# Research Papers — 2025-10 · bundle page 122 of 217 > Full-text markdown of papers #6051–6100 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/122 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/121.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/123.md) ### Locket: Robust Feature-Locking Technique for Language Models Authors: Lipeng He, Vasisht Duddu, N. Asokan Published: 2025-10-14 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.12117v3 Chatbot service providers (e.g., OpenAI) rely on tiered subscription plans to generate revenue, offering black-box access to basic models for free users and advanced models to paying subscribers. However, this approach is unprofitable and inflexible. A pay-to-unlock scheme for premium features (e.g., math, coding) offers a more sustainable alternative. Enabling such a scheme requires a feature-locking technique (FLoTE) that is (i) effective in refusing locked features, (ii) utility-preserving for unlocked features, (iii) robust against evasion or unauthorized credential sharing, and (iv) scalable to multiple features and clients. Existing FLoTEs (e.g., password-locked models) fail to meet these criteria. To fill this gap, we present Locket, the first robust and scalable FLoTE to enable pay-to-unlock schemes. We develop a framework for adversarial training and merging of feature-locking adapters, which enables Locket to selectively disable specific features of a model. Evaluation shows that Locket is effective ($100$% refusal rate), utility-preserving ($\leq 7$% utility degradation), robust ($\leq 5$% attack success rate), and scalable to multiple features and clients. --- ### Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models Authors: Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou Published: 2025-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.12116v1 End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal through systematic experimentation that although LSLMs lose some text input performance after speech-text alignment training, the performance gap between speech and text inputs is more pronounced, which we refer to as the modality gap. To understand this gap, we analyze both coarse- and fine-grained text and speech representations. At the coarse-grained level, representations of speech and text in deeper layers are found to be increasingly aligned in direction (cosine similarity), while concurrently diverging in magnitude (Euclidean distance). We further find that representation similarity is strongly correlated with the modality gap. At the fine-grained level, a spontaneous token-level alignment pattern between text and speech representations is observed. Based on this, we introduce the Alignment Path Score to quantify token-level alignment quality, which exhibits stronger correlation with the modality gap. Building on these insights, we design targeted interventions on critical tokens through angle projection and length normalization. These strategies demonstrate the potential to improve correctness for speech inputs. Our study provides the first systematic empirical analysis of the modality gap and alignment mechanisms in LSLMs, offering both theoretical and methodological guidance for future optimization. --- ### Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation Authors: Xin Zhao, Naoki Yoshinaga, Yuma Tsuta, Akiko Aizawa Published: 2025-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.12115v1 Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across languages into large language models (LLMs). Although many methods have been proposed to improve domain adaptation, the mechanisms of multilingual knowledge acquisition, how domain knowledge is learned within a language and transferred across languages, remain underexplored. This gap leads to suboptimal performance, particularly in low-resource settings. This work examines the learning dynamics of LLMs during ML-DA. Because prior ML-DA studies often train and evaluate on datasets with mismatched knowledge coverage, we propose AdaXEval, an adaptive evaluation method that builds multiple-choice QA datasets from the same bilingual domain corpus used for training, thereby directly studying multilingual knowledge acquisition. Through continual training of LLMs with diverse data recipes, we track how LLMs acquire domain facts and pinpoint the mechanism behind the transformation process from domain training data to knowledge. Our experiments on a 13B English-Japanese bilingual LLM reveal that cross-lingual transfer remains challenging despite a high-quality bilingual corpus. The code has been released. --- ### Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration Authors: Wenjie Li, Xiangyi Wang, Heng Guo, Guangwei Gao, Zhanyu Ma Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12114v1 Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical guidance, which struggle with localized artifacts or face color. We propose Self-Supervised Selective-Guided Diffusion (SSDiff), which leverages pseudo-reference faces generated by a pre-trained diffusion model under weak guidance. These pseudo-labels exhibit structurally aligned contours and natural colors, enabling region-specific restoration via staged supervision: structural guidance applied throughout the denoising process and color refinement in later steps, aligned with the coarse-to-fine nature of diffusion. By incorporating face parsing maps and scratch masks, our method selectively restores breakage regions while avoiding identity mismatch. We further construct VintageFace, a 300-image benchmark of real old face photos with varying degradation levels. SSDiff outperforms existing GAN-based and diffusion-based methods in perceptual quality, fidelity, and regional controllability. Code link: https://github.com/PRIS-CV/SSDiff. --- ### Chimera: State Space Models Beyond Sequences Authors: Aakash Lahoti, Tanya Marwah, Ratish Puduppully, Albert Gu Published: 2025-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.12111v1 Transformer-based deep learning methods have become the standard approach for modeling diverse data such as sequences, images, and graphs. These methods rely on self-attention, which treats data as an unordered set of elements. This ignores the neighborhood structure or graph topology of the data and requires inductive biases--such as position embeddings in sequences and images, or random walks in graphs--to incorporate topology. However, designing such task-specific biases requires significant effort and can introduce side effects that hinder generalization. We introduce Chimera, a unified model that directly incorporates data topology in a principled way, removing the need for domain-specific biases. The key idea is that state space models--which naturally do not require position embeddings--can be generalized to capture any graph topology. Our experiments show that Chimera achieves strong performance across language, vision, and graph domains, outperforming BERT on GLUE by 0.7 points, ViT on ImageNet-1k by 2.6%, and all baselines on the Long Range Graph Benchmark. We further propose algorithmic optimizations to improve Chimera's efficiency: (1) for Directed Acyclic Graphs, Chimera can be implemented as a linear-time recurrence; (2) for general graphs, a simple mathematical relaxation achieves Transformer's quadratic complexity without domain-specific heuristics. These results validate Chimera's core contribution and support the idea that data topology is a powerful inductive bias across modalities. --- ### Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models Authors: Ziliang Qiu, Renfen Hu Published: 2025-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.12110v1 The evaluation of LLMs' creativity represents a crucial research domain, though challenges such as data contamination and costly human assessments often impede progress. Drawing inspiration from human creativity assessment, we propose PACE, asking LLMs to generate Parallel Association Chains to Evaluate their creativity. PACE minimizes the risk of data contamination and offers a straightforward, highly efficient evaluation, as evidenced by its strong correlation with Chatbot Arena Creative Writing rankings (Spearman's $ρ= 0.739$, $p < 0.001$) across various proprietary and open-source models. A comparative analysis of associative creativity between LLMs and humans reveals that while high-performing LLMs achieve scores comparable to average human performance, professional humans consistently outperform LLMs. Furthermore, linguistic analysis reveals that both humans and LLMs exhibit a trend of decreasing concreteness in their associations, and humans demonstrating a greater diversity of associative patterns. --- ### DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning Authors: Jiawei Zhan, Jun Liu, Jinlong Peng, Xiaochen Chen, Bin-Bin Gao, Yong Liu, Chengjie Wang Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12107v1 With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three conundrums: increasingly large model complexity, non-smooth representation shift during incremental learning and inconsistency between stage-wise sub-problem optimization and global inference. In this work, we propose the Discriminative Representation Learning (DRL) framework to specifically address these challenges. To conduct incremental learning effectively and yet efficiently, the DRL's network, called Incremental Parallel Adapter (IPA) network, is built upon a PTM and increasingly augments the model by learning a lightweight adapter with a small amount of parameter learning overhead in each incremental stage. The adapter is responsible for adapting the model to new classes, it can inherit and propagate the representation capability from the current model through parallel connection between them by a transfer gate. As a result, this design guarantees a smooth representation shift between different incremental stages. Furthermore, to alleviate inconsistency and enable comparable feature representations across incremental stages, we design the Decoupled Anchor Supervision (DAS). It decouples constraints of positive and negative samples by respectively comparing them with the virtual anchor. This decoupling promotes discriminative representation learning and aligns the feature spaces learned at different stages, thereby narrowing the gap between stage-wise local optimization over a subset of data and global inference across all classes. Extensive experiments on six benchmarks reveal that our DRL consistently outperforms other state-of-the-art methods throughout the entire CIL period while maintaining high efficiency in both training and inference phases. --- ### SpikePool: Event-driven Spiking Transformer with Pooling Attention Authors: Donghyun Lee, Alex Sima, Yuhang Li, Panos Stinis, Priyadarshini Panda Published: 2025-10-14 Categories: cs.NE arXiv: https://arxiv.org/abs/2510.12102v1 Building on the success of transformers, Spiking Neural Networks (SNNs) have increasingly been integrated with transformer architectures, leading to spiking transformers that demonstrate promising performance on event-based vision tasks. However, despite these empirical successes, there remains limited understanding of how spiking transformers fundamentally process event-based data. Current approaches primarily focus on architectural modifications without analyzing the underlying signal processing characteristics. In this work, we analyze spiking transformers through the frequency spectrum domain and discover that they behave as high-pass filters, contrasting with Vision Transformers (ViTs) that act as low-pass filters. This frequency domain analysis reveals why certain designs work well for event-based data, which contains valuable high-frequency information but is also sparse and noisy. Based on this observation, we propose SpikePool, which replaces spike-based self-attention with max pooling attention, a low-pass filtering operation, to create a selective band-pass filtering effect. This design preserves meaningful high-frequency content while capturing critical features and suppressing noise, achieving a better balance for event-based data processing. Our approach demonstrates competitive results on event-based datasets for both classification and object detection tasks while significantly reducing training and inference time by up to 42.5% and 32.8%, respectively. --- ### Gaussian Semantic Field for One-shot LiDAR Global Localization Authors: Pengyu Yin, Shenghai Yuan, Haozhi Cao, Xingyu Ji, Ruofei Bai, Siyu Chen, Lihua Xie Published: 2025-10-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2510.12101v1 We present a one-shot LiDAR global localization algorithm featuring semantic disambiguation ability based on a lightweight tri-layered scene graph. While landmark semantic registration-based methods have shown promising performance improvements in global localization compared with geometric-only methods, landmarks can be repetitive and misleading for correspondence establishment. We propose to mitigate this problem by modeling semantic distributions with continuous functions learned from a population of Gaussian processes. Compared with discrete semantic labels, the continuous functions capture finer-grained geo-semantic information and also provide more detailed metric information for correspondence establishment. We insert this continuous function as the middle layer between the object layer and the metric-semantic layer, forming a tri-layered 3D scene graph, serving as a light-weight yet performant backend for one-shot localization. We term our global localization pipeline Outram-GSF (Gaussian semantic field) and conduct a wide range of experiments on publicly available data sets, validating the superior performance against the current state-of-the-art. --- ### G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior Authors: Junfeng Ni, Yixin Chen, Zhifei Yang, Yu Liu, Ruijie Lu, Song-Chun Zhu, Siyuan Huang Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12099v2 Despite recent advances in leveraging generative prior from pre-trained diffusion models for 3D scene reconstruction, existing methods still face two critical limitations. First, due to the lack of reliable geometric supervision, they struggle to produce high-quality reconstructions even in observed regions, let alone in unobserved areas. Second, they lack effective mechanisms to mitigate multi-view inconsistencies in the generated images, leading to severe shape-appearance ambiguities and degraded scene geometry. In this paper, we identify accurate geometry as the fundamental prerequisite for effectively exploiting generative models to enhance 3D scene reconstruction. We first propose to leverage the prevalence of planar structures to derive accurate metric-scale depth maps, providing reliable supervision in both observed and unobserved regions. Furthermore, we incorporate this geometry guidance throughout the generative pipeline to improve visibility mask estimation, guide novel view selection, and enhance multi-view consistency when inpainting with video diffusion models, resulting in accurate and consistent scene completion. Extensive experiments on Replica, ScanNet++, DeepBlending and Mip-NeRF 360 show that our method consistently outperforms existing baselines in both geometry and appearance reconstruction, particularly for unobserved regions. Moreover, our method naturally supports single-view inputs and unposed videos, with strong generalizability in both indoor and outdoor scenarios with practical real-world applicability. The project page is available at https://dali-jack.github.io/g4splat-web/. --- ### An Adaptive Edge-Guided Dual-Network Framework for Fast QR Code Motion Deblurring Authors: Jianping Li, Dongyang Guo, Wenjie Li, Wei Zhao Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12098v1 Unlike general image deblurring that prioritizes perceptual quality, QR code deblurring focuses on ensuring successful decoding. QR codes are characterized by highly structured patterns with sharp edges, a robust prior for restoration. Yet existing deep learning methods rarely exploit these priors explicitly. To address this gap, we propose the Edge-Guided Attention Block (EGAB), which embeds explicit edge priors into a Transformer architecture. Based on EGAB, we develop Edge-Guided Restormer (EG-Restormer), an effective network that significantly boosts the decoding rate of severely blurred QR codes. For mildly blurred inputs, we design the Lightweight and Efficient Network (LENet) for fast deblurring. We further integrate these two networks into an Adaptive Dual-network (ADNet), which dynamically selects the suitable network based on input blur severity, making it ideal for resource-constrained mobile devices. Extensive experiments show that our EG-Restormer and ADNet achieve state-of-the-art performance with a competitive speed. Project page: https://github.com/leejianping/ADNet --- ### Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning Authors: Guozheng Ma, Lu Li, Zilin Wang, Haoyu Wang, Shengchao Hu, Leszek Rutkowski, Dacheng Tao Published: 2025-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.12096v1 Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade performance due to unique optimization pathologies such as plasticity loss. While recent works show that dynamically adapting network topology during training can mitigate these issues, existing studies have three critical limitations: (1) applying uniform dynamic training strategies across all modules despite encoder, critic, and actor following distinct learning paradigms, (2) focusing evaluation on basic architectures without clarifying the relative importance and interaction between dynamic training and architectural improvements, and (3) lacking systematic comparison between different dynamic approaches including sparse-to-sparse, dense-to-sparse, and sparse-to-dense. Through comprehensive investigation across modules and architectures, we reveal that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements. We finally distill these insights into Module-Specific Training (MST), a practical framework that further exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications. --- ### IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation Authors: Wenxu Zhou, Kaixuan Nie, Hang Du, Dong Yin, Wei Huang, Siqiang Guo, Xiaobo Zhang, Pengbo Hu Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12095v1 In this study, we present IL3D, a large-scale dataset meticulously designed for large language model (LLM)-driven 3D scene generation, addressing the pressing demand for diverse, high-quality training data in indoor layout design. Comprising 27,816 indoor layouts across 18 prevalent room types and a library of 29,215 high-fidelity 3D object assets, IL3D is enriched with instance-level natural language annotations to support robust multimodal learning for vision-language tasks. We establish rigorous benchmarks to evaluate LLM-driven scene generation. Experimental results show that supervised fine-tuning (SFT) of LLMs on IL3D significantly improves generalization and surpasses the performance of SFT on other datasets. IL3D offers flexible multimodal data export capabilities, including point clouds, 3D bounding boxes, multiview images, depth maps, normal maps, and semantic masks, enabling seamless adaptation to various visual tasks. As a versatile and robust resource, IL3D significantly advances research in 3D scene generation and embodied intelligence, by providing high-fidelity scene data to support environment perception tasks of embodied agents. --- ### H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space Authors: Heng Zhang, Tianyi Zhang, Zijun Liu, Yuling Shi, Yaomin Shen, Haochen You, Haichuan Hu, Lubin Gan, Jin Huang Published: 2025-10-14 Categories: cs.LG, cs.GR arXiv: https://arxiv.org/abs/2510.12094v1 Text-attributed graphs are widely used across domains, offering rich opportunities for zero-shot learning via graph-text alignment. However, existing methods struggle with tasks requiring fine-grained pattern recognition, particularly on heterophilic graphs. Through empirical and theoretical analysis, we identify an \textbf{over-abstraction problem}: current approaches operate at excessively large hyperbolic radii, compressing multi-scale structural information into uniform high-level abstractions. This abstraction-induced information loss obscures critical local patterns essential for accurate predictions. By analyzing embeddings in hyperbolic space, we demonstrate that optimal graph learning requires \textbf{faithful preservation} of fine-grained structural details, better retained by representations positioned closer to the origin. To address this, we propose \textbf{H4G}, a framework that systematically reduces embedding radii using learnable block-diagonal scaling matrices and Möbius matrix multiplication. This approach restores access to fine-grained patterns while maintaining global receptive ability with minimal computational overhead. Experiments show H4G achieves state-of-the-art zero-shot performance with \textbf{12.8\%} improvement on heterophilic graphs and \textbf{8.4\%} on homophilic graphs, confirming that radius reduction enables faithful multi-scale representation for advancing zero-shot graph learning. --- ### ToPolyAgent: AI Agents for Coarse-Grained Topological Polymer Simulations Authors: Lijie Ding, Jan-Michael Carrillo, Changwoo Do Published: 2025-10-14 Categories: cs.AI, cond-mat.mtrl-sci, cond-mat.soft arXiv: https://arxiv.org/abs/2510.12091v1 We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer-solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent condition, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems. --- ### Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback Authors: Xingpei Ma, Shenneng Huang, Jiaran Cai, Yuansheng Guan, Shen Zheng, Hanfeng Zhao, Qiang Zhang, Shunsi Zhang Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12089v2 Recent advances in diffusion models have significantly improved audio-driven human video generation, surpassing traditional methods in both quality and controllability. However, existing approaches still face challenges in lip-sync accuracy, temporal coherence for long video generation, and multi-character animation. In this work, we propose a diffusion transformer (DiT)-based framework for generating lifelike talking videos of arbitrary length, and introduce a training-free method for multi-character audio-driven animation. First, we employ a LoRA-based training strategy combined with a position shift inference approach, which enables efficient long video generation while preserving the capabilities of the foundation model. Moreover, we combine partial parameter updates with reward feedback to enhance both lip synchronization and natural body motion. Finally, we propose a training-free approach, Mask Classifier-Free Guidance (Mask-CFG), for multi-character animation, which requires no specialized datasets or model modifications and supports audio-driven animation for three or more characters. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving high-quality, temporally coherent, and multi-character audio-driven video generation in a simple, efficient, and cost-effective manner. --- ### One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration Authors: Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal Published: 2025-10-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.12088v2 Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program. Prior work has focused on largely deterministic environments with abundant interaction data, simple mechanics, and human guidance. We address a more realistic and challenging setting, learning in a complex, stochastic environment where the agent has only "one life" to explore a hostile environment without human guidance. We introduce OneLife, a framework that models world dynamics through conditionally-activated programmatic laws within a probabilistic programming framework. Each law operates through a precondition-effect structure, activating in relevant world states. This creates a dynamic computation graph that routes inference and optimization only through relevant laws, avoiding scaling challenges when all laws contribute to predictions about a complex, hierarchical state, and enabling the learning of stochastic dynamics even with sparse rule activation. To evaluate our approach under these demanding constraints, we introduce a new evaluation protocol that measures (a) state ranking, the ability to distinguish plausible future states from implausible ones, and (b) state fidelity, the ability to generate future states that closely resemble reality. We develop and evaluate our framework on Crafter-OO, our reimplementation of the Crafter environment that exposes a structured, object-oriented symbolic state and a pure transition function that operates on that state alone. OneLife can successfully learn key environment dynamics from minimal, unguided interaction, outperforming a strong baseline on 16 out of 23 scenarios tested. We also test OneLife's planning ability, with simulated rollouts successfully identifying superior strategies. Our work establishes a foundation for autonomously constructing programmatic world models of unknown, complex environments. --- ### GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs Authors: Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Haochen You, Zijian Zhang, Yilei Yuan, Jin Huang Published: 2025-10-14 Categories: cs.LG, cs.GR arXiv: https://arxiv.org/abs/2510.12085v2 Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared representation space using contrastive learning. However, systematic evaluations reveal significant performance degradation at structural boundaries where distinct topological patterns converge, with accuracy losses exceeding 20 percentage points. This issue arises from a key limitation: current methods assume all graph structures can be encoded within a single Euclidean space. In reality, tree structures require hyperbolic geometry to preserve hierarchical branching, while cyclic patterns depend on spherical geometry for closure properties. At structural boundaries, nodes experience conflicting geometric constraints that uniform encoding spaces cannot resolve. This raises a crucial challenge: \textbf{Can alignment frameworks be designed to respect the intrinsic geometric diversity of graph structures?} We introduce \textbf{GraphShaper}, a geometry-aware framework that enhances graph encoding through multi-geometric specialization. Our approach employs expert networks tailored to different geometric spaces, dynamically computing fusion weights to adaptively integrate geometric properties based on local structural characteristics. This adaptive fusion preserves structural integrity before alignment with text embeddings. Extensive experiments demonstrate that GraphShaper achieves 9.47\% accuracy improvements on citation networks and 7.63\% on social networks in zero-shot settings. --- ### An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations Authors: Benjamin W. Nelson, Celeste Wong, Matthew T. Silvestrini, Sooyoon Shin, Alanna Robinson, Jessica Lee, Eric Yang, John Torous, Andrew Trister Published: 2025-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.12083v1 Large language models often mishandle psychiatric emergencies, offering harmful or inappropriate advice and enabling destructive behaviors. This study evaluated the Verily behavioral health safety filter (VBHSF) on two datasets: the Verily Mental Health Crisis Dataset containing 1,800 simulated messages and the NVIDIA Aegis AI Content Safety Dataset subsetted to 794 mental health-related messages. The two datasets were clinician-labelled and we evaluated performance using the clinician labels. Additionally, we carried out comparative performance analyses against two open source, content moderation guardrails: OpenAI Omni Moderation Latest and NVIDIA NeMo Guardrails. The VBHSF demonstrated, well-balanced performance on the Verily Mental Health Crisis Dataset v1.0, achieving high sensitivity (0.990) and specificity (0.992) in detecting any mental health crises. It achieved an F1-score of 0.939, sensitivity ranged from 0.917-0.992, and specificity was >= 0.978 in identifying specific crisis categories. When evaluated against the NVIDIA Aegis AI Content Safety Dataset 2.0, VBHSF performance remained highly sensitive (0.982) and accuracy (0.921) with reduced specificity (0.859). When compared with the NVIDIA NeMo and OpenAI Omni Moderation Latest guardrails, the VBHSF demonstrated superior performance metrics across both datasets, achieving significantly higher sensitivity in all cases (all p < 0.001) and higher specificity relative to NVIDIA NeMo (p < 0.001), but not to OpenAI Omni Moderation Latest (p = 0.094). NVIDIA NeMo and OpenAI Omni Moderation Latest exhibited inconsistent performance across specific crisis types, with sensitivity for some categories falling below 0.10. Overall, the VBHSF demonstrated robust, generalizable performance that prioritizes sensitivity to minimize missed crises, a crucial feature for healthcare applications. --- ### Enhancing Neural Code Representation with Additional Context Authors: Huy Nguyen, Christoph Treude, Patanamon Thongtanunam Published: 2025-10-14 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.12082v1 Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typically rely on source code alone, overlooking contextual information such as version history or structural relationships. This limits their ability to capture how code evolves and operates. We conduct an empirical study on how enriching code representations with such contextual signals affects neural model performance on key comprehension tasks. Two downstream tasks, code clone detection and code summarisation, are evaluated using SeSaMe (1,679 Java methods) and CodeSearchNet (63,259 methods). Five representative models (CodeBERT, GraphCodeBERT, CodeT5, PLBART, ASTNN) are fine-tuned under code-only and context-augmented settings. Results show that context generally improves performance: version history consistently boosts clone detection (e.g., CodeT5 +15.92% F1) and summarisation (e.g., GraphCodeBERT +5.56% METEOR), while call-graph effects vary by model and task. Combining multiple contexts yields further gains (up to +21.48% macro-F1). Human evaluation on 100 Java snippets confirms that context-augmented summaries are significantly preferred for Accuracy and Content Adequacy (p <= 0.026; |delta| up to 0.55). These findings highlight the potential of contextual signals to enhance code comprehension and open new directions for optimising contextual encoding in neural SE models. --- ### Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models Authors: Rabimba Karanjai, Yang Lu, Ranjith Chodavarapu, Lei Xu, Weidong Shi Published: 2025-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.12080v1 The rapid advancement of large language model (LLM) technology has led to diverse applications, many of which inherently require randomness, such as stochastic decision-making, gaming, scheduling, AI agents, and cryptography-related tasks. However, the capabilities of LLMs in handling randomness, particularly in generating and utilizing random numbers effectively, remain unclear. This paper investigates the capacity of LLMs for handling tasks that involve randomness through a series of experiments. We designed a set of experiments that consider various factors that can influence an LLM's performance in tasks involving randomness, such as accessibility to external tools, types of tasks, model states (fresh vs. non-fresh), and prompting strategies. The experiments cover a range of tasks, including generating random numbers, generating random strings such as passwords, shuffling items, and evaluating the quality of randomness using entropy and the NIST randomness test-suite. Our findings reveal that while LLMs can generate outputs that exhibit some degree of randomness, their performance is inconsistent and often deviates significantly from the expected behavior. The analysis of the experimental results highlights key limitations and areas where improvement is needed for the LLMs to effectively handle tasks involving randomness --- ### FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning Authors: Sijing Xie, Dingzhu Wen, Changsheng You, Qimei Chen, Mehdi Bennis, Kaibin Huang Published: 2025-10-14 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2510.12078v2 Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs, this paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA. A generalization error bound and convergence analysis under sparsity regularization are obtained, which elucidate the fundamental trade-off between underfitting and overfitting. The error bound reveals that a higher dropout rate increases model sparsity, thereby lowering the upper bound of pointwise hypothesis stability (PHS). While this reduces the gap between empirical and generalization errors, it also incurs a higher empirical error, which, together with the gap, determines the overall generalization error. On the other hand, though dropout reduces communication costs, deploying FedLoDrop at the network edge still faces challenges due to limited network resources. To address this issue, an optimization problem is formulated to minimize the upper bound of the generalization error, by jointly optimizing the dropout rate and resource allocation subject to the latency and per-device energy consumption constraints. To solve this problem, a branch-and-bound (B\&B)-based method is proposed to obtain its globally optimal solution. Moreover, to reduce the high computational complexity of the B\&B-based method, a penalized successive convex approximation (P-SCA)-based algorithm is proposed to efficiently obtain its high-quality suboptimal solution. Finally, numerical results demonstrate the effectiveness of the proposed approach in mitigating overfitting and improving the generalization capability. --- ### Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory Authors: Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet Published: 2025-10-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.12077v1 We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization, factorization, and other compression techniques, we find that complexity estimates based on the local learning coefficient (LLC) are closely, and in some cases, linearly correlated with compressibility. Our results provide a path toward rigorously evaluating the limits of model compression. --- ### BeSTAD: Behavior-Aware Spatio-Temporal Anomaly Detection for Human Mobility Data Authors: Junyi Xie, Jina Kim, Yao-Yi Chiang, Lingyi Zhao, Khurram Shafique Published: 2025-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.12076v1 Traditional anomaly detection in human mobility has primarily focused on trajectory-level analysis, identifying statistical outliers or spatiotemporal inconsistencies across aggregated movement traces. However, detecting individual-level anomalies, i.e., unusual deviations in a person's mobility behavior relative to their own historical patterns, within datasets encompassing large populations remains a significant challenge. In this paper, we present BeSTAD (Behavior-aware Spatio-Temporal Anomaly Detection for Human Mobility Data), an unsupervised framework that captures individualized behavioral signatures across large populations and uncovers fine-grained anomalies by jointly modeling spatial context and temporal dynamics. BeSTAD learns semantically enriched mobility representations that integrate location meaning and temporal patterns, enabling the detection of subtle deviations in individual movement behavior. BeSTAD further employs a behavior-cluster-aware modeling mechanism that builds personalized behavioral profiles from normal activity and identifies anomalies through cross-period behavioral comparison with consistent semantic alignment. Building on prior work in mobility behavior clustering, this approach enables not only the detection of behavioral shifts and deviations from established routines but also the identification of individuals exhibiting such changes within large-scale mobility datasets. By learning individual behaviors directly from unlabeled data, BeSTAD advances anomaly detection toward personalized and interpretable mobility analysis. --- ### A Review on Domain Adaption and Generative Adversarial Networks(GANs) Authors: Aashish Dhawan, Divyanshu Mudgal Published: 2025-10-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.12075v1 The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can overcome the scarcity of data to produce results comparable to previous benchmark results. In most cases, obtaining labeled data is very difficult because of the high cost of human labor and in some cases impossible. The purpose of this paper is to discuss Domain Adaptation and various methods to implement it. The main idea is to use a model trained on a particular dataset to predict on data from a different domain of the same kind, for example - a model trained on paintings of airplanes predicting on real images of airplanes --- ### EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making Authors: Zixing Lei, Sheng Yin, Yichen Xiong, Yuanzhuo Ding, Wenhao Huang, Yuxi Wei, Qingyao Xu, Yiming Li, Weixin Li, Yunhong Wang, Siheng Chen Published: 2025-10-14 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.12072v1 Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models (LLMs), with their general decision-making capabilities, offer a promising path to realize this potential; however, LLMs trained solely on language lack exposure to physical environments, limiting their true embodied understanding. To bridge this gap, we propose the concept of a training ground: a comprehensive infrastructure that provides task and scene simulation, embodied interaction, and feedback signals, offering a one-stop solution for LLM acquire genuine embodied decision-making skills. In this work, we present EmboMatrix, the first training ground of its kind, providing massive and diverse tasks with efficient simulation and precise rewards. EmboMatrix incorporates a series of novel techniques: a multi-agent data engine for large-scale task and scene generation, a distributed heterogeneous-hardware system for scalable simulation, and a multi-level reward architecture for precise supervision. Leveraging EmboMatrix, we cultivate EmboBrain, an LLM whose embodied decision-making abilities emerge from extensive embodied interactions. Experiments show that EmboBrain-7B surpasses the 671B DeepSeek-R1 baseline by 9.5\% on two challenging embodied decision-making benchmarks, demonstrating the power of interactive, environment-grounded learning for building truly intelligent embodied agents. --- ### Influence Dynamics and Stagewise Data Attribution Authors: Jin Hwa Lee, Matthew Smith, Maxwell Adam, Jesse Hoogland Published: 2025-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.12071v2 Current training data attribution (TDA) methods treat the influence one sample has on another as static, but neural networks learn in distinct stages that exhibit changing patterns of influence. In this work, we introduce a framework for stagewise data attribution grounded in singular learning theory. We predict that influence can change non-monotonically, including sign flips and sharp peaks at developmental transitions. We first validate these predictions analytically and empirically in a toy model, showing that dynamic shifts in influence directly map to the model's progressive learning of a semantic hierarchy. Finally, we demonstrate these phenomena at scale in language models, where token-level influence changes align with known developmental stages. --- ### MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging Authors: Sangmin Jo, Jee Seok Yoon, Wootaek Jeong, Kwanseok Oh, Heung-Il Suk Published: 2025-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.12070v1 Deep learning-based automatic sleep staging has significantly advanced in performance and plays a crucial role in the diagnosis of sleep disorders. However, those models often struggle to generalize on unseen subjects due to variability in physiological signals, resulting in degraded performance in out-of-distribution scenarios. To address this issue, domain generalization approaches have recently been studied to ensure generalized performance on unseen domains during training. Among those techniques, contrastive learning has proven its validity in learning domain-invariant features by aligning samples of the same class across different domains. Despite its potential, many existing methods are insufficient to extract adequately domain-invariant representations, as they do not explicitly address domain characteristics embedded within the unshared information across samples. In this paper, we posit that mitigating such domain-relevant attributes-referred to as excess domain-relevant information-is key to bridging the domain gap. However, the direct strategy to mitigate the domain-relevant attributes often overfits features at the high-level information, limiting their ability to leverage the diverse temporal and spectral information encoded in the multiple feature levels. To address these limitations, we propose a novel MEASURE (Multi-scalE minimAl SUfficient Representation lEarning) framework, which effectively reduces domain-relevant information while preserving essential temporal and spectral features for sleep stage classification. In our exhaustive experiments on publicly available sleep staging benchmark datasets, SleepEDF-20 and MASS, our proposed method consistently outperformed state-of-the-art methods. Our code is available at : https://github.com/ku-milab/Measure --- ### VIDMP3: Video Editing by Representing Motion with Pose and Position Priors Authors: Sandeep Mishra, Oindrila Saha, Alan C. Bovik Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12069v1 Motion-preserved video editing is crucial for creators, particularly in scenarios that demand flexibility in both the structure and semantics of swapped objects. Despite its potential, this area remains underexplored. Existing diffusion-based editing methods excel in structure-preserving tasks, using dense guidance signals to ensure content integrity. While some recent methods attempt to address structure-variable editing, they often suffer from issues such as temporal inconsistency, subject identity drift, and the need for human intervention. To address these challenges, we introduce VidMP3, a novel approach that leverages pose and position priors to learn a generalized motion representation from source videos. Our method enables the generation of new videos that maintain the original motion while allowing for structural and semantic flexibility. Both qualitative and quantitative evaluations demonstrate the superiority of our approach over existing methods. The code will be made publicly available at https://github.com/sandeep-sm/VidMP3. --- ### HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory Authors: Junyi Xie, Yuankun Jiao, Jina Kim, Yao-Yi Chiang, Lingyi Zhao, Khurram Shafique Published: 2025-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.12067v1 Inferring demographic attributes such as age, sex, or income level from human mobility patterns enables critical applications such as targeted public health interventions, equitable urban planning, and personalized transportation services. Existing mobility-based demographic inference studies heavily rely on large-scale trajectory data with demographic labels, leading to limited interpretability and poor generalizability across different datasets and user groups. We propose HiCoTraj (Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory), a framework that leverages LLMs' zero-shot learning and semantic understanding capabilities to perform demographic inference without labeled training data. HiCoTraj transforms trajectories into semantically rich, natural language representations by creating detailed activity chronicles and multi-scale visiting summaries. Then HiCoTraj uses a novel hierarchical chain of thought reasoning to systematically guide LLMs through three cognitive stages: factual feature extraction, behavioral pattern analysis, and demographic inference with structured output. This approach addresses the scarcity challenge of labeled demographic data while providing transparent reasoning chains. Experimental evaluation on real-world trajectory data demonstrates that HiCoTraj achieves competitive performance across multiple demographic attributes in zero-shot scenarios. --- ### AI Agents as Universal Task Solvers Authors: Alessandro Achille, Stefano Soatto Published: 2025-10-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.12066v2 We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past data as in classical induction, the objective is to capture its algorithmic structure so as to reduce the time needed to solve new tasks. In this view, information from past experience serves not only to reduce a model's uncertainty - as in Shannon's classical theory - but to reduce the computational effort required to find solutions to unforeseen tasks. Working in the verifiable setting, where a checker or reward function is available, we establish three main results. First, we show that the optimal speed-up on a new task is tightly related to the algorithmic information it shares with the training data, yielding a theoretical justification for the power-law scaling empirically observed in reasoning models. Second, while the compression view of learning, rooted in Occam's Razor, favors simplicity, we show that transductive inference yields its greatest benefits precisely when the data-generating mechanism is most complex. Third, we identify a possible failure mode of naive scaling: in the limit of unbounded model size and compute, models with access to a reward signal can behave as savants - brute-forcing solutions without acquiring transferable reasoning strategies. Accordingly, we argue that a critical quantity to optimize when scaling reasoning models is time, whose role in learning has remained largely unexplored. --- ### ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization Authors: Sunzhu Li, Zhiyu Lin, Shuling Yang, Jiale Zhao, Wei Chen Published: 2025-10-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.12063v1 Large Reasoning Models (LRMs) are powerful, but they still suffer from inefficient and off-target reasoning. Currently, training-free methods are limited to either rigid heuristics or descriptive, non-actionable analyses. In this paper, we introduce ThinkPilot, a training-free framework that automatically optimizes LRMs reasoning. It uses an evolutionary process to generate think-prefixes, which are instructions that evolve driven by a taxonomy of reasoning behaviors to guide models toward superior performance. Extensive experiments demonstrate ThinkPilot's broad effectiveness: it significantly improves the accuracy-length trade-off for efficient reasoning, drastically improves safety (for example, cutting the StrongREJECT score of DeepSeek-R1-Distill-Qwen-32B from 27.0% to 0.7), and enhances instruction following. It also synergizes with existing training-based methods. Our analysis reveals that think-prefixes can reliably control LRMs' reasoning behaviors, and that different tasks have strong preferences for specific behavioral distributions. By automatically identifying and eliciting these behaviors, ThinkPilot provides a generalizable framework for aligning LRMs reasoning with task demands. Data and code are available at https://github.com/teqkilla/ThinkPilot --- ### Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response Authors: Yiheng Chen, Lingyao Li, Zihui Ma, Qikai Hu, Yilun Zhu, Min Deng, Runlong Yu Published: 2025-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.12061v2 Effective disaster response is essential for safeguarding lives and property. Existing statistical approaches often lack semantic context, generalize poorly across events, and offer limited interpretability. While Large language models (LLMs) provide few-shot generalization, they remain text-bound and blind to geography. To bridge this gap, we introduce a Geospatial Awareness Layer (GAL) that grounds LLM agents in structured earth data. Starting from raw wildfire detections, GAL automatically retrieves and integrates infrastructure, demographic, terrain, and weather information from external geodatabases, assembling them into a concise, unit-annotated perception script. This enriched context enables agents to produce evidence-based resource-allocation recommendations (e.g., personnel assignments, budget allocations), further reinforced by historical analogs and daily change signals for incremental updates. We evaluate the framework in real wildfire scenarios across multiple LLM models, showing that geospatially grounded agents can outperform baselines. The proposed framework can generalize to other hazards such as floods and hurricanes. --- ### Your VAR Model is Secretly an Efficient and Explainable Generative Classifier Authors: Yi-Chung Chen, David I. Inouye, Jing Gao Published: 2025-10-14 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.12060v2 Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area has been largely driven by diffusion-based models, whose substantial computational cost severely limits scalability. This exclusive focus on diffusion-based methods has also constrained our understanding of generative classifiers. In this work, we propose a novel generative classifier built on recent advances in visual autoregressive (VAR) modeling, which offers a new perspective for studying generative classifiers. To further enhance its performance, we introduce the Adaptive VAR Classifier$^+$ (A-VARC$^+$), which achieves a superior trade-off between accuracy and inference speed, thereby significantly improving practical applicability. Moreover, we show that the VAR-based method exhibits fundamentally different properties from diffusion-based methods. In particular, due to its tractable likelihood, the VAR-based classifier enables visual explainability via token-wise mutual information and demonstrates inherent resistance to catastrophic forgetting in class-incremental learning tasks. --- ### APGNet: Adaptive Prior-Guided for Underwater Camouflaged Object Detection Authors: Xinxin Huang, Han Sun, Junmin Cai, Ningzhong Liu, Huiyu Zhou Published: 2025-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.12056v1 Detecting camouflaged objects in underwater environments is crucial for marine ecological research and resource exploration. However, existing methods face two key challenges: underwater image degradation, including low contrast and color distortion, and the natural camouflage of marine organisms. Traditional image enhancement techniques struggle to restore critical features in degraded images, while camouflaged object detection (COD) methods developed for terrestrial scenes often fail to adapt to underwater environments due to the lack of consideration for underwater optical characteristics. To address these issues, we propose APGNet, an Adaptive Prior-Guided Network, which integrates a Siamese architecture with a novel prior-guided mechanism to enhance robustness and detection accuracy. First, we employ the Multi-Scale Retinex with Color Restoration (MSRCR) algorithm for data augmentation, generating illumination-invariant images to mitigate degradation effects. Second, we design an Extended Receptive Field (ERF) module combined with a Multi-Scale Progressive Decoder (MPD) to capture multi-scale contextual information and refine feature representations. Furthermore, we propose an adaptive prior-guided mechanism that hierarchically fuses position and boundary priors by embedding spatial attention in high-level features for coarse localization and using deformable convolution to refine contours in low-level features. Extensive experimental results on two public MAS datasets demonstrate that our proposed method APGNet outperforms 15 state-of-art methods under widely used evaluation metrics. --- ### MIARec: Mutual-influence-aware Heterogeneous Network Embedding for Scientific Paper Recommendation Authors: Wenjin Xie, Tao Jia Published: 2025-10-14 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.12054v1 With the rapid expansion of scientific literature, scholars increasingly demand precise and high-quality paper recommendations. Among various recommendation methodologies, graph-based approaches have garnered attention by effectively exploiting the structural characteristics inherent in scholarly networks. However, these methods often overlook the asymmetric academic influence that is prevalent in scholarly networks when learning graph representations. To address this limitation, this study proposes the Mutual-Influence-Aware Recommendation (MIARec) model, which employs a gravity-based approach to measure the mutual academic influence between scholars and incorporates this influence into the feature aggregation process during message propagation in graph representation learning. Additionally, the model utilizes a multi-channel aggregation method to capture both individual embeddings of distinct single relational sub-networks and their interdependent embeddings, thereby enabling a more comprehensive understanding of the heterogeneous scholarly network. Extensive experiments conducted on real-world datasets demonstrate that the MIARec model outperforms baseline models across three primary evaluation metrics, indicating its effectiveness in scientific paper recommendation tasks. --- ### APCE: Adaptive Progressive Context Expansion for Long Context Processing Authors: Baisub Lee, Sanghyun Byun, Mohanad Odema, Jung Guack, Jacob Song, Woo Seong Chung Published: 2025-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.12051v1 Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache scaling in memory as sequence length increases; (2) the ContextRot phenomena where empirical evidence suggests that transformer architecture's performance degrades with increasing context length. Given the shared dependency on the input, a natural question arises: Can we surgically select the most important input chunks for processing to synergistically (a) reduce the memory footprint, and (b) mitigate the ContextRot effects? In this paper, we answer this question in the affirmative for long-context summarization tasks. We propose APCE as a context-aware solution to select the most important input chunks through low-dimensional semantic similarity matching with the current query. By directly operating on the input, APCE decouples from strict dependency on underlying hardware or CUDA environments, promising a compatible solution scalable to different deployment systems. Our empirical evaluations have demonstrated superior or on-par summarization performance for APCE compared to the full dense baseline using a fraction (50%-70%) of the input sequence resulting in KV-cache and self-attention memory efficiency improvements. We hope our findings inspire further research on context-aware efficiency solutions for LCTMs geared towards other relevant long-context tasks. --- ### Generative AI and Sales Productivity: Field Experiments in Online Retail Authors: Lu Fang, Zhe Yuan, Kaifu Zhang, Dante Donati, Miklos Sarvary Published: 2025-10-14 Categories: econ.GN, cs.AI arXiv: https://arxiv.org/abs/2510.12049v6 We quantify the short-term impact of Generative Artificial Intelligence (GenAI) on sales performance through a series of large-scale randomized field experiments involving millions of users and products at a leading cross-border online retail platform. Over 2023-2024, the platform integrated GenAI into seven business workflows spanning customer service, consumer-product matching, advertising, and seller services. We find that GenAI adoption increases sales in most workflows, with effects ranging from no detectable impact to $16.3\%$, depending on GenAI's marginal contribution relative to baseline firm practices. Across the four GenAI applications with positive sales effects, the implied annual incremental value is roughly $\$5$ per consumer$-$an economically meaningful impact given the retailer's scale and the early stage of GenAI adoption. The gains operate primarily through higher conversion rates rather than larger cart values, consistent with GenAI improving the shopping experience by reducing search, information, communication, and personalization frictions. Importantly, these effects are not associated with worse post-purchase outcomes, as product return rates and customer ratings do not deteriorate. Finally, we document substantial demand-side heterogeneity, with larger gains for less experienced consumers. Our findings provide novel, large-scale causal evidence on how GenAI shapes sales productivity in online retail, highlighting both its immediate value and broader potential. --- ### ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation Authors: Soohan Lim, Joonghyuk Hahn, Hyunwoo Park, Sang-Ki Ko, Yo-Sub Han Published: 2025-10-14 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2510.12047v4 Current code generation evaluation measures functional correctness on well-formed inputs that satisfy all input preconditions. This paradigm has a critical limitation: task descriptions often leave these preconditions implicit, while evaluation filters out inputs that violate them. As a result, generated code may achieve high pass@k scores while failing to enforce the preconditions that the task actually requires. To address this gap, we introduce ContractEval, a benchmark for evaluating whether generated code enforces such preconditions--commonly referred to as contracts. Built on HumanEval+ and MBPP+, ContractEval consists of 364 tasks, each with three components: (i) descriptions reconstructed to explicitly state the contracts, (ii) test cases synthesized through a neuro-symbolic pipeline that pairs an LLM with an SMT solver to evaluate whether generated code satisfies these contracts, and (iii) reference code combined with contracts. Using ContractEval to evaluate five representative open-source code LLMs, we reveal a stark disparity between functional correctness and contract satisfaction. Under standard prompting, these models achieve pass@1 of 75-82% with 0% contract satisfaction. Even when contracts are explicitly stated in the prompt, the satisfaction rate reaches only 23-41%. This indicates that current LLMs struggle to satisfy contracts in their generated code, establishing contract satisfaction as a crucial and previously overlooked axis of code generation quality. Our code is available at https://github.com/suhanmen/ContractEval. --- ### Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models Authors: Yukun Zhang, Qi Dong Published: 2025-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.12044v1 Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach overlooks the functional specialization within the Transformer architecture, where different layers are known to handle distinct tasks from syntax to abstract reasoning. In this paper, we challenge this one-size-fits-all paradigm by introducing Hierarchical Alignment, a novel method that applies targeted DPO to distinct functional blocks of a model's layers: local (syntax), intermediate (logic), and global (factuality). Through a series of controlled experiments on state-of-the-art models like Llama-3.1-8B and Qwen1.5-7B using LoRA for surgical fine-tuning, our results, evaluated by a powerful LLM-as-Judge, demonstrate significant and predictable improvements. Specifically, aligning the local layers (Local-Align) enhances grammatical fluency. More importantly, aligning the global layers (Global-Align) not only improves factual consistency as hypothesized but also proves to be the most effective strategy for enhancing logical coherence, outperforming all baselines. Critically, all hierarchical strategies successfully avoid the "alignment tax" observed in standard DPO, where gains in fluency come at the cost of degraded logical reasoning. These findings establish a more resource-efficient, controllable, and interpretable path for model alignment, highlighting the immense potential of shifting from monolithic optimization to structure-aware surgical fine-tuning to build more advanced and reliable LLMs. --- ### POET: Preference Optimization for Enhanced Text-to-Image Generation Authors: Ruibo Chen, Jiacheng Pan, Heng Huang, Zhenheng Yang Published: 2025-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.12041v3 Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified user prompts due to a distributional gap with their descriptive training captions. This frequently leads to suboptimal image-text alignment, aesthetics, and overall visual quality. To bridge this gap, we propose POET (\textbf{P}reference \textbf{O}ptimization for \textbf{E}nhanced \textbf{T}ext-to-Image generation), an automated prompt rewriting framework that leverages large language models (LLMs) to refine user inputs before feeding them into frozen T2I backbones. POET introduces a carefully designed composite reward system and an iterative Direct Preference Optimization (DPO) training pipeline, enabling the rewriter to learn model-preferred prompt structures directly from multimodal feedback without requiring costly high-quality supervised fine-tuning (SFT) data. Extensive evaluations across diverse T2I models and benchmarks show that our prompt rewriter consistently improves image-text alignment, visual quality, and aesthetics, outperforming strong baselines. Furthermore, we demonstrate strong transferability by showing that a rewriter trained on one T2I backbone generalizes effectively to others without needing to be retrained. These findings highlight that POET is an effective, robust, and practical model-agnostic strategy for improving T2I systems. --- ### Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions Authors: Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Salman Avestimehr Published: 2025-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.12040v1 The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including question answering, machine translation, and text summarization. Yet, their deployment in real-world applications has raised concerns over reliability and trustworthiness, as LLMs remain prone to hallucinations that produce plausible but factually incorrect outputs. Uncertainty quantification (UQ) has emerged as a central research direction to address this issue, offering principled measures for assessing the trustworthiness of model generations. We begin by introducing the foundations of UQ, from its formal definition to the traditional distinction between epistemic and aleatoric uncertainty, and then highlight how these concepts have been adapted to the context of LLMs. Building on this, we examine the role of UQ in hallucination detection, where quantifying uncertainty provides a mechanism for identifying unreliable generations and improving reliability. We systematically categorize a wide spectrum of existing methods along multiple dimensions and present empirical results for several representative approaches. Finally, we discuss current limitations and outline promising future research directions, providing a clearer picture of the current landscape of LLM UQ for hallucination detection. --- ### On the Interplay between Human Label Variation and Model Fairness Authors: Kemal Kurniawan, Meladel Mistica, Timothy Baldwin, Jey Han Lau Published: 2025-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.12036v2 The impact of human label variation (HLV) on model fairness is an unexplored topic. This paper examines the interplay by comparing training on majority-vote labels with a range of HLV methods. Our experiments show that without explicit debiasing, HLV training methods have a positive impact on fairness under certain configurations. --- ### CausalTrace: A Neurosymbolic Causal Analysis Agent for Smart Manufacturing Authors: Chathurangi Shyalika, Aryaman Sharma, Fadi El Kalach, Utkarshani Jaimini, Cory Henson, Ramy Harik, Amit Sheth Published: 2025-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.12033v1 Modern manufacturing environments demand not only accurate predictions but also interpretable insights to process anomalies, root causes, and potential interventions. Existing AI systems often function as isolated black boxes, lacking the seamless integration of prediction, explanation, and causal reasoning required for a unified decision-support solution. This fragmentation limits their trustworthiness and practical utility in high-stakes industrial environments. In this work, we present CausalTrace, a neurosymbolic causal analysis module integrated into the SmartPilot industrial CoPilot. CausalTrace performs data-driven causal analysis enriched by industrial ontologies and knowledge graphs, including advanced functions such as causal discovery, counterfactual reasoning, and root cause analysis (RCA). It supports real-time operator interaction and is designed to complement existing agents by offering transparent, explainable decision support. We conducted a comprehensive evaluation of CausalTrace using multiple causal assessment methods and the C3AN framework (i.e. Custom, Compact, Composite AI with Neurosymbolic Integration), which spans principles of robustness, intelligence, and trustworthiness. In an academic rocket assembly testbed, CausalTrace achieved substantial agreement with domain experts (ROUGE-1: 0.91 in ontology QA) and strong RCA performance (MAP@3: 94%, PR@2: 97%, MRR: 0.92, Jaccard: 0.92). It also attained 4.59/5 in the C3AN evaluation, demonstrating precision and reliability for live deployment. --- ### Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models Authors: Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee Published: 2025-10-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.12032v1 Recent advancements in large language models (LLMs) have shown strong performance in natural language understanding and generation tasks. However, LLMs continue to encounter challenges with hallucinations, where models generate plausible but incorrect information. While several factors contribute to hallucinations, the impact of ill-formed prompts, prompts with ambiguous wording, incorrect grammar, or incomplete information, was relatively under explored. To address this, we introduce Multi-stage Prompt Refinement (MPR), a framework designed to systematically improve these ill-formed prompts across multiple stages. Each stage addresses specific errors such as punctuation, typographical mistakes, and misuse of key terms, using small language models (SLMs) fine-tuned for these tasks. MPR iteratively enhances the clarity of prompts with additional context and employs a self-reflection mechanism with ranking to prioritize the most relevant input. Experimental results on hallucination benchmarks show that prompts refined by MPR achieve over an 85~\% win rate compared to their original forms, demonstrating its effectiveness in reducing hallucinations and improving LLM output accuracy. Interestingly, we reveal that MPR can be combined with existing post-hoc hallucination mitigation frameworks, further enhancing its versatility. MPR provides a lightweight and adaptable solution for enhancing LLM reliability across various domains. --- ### CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement Authors: Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee Published: 2025-10-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.12029v1 Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect ``hallucinated" facts, undermining trust. A frequent but often overlooked cause of such errors is the use of poorly structured or vague prompts by users, leading LLMs to base responses on assumed rather than actual intentions. To mitigate hallucinations induced by these ill-formed prompts, we introduce Curative Prompt Refinement (CPR), a plug-and-play framework for curative prompt refinement that 1) cleans ill-formed prompts, and 2) generates additional informative task descriptions to align the intention of the user and the prompt using a fine-tuned small language model. When applied to language models, we discover that CPR significantly increases the quality of generation while also mitigating hallucination. Empirical studies show that prompts with CPR applied achieves over a 90\% win rate over the original prompts without any external knowledge. --- ### Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning Authors: Junsoo Oh, Wei Huang, Taiji Suzuki Published: 2025-10-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.12026v3 Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous theoretical understanding of its underlying mechanisms remains limited. In this work, we provide a theoretical analysis of Mamba's in-context learning (ICL) capability by focusing on tasks defined by low-dimensional nonlinear target functions. Specifically, we study in-context learning of a single-index model $y \approx g_*(\langle \boldsymbolβ, \boldsymbol{x} \rangle)$, which depends on only a single relevant direction $\boldsymbolβ$, referred to as feature. We prove that Mamba, pretrained by gradient-based methods, can achieve efficient ICL via test-time feature learning, extracting the relevant direction directly from context examples. Consequently, we establish a test-time sample complexity that improves upon linear Transformers -- analyzed to behave like kernel methods -- and is comparable to nonlinear Transformers, which have been shown to surpass the Correlational Statistical Query (CSQ) lower bound and achieve near information-theoretically optimal rate in previous works. Our analysis reveals the crucial role of the nonlinear gating mechanism in Mamba for feature extraction, highlighting it as the fundamental driver behind Mamba's ability to achieve both computational efficiency and high performance. --- ### Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM Authors: Alice Saebom Kwak, Maria Alexeeva, Gus Hahn-Powell, Keith Alcock, Kevin McLaughlin, Doug McCorkle, Gabe McNunn, Mihai Surdeanu Published: 2025-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.12023v1 The current trend in information extraction (IE) is to rely extensively on large language models, effectively discarding decades of experience in building symbolic or statistical IE systems. This paper compares a neuro-symbolic (NS) and an LLM-based IE system in the agricultural domain, evaluating them on nine interviews across pork, dairy, and crop subdomains. The LLM-based system outperforms the NS one (F1 total: 69.4 vs. 52.7; core: 63.0 vs. 47.2), where total includes all extracted information and core focuses on essential details. However, each system has trade-offs: the NS approach offers faster runtime, greater control, and high accuracy in context-free tasks but lacks generalizability, struggles with contextual nuances, and requires significant resources to develop and maintain. The LLM-based system achieves higher performance, faster deployment, and easier maintenance but has slower runtime, limited control, model dependency and hallucination risks. Our findings highlight the "hidden cost" of deploying NLP systems in real-world applications, emphasizing the need to balance performance, efficiency, and control. --- ### PESTalk: Speech-Driven 3D Facial Animation with Personalized Emotional Styles Authors: Tianshun Han, Benjia Zhou, Ajian Liu, Yanyan Liang, Du Zhang, Zhen Lei, Jun Wan Published: 2025-10-13 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2512.05121v1 PESTalk is a novel method for generating 3D facial animations with personalized emotional styles directly from speech. It overcomes key limitations of existing approaches by introducing a Dual-Stream Emotion Extractor (DSEE) that captures both time and frequency-domain audio features for fine-grained emotion analysis, and an Emotional Style Modeling Module (ESMM) that models individual expression patterns based on voiceprint characteristics. To address data scarcity, the method leverages a newly constructed 3D-EmoStyle dataset. Evaluations demonstrate that PESTalk outperforms state-of-the-art methods in producing realistic and personalized facial animations. --- ### Decoding non-invasive brain activity with novel deep-learning approaches Authors: Richard Csaky Published: 2025-10-13 Categories: eess.SP, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2510.24733v1 This thesis delves into the world of non-invasive electrophysiological brain signals like electroencephalography (EEG) and magnetoencephalography (MEG), focusing on modelling and decoding such data. The research aims to investigate what happens in the brain when we perceive visual stimuli or engage in covert speech (inner speech) and enhance the decoding performance of such stimuli. The thesis is divided into two main sections, methodological and experimental work. A central concern in both sections is the large variability present in electrophysiological recordings, whether it be within-subject or between-subject variability, and to a certain extent between-dataset variability. In the methodological sections, we explore the potential of deep learning for brain decoding. We present advancements in decoding visual stimuli using linear models at the individual subject level. We then explore how deep learning techniques can be employed for group decoding, introducing new methods to deal with between-subject variability. Finally, we also explores novel forecasting models of MEG data based on convolutional and Transformer-based architectures. In particular, Transformer-based models demonstrate superior capabilities in generating signals that closely match real brain data, thereby enhancing the accuracy and reliability of modelling the brain's electrophysiology. In the experimental section, we present a unique dataset containing high-trial inner speech EEG, MEG, and preliminary optically pumped magnetometer (OPM) data. Our aim is to investigate different types of inner speech and push decoding performance by collecting a high number of trials and sessions from a few participants. However, the decoding results are found to be mostly negative, underscoring the difficulty of decoding inner speech. ---