, Cheng Jin Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09901v2 Modern deep neural networks rely heavily on massive model weights and training samples, incurring substantial computational costs. Weight pruning and coreset selection are two emerging paradigms proposed to improve computational efficiency. In this paper, we first explore the interplay between redundant weights and training samples through a transparent analysis: redundant samples, particularly noisy ones, cause model weights to become unnecessarily overtuned to fit them, complicating the identification of irrelevant weights during pruning; conversely, irrelevant weights tend to overfit noisy data, undermining coreset selection effectiveness. To further investigate and harness this interplay in deep learning, we develop a Simultaneous Weight and Sample Tailoring mechanism (SWaST) that alternately performs weight pruning and coreset selection to establish a synergistic effect in training. During this investigation, we observe that when simultaneously removing a large number of weights and samples, a phenomenon we term critical double-loss can occur, where important weights and their supportive samples are mistakenly eliminated at the same time, leading to model instability and nearly irreversible degradation that cannot be recovered in subsequent training. Unlike classic machine learning models, this issue can arise in deep learning due to the lack of theoretical guarantees on the correctness of weight pruning and coreset selection, which explains why these paradigms are often developed independently. We mitigate this by integrating a state preservation mechanism into SWaST, enabling stable joint optimization. Extensive experiments reveal a strong synergy between pruning and coreset selection across varying prune rates and coreset sizes, delivering accuracy boosts of up to 17.83% alongside 10% to 90% FLOPs reductions. --- ### Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search Authors: Yaodong Yang, Yang Wang, Jinpeng Li, Pei Guo, Da Han, Guangyong Chen, Pheng-Ann Heng Published: 2025-11-13 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2511.09900v4 Protein evolution through amino acid mutations is a cornerstone of life sciences. Recent advances in protein language models have shown rich evolutionary patterns, offering unprecedented potential for in-silicon directed evolution. However, existing directed evolution methods largely rely on heuristic evolution strategies and have yet to efficiently integrate the transformative protein language models with advanced optimization techniques, such as reinforcement learning, to adaptively learn superior evolution policies. To bridge this gap, we propose AlphaDE, a novel framework that evolves protein sequences by harnessing the innovative paradigms of large language models, such as fine-tuning and test-time inference. First, AlphaDE fine-tunes pretrained protein language models using masked language modeling on homologous protein sequences to activate the evolutionary plausibility of the interested protein family. Second, AlphaDE introduces test-time inference based on Monte Carlo tree search, which effectively evolves proteins with evolutionary guidance from the fine-tuned protein language model. Extensive benchmark experiments show that AlphaDE remarkably outperforms previous state-of-the-art methods even with few-shot fine-tuning. A case study further demonstrates that AlphaDE supports condensing the protein sequence space of avGFP through computational evolution. --- ### Theory and computation for structured variational inference Authors: Shunan Sheng, Bohan Wu, Bennett Zhu, Sinho Chewi, Aram-Alexandre Pooladian Published: 2025-11-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.09897v1 Structured variational inference constitutes a core methodology in modern statistical applications. Unlike mean-field variational inference, the approximate posterior is assumed to have interdependent structure. We consider the natural setting of star-structured variational inference, where a root variable impacts all the other ones. We prove the first results for existence, uniqueness, and self-consistency of the variational approximation. In turn, we derive quantitative approximation error bounds for the variational approximation to the posterior, extending prior work from the mean-field setting to the star-structured setting. We also develop a gradient-based algorithm with provable guarantees for computing the variational approximation using ideas from optimal transport theory. We explore the implications of our results for Gaussian measures and hierarchical Bayesian models, including generalized linear models with location family priors and spike-and-slab priors with one-dimensional debiasing. As a by-product of our analysis, we develop new stability results for star-separable transport maps which might be of independent interest. --- ### Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation Authors: Xiaoda Wang, Kaiqiao Han, Yuhao Xu, Xiao Luo, Yizhou Sun, Wei Wang, Carl Yang Published: 2025-11-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09895v1 Cardiovascular disease (CVD) is a leading cause of mortality worldwide. Electrocardiograms (ECGs) are the most widely used non-invasive tool for cardiac assessment, yet large, well-annotated ECG corpora are scarce due to cost, privacy, and workflow constraints. Generating ECGs can be beneficial for the mechanistic understanding of cardiac electrical activity, enable the construction of large, heterogeneous, and unbiased datasets, and facilitate privacy-preserving data sharing. Generating realistic ECG signals from clinical context is important yet underexplored. Recent work has leveraged diffusion models for text-to-ECG generation, but two challenges remain: (i) existing methods often overlook the physiological simulator knowledge of cardiac activity; and (ii) they ignore broader, experience-based clinical knowledge grounded in real-world practice. To address these gaps, we propose SE-Diff, a novel physiological simulator and experience enhanced diffusion model for comprehensive ECG generation. SE-Diff integrates a lightweight ordinary differential equation (ODE)-based ECG simulator into the diffusion process via a beat decoder and simulator-consistent constraints, injecting mechanistic priors that promote physiologically plausible waveforms. In parallel, we design an LLM-powered experience retrieval-augmented strategy to inject clinical knowledge, providing more guidance for ECG generation. Extensive experiments on real-world ECG datasets demonstrate that SE-Diff improves both signal fidelity and text-ECG semantic alignment over baselines, proving its superiority for text-to-ECG generation. We further show that the simulator-based and experience-based knowledge also benefit downstream ECG classification. --- ### EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Services Authors: Keshara Weerasinghe, Xueren Ge, Tessa Heick, Lahiru Nuwan Wijayasingha, Anthony Cortez, Abhishek Satpathy, John Stankovic, Homa Alemzadeh Published: 2025-11-13 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.09894v2 Emergency Medical Services (EMS) are critical to patient survival in emergencies, but first responders often face intense cognitive demands in high-stakes situations. AI cognitive assistants, acting as virtual partners, have the potential to ease this burden by supporting real-time data collection and decision making. In pursuit of this vision, we introduce EgoEMS, the first end-to-end, high-fidelity, multimodal, multiperson dataset capturing over 20 hours of realistic, procedural EMS activities from an egocentric view in 233 simulated emergency scenarios performed by 62 participants, including 46 EMS professionals. Developed in collaboration with EMS experts and aligned with national standards, EgoEMS is captured using an open-source, low-cost, and replicable data collection system and is annotated with keysteps, timestamped audio transcripts with speaker diarization, action quality metrics, and bounding boxes with segmentation masks. Emphasizing realism, the dataset includes responder-patient interactions reflecting real-world emergency dynamics. We also present a suite of benchmarks for real-time multimodal keystep recognition and action quality estimation, essential for developing AI support tools for EMS. We hope EgoEMS inspires the research community to push the boundaries of intelligent EMS systems and ultimately contribute to improved patient outcomes. --- ### Regional Attention-Enhanced Swin Transformer for Clinically Relevant Medical Image Captioning Authors: Zubia Naz, Farhan Asghar, Muhammad Ishfaq Hussain, Yahya Hadadi, Muhammad Aasim Rafique, Wookjin Choi, Moongu Jeon Published: 2025-11-13 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.09893v1 Automated medical image captioning translates complex radiological images into diagnostic narratives that can support reporting workflows. We present a Swin-BART encoder-decoder system with a lightweight regional attention module that amplifies diagnostically salient regions before cross-attention. Trained and evaluated on ROCO, our model achieves state-of-the-art semantic fidelity while remaining compact and interpretable. We report results as mean$\pm$std over three seeds and include $95\%$ confidence intervals. Compared with baselines, our approach improves ROUGE (proposed 0.603, ResNet-CNN 0.356, BLIP2-OPT 0.255) and BERTScore (proposed 0.807, BLIP2-OPT 0.645, ResNet-CNN 0.623), with competitive BLEU, CIDEr, and METEOR. We further provide ablations (regional attention on/off and token-count sweep), per-modality analysis (CT/MRI/X-ray), paired significance tests, and qualitative heatmaps that visualize the regions driving each description. Decoding uses beam search (beam size $=4$), length penalty $=1.1$, $no\_repeat\_ngram\_size$ $=3$, and max length $=128$. The proposed design yields accurate, clinically phrased captions and transparent regional attributions, supporting safe research use with a human in the loop. --- ### Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images Authors: Jinfu Li, Yuqi Huang, Hong Song, Ting Wang, Jianghan Xia, Yucong Lin, Jingfan Fan, Jian Yang Published: 2025-11-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.09891v1 Recently, despite the remarkable advancements in object detection, modern detectors still struggle to detect tiny objects in aerial images. One key reason is that tiny objects carry limited features that are inevitably degraded or lost during long-distance network propagation. Another is that smaller objects receive disproportionately greater regression penalties than larger ones during training. To tackle these issues, we propose a Scale-Aware Relay Layer (SARL) and a Scale-Adaptive Loss (SAL) for tiny object detection, both of which are seamlessly compatible with the top-performing frameworks. Specifically, SARL employs a cross-scale spatial-channel attention to progressively enrich the meaningful features of each layer and strengthen the cross-layer feature sharing. SAL reshapes the vanilla IoU-based losses so as to dynamically assign lower weights to larger objects. This loss is able to focus training on tiny objects while reducing the influence on large objects. Extensive experiments are conducted on three benchmarks (\textit{i.e.,} AI-TOD, DOTA-v2.0 and VisDrone2019), and the results demonstrate that the proposed method boosts the generalization ability by 5.5\% Average Precision (AP) when embedded in YOLOv5 (anchor-based) and YOLOx (anchor-free) baselines. Moreover, it also promotes the robust performance with 29.0\% AP on the real-world noisy dataset (\textit{i.e.,} AI-TOD-v2.0). --- ### A General Anchor-Based Framework for Scalable Fair Clustering Authors: Shengfei Wei, Suyuan Liu, Jun Wang, Ke Liang, Miaomiao Li, Lei Luo Published: 2025-11-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09889v1 Fair clustering is crucial for mitigating bias in unsupervised learning, yet existing algorithms often suffer from quadratic or super-quadratic computational complexity, rendering them impractical for large-scale datasets. To bridge this gap, we introduce the Anchor-based Fair Clustering Framework (AFCF), a novel, general, and plug-and-play framework that empowers arbitrary fair clustering algorithms with linear-time scalability. Our approach first selects a small but representative set of anchors using a novel fair sampling strategy. Then, any off-the-shelf fair clustering algorithm can be applied to this small anchor set. The core of our framework lies in a novel anchor graph construction module, where we formulate an optimization problem to propagate labels while preserving fairness. This is achieved through a carefully designed group-label joint constraint, which we prove theoretically ensures that the fairness of the final clustering on the entire dataset matches that of the anchor clustering. We solve this optimization efficiently using an ADMM-based algorithm. Extensive experiments on multiple large-scale benchmarks demonstrate that AFCF drastically accelerates state-of-the-art methods, which reduces computational time by orders of magnitude while maintaining strong clustering performance and fairness guarantees. --- ### Quantum Artificial Intelligence for Mission-Critical Systems: Foundations, Architectural Elements, and Future Directions Authors: Siva Sai, Rajkumar Buyya Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.09884v2 Mission critical (MC) applications such as defense operations, energy management, cybersecurity, and aerospace control require reliable, deterministic, and low-latency decision making under uncertainty. Although the classical Artificial Intelligence (AI) approaches are effective, they often struggle to meet the stringent constraints of robustness, timing, explainability, and safety in the MC domains. Quantum Artificial Intelligence (QAI), the fusion of artificial intelligence and quantum computing (QC), can potentially provide transformative solutions to the challenges faced by classical ML models. QAI is a broader umbrella than Quantum Machine Learning (QML) and additionally includes quantum optimization, search, and reasoning; we use QAI throughout the paper for the field at large, and QML only for learning-specific subroutines. The principal contributions of this work are: (i) a systematic survey of QAI methods analyzed through the lens of MC requirements like certification, robustness, and timing; (ii) a conceptual quantum cloud resource management and scheduling framework with deployment assumptions, complexity analysis, and failure-mode discussion; and (iii) an identification of the gaps between current QAI capabilities and MC systems requirements. We also propose a conceptual model for management of quantum resources and scheduling of applications driven by timeliness constraints. We discuss multiple challenges, including trainability limits, data access, and loading bottlenecks, verification of quantum components, and adversarial QAI. Finally, we outline future research directions toward achieving interpretable, scalable, and hardware-feasible QAI models for MC application deployment. --- ### HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models Authors: Liheng Zhang, Jin Wang, Hui Li, Bingfeng Zhang, Weifeng Liu Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09883v1 3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VLMs directly embed the 3D point clouds into 3D tokens, following large 2D-VLMs with powerful reasoning capabilities. However, this framework has a great computational cost limiting its application, where we identify that the bottleneck lies in processing all 3D tokens in the Large Language Model (LLM) part. This raises the question: how can we reduce the computational overhead introduced by 3D tokens while preserving the integrity of their essential information? To address this question, we introduce Hierarchical Compensatory Compression (HCC-3D) to efficiently compress 3D tokens while maintaining critical detail retention. Specifically, we first propose a global structure compression (GSC), in which we design global queries to compress all 3D tokens into a few key tokens while keeping overall structural information. Then, to compensate for the information loss in GSC, we further propose an adaptive detail mining (ADM) module that selectively recompresses salient but under-attended features through complementary scoring. Extensive experiments demonstrate that HCC-3D not only achieves extreme compression ratios (approximately 98%) compared to previous 3D-VLMs, but also achieves new state-of-the-art performance, showing the great improvements on both efficiency and performance. --- ### EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models Authors: Jialin Wu, Kecen Li, Zhicong Huang, Xinfeng Li, Xiaofeng Wang, Cheng Hong Published: 2025-11-13 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2511.09880v1 Many machine learning models are fine-tuned from large language models (LLMs) to achieve high performance in specialized domains like code generation, biomedical analysis, and mathematical problem solving. However, this fine-tuning process often introduces a critical vulnerability: the systematic degradation of safety alignment, undermining ethical guidelines and increasing the risk of harmful outputs. Addressing this challenge, we introduce EnchTable, a novel framework designed to transfer and maintain safety alignment in downstream LLMs without requiring extensive retraining. EnchTable leverages a Neural Tangent Kernel (NTK)-based safety vector distillation method to decouple safety constraints from task-specific reasoning, ensuring compatibility across diverse model architectures and sizes. Additionally, our interference-aware merging technique effectively balances safety and utility, minimizing performance compromises across various task domains. We implemented a fully functional prototype of EnchTable on three different task domains and three distinct LLM architectures, and evaluated its performance through extensive experiments on eleven diverse datasets, assessing both utility and model safety. Our evaluations include LLMs from different vendors, demonstrating EnchTable's generalization capability. Furthermore, EnchTable exhibits robust resistance to static and dynamic jailbreaking attacks, outperforming vendor-released safety models in mitigating adversarial prompts. Comparative analyses with six parameter modification methods and two inference-time alignment baselines reveal that EnchTable achieves a significantly lower unsafe rate, higher utility score, and universal applicability across different task domains. Additionally, we validate EnchTable can be seamlessly integrated into various deployment pipelines without significant overhead. --- ### Taught by the Flawed: How Dataset Insecurity Breeds Vulnerable AI Code Authors: Catherine Xia, Manar H. Alalfi Published: 2025-11-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.09879v1 AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of these generated code snippets remains essential. A key contributing factor to insecure outputs is the presence of vulnerabilities in the training datasets used to build large language models (LLMs). To address this issue, we propose curating training data to include only code that is free from detectable vulnerabilities. In this study, we constructed a secure dataset by filtering an existing Python corpus using a static analysis tool to retain only vulnerability-free functions. We then trained two transformer-based models: one on the curated dataset and one on the original, unfiltered dataset. The models were evaluated on both the correctness and security of the code they generated in response to natural language function descriptions. Our results show that the model trained on the curated dataset produced outputs with fewer security issues, while maintaining comparable functional correctness. These findings highlight the importance of secure training data in improving the reliability of AI-based programming assistants, though further enhancements to model architecture and evaluation are needed to reinforce these outcomes. --- ### RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion Authors: Wenzhe He, Xiaojun Chen, Wentang Chen, Hongyu Wang, Ying Liu, Ruihui Li Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09878v1 Semantic Scene Completion (SSC) aims to generate a complete semantic scene from an incomplete input. Existing approaches often employ dense network architectures with a high parameter count, leading to increased model complexity and resource demands. To address these limitations, we propose RWKV-PCSSC, a lightweight point cloud semantic scene completion network inspired by the Receptance Weighted Key Value (RWKV) mechanism. Specifically, we introduce a RWKV Seed Generator (RWKV-SG) module that can aggregate features from a partial point cloud to produce a coarse point cloud with coarse features. Subsequently, the point-wise feature of the point cloud is progressively restored through multiple stages of the RWKV Point Deconvolution (RWKV-PD) modules. By leveraging a compact and efficient design, our method achieves a lightweight model representation. Experimental results demonstrate that RWKV-PCSSC reduces the parameter count by 4.18$\times$ and improves memory efficiency by 1.37$\times$ compared to state-of-the-art methods PointSSC. Furthermore, our network achieves state-of-the-art performance on established indoor (SSC-PC, NYUCAD-PC) and outdoor (PointSSC) scene dataset, as well as on our proposed datasets (NYUCAD-PC-V2, 3D-FRONT-PC). --- ### HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning Authors: Nikunj Gupta, Bill Guo, Rajgopal Kannan, Viktor K. Prasanna Published: 2025-11-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.09873v1 Large Language Models (LLMs) deliver state-of-the-art performance across many tasks but impose high computational and memory costs, limiting their deployment in resource-constrained or real-time settings. To address this, we propose HierRouter, a hierarchical routing approach that dynamically assembles inference pipelines from a pool of specialized, lightweight language models. Formulated as a finite-horizon Markov Decision Process (MDP), our approach trains a Proximal Policy Optimization (PPO)-based reinforcement learning agent to iteratively select which models to invoke at each stage of multi-hop inference. The agent conditions on the evolving context and accumulated cost to make context-aware routing decisions. Experiments with three open-source candidate LLMs across six benchmarks, including QA, code generation, and mathematical reasoning, show that HierRouter improves response quality by up to 2.4x compared to using individual models independently, while incurring only a minimal additional inference cost on average. These results highlight the promise of hierarchical routing for cost-efficient, high-performance LLM inference. All codes can be found here https://github.com/ Nikunj-Gupta/hierouter. --- ### Randomized batch-sampling Kaczmarz methods for solving linear systems Authors: Dong-Yue Xie, Xi Yang Published: 2025-11-13 Categories: math.NA, stat.ML arXiv: https://arxiv.org/abs/2511.09872v2 To conduct a more in-depth investigation of randomized solvers for solving linear systems, we adopt a unified randomized batch-sampling Kaczmarz framework with per-iteration costs as low as cyclic block methods, and develop a general analysis technique to establish its convergence guarantee. With concentration inequalities, we derive new expected linear convergence rate bounds. The analysis applies to any randomized non-extended block Kaczmarz methods with arbitrary static stochastic samplings. In addition, the new rate bounds are scale-invariant, which eliminate the dependence on the magnitude of the data matrix. In most experiments, the new bounds are significantly tighter than existing ones and better reflect the empirical convergence behavior of block methods. Within this new framework, the batch-sampling distribution, as a learnable parameter, provides the possibility for block methods to achieve efficient performance in specific application scenarios, which deserves further investigation. --- ### Expandable and Differentiable Dual Memories with Orthogonal Regularization for Exemplar-free Continual Learning Authors: Hyung-Jun Moon, Sung-Bae Cho Published: 2025-11-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09871v1 Continual learning methods used to force neural networks to process sequential tasks in isolation, preventing them from leveraging useful inter-task relationships and causing them to repeatedly relearn similar features or overly differentiate them. To address this problem, we propose a fully differentiable, exemplar-free expandable method composed of two complementary memories: One learns common features that can be used across all tasks, and the other combines the shared features to learn discriminative characteristics unique to each sample. Both memories are differentiable so that the network can autonomously learn latent representations for each sample. For each task, the memory adjustment module adaptively prunes critical slots and minimally expands capacity to accommodate new concepts, and orthogonal regularization enforces geometric separation between preserved and newly learned memory components to prevent interference. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that the proposed method outperforms 14 state-of-the-art methods for class-incremental learning, achieving final accuracies of 55.13\%, 37.24\%, and 30.11\%, respectively. Additional analysis confirms that, through effective integration and utilization of knowledge, the proposed method can increase average performance across sequential tasks, and it produces feature extraction results closest to the upper bound, thus establishing a new milestone in continual learning. --- ### SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection Authors: Jia Lin, Xiaofei Zhou, Jiyuan Liu, Runmin Cong, Guodao Zhang, Zhi Liu, Jiyong Zhang Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09870v1 Recently segment anything model (SAM) has attracted widespread concerns, and it is often treated as a vision foundation model for universal segmentation. Some researchers have attempted to directly apply the foundation model to the RGB-D video salient object detection (RGB-D VSOD) task, which often encounters three challenges, including the dependence on manual prompts, the high memory consumption of sequential adapters, and the computational burden of memory attention. To address the limitations, we propose a novel method, namely Segment Anything Model with Depth-guided Adaptive Queries (SAM-DAQ), which adapts SAM2 to pop-out salient objects from videos by seamlessly integrating depth and temporal cues within a unified framework. Firstly, we deploy a parallel adapter-based multi-modal image encoder (PAMIE), which incorporates several depth-guided parallel adapters (DPAs) in a skip-connection way. Remarkably, we fine-tune the frozen SAM encoder under prompt-free conditions, where the DPA utilizes depth cues to facilitate the fusion of multi-modal features. Secondly, we deploy a query-driven temporal memory (QTM) module, which unifies the memory bank and prompt embeddings into a learnable pipeline. Concretely, by leveraging both frame-level queries and video-level queries simultaneously, the QTM module can not only selectively extract temporal consistency features but also iteratively update the temporal representations of the queries. Extensive experiments are conducted on three RGB-D VSOD datasets, and the results show that the proposed SAM-DAQ consistently outperforms state-of-the-art methods in terms of all evaluation metrics. --- ### Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies Authors: Peng Gao, Yujian Lee, Xiaofeng Zhang, Zailong Chen, Hui Zhang Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09868v1 Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-range dependencies under the usage of Rotary Positional Encoding (ROPE). Although it can facilitate precise modeling of token positions, it induces progressive attention decay as token distance increases, especially with progressive attention decay over distant token pairs, which severely impairs the model's ability to remember global context. To alleviate this issue, we propose inference-only Three-step Decay Resilience Strategies (T-DRS), comprising (1) Semantic-Driven DRS (SD-DRS), amplifying semantically meaningful but distant signals via content-aware residuals, (2) Distance-aware Control DRS (DC-DRS), which can purify attention by smoothly modulating weights based on positional distances, suppressing noise while preserving locality, and (3) re-Reinforce Distant DRS (reRD-DRS), consolidating the remaining informative remote dependencies to maintain global coherence. Together, the T-DRS recover suppressed long-range token pairs without harming local inductive biases. Extensive experiments on Vision Question Answering (VQA) benchmarks demonstrate that T-DRS can consistently improve performance in a training-free manner. The code can be accessed in https://github.com/labixiaoq-qq/Remember-me --- ### IPCD: Intrinsic Point-Cloud Decomposition Authors: Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda, Tomoyasu Shimada, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida, Akisato Kimura Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09866v1 Point clouds are widely used in various fields, including augmented reality (AR) and robotics, where relighting and texture editing are crucial for realistic visualization. Achieving these tasks requires accurately separating albedo from shade. However, performing this separation on point clouds presents two key challenges: (1) the non-grid structure of point clouds makes conventional image-based decomposition models ineffective, and (2) point-cloud models designed for other tasks do not explicitly consider global-light direction, resulting in inaccurate shade. In this paper, we introduce \textbf{Intrinsic Point-Cloud Decomposition (IPCD)}, which extends image decomposition to the direct decomposition of colored point clouds into albedo and shade. To overcome challenge (1), we propose \textbf{IPCD-Net} that extends image-based model with point-wise feature aggregation for non-grid data processing. For challenge (2), we introduce \textbf{Projection-based Luminance Distribution (PLD)} with a hierarchical feature refinement, capturing global-light ques via multi-view projection. For comprehensive evaluation, we create a synthetic outdoor-scene dataset. Experimental results demonstrate that IPCD-Net reduces cast shadows in albedo and enhances color accuracy in shade. Furthermore, we showcase its applications in texture editing, relighting, and point-cloud registration under varying illumination. Finally, we verify the real-world applicability of IPCD-Net. --- ### In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback Authors: Mingye Zhu, Yi Liu, Zheren Fu, Quan Wang, Yongdong Zhang Published: 2025-11-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.09865v1 Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas reinforcement learning with verifiable rewards struggles with credit assignment and prohibitive computational cost. To tackle these limitations, we introduce InTRO (In-Token Rationality Optimization), a new framework that enables both token-level exploration and self-feedback for accurate and concise reasoning. Instead of directly optimizing an intractable objective over all valid reasoning paths, InTRO leverages correction factors-token-wise importance weights estimated by the information discrepancy between the generative policy and its answer-conditioned counterpart, for informative next token selection. This approach allows the model to perform token-level exploration and receive self-generated feedback within a single forward pass, ultimately encouraging accurate and concise rationales. Across six math-reasoning benchmarks, InTRO consistently outperforms other baselines, raising solution accuracy by up to 20% relative to the base model. Its chains of thought are also notably more concise, exhibiting reduced verbosity. Beyond this, InTRO enables cross-domain transfer, successfully adapting to out-of-domain reasoning tasks that extend beyond the realm of mathematics, demonstrating robust generalization. --- ### Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models Authors: Manh Nguyen, Dung Nguyen, Dai Do, Svetha Venkatesh, Hung Le Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09864v1 Reinforcement learning (RL) finetuning is crucial to aligning large language models (LLMs), but the process is notoriously unstable and exhibits high variance across model checkpoints. In practice, selecting the best checkpoint is challenging: evaluating checkpoints on the validation set during training is computationally expensive and requires a good validation set, while relying on the final checkpoint provides no guarantee of good performance. We introduce an uncertainty-guided approach for checkpoint selection (UGCS) that avoids these pitfalls. Our method identifies hard question-answer pairs using per-sample uncertainty and ranks checkpoints by how well they handle these challenging cases. By averaging the rewards of the top-uncertain samples over a short training window, our method produces a stable and discriminative signal without additional forward passes or significant computation overhead. Experiments across three datasets and three LLMs demonstrate that it consistently identifies checkpoints with stronger generalization, outperforming traditional strategies such as relying on training or validation performance. These results highlight that models solving their hardest tasks with low uncertainty are the most reliable overall. --- ### Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting Authors: James Jin Kang, Dang Bui, Thanh Pham, Huo-Chong Ling Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09855v1 The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that sensitive information can be permanently removed once it has been used. Retraining from the beginning is prohibitively costly, and existing unlearning methods remain fragmented, difficult to verify, and often vulnerable to recovery. This paper surveys recent research on machine unlearning for LLMs and considers how far current approaches can address these challenges. We review methods for evaluating whether forgetting has occurred, the resilience of unlearned models against adversarial attacks, and mechanisms that can support user trust when model complexity or proprietary limits restrict transparency. Technical solutions such as differential privacy, homomorphic encryption, federated learning, and ephemeral memory are examined alongside institutional safeguards including auditing practices and regulatory frameworks. The review finds steady progress, but robust and verifiable unlearning is still unresolved. Efficient techniques that avoid costly retraining, stronger defenses against adversarial recovery, and governance structures that reinforce accountability are needed if LLMs are to be deployed safely in sensitive applications. By integrating technical and organizational perspectives, this study outlines a pathway toward AI systems that can be required to forget, while maintaining both privacy and public trust. --- ### TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domain Authors: Yidan Sun, Mengying Zhu, Feiyue Chen, Yangyang Wu, Xiaolei Dan, Mengyuan Yang, Xiaolin Zheng, Shenglin Ben Published: 2025-11-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.09854v2 Large language models (LLMs) have demonstrated impressive performance in text generation tasks; however, their embedding spaces often suffer from the isotropy problem, resulting in poor discrimination of domain-specific terminology, particularly in legal and financial contexts. This weakness in terminology-level representation can severely hinder downstream tasks such as legal judgment prediction or financial risk analysis, where subtle semantic distinctions are critical. To address this problem, we propose TermGPT, a multi-level contrastive fine-tuning framework designed for terminology adaptation. We first construct a sentence graph to capture semantic and structural relations, and generate semantically consistent yet discriminative positive and negative samples based on contextual and topological cues. We then devise a multi-level contrastive learning approach at both the sentence and token levels, enhancing global contextual understanding and fine-grained terminology discrimination. To support robust evaluation, we construct the first financial terminology dataset derived from official regulatory documents. Experiments show that TermGPT outperforms existing baselines in term discrimination tasks within the finance and legal domains. --- ### ConSurv: Multimodal Continual Learning for Survival Analysis Authors: Dianzhi Yu, Conghao Xiong, Yankai Chen, Wenqian Cui, Xinni Zhang, Yifei Zhang, Hao Chen, Joseph J. Y. Sung, Irwin King Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09853v2 Survival prediction of cancers is crucial for clinical practice, as it informs mortality risks and influences treatment plans. However, a static model trained on a single dataset fails to adapt to the dynamically evolving clinical environment and continuous data streams, limiting its practical utility. While continual learning (CL) offers a solution to learn dynamically from new datasets, existing CL methods primarily focus on unimodal inputs and suffer from severe catastrophic forgetting in survival prediction. In real-world scenarios, multimodal inputs often provide comprehensive and complementary information, such as whole slide images and genomics; and neglecting inter-modal correlations negatively impacts the performance. To address the two challenges of catastrophic forgetting and complex inter-modal interactions between gigapixel whole slide images and genomics, we propose ConSurv, the first multimodal continual learning (MMCL) method for survival analysis. ConSurv incorporates two key components: Multi-staged Mixture of Experts (MS-MoE) and Feature Constrained Replay (FCR). MS-MoE captures both task-shared and task-specific knowledge at different learning stages of the network, including two modality encoders and the modality fusion component, learning inter-modal relationships. FCR further enhances learned knowledge and mitigates forgetting by restricting feature deviation of previous data at different levels, including encoder-level features of two modalities and the fusion-level representations. Additionally, we introduce a new benchmark integrating four datasets, Multimodal Survival Analysis Incremental Learning (MSAIL), for comprehensive evaluation in the CL setting. Extensive experiments demonstrate that ConSurv outperforms competing methods across multiple metrics. --- ### Bridging Constraints and Stochasticity: A Fully First-Order Method for Stochastic Bilevel Optimization with Linear Constraints Authors: Cac Phan, Kai Wang Published: 2025-11-13 Categories: math.OC, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.09845v2 This work provides the first finite-time convergence guarantees for linearly constrained stochastic bilevel optimization using only first-order methods, requiring solely gradient information without any Hessian computations or second-order derivatives. We address the unprecedented challenge of simultaneously handling linear constraints, stochastic noise, and finite-time analysis in bilevel optimization, a combination that has remained theoretically intractable until now. While existing approaches either require second-order information, handle only unconstrained stochastic problems, or provide merely asymptotic convergence results, our method achieves finite-time guarantees using gradient-based techniques alone. We develop a novel framework that constructs hypergradient approximations via smoothed penalty functions, using approximate primal and dual solutions to overcome the fundamental challenges posed by the interaction between linear constraints and stochastic noise. Our theoretical analysis provides explicit finite-time bounds on the bias and variance of the hypergradient estimator, demonstrating how approximation errors interact with stochastic perturbations. We prove that our first-order algorithm converges to $(δ, ε)$-Goldstein stationary points using $Θ(δ^{-1}ε^{-5})$ stochastic gradient evaluations, establishing the first finite-time complexity result for this challenging problem class and representing a significant theoretical breakthrough in constrained stochastic bilevel optimization. --- ### Steering Pretrained Drafters during Speculative Decoding Authors: Frédéric Berdoz, Peer Rheinboldt, Roger Wattenhofer Published: 2025-11-13 Categories: cs.LG, cs.PF arXiv: https://arxiv.org/abs/2511.09844v1 Speculative decoding accelerates language model inference by separating generation into fast drafting and parallel verification. Its main limitation is drafter-verifier misalignment, which limits token acceptance and reduces overall effectiveness. While small drafting heads trained from scratch compensate with speed, they struggle when verification dominates latency or when inputs are out of distribution. In contrast, pretrained drafters, though slower, achieve higher acceptance rates thanks to stronger standalone generation capabilities, making them competitive when drafting latency is negligible relative to verification or communication overhead. In this work, we aim to improve the acceptance rates of pretrained drafters by introducing a lightweight dynamic alignment mechanism: a steering vector computed from the verifier's hidden states and injected into the pretrained drafter. Compared to existing offline alignment methods such as distillation, our approach boosts the number of accepted tokens by up to 35\% under standard sampling and 22\% under greedy sampling, all while incurring negligible computational overhead. Importantly, our approach can be retrofitted to existing architectures and pretrained models, enabling rapid adoption. --- ### CORONA-Fields: Leveraging Foundation Models for Classification of Solar Wind Phenomena Authors: Daniela Martin, Jinsu Hong, Connor O'Brien, Valmir P Moraes Filho, Jasmine R. Kobayashi, Evangelia Samara, Joseph Gallego Published: 2025-11-13 Categories: cs.CV, astro-ph.IM, astro-ph.SR arXiv: https://arxiv.org/abs/2511.09843v1 Space weather at Earth, driven by the solar activity, poses growing risks to satellites around our planet as well as to critical ground-based technological infrastructure. Major space weather contributors are the solar wind and coronal mass ejections whose variable density, speed, temperature, and magnetic field make the automated classification of those structures challenging. In this work, we adapt a foundation model for solar physics, originally trained on Solar Dynamics Observatory imagery, to create embeddings suitable for solar wind structure analysis. These embeddings are concatenated with the spacecraft position and solar magnetic connectivity encoded using Fourier features which generates a neural field-based model. The full deep learning architecture is fine-tuned bridging the gap between remote sensing and in situ observations. Labels are derived from Parker Solar Probe measurements, forming a downstream classification task that maps plasma properties to solar wind structures. Although overall classification performance is modest, likely due to coarse labeling, class imbalance, and limited transferability of the pretrained model, this study demonstrates the feasibility of leveraging foundation model embeddings for in situ solar wind tasks. As a first proof-of-concept, it lays the groundwork for future improvements toward more reliable space weather predictions. The code and configuration files used in this study are publicly available to support reproducibility. --- ### CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coverage Authors: Xuntao Lyu, Ching-Chi Lin, Abdullah Al Arafat, Georg von der Brüggen, Jian-Jia Chen, Zhishan Guo Published: 2025-11-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.09834v1 Adversarial patch attacks inject localized perturbations into images to mislead deep vision models. These attacks can be physically deployed, posing serious risks to real-world applications. In this paper, we propose CertMask, a certifiably robust defense that constructs a provably sufficient set of binary masks to neutralize patch effects with strong theoretical guarantees. While the state-of-the-art approach (PatchCleanser) requires two rounds of masking and incurs $O(n^2)$ inference cost, CertMask performs only a single round of masking with $O(n)$ time complexity, where $n$ is the cardinality of the mask set to cover an input image. Our proposed mask set is computed using a mathematically rigorous coverage strategy that ensures each possible patch location is covered at least $k$ times, providing both efficiency and robustness. We offer a theoretical analysis of the coverage condition and prove its sufficiency for certification. Experiments on ImageNet, ImageNette, and CIFAR-10 show that CertMask improves certified robust accuracy by up to +13.4\% over PatchCleanser, while maintaining clean accuracy nearly identical to the vanilla model. --- ### ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking Authors: Lequan Lin, Dai Shi, Andi Han, Feng Chen, Qiuzheng Chen, Jiawen Li, Zhaoyang Li, Jiyuan Li, Zhenbang Sun, Junbin Gao Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09833v2 Supervised learning relies on high-quality labeled data, but obtaining such data through human annotation is both expensive and time-consuming. Recent work explores using large language models (LLMs) for annotation, but LLM-generated labels still fall short of human-level quality. To address this problem, we propose the Annotation with Critical Thinking (ACT) data pipeline, where LLMs serve not only as annotators but also as judges to critically identify potential errors. Human effort is then directed towards reviewing only the most "suspicious" cases, significantly improving the human annotation efficiency. Our major contributions are as follows: (1) ACT is applicable to a wide range of domains, including natural language processing (NLP), computer vision (CV), and multimodal understanding, by leveraging multimodal-LLMs (MLLMs). (2) Through empirical studies, we derive 7 insights on how to enhance annotation quality while efficiently reducing the human cost, and then translate these findings into user-friendly guidelines. (3) We theoretically analyze how to modify the loss function so that models trained on ACT data achieve similar performance to those trained on fully human-annotated data. Our experiments show that the performance gap can be reduced to less than 2% on most benchmark datasets while saving up to 90% of human costs. --- ### Learning Intersections of Two Margin Halfspaces under Factorizable Distributions Authors: Ilias Diakonikolas, Mingchen Ma, Lisheng Ren, Christos Tzamos Published: 2025-11-13 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2511.09832v2 Learning intersections of halfspaces is a central problem in Computational Learning Theory. Even for just two halfspaces, it remains a major open question whether learning is possible in polynomial time with respect to the margin $γ$ of the data points and their dimensionality $d$. The best-known algorithms run in quasi-polynomial time $d^{O(\log(1/γ))}$, and it has been shown that this complexity is unavoidable for any algorithm relying solely on correlational statistical queries (CSQ). In this work, we introduce a novel algorithm that provably circumvents the CSQ hardness barrier. Our approach applies to a broad class of distributions satisfying a natural, previously studied, factorizability assumption. Factorizable distributions lie between distribution-specific and distribution-free settings, and significantly extend previously known tractable cases. Under these distributions, we show that CSQ-based methods still require quasipolynomial time even for weakly learning, whereas our algorithm achieves $poly(d,1/γ)$ time by leveraging more general statistical queries (SQ), establishing a strong separation between CSQ and SQ for this simple realizable PAC learning problem. Our result is grounded in a rigorous analysis utilizing a novel duality framework that characterizes the moment tensor structure induced by the marginal distributions. Building on these structural insights, we propose new, efficient learning algorithms. These algorithms combine a refined variant of Jennrich's Algorithm with PCA over random projections of the moment tensor, along with a gradient-descent-based non-convex optimization framework. --- ### Answering Students' Questions on Course Forums Using Multiple Chain-of-Thought Reasoning and Finetuning RAG-Enabled LLM Authors: Neo Wang, Sonit Singh Published: 2025-11-13 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.09831v1 The course forums are increasingly significant and play vital role in facilitating student discussions and answering their questions related to the course. It provides a platform for students to post their questions related to the content and admin issues related to the course. However, there are several challenges due to the increase in the number of students enrolled in the course. The primary challenge is that students' queries cannot be responded immediately and the instructors have to face lots of repetitive questions. To mitigate these issues, we propose a question answering system based on large language model with retrieval augmented generation (RAG) method. This work focuses on designing a question answering system with open source Large Language Model (LLM) and fine-tuning it on the relevant course dataset. To further improve the performance, we use a local knowledge base and applied RAG method to retrieve relevant documents relevant to students' queries, where the local knowledge base contains all the course content. To mitigate the hallucination of LLMs, We also integrate it with multi chain-of-thought reasoning to overcome the challenge of hallucination in LLMs. In this work, we experiment fine-tuned LLM with RAG method on the HotpotQA dataset. The experimental results demonstrate that the fine-tuned LLM with RAG method has a strong performance on question answering task. --- ### Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems Authors: Jiahuan Long, Tingsong Jiang, Hanqing Liu, Chao Ma, Weien Zhou, Yang Yang, Wen Yao Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.09829v3 Adversarial patches have emerged as a popular privacy-preserving approach for resisting AI-driven surveillance systems. However, their conspicuous appearance makes them difficult to deploy in real-world scenarios. In this paper, we propose a thermally activated adversarial wearable designed to ensure adaptability and effectiveness in complex real-world environments. The system integrates thermochromic dyes with flexible heating units to induce visually dynamic adversarial patterns on clothing surfaces. In its default state, the clothing appears as an ordinary black T-shirt. Upon heating via an embedded thermal unit, hidden adversarial patterns on the fabric are activated, allowing the wearer to effectively evade detection across both visible and infrared modalities. Physical experiments demonstrate that the adversarial wearable achieves rapid texture activation within 50 seconds and maintains an adversarial success rate above 80\% across diverse real-world surveillance environments. This work demonstrates a new pathway toward physically grounded, user-controllable anti-AI systems, highlighting the growing importance of proactive adversarial techniques for privacy protection in the age of ubiquitous AI surveillance. --- ### SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data Authors: Mingkun Yang, Ran Zhu, Qing Wang, Jie Yang Published: 2025-11-13 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.09828v2 Split Federated Learning is a system-efficient federated learning paradigm that leverages the rich computing resources at a central server to train model partitions. Data heterogeneity across silos, however, presents a major challenge undermining the convergence speed and accuracy of the global model. This paper introduces Step-wise Momentum Fusion (SMoFi), an effective and lightweight framework that counteracts gradient divergence arising from data heterogeneity by synchronizing the momentum buffers across server-side optimizers. To control gradient divergence over the training process, we design a staleness-aware alignment mechanism that imposes constraints on gradient updates of the server-side submodel at each optimization step. Extensive validations on multiple real-world datasets show that SMoFi consistently improves global model accuracy (up to 7.1%) and convergence speed (up to 10.25$\times$). Furthermore, SMoFi has a greater impact with more clients involved and deeper learning models, making it particularly suitable for model training in resource-constrained contexts. --- ### AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting Authors: Aymen Mir, Jian Wang, Riza Alp Guler, Chuan Guo, Gerard Pons-Moll, Bing Zhou Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09827v2 We present a novel framework for animating humans in 3D scenes using 3D Gaussian Splatting (3DGS), a neural scene representation that has recently achieved state-of-the-art photorealistic results for novel-view synthesis but remains under-explored for human-scene animation and interaction. Unlike existing animation pipelines that use meshes or point clouds as the underlying 3D representation, our approach introduces the use of 3DGS as the 3D representation for animating humans in scenes. By representing humans and scenes as Gaussians, our approach allows geometry-consistent free-viewpoint rendering of humans interacting with 3D scenes. Our key insight is that rendering can be decoupled from motion synthesis, and each sub-problem can be addressed independently without the need for paired human-scene data. Central to our method is a Gaussian-aligned motion module that synthesizes motion without explicit scene geometry, using opacity-based cues and projected Gaussian structures to guide human placement and pose alignment. To ensure natural interactions, we further propose a human-scene Gaussian refinement optimization that enforces realistic contact and navigation. We evaluate our approach on scenes from Scannet++ and the SuperSplat library, and on avatars reconstructed from sparse and dense multi-view human capture. Finally, we demonstrate that our framework enables novel applications such as geometry-consistent free-viewpoint rendering of edited monocular RGB videos with newly animated humans, showcasing the unique advantages of 3DGS for monocular video-based human animation. To assess the full quality of our results, we encourage readers to view the supplementary material available at https://miraymen.github.io/aha/ . --- ### Transforming User Defined Criteria into Explainable Indicators with an Integrated LLM AHP System Authors: Geonwoo Bang, Dongho Kim, Moohong Min Published: 2025-11-12 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.05267v1 Evaluating complex texts across domains requires converting user defined criteria into quantitative, explainable indicators, which is a persistent challenge in search and recommendation systems. Single prompt LLM evaluations suffer from complexity and latency issues, while criterion specific decomposition approaches rely on naive averaging or opaque black-box aggregation methods. We present an interpretable aggregation framework combining LLM scoring with the Analytic Hierarchy Process. Our method generates criterion specific scores via LLM as judge, measures discriminative power using Jensen Shannon distance, and derives statistically grounded weights through AHP pairwise comparison matrices. Experiments on Amazon review quality assessment and depression related text scoring demonstrate that our approach achieves high explainability and operational efficiency while maintaining comparable predictive power, making it suitable for real time latency sensitive web services. --- ### Refined Bayesian Optimization for Efficient Beam Alignment in Intelligent Indoor Wireless Environments Authors: Parth Ashokbhai Shiroya, Amod Ashtekar, Swarnagowri Shashidhar, Mohammed E. Eltayeb Published: 2025-11-12 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2512.00036v2 Future intelligent indoor wireless environments require fast and reliable beam alignment to sustain high-throughput links under mobility and blockage. Exhaustive beam training achieves optimal performance but is prohibitively costly. In indoor settings, dense scatterers and transceiver hardware imperfections introduce multipath and sidelobe leakage, producing measurable power across multiple angles and reducing the effectiveness of outdoor-oriented alignment algorithms. This paper presents a Refined Bayesian Optimization (R-BO) framework that exploits the inherent structure of mmWave transceiver patterns, where received power gradually increases as the transmit and receive beams converge toward the optimum. R-BO integrates a Gaussian Process (GP) surrogate with a Matern kernel and an Expected Improvement (EI) acquisition function, followed by a localized refinement around the predicted optimum. The GP hyperparameters are re-optimized online to adapt to irregular variations in the measured angular power field caused by reflections and sidelobe leakage. Experiments across 43 receiver positions in an indoor laboratory demonstrate 97.7% beam-alignment accuracy within 10 degrees, less than 0.3 dB average loss, and an 88% reduction in probing overhead compared to exhaustive search. These results establish R-BO as an efficient and adaptive beam-alignment solution for real-time intelligent indoor wireless environments. --- ### TIP and Polish: Text-Image-Prototype Guided Multi-Modal Generation via Commonality-Discrepancy Modeling and Refinement Authors: Zhiyong Ma, Jiahao Chen, Qingyuan Chuai, Zhengping Li Published: 2025-11-12 Categories: cs.MM, cs.AI arXiv: https://arxiv.org/abs/2511.21698v1 Multi-modal generation struggles to ensure thematic coherence and style consistency. Semantically, existing methods suffer from cross-modal mismatch and lack explicit modeling of commonality and discrepancy. Methods that rely on fine-grained training fail to balance semantic precision with writing style consistency. These shortcomings lead to suboptimal generation quality. To tackle these issues, we propose \textbf{\textit{TIPPo}}, a simple yet effective framework with explicit input modeling and comprehensive optimization objectives. It extracts the input text and images via multi-modal encoder and adapters, then measures the visual prototype. \textbf{T}extual, \textbf{I}mage, and \textbf{P}rototype signals are then fed to our proposed Dual Alignment Attention and Difference Operator modules before language model decoding. The proposed \textbf{Po}lishPPO reinforces the style consistency, while the unsupervised contrastive learning during SFT mitigates inter-sample representation collapse. Experimental results demonstrate the promising performance of \textbf{\textit{TIPPo}} in automatic evaluation and LLM-based criteria for creativity and semantic consistency. --- ### A centroid based framework for text classification in itsm environments Authors: Hossein Mohanna, Ali Ait-Bachir Published: 2025-11-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.20667v1 Text classification with hierarchical taxonomies is a fundamental requirement in IT Service Management (ITSM) systems, where support tickets must be categorized into tree-structured taxonomies. We present a dual-embedding centroid-based classification framework that maintains separate semantic and lexical centroid representations per category, combining them through reciprocal rank fusion at inference time. The framework achieves performance competitive with Support Vector Machines (hierarchical F1: 0.731 vs 0.727) while providing interpretability through centroid representations. Evaluated on 8,968 ITSM tickets across 123 categories, this method achieves 5.9 times faster training and up to 152 times faster incremental updates. With 8.6-8.8 times speedup across batch sizes (100-1000 samples) when excluding embedding computation. These results make the method suitable for production ITSM environments prioritizing interpretability and operational efficiency. --- ### On the Structural and Statistical Flaws of the Exponential-Trigonometric Optimizer Authors: Ngaiming Kwok Published: 2025-11-12 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.17557v1 The proliferation of metaphor-based metaheuristics has often been accompanied by issues of symbolic inflation, benchmarking opacity, and statistical misuse. This study presents a diagnostic critique of the recently proposed Exponential Trigonometric Optimizer (ETO), exposing fundamental flaws in its algorithmic structure and the statistical reporting of its performance. Through a stripped mathematical reconstruction, we identify inert symbolic constructs, ill-defined recurrence schedules, and ineffective update mechanisms that collectively undermine the algorithm's purported balance and effectiveness. A principled benchmarking comparison against nine established metaheuristics on the CEC 2017 and 2021 suites reveals that ETO's performance claims are inflated. While it demonstrates mid-tier competitiveness, it consistently fails against top-tier algorithms, especially under high-dimensional and shift-rotated landscapes. Our statistical framework, employing rank-based non-parametric tests and effect size diagnostics, quantifies these limitations and highlights ETO's structural fragility and lack of scalability. The paper concludes by advocating for a reformist framework in metaheuristic research, emphasizing symbolic hygiene, operator attribution, and statistical transparency to mitigate misleading narratives and foster a more robust and reproducible optimization literature. --- ### Further Commentary on the Sooty Tern Optimization Algorithm and Tunicate Swarm Algorithm Authors: Ngaiming Kwok Published: 2025-11-12 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.17556v1 In the article (Kudela, 2022), experimental demonstrations indicated that two Bio-/Nature inspired optimization algorithms (BNIOAs), Sooty Tern Optimization Algorithm (STOA) and Tunicate Swarm Algorithm (TSA), exhibit a zero-bias, leading to the conclusion that the claims made in the original papers were overstated. In this work, we extend the analysis by investigating the source of this bias from a probabilistic perspective. Our findings suggest that operations involving exponentiation, trigonometric functions, and divisions between random numbers are the primary causes of design flaws. These operations result in probability density distributions with a noticeable shift toward zero. Therefore, the application of these two algorithms should be approached with due caution. --- ### Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward Authors: Guansu Wang, Peijie Sun Published: 2025-11-12 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2511.17555v1 Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform regression over entire utterances, while failures usually occur in a few problematic words. We observe that encoder-decoder ASR models (e.g., Whisper) surface word-level mismatches between speech and text via cross-attention, providing a fine-grained reward signal. Building on this, we introduce Word-level TTS Alignment by ASR-driven Attentive Reward (W3AR). Without explicit reward annotations, W3AR uses attention from a pre-trained ASR model to drive finer-grained alignment and optimization of sequences predicted by a TTS model. Experiments show that W3AR improves the quality of existing TTS systems and strengthens zero-shot robustness on unseen speakers. More broadly, our results suggest a simple recipe for generative modeling: understanding models can act as evaluators, delivering informative, fine-grained feedback for optimization. --- ### Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health Authors: Sumon Kanti Dey, Manvi S, Zeel Mehta, Meet Shah, Unnati Agrawal, Suhani Jalota, Azra Ismail Published: 2025-11-12 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2511.17554v2 Large Language Models (LLMs) have been positioned as having the potential to expand access to health information in the Global South, yet their evaluation remains heavily dependent on benchmarks designed around Western norms. We present insights from a preliminary benchmarking exercise with a chatbot for sexual and reproductive health (SRH) for an underserved community in India. We evaluated using HealthBench, a benchmark for conversational health models by OpenAI. We extracted 637 SRH queries from the dataset and evaluated on the 330 single-turn conversations. Responses were evaluated using HealthBench's rubric-based automated grader, which rated responses consistently low. However, qualitative analysis by trained annotators and public health experts revealed that many responses were actually culturally appropriate and medically accurate. We highlight recurring issues, particularly a Western bias, such as for legal framing and norms (e.g., breastfeeding in public), diet assumptions (e.g., fish safe to eat during pregnancy), and costs (e.g., insurance models). Our findings demonstrate the limitations of current benchmarks in capturing the effectiveness of systems built for different cultural and healthcare contexts. We argue for the development of culturally adaptive evaluation frameworks that meet quality standards while recognizing needs of diverse populations. --- ### Practical Machine Learning for Aphasic Discourse Analysis Authors: Jason M. Pittman, Anton Phillips, Yesenia Medina-Santos, Brielle C. Stark Published: 2025-11-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17553v1 Analyzing spoken discourse is a valid means of quantifying language ability in persons with aphasia. There are many ways to quantify discourse, one common way being to evaluate the informativeness of the discourse. That is, given the total number of words produced, how many of those are context-relevant and accurate. This type of analysis is called Correct Information Unit (CIU) analysis and is one of the most prevalent discourse analyses used by speech-language pathologists (SLPs). Despite this, CIU analysis in the clinic remains limited due to the manual labor needed by SLPs to code and analyze collected speech. Recent advances in machine learning (ML) seek to augment such labor by automating modeling of propositional, macrostructural, pragmatic, and multimodal dimensions of discourse. To that end, this study evaluated five ML models for reliable identification of Correct Information Units (CIUs, Nicholas & Brookshire, 1993), during a picture description task. The five supervised ML models were trained using randomly selected human-coded transcripts and accompanying words and CIUs from persons with aphasia. The baseline model training produced a high accuracy across transcripts for word vs non-word, with all models achieving near perfect performance (0.995) with high AUC range (0.914 min, 0.995 max). In contrast, CIU vs non-CIU showed a greater variability, with the k-nearest neighbor (k-NN) model the highest accuracy (0.824) and second highest AUC (0.787). These findings indicate that while the supervised ML models can distinguish word from not word, identifying CIUs is challenging. --- ### How Well Do LLMs Understand Tunisian Arabic? Authors: Mohamed Mahdi Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.16683v1 Large Language Models (LLMs) are the engines driving today's AI agents. The better these models understand human languages, the more natural and user-friendly the interaction with AI becomes, from everyday devices like computers and smartwatches to any tool that can act intelligently. Yet, the ability of industrial-scale LLMs to comprehend low-resource languages, such as Tunisian Arabic (Tunizi), is often overlooked. This neglect risks excluding millions of Tunisians from fully interacting with AI in their own language, pushing them toward French or English. Such a shift not only threatens the preservation of the Tunisian dialect but may also create challenges for literacy and influence younger generations to favor foreign languages. In this study, we introduce a novel dataset containing parallel Tunizi, standard Tunisian Arabic, and English translations, along with sentiment labels. We benchmark several popular LLMs on three tasks: transliteration, translation, and sentiment analysis. Our results reveal significant differences between models, highlighting both their strengths and limitations in understanding and processing Tunisian dialects. By quantifying these gaps, this work underscores the importance of including low-resource languages in the next generation of AI systems, ensuring technology remains accessible, inclusive, and culturally grounded. --- ### Bench360: Benchmarking Local LLM Inference from 360 Degrees Authors: Linus Stuhlmann, Mauricio Fadel Argerich, Jonathan Fürst Published: 2025-11-12 Categories: cs.CL, cs.AI, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2511.16682v2 Running LLMs locally has become increasingly common, but users face a complex design space across models, quantization levels, inference engines, and serving scenarios. Existing inference benchmarks are fragmented and focus on isolated goals, offering little guidance for practical deployments. We present Bench360, a framework for evaluating local LLM inference across tasks, usage patterns, and system metrics in one place. Bench360 supports custom tasks, integrates multiple inference engines and quantization formats, and reports both task quality and system behavior (latency, throughput, energy, startup time). We demonstrate it on four NLP tasks across three GPUs and four engines, showing how design choices shape efficiency and output quality. Results confirm that tradeoffs are substantial and configuration choices depend on specific workloads and constraints. There is no universal best option, underscoring the need for comprehensive, deployment-oriented benchmarks. --- ### SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases Authors: Dong Liu, Yanxuan Yu Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.16681v3 Vector databases (VecDBs) are increasingly deployed in retrieval-augmented generation (RAG) pipelines where query processing and document ingestion occur concurrently. The index layer needs to provide low-latency search while incorporating new vectors without frequent global rebuilding. Existing VecDB pipelines typically operate within a uniform representation regime, despite substantial variation in the semantic granularity required across queries. This motivates an index design that supports incremental updates while adapting retrieval depth to query distribution and complexity. We propose \textbf{Semantic Pyramid Indexing (SPI)}, a VecDB-layer indexing framework that organizes embeddings into $L$ semantically aligned resolution levels and selects retrieval depth per query via a lightweight uncertainty-aware controller. SPI supports progressive coarse-to-fine ANN search, level-wise streaming insertion without global rebuilds, and distributed execution through LSH partitioning with asynchronous gRPC coordination. Unlike hierarchical ANN structures with fixed traversal rules (e.g., SPANN), SPI adapts resolution at query time while remaining compatible with FAISS and Qdrant backends. On MS MARCO and Natural Questions, SPI achieves competitive Recall@10 with lower latency under the same dense encoder family, yielding a \textbf{1.4--2.3$\times$} average retrieval latency reduction under fixed Recall@10 targets relative to comparable approximate-ANN baselines. A prototype scaling study up to 8 nodes shows $6.2\times$ throughput scaling (${\approx}73\%$ efficiency); the 16-node configuration is included for completeness but shows diminishing efficiency. We provide a top-$K$ stability guarantee: queries with sufficient retrieval margin return an identical top-$K$ set at a shallower level. Code and configurations are available at https://github.com/FastLM/SPI_VecDB. ---