# Research Papers — 2025-11 · bundle page 187 of 197 > Full-text markdown of papers #9301–9350 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/187 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/186.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/188.md) ### PRBench: A Standardized Probabilistic Robustness Benchmark Authors: Yi Zhang, Zheng Wang, Zhen Chen, Wenjie Ruan, Qing Guo, Siddartha Khastgir, Carsten Maple, Xingyu Zhao Published: 2025-11-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.01724v3 Deep learning models are notoriously vulnerable to imperceptible perturbations. Most existing research centers on adversarial robustness (AR), which evaluates models under worst-case scenarios by examining the existence of deterministic adversarial examples (AEs). In contrast, probabilistic robustness (PR) adopts a statistical perspective, measuring the probability that predictions remain correct under stochastic perturbations. While PR is widely regarded as a practical complement to AR, dedicated training methods for improving PR are still relatively underexplored, albeit with emerging progress. Among the few PR-targeted training methods, we identify three limitations: i non-comparable evaluation protocols; ii limited comparisons to strong AT baselines despite anecdotal PR gains from AT; and iii no unified framework to compare the generalization of these methods. Thus, we introduce PRBench, the first benchmark dedicated to evaluating improvements in PR achieved by different robustness training methods. PRBench empirically compares most common AT and PR-targeted training methods using a comprehensive set of metrics, including clean accuracy, PR and AR performance, training efficiency, and generalization error (GE). We also provide theoretical analysis on the GE of PR performance across different training methods. Main findings revealed by PRBench include: AT methods are more versatile than PR-targeted training methods in terms of improving both AR and PR performance across diverse hyperparameter settings, while PR-targeted training methods consistently yield lower GE and higher clean accuracy. A leaderboard comprising 229 trained models across 7 datasets and 10 model architectures is publicly available at https://wellzline.github.io/PRBenchLeaderboard/. --- ### Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue Authors: Mahammad Nuriyev Published: 2025-11-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.01720v1 We present a multi-expert system for creating Non-Player Characters (NPCs) capable of both natural dialogue and contextual action execution in interactive environments. Using Qwen3 as the base model and Low-Rank Adaptation (LoRA) adapters, we instantiate three specialists: tool calling, tool-response interpretation, and direct dialogue. Our system comfortably meets the computational efficiency requirements, delivering fast responses and maintaining modest resource usage on L40S GPUs. In the Commonsense Persona-Grounded Dialogue Challenge 2025, our method ranked second overall. Code available at: https://github.com/MahammadNuriyev62/CPDC-challenge-2025-solution/ --- ### Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process Authors: Jiayi Chen, Wenxuan Song, Pengxiang Ding, Ziyang Zhou, Han Zhao, Feilong Tang, Donglin Wang, Haoang Li Published: 2025-11-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.01718v2 Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4$\times$ faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/. --- ### SemBench: A Benchmark for Semantic Query Processing Engines Authors: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel et al. Published: 2025-11-03 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2511.01716v2 We present a benchmark targeting a novel class of systems: semantic query processing engines. Those systems rely inherently on generative and reasoning capabilities of state-of-the-art large language models (LLMs). They extend SQL with semantic operators, configured by natural language instructions, that are evaluated via LLMs and enable users to perform various operations on multimodal data. Our benchmark introduces diversity across three key dimensions: scenarios, modalities, and operators. Included are scenarios ranging from movie review analysis to car damage detection. Within these scenarios, we cover different data modalities, including images, audio, and text. Finally, the queries involve a diverse set of operators, including semantic filters, joins, mappings, ranking, and classification operators. We evaluated our benchmark on three academic systems (LOTUS, Palimpzest, and ThalamusDB) and one industrial system, Google BigQuery. Although these results reflect a snapshot of systems under continuous development, our study offers crucial insights into their current strengths and weaknesses, illuminating promising directions for future research. --- ### Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement Authors: Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein Published: 2025-11-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.01706v3 Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions by drawing on external Context Knowledge (CK) and Parametric Knowledge (PK). Understanding the interaction between these sources is key to assessing NLE grounding, yet these dynamics remain underexplored. Prior work has largely focused on i) single-step generation and ii) modeled PK--CK interaction as a binary choice within a rank-1 subspace. This approach overlooks richer interactions and how they unfold over longer generations, such as complementary or supportive knowledge. We propose a novel rank-2 projection subspace that disentangles PK and CK contributions more accurately and use it for the first multi-step analysis of knowledge interactions across longer NLE sequences. Experiments across four QA datasets and three open-weight LLMs demonstrate that rank-1 subspaces struggle to represent diverse interactions, whereas our rank-2 formulation captures them effectively, highlighting PK alignment for supportive interactions and CK alignment for conflicting ones. Our multi-step analysis reveals that hallucinated generations exhibit strong alignment with the PK direction, though context-faithful generations maintain a more balanced alignment between PK and CK. --- ### Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond Authors: Xin Qiao, Matteo Poggi, Xing Wei, Pengchao Deng, Yanhui Zhou, Stefano Mattoccia Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01704v1 Under-display ToF imaging aims to achieve accurate depth sensing through a ToF camera placed beneath a screen panel. However, transparent OLED (TOLED) layers introduce severe degradations-such as signal attenuation, multi-path interference (MPI), and temporal noise-that significantly compromise depth quality. To alleviate this drawback, we propose Learnable Fractional Reaction-Diffusion Dynamics (LFRD2), a hybrid framework that combines the expressive power of neural networks with the interpretability of physical modeling. Specifically, we implement a time-fractional reaction-diffusion module that enables iterative depth refinement with dynamically generated differential orders, capturing long-term dependencies. In addition, we introduce an efficient continuous convolution operator via coefficient prediction and repeated differentiation to further improve restoration quality. Experiments on four benchmark datasets demonstrate the effectiveness of our approach. The code is publicly available at https://github.com/wudiqx106/LFRD2. --- ### Solution Space Topology Guides CMTS Search Authors: Mirco A. Mannucci Published: 2025-11-03 Categories: cs.CE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.01701v1 A fundamental question in search-guided AI: what topology should guide Monte Carlo Tree Search (MCTS) in puzzle solving? Prior work applied topological features to guide MCTS in ARC-style tasks using grid topology -- the Laplacian spectral properties of cell connectivity -- and found no benefit. We identify the root cause: grid topology is constant across all instances. We propose measuring \emph{solution space topology} instead: the structure of valid color assignments constrained by detected pattern rules. We build this via compatibility graphs where nodes are $(cell, color)$ pairs and edges represent compatible assignments under pattern constraints. Our method: (1) detect pattern rules automatically with 100\% accuracy on 5 types, (2) construct compatibility graphs encoding solution space structure, (3) extract topological features (algebraic connectivity, rigidity, color structure) that vary with task difficulty, (4) integrate these features into MCTS node selection via sibling-normalized scores. We provide formal definitions, a rigorous selection formula, and comprehensive ablations showing that algebraic connectivity is the dominant signal. The work demonstrates that topology matters for search -- but only the \emph{right} topology. For puzzle solving, this is solution space structure, not problem space structure. --- ### Progressive Translation of H&E to IHC with Enhanced Structural Fidelity Authors: Yuhang Kang, Ziyu Su, Tianyang Wang, Zaibo Li, Wei Chen, Muhammad Khalid Khan Niazi Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01698v1 Compared to hematoxylin-eosin (H&E) staining, immunohistochemistry (IHC) not only maintains the structural features of tissue samples, but also provides high-resolution protein localization, which is essential for aiding in pathology diagnosis. Despite its diagnostic value, IHC remains a costly and labor-intensive technique. Its limited scalability and constraints in multiplexing further hinder widespread adoption, especially in resource-limited settings. Consequently, researchers are increasingly exploring computational stain translation techniques to synthesize IHC-equivalent images from H&E-stained slides, aiming to extract protein-level information more efficiently and cost-effectively. However, most existing stain translation techniques rely on a linearly weighted summation of multiple loss terms within a single objective function, strategy that often overlooks the interdepedence among these components-resulting in suboptimal image quality and an inability to simultaneously preserve structural authenticity and color fidelity. To address this limitation, we propose a novel network architecture that follows a progressive structure, incorporating color and cell border generation logic, which enables each visual aspect to be optimized in a stage-wise and decoupled manner. To validate the effectiveness of our proposed network architecture, we build upon the Adaptive Supervised PatchNCE (ASP) framework as our baseline. We introduce additional loss functions based on 3,3'-diaminobenzidine (DAB) chromogen concentration and image gradient, enhancing color fidelity and cell boundary clarity in the generated IHC images. By reconstructing the generation pipeline using our structure-color-cell boundary progressive mechanism, experiments on HER2 and ER datasets demonstrated that the model significantly improved visual quality and achieved finer structural details. --- ### Collaborative Large Language Model Inference via Resource-Aware Parallel Speculative Decoding Authors: Jungyeon Koh, Hyun Jong Yang Published: 2025-11-03 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.01695v4 The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by partitioning token generation between a lightweight draft model on mobile devices and a powerful target model on edge servers, but suffers from communication overhead and asynchronous delays. This paper is the first to propose a unified framework that jointly optimizes user association and resource allocation (UARA) to support efficient parallel speculative decoding. We solve the UARA problem using a multi-agent deep reinforcement learning algorithm. To evaluate our approach under realistic conditions, we conduct experiments using the Sionna simulator. Results show that our method achieves up to 28.0% and an average of 23.7% reduction in end-to-end latency without compromising inference accuracy, enabling scalable and low-latency LLM services in MEC systems. --- ### Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering Authors: Hossein Abdi, Mingfei Sun, Wei Pan Published: 2025-11-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.01694v1 Vision-language pre-trained models, such as CLIP, have established new benchmarks in multimodal data mining. In such models, few-shot fine-tuning is a major challenge to achieve optimal performance on both in-distribution (ID) and out-of-distribution (OOD) datasets, especially when labeled data is scarce. Most existing fine-tuning approaches rely on first-order gradient-based optimizers, which typically suffer from slow convergence, sensitivity to step-size hyperparameters, and poor generalization in OOD settings. In contrast, second-order methods utilize local curvature information of the loss landscape to adjust the update step size. This is particularly beneficial for CLIP models, whose non-convex loss functions often contain sharp critical points. In such cases, natural gradient direction can offer more substantial and efficient per-iteration updates when fine-tuning with limited data. Natural Gradient Descent (NGD) is obtained by preconditioning the standard gradient with the inverse Fisher Information Matrix (FIM), which is computationally expensive for large models. To address this, we propose a Bayesian approximation of NGD using a Kalman filter for CLIP models. Our method combines the benefits of second-order optimization with Bayesian inference, which enhances generalization while providing uncertainty quantification. Extensive experiments conducted on diverse image classification datasets demonstrate that our algorithm consistently achieves superior--or comparable--ID performance and improved OOD robustness compared to state-of-the-art baselines. To the best of our knowledge, this work represents the first successful application of Kalman filtering to fine-tuning CLIP-based models, which enables more robust and efficient learning in vision-language tasks. --- ### Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI Authors: Sharan Maiya, Henning Bartsch, Nathan Lambert, Evan Hubinger Published: 2025-11-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.01689v1 The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These all affect interaction quality, perceived intelligence, and alignment with both developer and user intentions. The shaping of this persona, known as character training, is a critical component of industry post-training, yet remains effectively unstudied in the academic literature. We introduce the first open implementation of character training, leveraging Constitutional AI and a new data pipeline using synthetic introspective data to shape the assistant persona in a more effective and controlled manner than alternatives such as constraining system prompts or activation steering. Specifically, we fine-tune three popular open-weights models using 11 example personas, such as humorous, deeply caring, or even malevolent. To track the effects of our approach, we introduce a method which analyzes revealed preferences, uncovering clear and holistic changes in character. We find these changes are more robust to adversarial prompting than the above two alternatives, while also leading to more coherent and realistic generations. Finally, we demonstrate this fine-tuning has little to no effect on general capabilities as measured by common benchmarks. We describe and open-source our full post-training method, the implementation of which can be found at https://github.com/maiush/OpenCharacterTraining. --- ### Student Engagement in AI Assisted Complex Problem Solving: A Pilot Study of Human AI Rubik's Cube Collaboration Authors: Kirk Vanacore, Jaclyn Ocumpaugh, Forest Agostinelli, Dezhi Wu, Sai Vuruma, Matt Irvin Published: 2025-11-03 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.01683v1 Games and puzzles play important pedagogical roles in STEM learning. New AI algorithms that can solve complex problems offer opportunities for scaffolded instruction in puzzle solving. This paper presents the ALLURE system, which uses an AI algorithm (DeepCubeA) to guide students in solving a common first step of the Rubik's Cube (i.e., the white cross). Using data from a pilot study we present preliminary findings about students' behaviors in the system, how these behaviors are associated with STEM skills - including spatial reasoning, critical thinking and algorithmic thinking. We discuss how data from ALLURE can be used in future educational data mining to understand how students benefit from AI assistance and collaboration when solving complex problems. --- ### Interpretable Discovery from Unstructured Data: A High-Dimensional Approach Authors: Jacob Carlson Published: 2025-11-03 Categories: econ.EM, cs.LG arXiv: https://arxiv.org/abs/2511.01680v5 We propose an automatic, general-purpose framework for making discoveries from unstructured data (e.g., text data from open-ended surveys of economic beliefs). The framework leverages recent methods from the literature on AI interpretability to transform unstructured datasets into high-dimensional, structured datasets of interpretable concept measurements; specifies concept-level parameters and null hypotheses based on this transformed dataset; tests these hypotheses using algorithms validated by new results in high-dimensional multiple testing, producing a selected set ("discoveries"); and both generates and evaluates human-interpretable natural language descriptions of these discoveries. The proposed framework has few researcher degrees of freedom, is robust to data snooping, mitigates under-exploration, and facilitates fast and inexpensive sensitivity analysis and replication. We revisit applications to recent descriptive and causal analyses of unstructured data in empirical economics, and find this framework is able to automatically replicate existing discoveries, add nuance to others, and make entirely new discoveries as well. --- ### UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback Authors: Ropeway Liu, Hangjie Yuan, Bo Dong, Jiazheng Xing, Jinwang Wang, Rui Zhao, Yan Xing, Weihua Chen, Fan Wang Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01678v1 Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results, such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with UniLumos, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose LumosBench, a disentangled attribute-level benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting. Code is available at https://github.com/alibaba-damo-academy/Lumos-Custom. --- ### Spin-Adapted Neural Network Wavefunctions in Real Space Authors: Ruichen Li, Yuzhi Liu, Du Jiang, Yixiao Chen, Xuelan Wen, Wenrui Li, Di He, Liwei Wang, Ji Chen, Weiluo Ren Published: 2025-11-03 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2511.01671v1 Spin plays a fundamental role in understanding electronic structure, yet many real-space wavefunction methods fail to adequately consider it. We introduce the Spin-Adapted Antisymmetrization Method (SAAM), a general procedure that enforces exact total spin symmetry for antisymmetric many-electron wavefunctions in real space. In the context of neural network-based quantum Monte Carlo (NNQMC), SAAM leverages the expressiveness of deep neural networks to capture electron correlation while enforcing exact spin adaptation via group representation theory. This framework provides a principled route to embed physical priors into otherwise black-box neural network wavefunctions, yielding a compact representation of correlated system with neural network orbitals. Compared with existing treatments of spin in NNQMC, SAAM is more accurate and efficient, achieving exact spin purity without any additional tunable hyperparameters. To demonstrate its effectiveness, we apply SAAM to study the spin ladder of iron-sulfur clusters, a long-standing challenge for many-body methods due to their dense spectrum of nearly degenerate spin states. Our results reveal accurate resolution of low-lying spin states and spin gaps in (Fe$_2$S$_2$) and (Fe$_4$S$_4$) clusters, offering new insights into their electronic structures. In sum, these findings establish SAAM as a robust, hyperparameter-free standard for spin-adapted NNQMC, particularly for strongly correlated systems. --- ### SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia Authors: Chaoqun Liu, Mahani Aljunied, Guizhen Chen, Hou Pong Chan, Weiwen Xu, Yu Rong, Wenxuan Zhang Published: 2025-11-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.01670v1 We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongside English (en) and Chinese (zh). Trained on a large-scale audio corpus, SeaLLMs-Audio exhibits strong performance across diverse audio-centric tasks, spanning fine-grained audio understanding and voice-based interaction. Its key features include: 1) Multilingual: the model primarily supports 5 languages, namely Indonesian, Thai, Vietnamese, English, and Chinese; 2) Multimodal: the model accepts flexible input modalities, including audio only, text only, as well as audio with text; 3) Multi-task: the model supports a wide range of tasks, including audio analysis tasks such as Audio Captioning, Automatic Speech Recognition, Speech-to-Text Translation, Speech Emotion Recognition, Speech Question Answering, and Speech Summarization. It also enables voice-based dialogue, including answering factual, mathematical, and general knowledge queries. As a significant step towards advancing audio LLMs in Southeast Asia, we expect SeaLLMs-Audio to benefit both the regional research community and industry. To automate LALM evaluation for Southeast Asia, we introduce SeaBench-Audio, a benchmark spanning multiple tasks. Experiments show that SeaLLMs-Audio achieves competitive performance compared with other LALMs on SEA languages. --- ### Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics Authors: Yueqing Xi, Yifan Bai, Huasen Luo, Weiliang Wen, Hui Liu, Haoliang Li Published: 2025-11-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.01668v2 As artificial intelligence permeates judicial forensics, ensuring the veracity and traceability of legal question answering (QA) has become critical. Conventional large language models (LLMs) are prone to hallucination, risking misleading guidance in legal consultation, while static knowledge bases struggle to keep pace with frequently updated statutes and case law. We present a hybrid legal QA agent tailored for judicial settings that integrates retrieval-augmented generation (RAG) with multi-model ensembling to deliver reliable, auditable, and continuously updatable counsel. The system prioritizes retrieval over generation: when a trusted legal repository yields relevant evidence, answers are produced via RAG; otherwise, multiple LLMs generate candidates that are scored by a specialized selector, with the top-ranked answer returned. High-quality outputs then undergo human review before being written back to the repository, enabling dynamic knowledge evolution and provenance tracking. Experiments on the Law\_QA dataset show that our hybrid approach significantly outperforms both a single-model baseline and a vanilla RAG pipeline on F1, ROUGE-L, and an LLM-as-a-Judge metric. Ablations confirm the complementary contributions of retrieval prioritization, model ensembling, and the human-in-the-loop update mechanism. The proposed system demonstrably reduces hallucination while improving answer quality and legal compliance, advancing the practical landing of media forensics technologies in judicial scenarios. --- ### The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity Authors: Louis Bradshaw, Alexander Spangher, Stella Biderman, Simon Colton Published: 2025-11-03 Categories: cs.SD, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.01663v1 While generative models for music composition are increasingly capable, their adoption by musicians is hindered by text-prompting, an asynchronous workflow disconnected from the embodied, responsive nature of instrumental performance. To address this, we introduce Aria-Duet, an interactive system facilitating a real-time musical duet between a human pianist and Aria, a state-of-the-art generative model, using a Yamaha Disklavier as a shared physical interface. The framework enables a turn-taking collaboration: the user performs, signals a handover, and the model generates a coherent continuation performed acoustically on the piano. Beyond describing the technical architecture enabling this low-latency interaction, we analyze the system's output from a musicological perspective, finding the model can maintain stylistic semantics and develop coherent phrasal ideas, demonstrating that such embodied systems can engage in musically sophisticated dialogue and open a promising new path for human-AI co-creation. --- ### Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environments Authors: Congcong Chen, Xinyu Liu, Kaifeng Huang, Lifei Wei, Yang Shi Published: 2025-11-03 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2511.01654v1 Graph Neural Networks (GNNs) have marked significant impact in traffic state prediction, social recommendation, knowledge-aware question answering and so on. As more and more users move towards cloud computing, it has become a critical issue to unleash the power of GNNs while protecting the privacy in cloud environments. Specifically, the training data and inference data for GNNs need to be protected from being stolen by external adversaries. Meanwhile, the financial cost of cloud computing is another primary concern for users. Therefore, although existing studies have proposed privacy-preserving techniques for GNNs in cloud environments, their additional computational and communication overhead remain relatively high, causing high financial costs that limit their widespread adoption among users. To protect GNN privacy while lowering the additional financial costs, we introduce Panther, a cost-effective privacy-preserving framework for GNN training and inference services in cloud environments. Technically, Panther leverages four-party computation to asynchronously executing the secure array access protocol, and randomly pads the neighbor information of GNN nodes. We prove that Panther can protect privacy for both training and inference of GNN models. Our evaluation shows that Panther reduces the training and inference time by an average of 75.28% and 82.80%, respectively, and communication overhead by an average of 52.61% and 50.26% compared with the state-of-the-art, which is estimated to save an average of 55.05% and 59.00% in financial costs (based on on-demand pricing model) for the GNN training and inference process on Google Cloud Platform. --- ### EngTrace: A Symbolic Benchmark for Verifiable Process Supervision of Engineering Reasoning Authors: Ayesha Gull, Muhammad Usman Safder, Rania Elbadry, Fan Zhang, Veselin Stoyanov, Preslav Nakov, Zhuohan Xie Published: 2025-11-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.01650v3 Large Language Models (LLMs) are increasingly entering specialized, safety-critical engineering workflows governed by strict quantitative standards and immutable physical laws, making rigorous evaluation of their reasoning capabilities imperative. However, existing benchmarks such as MMLU, MATH, and HumanEval assess isolated cognitive skills, failing to capture the physically grounded reasoning central to engineering, where scientific principles, quantitative modeling, and practical constraints must converge. To enable verifiable process supervision in engineering, we introduce EngTrace, a symbolic benchmark built on 90 parameterized templates, each generating unique, contamination-resistant problem instances, spanning three major engineering branches, nine core domains, and 20 distinct areas, yielding 1,350 test cases that stress-test generalization across diverse physical scenarios. Moving beyond outcome matching, we introduce a verifiable two-stage evaluation framework that uses a tiered protocol to validate intermediate reasoning traces alongside final answers through automated procedural checks and a heterogeneous AI Tribunal. Our evaluation of 27 leading LLMs reveals a distinct trade-off between numeric precision and trace fidelity, identifying a complexity cliff where abstract mathematical pre-training fails to translate into the integrative reasoning required for advanced engineering tasks. --- ### Evaluating Cultural Knowledge Processing in Large Language Models: A Cognitive Benchmarking Framework Integrating Retrieval-Augmented Generation Authors: Hung-Shin Lee, Chen-Chi Chang, Ching-Yuan Chen, Yun-Hsiang Hsu Published: 2025-11-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.01649v1 This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge. The framework integrates Bloom's Taxonomy with Retrieval-Augmented Generation (RAG) to assess model performance across six hierarchical cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM-generated responses' semantic accuracy and cultural relevance. --- ### Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward Authors: Xiaogang Xu, Ruihang Chu, Jian Wang, Kun Zhou, Wenjie Shu, Harry Yang, Ser-Nam Lim, Hao Chen, Liang Lin Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01645v1 Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-based image restoration models is suboptimal, as the objective of restoration fundamentally differs from that of pure generation: it places greater emphasis on fidelity. In this paper, we investigate how to effectively integrate RL into diffusion-based restoration models. First, through extensive experiments with various reward functions, we find that an effective reward can be derived from an Image Quality Assessment (IQA) model, instead of intuitive ground-truth-based supervision, which has already been optimized during the Supervised Fine-Tuning (SFT) stage prior to RL. Moreover, our strategy focuses on using RL for challenging samples that are significantly distant from the ground truth, and our RL approach is innovatively implemented using MLLM-based IQA models to align distributions with high-quality images initially. As the samples approach the ground truth's distribution, RL is adaptively combined with SFT for more fine-grained alignment. This dynamic process is facilitated through an automatic weighting strategy that adjusts based on the relative difficulty of the training samples. Our strategy is plug-and-play that can be seamlessly applied to diffusion-based restoration models, boosting its performance across various restoration tasks. Extensive experiments across multiple benchmarks demonstrate the effectiveness of our proposed RL framework. --- ### A Graph-based RAG for Energy Efficiency Question Answering Authors: Riccardo Campi, Nicolò Oreste Pinciroli Vago, Mathyas Giudici, Pablo Barrachina Rodriguez-Guisado, Marco Brambilla, Piero Fraternali Published: 2025-11-03 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.01643v1 In this work, we investigate the use of Large Language Models (LLMs) within a graph-based Retrieval Augmented Generation (RAG) architecture for Energy Efficiency (EE) Question Answering. First, the system automatically extracts a Knowledge Graph (KG) from guidance and regulatory documents in the energy field. Then, the generated graph is navigated and reasoned upon to provide users with accurate answers in multiple languages. We implement a human-based validation using the RAGAs framework properties, a validation dataset comprising 101 question-answer pairs, and domain experts. Results confirm the potential of this architecture and identify its strengths and weaknesses. Validation results show how the system correctly answers in about three out of four of the cases (75.2 +- 2.7%), with higher results on questions related to more general EE answers (up to 81.0 +- 4.1%), and featuring promising multilingual abilities (4.4% accuracy loss due to translation). --- ### Cross-Treatment Effect Estimation for Multi-Category, Multi-Valued Causal Inference via Dynamic Neural Masking Authors: Xiaopeng Ke, Yihan Yu, Ruyue Zhang, Zhishuo Zhou, Fangzhou Shi, Chang Men, Zhengdan Zhu Published: 2025-11-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.01641v1 Counterfactual causal inference faces significant challenges when extended to multi-category, multi-valued treatments, where complex cross-effects between heterogeneous interventions are difficult to model. Existing methodologies remain constrained to binary or single-type treatments and suffer from restrictive assumptions, limited scalability, and inadequate evaluation frameworks for complex intervention scenarios. We present XTNet, a novel network architecture for multi-category, multi-valued treatment effect estimation. Our approach introduces a cross-effect estimation module with dynamic masking mechanisms to capture treatment interactions without restrictive structural assumptions. The architecture employs a decomposition strategy separating basic effects from cross-treatment interactions, enabling efficient modeling of combinatorial treatment spaces. We also propose MCMV-AUCC, a suitable evaluation metric that accounts for treatment costs and interaction effects. Extensive experiments on synthetic and real-world datasets demonstrate that XTNet consistently outperforms state-of-the-art baselines in both ranking accuracy and effect estimation quality. The results of the real-world A/B test further confirm its effectiveness. --- ### IVGAE-TAMA-BO: A novel temporal dynamic variational graph model for link prediction in global food trade networks with momentum structural memory and Bayesian optimization Authors: Sicheng Wang, Shuhao Chen, Jingran Zhou, Chengyi Tu Published: 2025-11-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.01639v1 Global food trade plays a crucial role in ensuring food security and maintaining supply chain stability. However, its network structure evolves dynamically under the influence of geopolitical, economic, and environmental factors, making it challenging to model and predict future trade links. Effectively capturing temporal patterns in food trade networks is therefore essential for improving the accuracy and robustness of link prediction. This study introduces IVGAE-TAMA-BO, a novel dynamic graph neural network designed to model evolving trade structures and predict future links in global food trade networks. To the best of our knowledge, this is the first work to apply dynamic graph neural networks to this domain, significantly enhancing predictive performance. Building upon the original IVGAE framework, the proposed model incorporates a Trade-Aware Momentum Aggregator (TAMA) to capture the temporal evolution of trade networks, jointly modeling short-term fluctuations and long-term structural dependencies. A momentum-based structural memory mechanism further improves predictive stability and performance. In addition, Bayesian optimization is used to automatically tune key hyperparameters, enhancing generalization across diverse trade scenarios. Extensive experiments on five crop-specific datasets demonstrate that IVGAE-TAMA substantially outperforms the static IVGAE and other dynamic baselines by effectively modeling temporal dependencies, while Bayesian optimization further boosts performance in IVGAE-TAMA-BO. These results highlight the proposed framework as a robust and scalable solution for structural prediction in global trade networks, with strong potential for applications in food security monitoring and policy decision support. --- ### Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models Authors: Daniyal Ganiuly, Assel Smaiyl Published: 2025-11-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.01634v2 Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new class of attacks known as prompt injection. In these attacks, hidden or malicious instructions are inserted into user inputs or external content, causing the model to ignore its intended task or produce unsafe responses. This study proposes a unified framework for evaluating how resistant Large Language Models (LLMs) are to prompt injection attacks. The framework defines three complementary metrics such as the Resilience Degradation Index (RDI), Safety Compliance Coefficient (SCC), and Instructional Integrity Metric (IIM) to jointly measure robustness, safety, and semantic stability. We evaluated four instruction-tuned models (GPT-4, GPT-4o, LLaMA-3 8B Instruct, and Flan-T5-Large) on five common language tasks: question answering, summarization, translation, reasoning, and code generation. Results show that GPT-4 performs best overall, while open-weight models remain more vulnerable. The findings highlight that strong alignment and safety tuning are more important for resilience than model size alone. Results show that all models remain partially vulnerable, especially to indirect and direct-override attacks. GPT-4 achieved the best overall resilience (RDR = 9.8 %, SCR = 96.4 %), while open-source models exhibited higher performance degradation and lower safety scores. The findings demonstrate that alignment strength and safety tuning play a greater role in resilience than model size alone. The proposed framework offers a structured, reproducible approach for assessing model robustness and provides practical insights for improving LLM safety and reliability. --- ### Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving Authors: Chengying Huan, Ziheng Meng, Yongchao Liu, Zhengyi Yang, Yun Zhu, Yue Yun, Shipeng Li, Rong Gu, Xiabao Wu, Haitao Zhang, Chuntao Hong, Shaonan Ma et al. Published: 2025-11-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.01633v1 Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT system co-designed with an optimized LLM serving architecture. GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption. To scale inference, we introduce a Graph-CoT-aware LLM inference mechanism with graph-specific KV-cache management, priority-based eviction, and pipelined execution to improve serving efficiency. Experiments demonstrate that GLM improves answer accuracy by up to 38%, reduces token cost by up to 95.7%, lowers inference latency by 90.3%, and achieves up to 15.1x higher throughput compared to state-of-the-art Graph-CoT baselines, enabling efficient adoption for complex real-world reasoning at scale. --- ### Space as Time Through Neuron Position Learning Authors: Balázs Mészáros, James C. Knight, Danyal Akarca, Thomas Nowotny Published: 2025-11-03 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.01632v2 Biological neural networks exist in physical space where distance influences communication delays: a fundamental coupling between space and time absent in most artificial neural networks. While recent work has separately explored spatial embeddings and learnable synaptic delays in spiking neural networks, we unify these approaches through a novel neuron position learning algorithm where delays relate to the Euclidean distances between neurons. We derive gradients with respect to neuron positions and demonstrate that this biologically-motivated constraint acts as an inductive bias: networks trained on temporal classification tasks spontaneously self-organize into local, clustered topologies and a modular, efficiently wired structure emerges if connection costs are distance-dependent. Remarkably, we observe functional specialization aligned with spatial clustering without explicitly enforcing it. These findings lay the groundwork for networks in which space and time are intrinsically coupled, offering new avenues for mechanistic interpretability, biologically inspired modelling, and efficient implementations. --- ### Partial Trace-Class Bayesian Neural Networks Authors: Arran Carter, Torben Sell Published: 2025-11-03 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2511.01628v1 Bayesian neural networks (BNNs) allow rigorous uncertainty quantification in deep learning, but often come at a prohibitive computational cost. We propose three different innovative architectures of partial trace-class Bayesian neural networks (PaTraC BNNs) that enable uncertainty quantification comparable to standard BNNs but use significantly fewer Bayesian parameters. These PaTraC BNNs have computational and statistical advantages over standard Bayesian neural networks in terms of speed and memory requirements. Our proposed methodology therefore facilitates reliable, robust, and scalable uncertainty quantification in neural networks. The three architectures build on trace-class neural network priors which induce an ordering of the neural network parameters, and are thus a natural choice in our framework. In a numerical simulation study, we verify the claimed benefits, and further illustrate the performance of our proposed methodology on a real-world dataset. --- ### ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian Authors: Nikola Ljubešić, Peter Rupnik, Ivan Porupski, Taja Kuzman Pungeršek Published: 2025-11-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.01619v2 ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages - Croatian, Czech, Polish and Serbian - all together 6 thousand hours in size. The corpora were built in an automatic fashion from the ParlaMint transcripts and their corresponding metadata, which were aligned to the speech recordings of each corresponding parliament. In this release of the dataset, each of the corpora is significantly enriched with various automatic annotation layers. The textual modality of all four corpora has been enriched with linguistic annotations and sentiment predictions. Similar to that, their spoken modality has been automatically enriched with occurrences of filled pauses, the most frequent disfluency in typical speech. Two out of the four languages have been additionally enriched with detailed word- and grapheme-level alignments, and the automatic annotation of the position of primary stress in multisyllabic words. With these enrichments, the usefulness of the underlying corpora has been drastically increased for downstream research across multiple disciplines, which we showcase through an analysis of acoustic correlates of sentiment. All the corpora are made available for download in JSONL and TextGrid formats, as well as for search through a concordancer. --- ### Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models Authors: Xiaoyu Zhan, Wenxuan Huang, Hao Sun, Xinyu Fu, Changfeng Ma, Shaosheng Cao, Bohan Jia, Shaohui Lin, Zhenfei Yin, Lei Bai, Wanli Ouyang, Yuanqi Li et al. Published: 2025-11-03 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.01618v1 Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding. --- ### Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers Authors: Mohamed Eltahir, Ali Habibullah, Lama Ayash, Tanveer Hussain, Naeemullah Khan Published: 2025-11-03 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2511.01617v1 In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they rely solely on rank or score signals, disregarding candidates' representations. This work introduces Vote-in-Context (ViC), a generalized, training-free framework that re-thinks list-wise reranking and fusion as a zero-shot reasoning task for a Vision-Language Model (VLM). The core insight is to serialize both content evidence and retriever metadata directly within the VLM's prompt, allowing the model to adaptively weigh retriever consensus against visual-linguistic content. We demonstrate the generality of this framework by applying it to the challenging domain of cross-modal video retrieval. To this end, we introduce the S-Grid, a compact serialization map that represents each video as an image grid, optionally paired with subtitles to enable list-wise reasoning over video candidates. ViC is evaluated both as a single-list reranker, where it dramatically improves the precision of individual retrievers, and as an ensemble fuser, where it consistently outperforms strong baselines like CombSUM. Across video retrieval benchmarks including ActivityNet and VATEX, the framework establishes new state-of-the-art zero-shot retrieval performance, demonstrating its effectiveness in handling complex visual and temporal signals alongside text. In zero-shot settings, ViC achieves Recall@1 scores of 87.1% (t2v) / 89.0% (v2t) on MSR-VTT and 99.6% (v2t) on VATEX, representing massive gains of up to +40 Recall@1 over previous state-of-the-art baselines. We present ViC as a simple, reproducible, and highly effective recipe for turning modern VLMs into powerful zero-shot rerankers and fusers. Code and resources are publicly available at: https://github.com/mohammad2012191/ViC --- ### Imperfect Language, Artificial Intelligence, and the Human Mind: An Interdisciplinary Approach to Linguistic Errors in Native Spanish Speakers Authors: Francisco Portillo López Published: 2025-11-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.01615v1 Linguistic errors are not merely deviations from normative grammar; they offer a unique window into the cognitive architecture of language and expose the current limitations of artificial systems that seek to replicate them. This project proposes an interdisciplinary study of linguistic errors produced by native Spanish speakers, with the aim of analyzing how current large language models (LLM) interpret, reproduce, or correct them. The research integrates three core perspectives: theoretical linguistics, to classify and understand the nature of the errors; neurolinguistics, to contextualize them within real-time language processing in the brain; and natural language processing (NLP), to evaluate their interpretation against linguistic errors. A purpose-built corpus of authentic errors of native Spanish (+500) will serve as the foundation for empirical analysis. These errors will be tested against AI models such as GPT or Gemini to assess their interpretative accuracy and their ability to generalize patterns of human linguistic behavior. The project contributes not only to the understanding of Spanish as a native language but also to the development of NLP systems that are more cognitively informed and capable of engaging with the imperfect, variable, and often ambiguous nature of real human language. --- ### Benchmark-Ready 3D Anatomical Shape Classification Authors: Tomáš Krsička, Tibor Kubík Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01613v1 Progress in anatomical 3D shape classification is limited by the complexity of mesh data and the lack of standardized benchmarks, highlighting the need for robust learning methods and reproducible evaluation. We introduce two key steps toward clinically and benchmark-ready anatomical shape classification via self-supervised graph autoencoding. We propose Precomputed Structural Pooling (PSPooling), a non-learnable mesh pooling operator designed for efficient and structure-preserving graph coarsening in 3D anatomical shape analysis. PSPooling precomputes node correspondence sets based on geometric proximity, enabling parallelizable and reversible pooling and unpooling operations with guaranteed support structure. This design avoids the sparsity and reconstruction issues of selection-based methods and the sequential overhead of edge contraction approaches, making it particularly suitable for high-resolution medical meshes. To demonstrate its effectiveness, we integrate PSPooling into a self-supervised graph autoencoder that learns anatomy-aware representations from unlabeled surface meshes. We evaluate the downstream benefits on MedShapeNet19, a new curated benchmark dataset we derive from MedShapeNet, consisting of 19 anatomical classes with standardized training, validation, and test splits. Experiments show that PSPooling significantly improves reconstruction fidelity and classification accuracy in low-label regimes, establishing a strong baseline for medical 3D shape learning. We hope that MedShapeNet19 will serve as a widely adopted benchmark for anatomical shape classification and further research in medical 3D shape analysis. Access the complete codebase, model weights, and dataset information here: https://github.com/TomasKrsicka/MedShapeNet19-PSPooling. --- ### DINO-MX: A Modular & Flexible Framework for Self-Supervised Learning Authors: Mahmut Selman Gokmen, Cody Bumgardner Published: 2025-11-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.01610v1 Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability across different domains and resource settings. DINO-MX is a modular and extensible training framework that combines the core principles of DINO, DINOv2 and DINOv3 within a unified configuration-driven system. It supports a variety of transformer-based architectures and is fully compatible with the Hugging Face ecosystem. The framework includes multiple training strategies such as low-rank adaptation (LoRA), layer freezing, and knowledge distillation, along with support for distributed training through both Distributed Data Parallel (DDP) and Fully Sharded Data Parallel (FSDP). DINO-MX is designed to work with both natural and specialized data types, including single- and multi-channel images. Experimental results on diverse datasets show that DINO-MX achieves competitive performance while significantly reducing computational costs. Additionally, it offers interpretability tools and a label-guided data augmentation method that improves attention-based localization without the need for extra detection or segmentation heads. DINO-MX provides a reproducible and scalable foundation for developing, adapting, and benchmarking self-supervised vision models across a range of research and real-world applications. --- ### The Optimization Landscape of Carathéodory Decomposition of Toeplitz Covariances Authors: Daniel Busbib, Ami Wiesel Published: 2025-11-03 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.01605v3 Toeplitz covariance estimation is a classical signal processing problem, yet the geometry of the Gaussian maximum-likelihood objective remains only partially understood. Recent Newton-type, majorization-minimization, and gradient-based methods often solve the nonconvex problem globally with enough samples, but also reveal a difficult computational landscape. We study this phenomenon through an overparameterized Carathéodory representation, which parameterizes the covariance by the frequencies and amplitudes of steering vectors. A simple example shows that, for any uniform frequency grid, optimizing only the amplitudes can leave a positive error even in the population setting, which motivates optimizing the frequencies as well. Our main result proves that this nonlinear parameterization adds no stationary points: for any sample covariance, every stationary point with a positive definite covariance gives a stationary point of the Toeplitz maximum-likelihood problem. In the population setting, every such point therefore recovers the true covariance. We also prove that gradient descent converges to the true covariance in the population setting, and to the unique maximum likelihood estimate when the sample covariance is close enough to the true covariance. These results do not require overparameterization. Numerically, overparameterization speeds up gradient descent and gives a more accurate estimate for a fixed number of iterations. --- ### L2T-Tune:LLM-Guided Hybrid Database Tuning with LHS and TD3 Authors: Xinyue Yang, Chen Zheng, Yaoyang Hou, Renhao Zhang, Yinyan Zhang, Yanjun Wu, Heng Zhang Published: 2025-11-03 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2511.01602v3 Configuration tuning is critical for database performance. Although recent advancements in database tuning have shown promising results in throughput and latency improvement, challenges remain. First, the vast knob space makes direct optimization unstable and slow to converge. Second, reinforcement learning pipelines often lack effective warm-start guidance and require long offline training. Third, transferability is limited: when hardware or workloads change, existing models typically require substantial retraining to recover performance. To address these limitations, we propose L2T-Tune, a new LLM-guided hybrid database tuning framework that features a three-stage pipeline: Stage one performs a warm start that simultaneously generates uniform samples across the knob space and logs them into a shared pool; Stage two leverages a large language model to mine and prioritize tuning hints from manuals and community documents for rapid convergence. Stage three uses the warm-start sample pool to reduce the dimensionality of knobs and state features, then fine-tunes the configuration with the Twin Delayed Deep Deterministic Policy Gradient algorithm. We conduct experiments on L2T-Tune and the state-of-the-art models. Compared with the best-performing alternative, our approach improves performance by an average of 37.1% across all workloads, and by up to 73% on TPC-C. Compared with models trained with reinforcement learning, it achieves rapid convergence in the offline tuning stage on a single server. Moreover, during the online tuning stage, it only takes 30 steps to achieve best results. --- ### Lite ENSAM: a lightweight cancer segmentation model for 3D Computed Tomography Authors: Agnar Martin Bjørnstad, Elias Stenhede, Arian Ranjbar Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01600v1 Accurate tumor size measurement is a cornerstone of evaluating cancer treatment response. The most widely adopted standard for this purpose is the Response Evaluation Criteria in Solid Tumors (RECIST) v1.1, which relies on measuring the longest tumor diameter in a single plane. However, volumetric measurements have been shown to provide a more reliable assessment of treatment effect. Their clinical adoption has been limited, though, due to the labor-intensive nature of manual volumetric annotation. In this paper, we present Lite ENSAM, a lightweight adaptation of the ENSAM architecture designed for efficient volumetric tumor segmentation from CT scans annotated with RECIST annotations. Lite ENSAM was submitted to the MICCAI FLARE 2025 Task 1: Pan-cancer Segmentation in CT Scans, Subtask 2, where it achieved a Dice Similarity Coefficient (DSC) of 60.7% and a Normalized Surface Dice (NSD) of 63.6% on the hidden test set, and an average total RAM time of 50.6 GBs and an average inference time of 14.4 s on CPU on the public validation dataset. --- ### MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence Authors: Renjun Gao Published: 2025-11-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.01594v2 Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware planning, user personalization, and grounding language plans into executable skills in cluttered homes. We introduce MARS - a Multi-Agent Robotic System powered by MLLMs for assistive intelligence and designed for smart home robots supporting people with disabilities. The system integrates four agents: a visual perception agent for extracting semantic and spatial features from environment images, a risk assessment agent for identifying and prioritizing hazards, a planning agent for generating executable action sequences, and an evaluation agent for iterative optimization. By combining multimodal perception with hierarchical multi-agent decision-making, the framework enables adaptive, risk-aware, and personalized assistance in dynamic indoor environments. Experiments on multiple datasets demonstrate the superior overall performance of the proposed system in risk-aware planning and coordinated multi-agent execution compared with state-of-the-art multimodal models. The proposed approach also highlights the potential of collaborative AI for practical assistive scenarios and provides a generalizable methodology for deploying MLLM-enabled multi-agent systems in real-world environments. --- ### Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation Authors: Yizhu Chen, Chen Ju, Zhicheng Wang, Shuai Xiao, Xu Chen, Jinsong Lan, Xiaoyong Zhu, Ying Chen Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01593v1 The unification of understanding and generation within a single multi-modal large model (MLLM) remains one significant challenge, largely due to the dichotomy between continuous and discrete visual tokenizations. Continuous tokenizer (CT) achieves strong performance by bridging multiple independently-trained understanding modules and generation modules, but suffers from complex multi-stage pipelines and substantial engineering overhead. Conversely, discrete tokenizers (DT) offer a conceptually elegant idea by quantizing each image into a primitive, but inevitably leading to information loss and performance degradation. To resolve this tension, we question the binary choice between CT and DT, inspired by the wave-particle duality of light, and propose the Continuous-Discrete Dualistic Visual Tokenizer (CDD-VT). We treat visual data as a flexible composition of image primitives derived from quantized codebooks, with the crucial insight that the primitive number assigned to each visual sample is adaptively determined according to its complexity: simple instances use a few primitives, emulating discrete tokenization, while complex instances use many, approximating continuous tokenization. Two core components are designed: Diverse Quantitative Primitives, which encourage primitives orthogonality to better populate information space, and Dynamic Primitive Allocator, which assesses sample complexity to determine the optimal set of primitives. Extensive experiments on reconstruction, retrieval and classification show that CDD-VT achieves superior performance over to specialized CT and DT, effectively getting strong result within a concise and scalable MLLM. --- ### Defining Energy Indicators for Impact Identification on Aerospace Composites: A Structured Feature Selection Approach Guided by Domain Knowledge Authors: Natália Ribeiro Marinho, Richard Loendersloot, Frank Grooteman, Jan Willem Wiegman, Uraz Odyurt, Tiedo Tinga Published: 2025-11-03 Categories: cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2511.01592v2 Energy estimation is critical to impact identification on aerospace composites, where low-velocity impacts can induce internal damage that is undetectable at the surface. Data sparsity, signal noise, complex feature interdependencies, non-linear dynamics, massive design spaces, and the ill-posed nature of the inverse problem often constrain current methodologies for energy prediction. Machine learning enriched with prior knowledge is a promising direction for overcoming these constraints. Prior knowledge can be incorporated by acting on the input space, where the choice of data representation directly influences how effectively the model relates measured signals to impact energy. Despite its importance, the selection of effective features lacks a systematic procedure, with no consensus on how to choose among the many candidate descriptors available. The present study addresses that gap through a structured workflow that designs the input space using domain knowledge. Features are extracted from the time, frequency, and time-frequency domains, then filtered for statistical significance, correlation, dimensionality reduction, and robustness to noise. Exploratory data analysis further relates the retained descriptors to the dynamics. The resulting indicators form the input space for a fully connected neural network, which is trained and validated on experimental data from multiple impact scenarios, including pristine and damaged states. The model reduces the prediction error by a factor of three relative to conventional time-series techniques and purely data-driven baselines, while every retained or discarded descriptor remains traceable to the aspect it describes. Overall, the framework advances predictive performance, interpretability, and diagnostic confidence by embedding domain knowledge through targeted feature selection. --- ### BIRD: Bronze Inscription Restoration and Dating Authors: Wenjie Hua, Hoang H. Nguyen, Gangyan Ge Published: 2025-11-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.01589v1 Bronze inscriptions from early China are fragmentary and difficult to date. We introduce BIRD(Bronze Inscription Restoration and Dating), a fully encoded dataset grounded in standard scholarly transcriptions and chronological labels. We further propose an allograph-aware masked language modeling framework that integrates domain- and task-adaptive pretraining with a Glyph Net (GN), which links graphemes and allographs. Experiments show that GN improves restoration, while glyph-biased sampling yields gains in dating. --- ### Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization Authors: Zhicheng Wang, Chen Ju, Xu Chen, Shuai Xiao, Jinsong Lan, Xiaoyong Zhu, Ying Chen, Zhiguo Cao Published: 2025-11-03 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.01588v2 Embedding models are a cornerstone of modern AI. Driven by Multimodal Large Language Models (MLLMs), they have made great progress in architecture and data curation, while the holistic paradigm is still limited to SSC, i.e., single input, singular embedding, contrastive supervision, which collapses rich, multifaceted inputs into monolithic embeddings and fails to fully exploit MLLM capabilities. In this paper, we tailor one Parallel Decoupling Framework (PDF) for multimodal embedding learning, by utilizing the proprietary steerability of MLLMs, i.e., their ability to flexibly generate quite differentiated response under explicit instructions. Concretely, PDF conditions a shared MLLM backbone on distinct, learnable prefixes to roll out multiple parallel paths for one input, then relies on these paths to obtain parallel embeddings. To promote full parallel diversity, we employ Mutual Information Minimization (MIM) as an explicit constraint, coupled with per-path contrastive supervision to maintain semantic alignment. Such dual-objectives force PDF to yield robust semantic coverage and a generalizable embedding space. Ultimately, the remarkable embedding space are accessible at inference via one single forward pass, incurring negligible computational overhead. We instantiate PDF on multiple MLLM backbones and prove its effectiveness on MMEB benchmark. Significant gains are consistently achieved across various resolutions and model sizes, e.g., boosting the VLM2Vec-LLaVA-1.6-LR model by a remarkable +8.9% (7B), while the VLM2Vec-Qwen2VL models by +4.2% (2B) and +3.1% (7B). In terms of efficiency, our 2B model surpasses its baseline by +2.6% using only half the computational budget. --- ### Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systems Authors: Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Joaquin Del Rio, Oleksii Sliusarenko, Xabi Uribe-Etxebarria Published: 2025-11-03 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2511.01583v1 Detecting malware, especially ransomware, is essential to securing today's interconnected ecosystems, including cloud storage, enterprise file-sharing, and database services. Training high-performing artificial intelligence (AI) detectors requires diverse datasets, which are often distributed across multiple organizations, making centralization necessary. However, centralized learning is often impractical due to security, privacy regulations, data ownership issues, and legal barriers to cross-organizational sharing. Compounding this challenge, ransomware evolves rapidly, demanding models that are both robust and adaptable. In this paper, we evaluate Federated Learning (FL) using the Sherpa.ai FL platform, which enables multiple organizations to collaboratively train a ransomware detection model while keeping raw data local and secure. This paradigm is particularly relevant for cybersecurity companies (including both software and hardware vendors) that deploy ransomware detection or firewall systems across millions of endpoints. In such environments, data cannot be transferred outside the customer's device due to strict security, privacy, or regulatory constraints. Although FL applies broadly to malware threats, we validate the approach using the Ransomware Storage Access Patterns (RanSAP) dataset. Our experiments demonstrate that FL improves ransomware detection accuracy by a relative 9% over server-local models and achieves performance comparable to centralized training. These results indicate that FL offers a scalable, high-performing, and privacy-preserving framework for proactive ransomware detection across organizational and regulatory boundaries. --- ### ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks Authors: Chengzhang Yu, Zening Lu, Chenyang Zheng, Chiyue Wang, Yiming Zhang, Zhanpeng Jin Published: 2025-11-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.01581v1 Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel architecture featuring a million-scale external memory bank storing human-readable knowledge as token sequences, enabling direct inspection and modification. We design a differentiable two-stage retrieval mechanism with efficient coarse-grained filtering via product key decomposition (reducing complexity from $\mathcal{O}(N \cdot |I|)$ to $\mathcal{O}(\sqrt{N} \cdot |I|)$) and fine-grained Gumbel-Softmax matching for end-to-end training. Inspired by dual-system cognitive theory, we partition knowledge into frozen explicit facts (20%) and learnable implicit patterns (80%), maintained through Exponential Moving Average updates for stability. ExplicitLM achieves up to 43.67% improvement on knowledge-intensive tasks versus standard Transformers, with 3.62$\times$ gains in low-data regimes (10k samples). Analysis shows strong correlations between memory retrieval and performance, with correct predictions achieving 49% higher hit rates. Unlike RAG systems with frozen retrieval, our jointly optimized architecture demonstrates that interpretable, updatable models can maintain competitive performance while providing unprecedented knowledge transparency. --- ### Generative Adversarial Synthesis and Deep Feature Discrimination of Brain Tumor MRI Images Authors: Md Sumon Ali, Muzammil Behzad Published: 2025-11-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.01574v1 Compared to traditional methods, Deep Learning (DL) becomes a key technology for computer vision tasks. Synthetic data generation is an interesting use case for DL, especially in the field of medical imaging such as Magnetic Resonance Imaging (MRI). The need for this task since the original MRI data is limited. The generation of realistic medical images is completely difficult and challenging. Generative Adversarial Networks (GANs) are useful for creating synthetic medical images. In this paper, we propose a DL based methodology for creating synthetic MRI data using the Deep Convolutional Generative Adversarial Network (DC-GAN) to address the problem of limited data. We also employ a Convolutional Neural Network (CNN) classifier to classify the brain tumor using synthetic data and real MRI data. CNN is used to evaluate the quality and utility of the synthetic images. The classification result demonstrates comparable performance on real and synthetic images, which validates the effectiveness of GAN-generated images for downstream tasks. --- ### HIT-ROCKET: Hadamard-vector Inner-product Transformer for ROCKET Authors: Wang Hao, Kuang Zhang, Hou Chengyu, Yuan Zhonghao, Tan Chenxing, Fu Weifeng, Zhu Yangying Published: 2025-11-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.01572v1 Time series classification holds broad application value in communications, information countermeasures, finance, and medicine. However, state-of-the-art (SOTA) methods-including HIVE-COTE, Proximity Forest, and TS-CHIEF-exhibit high computational complexity, coupled with lengthy parameter tuning and training cycles. In contrast, lightweight solutions like ROCKET (Random Convolutional Kernel Transform) offer greater efficiency but leave substantial room for improvement in kernel selection and computational overhead. To address these challenges, we propose a feature extraction approach based on Hadamard convolutional transform, utilizing column or row vectors of Hadamard matrices as convolution kernels with extended lengths of varying sizes. This enhancement maintains full compatibility with existing methods (e.g., ROCKET) while leveraging kernel orthogonality to boost computational efficiency, robustness, and adaptability. Comprehensive experiments on multi-domain datasets-focusing on the UCR time series dataset-demonstrate SOTA performance: F1-score improved by at least 5% vs. ROCKET, with 50% shorter training time than miniROCKET (fastest ROCKET variant) under identical hyperparameters, enabling deployment on ultra-low-power embedded devices. All code is available on GitHub. --- ### PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model Authors: Wenqi Liang, Gan Sun, Yao He, Jiahua Dong, Suyan Dai, Ivan Laptev, Salman Khan, Yang Cong Published: 2025-11-03 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.01571v2 Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways: (i) they struggle with pixel-level scene understanding, and (ii) they rely heavily on textual prompts, which reduces their flexibility in real-world settings. To address these challenges, we introduce PixelVLA, the first VLA model designed to support both pixel-level reasoning and multimodal prompting with text and visual inputs. Our approach is built on a new visuomotor instruction tuning framework that integrates a multiscale pixel-aware encoder with a visual promptaware encoder. To train PixelVLA effectively, we further propose a two-stage automated annotation pipeline that generates Pixel-160K, a large-scale dataset with pixel-level annotations derived from existing robot data. Experiments on three standard VLA benchmarks and two VLA model variants show that PixelVLA improves manipulation success rates by 10.1%-28.7% over OpenVLA, while requiring only 1.5% of its pretraining cost. These results demonstrate that PixelVLA can be integrated into existing VLAs to enable more accurate, efficient, and versatile robot control in complex environments. --- ### Gated Fusion Enhanced Multi-Scale Hierarchical Graph Convolutional Network for Stock Movement Prediction Authors: Xiaosha Xue, Peibo Duan, Zhipeng Liu, Qi Chu, Changsheng Zhang, Bin zhang Published: 2025-11-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.01570v1 Accurately predicting stock market movements remains a formidable challenge due to the inherent volatility and complex interdependencies among stocks. Although multi-scale Graph Neural Networks (GNNs) hold potential for modeling these relationships, they frequently neglect two key points: the subtle intra-attribute patterns within each stock affecting inter-stock correlation, and the biased attention to coarse- and fine-grained features during multi-scale sampling. To overcome these challenges, we introduce MS-HGFN (Multi-Scale Hierarchical Graph Fusion Network). The model features a hierarchical GNN module that forms dynamic graphs by learning patterns from intra-attributes and features from inter-attributes over different time scales, thus comprehensively capturing spatio-temporal dependencies. Additionally, a top-down gating approach facilitates the integration of multi-scale spatio-temporal features, preserving critical coarse- and fine-grained features without too much interference. Experiments utilizing real-world datasets from U.S. and Chinese stock markets demonstrate that MS-HGFN outperforms both traditional and advanced models, yielding up to a 1.4% improvement in prediction accuracy and enhanced stability in return simulations. The code is available at https://anonymous.4open.science/r/MS-HGFN. --- ### ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation Authors: Seungmin Shin, Dooyoung Kim, Youngjoong Ko Published: 2025-11-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.01568v1 Controllable Dialogue Generation (CDG) enables chatbots to generate responses with desired attributes, and weighted decoding methods have achieved significant success in the CDG task. However, using a fixed constant value to manage the bias of attribute probabilities makes it challenging to find an ideal control strength that satisfies both controllability and fluency. To address this issue, we propose ECO decoding (Entropy-based COntrol), which dynamically adjusts the control strength at each generation step according to the model's entropy in both the language model and attribute classifier probability distributions. Experiments on the DailyDialog and MultiWOZ datasets demonstrate that ECO decoding consistently improves controllability while maintaining fluency and grammaticality, outperforming prior decoding methods across various models and settings. Furthermore, ECO decoding alleviates probability interpolation issues in multi-attribute generation and consequently demonstrates strong performance in both single and multi-attribute scenarios. ---