# Research Papers — 2025-10 · bundle page 106 of 217 > Full-text markdown of papers #5251–5300 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/106 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/105.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/107.md) ### PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering Authors: Md Mahadi Hasan Nahid, Davood Rafiei Published: 2025-10-16 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.14278v2 Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We propose PRISM, an agentic retrieval framework that leverages large language models (LLMs) in a structured loop to retrieve relevant evidence with high precision and recall. PRISM decomposes retrieval into three specialized agents: a Question Analyzer that breaks complex queries into sub-questions, a Selector that identifies the most relevant context for each sub-question (focusing on precision), and an Adder that brings in any missing evidence (focusing on recall). The iterative interaction between the Selector and Adder produces a compact yet comprehensive evidence set, avoiding both brittle error propagation and noisy context accumulation. It achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on significantly less irrelevant information. Experiments on four challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG, demonstrate that our approach consistently outperforms strong baselines. --- ### Qwen3Guard Technical Report Authors: Haiquan Zhao, Chenhan Yuan, Fei Huang, Xiaomeng Hu, Yichang Zhang, An Yang, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin, Baosong Yang, Chen Cheng et al. Published: 2025-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14276v1 As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in static evaluation settings, face two major limitations in real-world applications: (1) they typically output only binary "safe/unsafe" labels, which can be interpreted inconsistently across diverse safety policies, rendering them incapable of accommodating varying safety tolerances across domains; and (2) they require complete model outputs before performing safety checks, making them fundamentally incompatible with streaming LLM inference, thereby preventing timely intervention during generation and increasing exposure to harmful partial outputs. To address these challenges, we present Qwen3Guard, a series of multilingual safety guardrail models with two specialized variants: Generative Qwen3Guard, which casts safety classification as an instruction-following task to enable fine-grained tri-class judgments (safe, controversial, unsafe); and Stream Qwen3Guard, which introduces a token-level classification head for real-time safety monitoring during incremental text generation. Both variants are available in three sizes (0.6B, 4B, and 8B parameters) and support up to 119 languages and dialects, providing comprehensive, scalable, and low-latency safety moderation for global LLM deployments. Evaluated across English, Chinese, and multilingual benchmarks, Qwen3Guard achieves state-of-the-art performance in both prompt and response safety classification. All models are released under the Apache 2.0 license for public use. --- ### Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters Authors: Lifu Tu, Yingbo Zhou, Semih Yavuz Published: 2025-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14274v2 Training effective multilingual embedding models presents unique challenges due to the diversity of languages and task objectives. Although small multilingual models (<1 B parameters) perform well on multilingual tasks generally, they consistently lag behind larger models (>1 B) in the most prevalent use case: retrieval. This raises a critical question: Can smaller models be retrofitted specifically for retrieval tasks to enhance their performance? In this work, we investigate key factors that influence the effectiveness of multilingual embeddings, focusing on training data scale, negative sampling strategies, and data diversity. We find that while increasing the scale of training data yields initial performance gains, these improvements quickly plateau - indicating diminishing returns. Incorporating hard negatives proves essential for consistently improving retrieval accuracy. Furthermore, our analysis reveals that task diversity in the training data contributes more significantly to performance than language diversity alone. As a result, we develop a compact (approximately 300M) multilingual model that achieves retrieval performance comparable to or even surpassing current strong 7B models. --- ### CLEAR: Causal Learning Framework For Robust Histopathology Tumor Detection Under Out-Of-Distribution Shifts Authors: Kieu-Anh Truong Thi, Huy-Hieu Pham, Duc-Trong Le Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14273v2 Domain shift in histopathology, often caused by differences in acquisition processes or data sources, poses a major challenge to the generalization ability of deep learning models. Existing methods primarily rely on modeling statistical correlations by aligning feature distributions or introducing statistical variation, yet they often overlook causal relationships. In this work, we propose a novel causal-inference-based framework that leverages semantic features while mitigating the impact of confounders. Our method implements the front-door principle by designing transformation strategies that explicitly incorporate mediators and observed tissue slides. We validate our method on the CAMELYON17 dataset and a private histopathology dataset, demonstrating consistent performance gains across unseen domains. As a result, our approach achieved up to a 7% improvement in both the CAMELYON17 dataset and the private histopathology dataset, outperforming existing baselines. These results highlight the potential of causal inference as a powerful tool for addressing domain shift in histopathology image analysis. --- ### Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation Authors: Yilun Zheng, Dan Yang, Jie Li, Lin Shang, Lihui Chen, Jiahao Xu, Sitao Luan Published: 2025-10-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.14271v1 Retrieval-Augmented Generation (RAG) systems enable large language models (LLMs) instant access to relevant information for the generative process, demonstrating their superior performance in addressing common LLM challenges such as hallucination, factual inaccuracy, and the knowledge cutoff. Graph-based RAG further extends this paradigm by incorporating knowledge graphs (KGs) to leverage rich, structured connections for more precise and inferential responses. A critical challenge, however, is that most Graph-based RAG systems rely on LLMs for automated KG construction, often yielding noisy KGs with redundant entities and unreliable relationships. This noise degrades retrieval and generation performance while also increasing computational cost. Crucially, current research does not comprehensively address the denoising problem for LLM-generated KGs. In this paper, we introduce DEnoised knowledge Graphs for Retrieval Augmented Generation (DEG-RAG), a framework that addresses these challenges through: (1) entity resolution, which eliminates redundant entities, and (2) triple reflection, which removes erroneous relations. Together, these techniques yield more compact, higher-quality KGs that significantly outperform their unprocessed counterparts. Beyond the methods, we conduct a systematic evaluation of entity resolution for LLM-generated KGs, examining different blocking strategies, embedding choices, similarity metrics, and entity merging techniques. To the best of our knowledge, this is the first comprehensive exploration of entity resolution in LLM-generated KGs. Our experiments demonstrate that this straightforward approach not only drastically reduces graph size but also consistently improves question answering performance across diverse popular Graph-based RAG variants. --- ### GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering Authors: Alexander Valverde, Brian Xu, Yuyin Zhou, Meng Xu, Hongyun Wang Published: 2025-10-16 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2510.14270v3 Scene reconstruction has emerged as a central challenge in computer vision, with approaches such as Neural Radiance Fields (NeRF) and Gaussian Splatting achieving remarkable progress. While Gaussian Splatting demonstrates strong performance on large-scale datasets, it often struggles to capture fine details or maintain realism in regions with sparse coverage, largely due to the inherent limitations of sparse 3D training data. In this work, we propose GauSSmart, a hybrid method that effectively bridges 2D foundational models and 3D Gaussian Splatting reconstruction. Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision from foundational models such as DINO, to enhance Gaussian-based scene reconstruction. By leveraging 2D segmentation priors and high-dimensional feature embeddings, our method guides the densification and refinement of Gaussian splats, improving coverage in underrepresented areas and preserving intricate structural details. We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting in the majority of evaluated scenes. Our results demonstrate the significant potential of hybrid 2D-3D approaches, highlighting how the thoughtful combination of 2D foundational models with 3D reconstruction pipelines can overcome the limitations inherent in either approach alone. --- ### Nonparametric Data Attribution for Diffusion Models Authors: Yutian Zhao, Chao Du, Xiaosen Zheng, Tianyu Pang, Min Lin Published: 2025-10-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.14269v1 Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, limiting their applicability in proprietary or large-scale settings. We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images. Our approach is grounded in the analytical form of the optimal score function and naturally extends to multiscale representations, while remaining computationally efficient through convolution-based acceleration. In addition to producing spatially interpretable attributions, our framework uncovers patterns that reflect intrinsic relationships between training data and outputs, independent of any specific model. Experiments demonstrate that our method achieves strong attribution performance, closely matching gradient-based approaches and substantially outperforming existing nonparametric baselines. Code is available at https://github.com/sail-sg/NDA. --- ### Experimental Demonstration of Event-based Optical Camera Communication in Long-Range Outdoor Environment Authors: Miu Sumino, Mayu Ishii, Shun Kaizu, Daisuke Hisano, Yu Nakayama Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14266v1 We propose a robust demodulation scheme for optical camera communication systems using an event-based vision sensor, combining OOK with toggle demodulation and a digital phase-locked loop. This is the first report to achieve a $\mathrm{BER} < 10^{-3}$ at 200m-60kbps and 400m-30kbps in outdoor experiments. --- ### MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning Authors: Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An et al. Published: 2025-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14265v1 With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existing benchmarks designed to assess the reasoning abilities of large models tend to be limited in scope and lack the flexibility to adapt their difficulty according to the evolving reasoning capacities of the models. To address this, we propose MorphoBench, a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. Specifically, we curate the benchmark by selecting and collecting complex reasoning questions from existing benchmarks and sources such as Olympiad-level competitions. Additionally, MorphoBench adaptively modifies the analytical challenge of questions by leveraging key statements generated during the model's reasoning process. Furthermore, it includes questions generated using simulation software, enabling dynamic adjustment of benchmark difficulty with minimal resource consumption. We have gathered over 1,300 test questions and iteratively adjusted the difficulty of MorphoBench based on the reasoning capabilities of models such as o3 and GPT-5. MorphoBench enhances the comprehensiveness and validity of model reasoning evaluation, providing reliable guidance for improving both the reasoning abilities and scientific robustness of large models. The code has been released in https://github.com/OpenDCAI/MorphoBench. --- ### CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions Authors: Zihao Fu, Ming Liao, Chris Russell, Zhenguang G. Cai Published: 2025-10-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.14262v1 Large language models have achieved remarkable success but remain largely black boxes with poorly understood internal mechanisms. To address this limitation, many researchers have proposed various interpretability methods including mechanistic analysis, probing classifiers, and activation visualization, each providing valuable insights from different perspectives. Building upon this rich landscape of complementary approaches, we introduce CAST (Compositional Analysis via Spectral Tracking), a probe-free framework that contributes a novel perspective by analyzing transformer layer functions through direct transformation matrix estimation and comprehensive spectral analysis. CAST offers complementary insights to existing methods by estimating the realized transformation matrices for each layer using Moore-Penrose pseudoinverse and applying spectral analysis with six interpretable metrics characterizing layer behavior. Our analysis reveals distinct behaviors between encoder-only and decoder-only models, with decoder models exhibiting compression-expansion cycles while encoder models maintain consistent high-rank processing. Kernel analysis further demonstrates functional relationship patterns between layers, with CKA similarity matrices clearly partitioning layers into three phases: feature extraction, compression, and specialization. --- ### Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior Authors: Rahul Nadkarni, Yanai Elazar, Hila Gonen, Noah A. Smith Published: 2025-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14261v2 We present an experimental recipe for studying the relationship between training data and language model (LM) behavior. We outline steps for intervening on data batches -- i.e., ``rewriting history'' -- and then retraining model checkpoints over that data to test hypotheses relating data to behavior. Our recipe breaks down such an intervention into stages that include selecting evaluation items from a benchmark that measures model behavior, matching relevant documents to those items, and modifying those documents before retraining and measuring the effects. We demonstrate the utility of our recipe through case studies on factual knowledge acquisition in LMs, using both cooccurrence statistics and information retrieval methods to identify documents that might contribute to knowledge learning. Our results supplement past observational analyses that link cooccurrence to model behavior, while demonstrating that extant methods for identifying relevant training documents do not fully explain an LM's ability to correctly answer knowledge questions. Overall, we outline a recipe that researchers can follow to test further hypotheses about how training data affects model behavior. Our code is made publicly available to promote future work. --- ### MatchAttention: Embedding Explicit Matching Constraints into Attention for Efficient Stereo Matching Authors: Tingman Yan, Tao Liu, Chenghao Li, Quanli Liu, Xilian Yang, Qunfei Zhao, Zeyang Xia Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14260v3 Standard attention mechanisms are not well suited to stereo matching. Global attention scales quadratically and provides no explicit matching constraint, while local attention is efficient but loses long-range correspondences. We propose MatchAttention, an attention mechanism that embeds an explicit matching constraint into attention by treating the relative position between a query and its matched key as a learnable component of attention sampling. Centering a small contiguous sampling window on this learnable relative position enforces the matching constraint and supports long-range correspondence at strictly linear attention complexity. A differentiable contiguous attention sampling (CAS) operator enables sub-pixel accuracy, and cascaded MatchAttention blocks iteratively refine the relative positions through residual connections. We instantiate MatchAttention as a hierarchical coarse-to-fine stereo network with two variants. MatchAttentionXL targets accuracy and MatchAttentionRT targets real-time edge inference. MatchAttentionXL achieves state-of-the-art accuracy on Middlebury V3 and top results across KITTI 2012/2015 and ETH3D. MatchAttentionRT runs at 9.3 ms on RTX 4060 Ti and 79.1 ms on Jetson Orin NX 16 GB at 1024 x 512, making it the first stereo model to deliver real-time edge inference without sacrificing zero-shot generalization. The code is available at https://github.com/TingmanYan/MatchAttention. --- ### Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning Authors: Xiangyu Meng, Zixian Zhang, Zhenghao Zhang, Junchao Liao, Long Qin, Weizhi Wang Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14256v3 While advanced methods like VACE and Phantom have advanced video generation for specific subjects in diverse scenarios, they struggle with multi-human identity preservation in dynamic interactions, where consistent identities across multiple characters are critical. To address this, we propose Identity-GRPO, a human feedback-driven optimization pipeline for refining multi-human identity-preserving video generation. First, we construct a video reward model trained on a large-scale preference dataset containing human-annotated and synthetic distortion data, with pairwise annotations focused on maintaining human consistency throughout the video. We then employ a GRPO variant tailored for multi-human consistency, which greatly enhances both VACE and Phantom. Through extensive ablation studies, we evaluate the impact of annotation quality and design choices on policy optimization. Experiments show that Identity-GRPO achieves up to 18.9% improvement in human consistency metrics over baseline methods, offering actionable insights for aligning reinforcement learning with personalized video generation. --- ### Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization Authors: Liao Shen, Wentao Jiang, Yiran Zhu, Jiahe Li, Tiezheng Ge, Zhiguo Cao, Bo Zheng Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14255v4 Recent advances in image-to-video (I2V) generation have achieved remarkable progress in synthesizing high-quality, temporally coherent videos from static images. Among all the applications of I2V, human-centric video generation includes a large portion. However, existing I2V models encounter difficulties in maintaining identity consistency between the input human image and the generated video, especially when the person in the video exhibits significant expression changes and movements. This issue becomes critical when the human face occupies merely a small fraction of the image. Since humans are highly sensitive to identity variations, this poses a critical yet under-explored challenge in I2V generation. In this paper, we propose Identity-Preserving Reward-guided Optimization (IPRO), a novel video diffusion framework based on reinforcement learning to enhance identity preservation. Instead of introducing auxiliary modules or altering model architectures, our approach introduces a direct and effective tuning algorithm that optimizes diffusion models using a face identity scorer. To improve performance and accelerate convergence, our method backpropagates the reward signal through the last steps of the sampling chain, enabling richer gradient feedback. We also propose a novel facial scoring mechanism that treats faces in ground-truth videos as facial feature pools, providing multi-angle facial information to enhance generalization. A KL-divergence regularization is further incorporated to stabilize training and prevent overfitting to the reward signal. Extensive experiments on Wan 2.2 I2V model and our in-house I2V model demonstrate the effectiveness of our method. Our project and code are available at https://ipro-alimama.github.io/. --- ### Generalist vs Specialist Time Series Foundation Models: Investigating Potential Emergent Behaviors in Assessing Human Health Using PPG Signals Authors: Saurabh Kataria, Yi Wu, Zhaoliang Chen, Hyunjung Gloria Kwak, Yuhao Xu, Lovely Yeswanth Panchumarthi, Ran Xiao, Jiaying Lu, Ayca Ermis, Anni Zhao, Runze Yan, Alex Federov et al. Published: 2025-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14254v1 Foundation models are large-scale machine learning models that are pre-trained on massive amounts of data and can be adapted for various downstream tasks. They have been extensively applied to tasks in Natural Language Processing and Computer Vision with models such as GPT, BERT, and CLIP. They are now also increasingly gaining attention in time-series analysis, particularly for physiological sensing. However, most time series foundation models are specialist models - with data in pre-training and testing of the same type, such as Electrocardiogram, Electroencephalogram, and Photoplethysmogram (PPG). Recent works, such as MOMENT, train a generalist time series foundation model with data from multiple domains, such as weather, traffic, and electricity. This paper aims to conduct a comprehensive benchmarking study to compare the performance of generalist and specialist models, with a focus on PPG signals. Through an extensive suite of total 51 tasks covering cardiac state assessment, laboratory value estimation, and cross-modal inference, we comprehensively evaluate both models across seven dimensions, including win score, average performance, feature quality, tuning gain, performance variance, transferability, and scalability. These metrics jointly capture not only the models' capability but also their adaptability, robustness, and efficiency under different fine-tuning strategies, providing a holistic understanding of their strengths and limitations for diverse downstream scenarios. In a full-tuning scenario, we demonstrate that the specialist model achieves a 27% higher win score. Finally, we provide further analysis on generalization, fairness, attention visualizations, and the importance of training data choice. --- ### Towards Agentic Self-Learning LLMs in Search Environment Authors: Wangtao Sun, Xiang Cheng, Jialin Fan, Yao Xu, Xing Yu, Shizhu He, Jun Zhao, Kang Liu Published: 2025-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14253v2 We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable agent training: the source of reward signals and the scale of agent task data. We find that rewards from a Generative Reward Model (GRM) outperform rigid rule-based signals for open-domain learning, and that co-evolving the GRM with the policy further boosts performance. Increasing the volume of agent task data-even when synthetically generated-substantially enhances agentic capabilities. Building on these insights, we propose \textbf{Agentic Self-Learning} (ASL), a fully closed-loop, multi-role reinforcement learning framework that unifies task generation, policy execution, and evaluation within a shared tool environment and LLM backbone. ASL coordinates a Prompt Generator, a Policy Model, and a Generative Reward Model to form a virtuous cycle of harder task setting, sharper verification, and stronger solving. Empirically, ASL delivers steady, round-over-round gains, surpasses strong RLVR baselines (e.g., Search-R1) that plateau or degrade, and continues improving under zero-labeled-data conditions, indicating superior sample efficiency and robustness. We further show that GRM verification capacity is the main bottleneck: if frozen, it induces reward hacking and stalls progress; continual GRM training on the evolving data distribution mitigates this, and a small late-stage injection of real verification data raises the performance ceiling. This work establishes reward source and data scale as critical levers for open-domain agent learning and demonstrates the efficacy of multi-role co-evolution for scalable, self-improving agents. The data and code of this paper are released at https://github.com/forangel2014/Towards-Agentic-Self-Learning --- ### MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems Authors: Jihao Zhao, Zhiyuan Ji, Simin Niu, Hanyu Wang, Feiyu Xiong, Zhiyu Li Published: 2025-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14252v1 The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilities. To address this limitation, our research transforms the text processing in RAG from passive chunking to proactive understanding, defining this process as document memory extraction with the objective of simulating human cognitive processes during reading. Building upon this, we propose the Mixtures of scenario-aware document Memories (MoM) framework, engineered to efficiently handle documents from multiple domains and train small language models (SLMs) to acquire the ability to proactively explore and construct document memories. The MoM initially instructs large language models (LLMs) to simulate domain experts in generating document logical outlines, thereby directing structured chunking and core content extraction. It employs a multi-path sampling and multi-perspective evaluation mechanism, specifically designing comprehensive metrics that represent chunk clarity and extraction completeness to select the optimal document memories. Additionally, to infuse deeper human-like reading abilities during the training of SLMs, we incorporate a reverse reasoning strategy, which deduces refined expert thinking paths from high-quality outcomes. Finally, leveraging diverse forms of content generated by MoM, we develop a three-layer document memory retrieval mechanism, which is grounded in our theoretical proof from the perspective of probabilistic modeling. Extensive experimental results across three distinct domains demonstrate that the MoM framework not only resolves text chunking challenges in existing RAG systems, providing LLMs with semantically complete document memories, but also paves the way for SLMs to achieve human-centric intelligent text processing. --- ### MACE: Mixture-of-Experts Accelerated Coordinate Encoding for Large-Scale Scene Localization and Rendering Authors: Mingkai Liu, Dikai Fan, Haohua Que, Haojia Gao, Xiao Liu, Shuxue Peng, Meixia Lin, Shengyu Gu, Ruicong Ye, Wanli Qiu, Handong Yao, Ruopeng Zhang et al. Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14251v1 Efficient localization and high-quality rendering in large-scale scenes remain a significant challenge due to the computational cost involved. While Scene Coordinate Regression (SCR) methods perform well in small-scale localization, they are limited by the capacity of a single network when extended to large-scale scenes. To address these challenges, we propose the Mixed Expert-based Accelerated Coordinate Encoding method (MACE), which enables efficient localization and high-quality rendering in large-scale scenes. Inspired by the remarkable capabilities of MOE in large model domains, we introduce a gating network to implicitly classify and select sub-networks, ensuring that only a single sub-network is activated during each inference. Furtheremore, we present Auxiliary-Loss-Free Load Balancing(ALF-LB) strategy to enhance the localization accuracy on large-scale scene. Our framework provides a significant reduction in costs while maintaining higher precision, offering an efficient solution for large-scale scene applications. Additional experiments on the Cambridge test set demonstrate that our method achieves high-quality rendering results with merely 10 minutes of training. --- ### A Physics Prior-Guided Dual-Stream Attention Network for Motion Prediction of Elastic Bragg Breakwaters Authors: Lianzi Jiang, Jianxin Zhang, Xinyu Han, Huanhe Dong, Xiangrong Wang Published: 2025-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14250v1 Accurate motion response prediction for elastic Bragg breakwaters is critical for their structural safety and operational integrity in marine environments. However, conventional deep learning models often exhibit limited generalization capabilities when presented with unseen sea states. These deficiencies stem from the neglect of natural decay observed in marine systems and inadequate modeling of wave-structure interaction (WSI). To overcome these challenges, this study proposes a novel Physics Prior-Guided Dual-Stream Attention Network (PhysAttnNet). First, the decay bidirectional self-attention (DBSA) module incorporates a learnable temporal decay to assign higher weights to recent states, aiming to emulate the natural decay phenomenon. Meanwhile, the phase differences guided bidirectional cross-attention (PDG-BCA) module explicitly captures the bidirectional interaction and phase relationship between waves and the structure using a cosine-based bias within a bidirectional cross-computation paradigm. These streams are synergistically integrated through a global context fusion (GCF) module. Finally, PhysAttnNet is trained with a hybrid time-frequency loss that jointly minimizes time-domain prediction errors and frequency-domain spectral discrepancies. Comprehensive experiments on wave flume datasets demonstrate that PhysAttnNet significantly outperforms mainstream models. Furthermore,cross-scenario generalization tests validate the model's robustness and adaptability to unseen environments, highlighting its potential as a framework to develop predictive models for complex systems in ocean engineering. --- ### Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics? Authors: Qixin Deng, Bryan Pardo, Thrasyvoulos N Pappas Published: 2025-10-16 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2510.14249v2 Understanding and modeling the relationship between language and sound are essential for applications such as music information retrieval, text-guided music generation, and audio captioning. Central to these tasks are joint language-audio embedding spaces, which map textual descriptions and auditory content into a shared representation. Although multimodal embedding models such as MS-CLAP, LAION-CLAP, MuQ-MuLan, and OpenFLAM have shown strong performance in language-audio alignment, their correspondence to human perception of timbre, a multifaceted attribute encompassing qualities such as brightness, roughness, and warmth, remains under-explored. In this paper, we evaluate these joint language-audio embedding models in terms of their ability to capture perceptual timbre semantics. Across two complementary experiments, we find that LAION-CLAP shows relatively strong and consistent alignment with human-perceived timbre semantics across both instrumental sounds and descriptor-conditioned audio effects. At the same time, the overall strength of this alignment remains limited, suggesting that current joint language-audio embeddings capture perceptual timbre semantics only partially. We also observe that, overall, reverb-induced timbre semantics are more consistently encoded than equalization-induced timbre semantics. --- ### Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation Authors: Jingwen Gu, Yiting He, Zhishuai Liu, Pan Xu Published: 2025-10-16 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2510.14246v1 Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ. We study this problem through the lens of robust Markov decision processes (RMDPs), which optimize performance against adversarial transition dynamics. Our focus is the online setting, where the agent has only limited interaction with the environment, making sample efficiency and exploration especially critical. Policy optimization, despite its success in standard RL, remains theoretically and empirically underexplored in robust RL. To bridge this gap, we propose \textbf{D}istributionally \textbf{R}obust \textbf{R}egularized \textbf{P}olicy \textbf{O}ptimization algorithm (DR-RPO), a model-free online policy optimization method that learns robust policies with sublinear regret. To enable tractable optimization within the softmax policy class, DR-RPO incorporates reference-policy regularization, yielding RMDP variants that are doubly constrained in both transitions and policies. To scale to large state-action spaces, we adopt the $d$-rectangular linear MDP formulation and combine linear function approximation with an upper confidence bonus for optimistic exploration. We provide theoretical guarantees showing that policy optimization can achieve polynomial suboptimality bounds and sample efficiency in robust RL, matching the performance of value-based approaches. Finally, empirical results across diverse domains corroborate our theory and demonstrate the robustness of DR-RPO. --- ### Event Interval Modulation: A Novel Scheme for Event-based Optical Camera Communication Authors: Miu Sumino, Mayu Ishii, Shun Kaizu, Daisuke Hisano, Yu Nakayama Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14245v1 Optical camera communication (OCC) represents a promising visible light communication technology. Nonetheless, typical OCC systems utilizing frame-based cameras are encumbered by limitations, including low bit rate and high processing load. To address these issues, OCC system utilizing an event-based vision sensor (EVS) as receivers have been proposed. The EVS enables high-speed, low-latency, and robust communication due to its asynchronous operation and high dynamic range. In existing event-based OCC systems, conventional modulation schemes such as on-off keying (OOK) and pulse position modulation have been applied, however, to the best of our knowledge, no modulation method has been proposed that fully exploits the unique characteristics of the EVS. This paper proposes a novel modulation scheme, called the event interval modulation (EIM) scheme, specifically designed for event-based OCC. EIM enables improvement in transmission speed by modulating information using the intervals between events. This paper proposes a theoretical model of EIM and conducts a proof-of-concept experiment. First, the parameters of the EVS are tuned and customized to optimize the frequency response specifically for EIM. Then, the maximum modulation order usable in EIM is determined experimentally. We conduct transmission experiments based on the obtained parameters. Finally, we report successful transmission at 28 kbps over 10 meters and 8.4 kbps over 50 meters in an indoor environment. This sets a new benchmark for bit rate in event-based OCC systems. --- ### Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation Authors: Arnaud Judge, Nicolas Duchateau, Thierry Judge, Roman A. Sandler, Joseph Z. Sokol, Christian Desrosiers, Olivier Bernard, Pierre-Marc Jodoin Published: 2025-10-16 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.14244v2 Domain adaptation methods aim to bridge the gap between datasets by enabling knowledge transfer across domains, reducing the need for additional expert annotations. However, many approaches struggle with reliability in the target domain, an issue particularly critical in medical image segmentation, where accuracy and anatomical validity are essential. This challenge is further exacerbated in spatio-temporal data, where the lack of temporal consistency can significantly degrade segmentation quality, and particularly in echocardiography, where the presence of artifacts and noise can further hinder segmentation performance. To address these issues, we present RL4Seg3D, an unsupervised domain adaptation framework for 2D + time echocardiography segmentation. RL4Seg3D integrates novel reward functions and a fusion scheme to enhance key landmark precision in its segmentations while processing full-sized input videos. By leveraging reinforcement learning for image segmentation, our approach improves accuracy, anatomical validity, and temporal consistency while also providing, as a beneficial side effect, a robust uncertainty estimator, which can be used at test time to further enhance segmentation performance. We demonstrate the effectiveness of our framework on over 30,000 echocardiographic videos, showing that it outperforms standard domain adaptation techniques without the need for any labels on the target domain. Code is available at https://github.com/arnaudjudge/RL4Seg3D. --- ### Spatial Computing Communications for Multi-User Virtual Reality in Distributed Mobile Edge Computing Network Authors: Caolu Xu, Zhiyong Chen, Meixia Tao, Li Song, Wenjun Zhang Published: 2025-10-16 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2510.14243v1 Immersive virtual reality (VR) applications impose stringent requirements on latency, energy efficiency, and computational resources, particularly in multi-user interactive scenarios. To address these challenges, we introduce the concept of spatial computing communications (SCC), a framework designed to meet the latency and energy demands of multi-user VR over distributed mobile edge computing (MEC) networks. SCC jointly represents the physical space, defined by users and base stations, and the virtual space, representing shared immersive environments, using a probabilistic model of user dynamics and resource requirements. The resource deployment task is then formulated as a multi-objective combinatorial optimization (MOCO) problem that simultaneously minimizes system latency and energy consumption across distributed MEC resources. To solve this problem, we propose MO-CMPO, a multi-objective consistency model with policy optimization that integrates supervised learning and reinforcement learning (RL) fine-tuning guided by preference weights. Leveraging a sparse graph neural network (GNN), MO-CMPO efficiently generates Pareto-optimal solutions. Simulations with real-world New Radio base station datasets demonstrate that MO-CMPO achieves superior hypervolume performance and significantly lower inference latency than baseline methods. Furthermore, the analysis reveals practical deployment patterns: latency-oriented solutions favor local MEC execution to reduce transmission delay, while energy-oriented solutions minimize redundant placements to save energy. --- ### Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs Authors: Parsa Hejabi, Elnaz Rahmati, Alireza S. Ziabari, Morteza Dehghani Published: 2025-10-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.14242v2 Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to such perturbations. $F^2C$ is composed of two key components. The first, Consensus Cross-Entropy (CCE), uses a majority vote across prompt variations to create a hard pseudo-label. The second is a representation alignment loss that pulls lower-confidence and non-majority predictors toward the consensus established by high-confidence, majority-voting variations. We evaluate our method on 11 datasets spanning four NLP tasks, with 4-15 prompt variations per dataset. On average, $F^2C$ raises observed agreement by 11.62%, improves mean $F_1$ by 8.94%, and reduces performance variance across formats by 3.29%. In out-of-domain evaluations, $F^2C$ generalizes effectively, increasing $\overline{F_1}$ and agreement while decreasing variance across most source-target pairs. Finally, when trained on only a subset of prompt perturbations and evaluated on held-out formats, $F^2C$ consistently improves both performance and agreement while reducing variance. These findings highlight $F^2C$ as an effective unsupervised method for enhancing LLM consistency, performance, and generalization under prompt perturbations. Code is available at https://github.com/ParsaHejabi/Flip-Flop-Consistency-Unsupervised-Training-for-Robustness-to-Prompt-Perturbations-in-LLMs. --- ### PIA: Deepfake Detection Using Phoneme-Temporal and Identity-Dynamic Analysis Authors: Soumyya Kanti Datta, Tanvi Ranga, Chengzhe Sun, Siwei Lyu Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14241v1 The rise of manipulated media has made deepfakes a particularly insidious threat, involving various generative manipulations such as lip-sync modifications, face-swaps, and avatar-driven facial synthesis. Conventional detection methods, which predominantly depend on manually designed phoneme-viseme alignment thresholds, fundamental frame-level consistency checks, or a unimodal detection strategy, inadequately identify modern-day deepfakes generated by advanced generative models such as GANs, diffusion models, and neural rendering techniques. These advanced techniques generate nearly perfect individual frames yet inadvertently create minor temporal discrepancies frequently overlooked by traditional detectors. We present a novel multimodal audio-visual framework, Phoneme-Temporal and Identity-Dynamic Analysis(PIA), incorporating language, dynamic face motion, and facial identification cues to address these limitations. We utilize phoneme sequences, lip geometry data, and advanced facial identity embeddings. This integrated method significantly improves the detection of subtle deepfake alterations by identifying inconsistencies across multiple complementary modalities. Code is available at https://github.com/skrantidatta/PIA --- ### LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild Authors: Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty Published: 2025-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14240v5 Deep research -- producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources -- marks an important frontier for agentic systems. To rigorously evaluate this ability, four principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, (3) unambiguous, ensuring consistent interpretation across users, and (4) multi-faceted and search-intensive, requiring search over numerous web sources and in-depth analysis. Existing benchmarks fall short of these principles, often focusing on narrow domains or posing ambiguous questions that hinder fair comparison. Guided by these principles, we introduce LiveResearchBench, a benchmark of 100 expert-curated tasks spanning daily life, enterprise, and academia, each requiring extensive, dynamic, real-time web search and synthesis. Built with over 1,500 hours of human labor, LiveResearchBench provides a rigorous basis for systematic evaluation. To evaluate citation-grounded long-form reports, we introduce DeepEval, a comprehensive suite covering both content- and report-level quality, including coverage, presentation, citation accuracy and association, consistency and depth of analysis. DeepEval integrates four complementary evaluation protocols, each designed to ensure stable assessment and high agreement with human judgments. Using LiveResearchBench and DeepEval, we conduct a comprehensive evaluation of 17 frontier deep research systems, including single-agent web search, single-agent deep research, and multi-agent systems. Our analysis reveals current strengths, recurring failure modes, and key system components needed to advance reliable, insightful deep research. Our code is available at: https://github.com/SalesforceAIResearch/LiveResearchBench. --- ### Spiking Neural Network Architecture Search: A Survey Authors: Kama Svoboda, Tosiron Adegbija Published: 2025-10-16 Categories: cs.NE arXiv: https://arxiv.org/abs/2510.14235v2 This survey paper presents a comprehensive examination of Spiking Neural Network (SNN) architecture search (SNNaS) from a unique hardware/software co-design perspective. SNNs, inspired by biological neurons, have emerged as a promising approach to neuromorphic computing. They offer significant advantages in terms of power efficiency and real-time resource-constrained processing, making them ideal for edge computing and IoT applications. However, designing optimal SNN architectures poses significant challenges, due to their inherent complexity (e.g., with respect to training) and the interplay between hardware constraints and SNN models. We begin by providing an overview of SNNs, emphasizing their operational principles and key distinctions from traditional artificial neural networks (ANNs). We then provide a brief overview of the state of the art in NAS for ANNs, highlighting the challenges of directly applying these approaches to SNNs. We then survey the state of the art in SNN-specific NAS approaches. Finally, we conclude with insights into future research directions for SNN research, emphasizing the potential of hardware/software co-design in unlocking the full capabilities of SNNs. This survey aims to serve as a valuable resource for researchers and practitioners in the field, offering a holistic view of SNNaS and underscoring the importance of a co-design approach to harness the true potential of neuromorphic computing. --- ### Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models Authors: Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran, Siddhartha Jain, Wasi Uddin Ahmad, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg Published: 2025-10-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.14232v2 Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). The International Olympiad in Informatics (IOI) stands out as one of the most prestigious annual competitions in competitive programming and has become a key benchmark for comparing human and AI-level programming ability. While several proprietary models have been claimed to achieve gold medal-level performance at the IOI, often with undisclosed methods, achieving comparable results with open-weight models remains a significant challenge. In this paper, we present GenCluster, a scalable and reproducible test-time compute framework that attains IOI gold-level performance using open-weight models. It combines large-scale generation, behavioral clustering, ranking, and a round-robin submission strategy to efficiently explore diverse solution spaces under limited validation budgets. Our experiments show that the performance of our proposed approach scales consistently with available compute, narrowing the gap between open and closed systems. Notably, we will show that GenCluster can achieve a gold medal at IOI 2025 for the first time with an open-weight model gpt-oss-120b, setting a new benchmark for transparent and reproducible evaluation of reasoning in LLMs --- ### When Flatness Does (Not) Guarantee Adversarial Robustness Authors: Nils Philipp Walter, Linara Adilova, Jilles Vreeken, Michael Kamp Published: 2025-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14231v1 Despite their empirical success, neural networks remain vulnerable to small, adversarial perturbations. A longstanding hypothesis suggests that flat minima, regions of low curvature in the loss landscape, offer increased robustness. While intuitive, this connection has remained largely informal and incomplete. By rigorously formalizing the relationship, we show this intuition is only partially correct: flatness implies local but not global adversarial robustness. To arrive at this result, we first derive a closed-form expression for relative flatness in the penultimate layer, and then show we can use this to constrain the variation of the loss in input space. This allows us to formally analyze the adversarial robustness of the entire network. We then show that to maintain robustness beyond a local neighborhood, the loss needs to curve sharply away from the data manifold. We validate our theoretical predictions empirically across architectures and datasets, uncovering the geometric structure that governs adversarial vulnerability, and linking flatness to model confidence: adversarial examples often lie in large, flat regions where the model is confidently wrong. Our results challenge simplified views of flatness and provide a nuanced understanding of its role in robustness. --- ### LOTA: Bit-Planes Guided AI-Generated Image Detection Authors: Hongsong Wang, Renxi Cheng, Yang Zhang, Chaolei Han, Jie Gui Published: 2025-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.14230v1 The rapid advancement of GAN and Diffusion models makes it more difficult to distinguish AI-generated images from real ones. Recent studies often use image-based reconstruction errors as an important feature for determining whether an image is AI-generated. However, these approaches typically incur high computational costs and also fail to capture intrinsic noisy features present in the raw images. To solve these problems, we innovatively refine error extraction by using bit-plane-based image processing, as lower bit planes indeed represent noise patterns in images. We introduce an effective bit-planes guided noisy image generation and exploit various image normalization strategies, including scaling and thresholding. Then, to amplify the noise signal for easier AI-generated image detection, we design a maximum gradient patch selection that applies multi-directional gradients to compute the noise score and selects the region with the highest score. Finally, we propose a lightweight and effective classification head and explore two different structures: noise-based classifier and noise-guided classifier. Extensive experiments on the GenImage benchmark demonstrate the outstanding performance of our method, which achieves an average accuracy of \textbf{98.9\%} (\textbf{11.9}\%~$\uparrow$) and shows excellent cross-generator generalization capability. Particularly, our method achieves an accuracy of over 98.2\% from GAN to Diffusion and over 99.2\% from Diffusion to GAN. Moreover, it performs error extraction at the millisecond level, nearly a hundred times faster than existing methods. The code is at https://github.com/hongsong-wang/LOTA. --- ### Large Scale Retrieval for the LinkedIn Feed using Causal Language Models Authors: Sudarshan Srinivasa Ramanujam, Antonio Alonso, Saurabh Kataria, Siddharth Dangi, Akhilesh Gupta, Birjodh Singh Tiwana, Manas Somaiya, Luke Simon, David Byrne, Sojeong Ha, Sen Zhou, Andrei Akterskii et al. Published: 2025-10-16 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2510.14223v1 In large scale recommendation systems like the LinkedIn Feed, the retrieval stage is critical for narrowing hundreds of millions of potential candidates to a manageable subset for ranking. LinkedIn's Feed serves suggested content from outside of the member's network (based on the member's topical interests), where 2000 candidates are retrieved from a pool of hundreds of millions candidate with a latency budget of a few milliseconds and inbound QPS of several thousand per second. This paper presents a novel retrieval approach that fine-tunes a large causal language model (Meta's LLaMA 3) as a dual encoder to generate high quality embeddings for both users (members) and content (items), using only textual input. We describe the end to end pipeline, including prompt design for embedding generation, techniques for fine-tuning at LinkedIn's scale, and infrastructure for low latency, cost effective online serving. We share our findings on how quantizing numerical features in the prompt enables the information to get properly encoded in the embedding, facilitating greater alignment between the retrieval and ranking layer. The system was evaluated using offline metrics and an online A/B test, which showed substantial improvements in member engagement. We observed significant gains among newer members, who often lack strong network connections, indicating that high-quality suggested content aids retention. This work demonstrates how generative language models can be effectively adapted for real time, high throughput retrieval in industrial applications. --- ### A novel Information-Driven Strategy for Optimal Regression Assessment Authors: Benjamín Castro, Camilo Ramírez, Sebastián Espinosa, Jorge F. Silva, Marcos E. Orchard, Heraldo Rozas Published: 2025-10-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.14222v2 In Machine Learning (ML), a regression algorithm aims to minimize a loss function based on data. An assessment method in this context seeks to quantify the discrepancy between the optimal response for an input-output system and the estimate produced by a learned predictive model (the student). Evaluating the quality of a learned regressor remains challenging without access to the true data-generating mechanism, as no data-driven assessment method can ensure the achievability of global optimality. This work introduces the Information Teacher, a novel data-driven framework for evaluating regression algorithms with formal performance guarantees to assess global optimality. Our novel approach builds on estimating the Shannon mutual information (MI) between the input variables and the residuals and applies to a broad class of additive noise models. Through numerical experiments, we confirm that the Information Teacher is capable of detecting global optimality, which is aligned with the condition of zero estimation error with respect to the -- inaccessible, in practice -- true model, working as a surrogate measure of the ground truth assessment loss and offering a principled alternative to conventional empirical performance metrics. --- ### Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalization Authors: Asma Jamali, Tin Sum Cheng, Rodrigo A. Vargas-Hernández Published: 2025-10-16 Categories: cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2510.14217v3 The spectral properties of feature embeddings offer critical insights into model generalization and representation quality. While deep learning models are widely used for molecular property prediction, kernel methods remain competitive in low-data regimes, yet their spectral behavior is largely unexplored. We present the first comprehensive spectral analysis of kernel ridge regression across diverse representations, including molecular fingerprints (ECFP), pretrained transformers, graph neural networks, and 3D descriptors, evaluated on QM9, MoleculeNet, and Therapeutics Data Commons benchmarks. Surprisingly, richer spectral features do not consistently yield better generalization performance, contradicting common representation heuristics used in self-supervised learning (SSL). Across four spectral metrics, only ECFP-based kernels show a strictly positive correlation with performance, particularly SSE, ID, and SR on MoleculeNet. Global 3D representations exhibit mixed behavior; transformer-based representations are consistently positive across all four metrics, whereas local 3D representations show a negative trend and no significant correlations. Truncation analysis further emphasizes this disparity: for local 3D representations on thermodynamic targets, fewer than 2% of eigenvalues, and occasionally as few as 0.02%, are needed to recover 95% of performance, whereas ECFP and transformer kernels require significantly more. By demonstrating a strong dependence on both task and representation, our results challenge the heuristic that richer spectra inherently improve generalization, providing new guidance for evaluating representations in SSL and in label-limited scientific tasks. --- ### LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning Authors: Beomseok Kang, Jiwon Song, Jae-Joon Kim Published: 2025-10-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.14211v2 Multi-stage reasoning has emerged as an effective strategy for enhancing the reasoning capability of small language models by decomposing complex problems into sequential sub-stages. However, this comes at the cost of increased latency. We observe that existing adaptive acceleration techniques, such as layer skipping, struggle to balance efficiency and accuracy in this setting due to two key challenges: (1) stage-wise variation in skip sensitivity, and (2) the generation of redundant output tokens. To address these, we propose LiteStage, a latency-aware layer skipping framework for multi-stage reasoning. LiteStage combines a stage-wise offline search that allocates optimal layer budgets with an online confidence-based generation early exit to suppress unnecessary decoding. Experiments on three benchmarks, e.g., OBQA, CSQA, and StrategyQA, show that LiteStage outperforms prior training-free layer skipping methods. --- ### Incentive-Based Federated Learning: Architectural Elements and Future Directions Authors: Chanuka A. S. Hewa Kaluannakkage, Rajkumar Buyya Published: 2025-10-16 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2510.14208v2 Federated learning promises to revolutionize machine learning by enabling collaborative model training without compromising data privacy. However, practical adaptability can be limited by critical factors, such as the participation dilemma. Participating entities are often unwilling to contribute to a learning system unless they receive some benefits, or they may pretend to participate and free-ride on others. This chapter identifies the fundamental challenges in designing incentive mechanisms for federated learning systems. It examines how foundational concepts from economics and game theory can be applied to federated learning, alongside technology-driven solutions such as blockchain and deep reinforcement learning. This work presents a comprehensive taxonomy that thoroughly covers both centralized and decentralized architectures based on the aforementioned theoretical concepts. Furthermore, the concepts described are presented from an application perspective, covering emerging industrial applications, including healthcare, smart infrastructure, vehicular networks, and blockchain-based decentralized systems. Through this exploration, this chapter demonstrates that well-designed incentive mechanisms are not merely optional features but essential components for the practical success of federated learning. This analysis reveals both the promising solutions that have emerged and the significant challenges that remain in building truly sustainable, fair, and robust federated learning ecosystems. --- ### Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks Authors: Trilok Padhi, Pinxian Lu, Abdulkadir Erol, Tanmay Sutar, Gauri Sharma, Mina Sonmez, Munmun De Choudhury, Ugur Kursuncu Published: 2025-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14207v3 Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often unfolds over multi-turn interactions. In this work, we present the Online Harassment Agentic Benchmark consisting of: (i) a synthetic multi-turn harassment conversation dataset, (ii) a multi-agent (e.g., harasser, victim) simulation informed by repeated game theory, (iii) three jailbreak methods attacking agents across memory, planning, and fine-tuning, and (iv) a mixed-methods evaluation framework. We utilize two prominent LLMs, LLaMA-3.1-8B-Instruct (open-source) and Gemini-2.0-flash (closed-source). Our results show that jailbreak tuning makes harassment nearly guaranteed with an attack success rate of 95.78--96.89% vs. 57.25--64.19% without tuning in Llama, and 99.33% vs. 98.46% without tuning in Gemini, while sharply reducing refusal rate to 1-2% in both models. The most prevalent toxic behaviors are Insult with 84.9--87.8% vs. 44.2--50.8% without tuning, and Flaming with 81.2--85.1% vs. 31.5--38.8% without tuning, indicating weaker guardrails compared to sensitive categories such as sexual or racial harassment. Qualitative evaluation further reveals that attacked agents reproduce human-like aggression profiles, such as Machiavellian/psychopathic patterns under planning, and narcissistic tendencies with memory. Counterintuitively, closed-source and open-source models exhibit distinct escalation trajectories across turns, with closed-source models showing significant vulnerability. Overall, our findings show that multi-turn and theory-grounded attacks not only succeed at high rates but also mimic human-like harassment dynamics, motivating the development of robust safety guardrails to ultimately keep online platforms safe and responsible. --- ### DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans Authors: Bingsheng Yao, Bo Sun, Yuanzhe Dong, Yuxuan Lu, Dakuo Wang Published: 2025-10-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.14205v3 The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework (DPRF). DPRF aims to optimize the alignment of LLM RPAs' behaviors with those of target individuals by iteratively identifying the cognitive divergence, either through free-form or theory-grounded, structured analysis, between generated behaviors and human ground truth, and refining the persona profile to mitigate these divergences. We evaluate DPRF with five LLMs on four diverse behavior-prediction scenarios: formal debates, social media posts with mental health issues, public interviews, and movie reviews. DPRF can consistently improve behavioral alignment considerably over baseline personas and generalizes across models and scenarios. Our work provides a robust methodology for creating high-fidelity persona profiles and enhancing the validity of downstream applications, such as user simulation, social studies, and personalized AI. --- ### Joint Modeling of Big Five and HEXACO for Multimodal Apparent Personality-trait Recognition Authors: Ryo Masumura, Shota Orihashi, Mana Ihori, Tomohiro Tanaka, Naoki Makishima, Taiga Yamane, Naotaka Kawata, Satoshi Suzuki, Taichi Katayama Published: 2025-10-16 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2510.14203v1 This paper proposes a joint modeling method of the Big Five, which has long been studied, and HEXACO, which has recently attracted attention in psychology, for automatically recognizing apparent personality traits from multimodal human behavior. Most previous studies have used the Big Five for multimodal apparent personality-trait recognition. However, no study has focused on apparent HEXACO which can evaluate an Honesty-Humility trait related to displaced aggression and vengefulness, social-dominance orientation, etc. In addition, the relationships between the Big Five and HEXACO when modeled by machine learning have not been clarified. We expect awareness of multimodal human behavior to improve by considering these relationships. The key advance of our proposed method is to optimize jointly recognizing the Big Five and HEXACO. Experiments using a self-introduction video dataset demonstrate that the proposed method can effectively recognize the Big Five and HEXACO. --- ### RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following Authors: Zhichao Wang, Andy Wong, Ruslan Belkin Published: 2025-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14200v1 After the pretraining stage of LLMs, techniques such as SFT, RLHF, RLVR, and RFT are applied to enhance instruction-following ability, mitigate undesired responses, improve reasoning capability and enable efficient domain adaptation with minimal data. SFT relies on the next-token prediction objective to strengthen instruction following in a base model using a large corpus of human-labeled responses. In contrast, RFT employs a RL-based approach to adapt fine-tuned reasoning models to specific domains with limited supervision. Inspired by RFT, we propose replacing SFT with RLSR to leverage the extensive SFT dataset in an RL framework, thereby improving the base model's instruction-following ability. In RLSR, the base model generates multiple responses for each prompt, and reward scores are computed as the cosine similarity in the semantic embedding space between the generated and human-labeled responses. RLSR can be utilized in multiple ways. It can directly replace SFT, achieving superior performance on instruction-following benchmarks-for example, RLSR (SB) on Qwen-7B (INFINITY) achieved an AlpacaEval win rate of 26.34%, surpassing SFT's 21.01%. Furthermore, combining SFT and RLSR further enhances downstream task performance; Qwen-7B (INFINITY) achieved a win rate of 30.73% when trained with SFT + RLSR. --- ### Implementation of AI in Precision Medicine Authors: Göktuğ Bender, Samer Faraj, Anand Bhardwaj Published: 2025-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14194v1 Artificial intelligence (AI) has become increasingly central to precision medicine by enabling the integration and interpretation of multimodal data, yet implementation in clinical settings remains limited. This paper provides a scoping review of literature from 2019-2024 on the implementation of AI in precision medicine, identifying key barriers and enablers across data quality, clinical reliability, workflow integration, and governance. Through an ecosystem-based framework, we highlight the interdependent relationships shaping real-world translation and propose future directions to support trustworthy and sustainable implementation. --- ### Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation Authors: Ruchi Sandilya, Sumaira Perez, Charles Lynch, Lindsay Victoria, Benjamin Zebley, Derrick Matthew Buchanan, Mahendra T. Bhati, Nolan Williams, Timothy J. Spellman, Faith M. Gunning, Conor Liston, Logan Grosenick Published: 2025-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14190v3 Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies contrastive learning to pretrained diffusion latents using auxiliary variables (e.g., time, stimulation parameters, facial action units). ConDA learns a low-dimensional embedding whose directions align with underlying dynamical factors, consistent with recent contrastive learning results on structured and disentangled representations. In this embedding, simple nonlinear trajectories support smooth interpolation, extrapolation, and counterfactual editing while rendering remains in the original diffusion space. ConDA separates editing and rendering by lifting embedding trajectories back to diffusion latents with a neighborhood-preserving kNN decoder and is robust across inversion solvers. Across fluid dynamics, neural calcium imaging, therapeutic neurostimulation, facial expression dynamics, and monkey motor cortex activity, ConDA yields more interpretable and controllable latent structure than linear traversals and conditioning-based baselines, indicating that diffusion latents encode dynamics-relevant structure that can be exploited by an explicit contrastive geometry layer. --- ### MAFA: A Multi-Agent Framework for Enterprise-Scale Annotation with Configurable Task Adaptation Authors: Mahmood Hegazy, Aaron Rodrigues, Azzam Naeem Published: 2025-10-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.14184v1 We present MAFA (Multi-Agent Framework for Annotation), a production-deployed system that transforms enterprise-scale annotation workflows through configurable multi-agent collaboration. Addressing the critical challenge of annotation backlogs in financial services, where millions of customer utterances require accurate categorization, MAFA combines specialized agents with structured reasoning and a judge-based consensus mechanism. Our framework uniquely supports dynamic task adaptation, allowing organizations to define custom annotation types (FAQs, intents, entities, or domain-specific categories) through configuration rather than code changes. Deployed at JP Morgan Chase, MAFA has eliminated a 1 million utterance backlog while achieving, on average, 86% agreement with human annotators, annually saving over 5,000 hours of manual annotation work. The system processes utterances with annotation confidence classifications, which are typically 85% high, 10% medium, and 5% low across all datasets we tested. This enables human annotators to focus exclusively on ambiguous and low-coverage cases. We demonstrate MAFA's effectiveness across multiple datasets and languages, showing consistent improvements over traditional and single-agent annotation baselines: 13.8% higher Top-1 accuracy, 15.1% improvement in Top-5 accuracy, and 16.9% better F1 in our internal intent classification dataset and similar gains on public benchmarks. This work bridges the gap between theoretical multi-agent systems and practical enterprise deployment, providing a blueprint for organizations facing similar annotation challenges. --- ### Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures Authors: Yuancheng Xu, Wenqi Xian, Li Ma, Julien Philip, Ahmet Levent Taşel, Yiwei Zhao, Ryan Burgert, Mingming He, Oliver Hermann, Oliver Pilarski, Rahul Garg, Paul Debevec et al. Published: 2025-10-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.14179v1 We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric capture performances re-rendered with diverse camera trajectories via 4D Gaussian Splatting (4DGS), lighting variability obtained with a video relighting model. We fine-tune state-of-the-art open-source video diffusion models on this data to provide strong multi-view identity preservation, precise camera control, and lighting adaptability. Our framework also supports core capabilities for virtual production, including multi-subject generation using two approaches: joint training and noise blending, the latter enabling efficient composition of independently customized models at inference time; it also achieves scene and real-life video customization as well as control over motion and spatial layout during customization. Extensive experiments show improved video quality, higher personalization accuracy, and enhanced camera control and lighting adaptability, advancing the integration of video generation into virtual production. Our project page is available at: https://eyeline-labs.github.io/Virtually-Being. --- ### ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning Authors: Roger Creus Castanyer, Faisal Mohamed, Pablo Samuel Castro, Cyrus Neary, Glen Berseth Published: 2025-10-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.14176v3 Reinforcement learning (RL) algorithms are highly sensitive to reward function specification, which remains a central challenge limiting their broad applicability. We present ARM-FM: Automated Reward Machines via Foundation Models, a framework for automated, compositional reward design in RL that leverages the high-level reasoning capabilities of foundation models (FMs). Reward machines (RMs) -- an automata-based formalism for reward specification -- are used as the mechanism for RL objective specification, and are automatically constructed via the use of FMs. The structured formalism of RMs yields effective task decompositions, while the use of FMs enables objective specifications in natural language. Concretely, we (i) use FMs to automatically generate RMs from natural language specifications; (ii) associate language embeddings with each RM automata-state to enable generalization across tasks; and (iii) provide empirical evidence of ARM-FM's effectiveness in a diverse suite of challenging environments, including evidence of zero-shot generalization. --- ### JEDA: Query-Free Clinical Order Search from Ambient Dialogues Authors: Praphul Singh, Corey Barrett, Sumana Srivasta, Amitabh Saikia, Irfan Bulu, Sri Gadde, Krishnaram Kenthapadi Published: 2025-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14169v2 Clinical conversations mix explicit directives (order a chest X-ray) with implicit reasoning (the cough worsened overnight, we should check for pneumonia). Many systems rely on LLM rewriting, adding latency, instability, and opacity that hinder real-time ordering. We present JEDA (Joint Embedding for Direct and Ambient clinical orders), a domain-initialized bi-encoder that retrieves canonical orders directly and, in a query-free mode, encodes a short rolling window of ambient dialogue to trigger retrieval. Initialized from PubMedBERT and fine-tuned with a duplicate-safe contrastive objective, JEDA aligns heterogeneous expressions of intent to shared order concepts. Training uses constrained LLM guidance to tie each signed order to complementary formulations (command only, context only, command+context, context+reasoning), producing clearer inter-order separation, tighter query extendash order coupling, and stronger generalization. The query-free mode is noise-resilient, reducing sensitivity to disfluencies and ASR errors by conditioning on a short window rather than a single utterance. Deployed in practice, JEDA yields large gains and substantially outperforms its base encoder and recent open embedders (Linq Embed Mistral, SFR Embedding, GTE Qwen, BGE large, Embedding Gemma). The result is a fast, interpretable, LLM-free retrieval layer that links ambient context to actionable clinical orders in real time. --- ### Leveraging LLMs for Design Ideation: An AI Tool to Assist Creativity Authors: Rutvik Kokate, Pranati Kompella, Prasad Onkar Published: 2025-10-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.00010v1 The creative potential of computers has intrigued researchers for decades. Since the emergence of Generative AI (Gen AI), computer creativity has found many new dimensions and applications. As Gen AI permeates mainstream discourse and usage, researchers are delving into how it can improve and complement what humans do. Creative potential is a highly relevant notion to design practice and research, especially in the initial stages of ideation and conceptualisation. There is scope to improve creative potential in these stages, especially using machine intelligence. We propose a structured ideation session involving inspirational stimuli and utilise Gen AI in delivering this structure to designers through ALIA: Analogical LLM Ideation Agent, a tool for small-group ideation scenarios. The tool is developed by enabling speech based interactions with a Large Language Model (LLM) for inference generation. Inspiration is drawn from the synectic ideation method and the dialectics philosophy to design the optimal stimuli in group ideation. The tool is tested in design ideation sessions to compare the output of the AI-assisted ideation sessions to that of tradi tional ideation sessions. Preliminary findings showcase that participants have rated their ideas better when assisted by ALIA and respond favourably to speech-based interactions. --- ### PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization Authors: Jiajun Zhang, Jianke Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Binyuan Hui, Qiang Liu, Zilei Wang, Liang Wang, Junyang Lin Published: 2025-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.00010v2 Recent Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation. However, their ability to create complex visualizations for scaled and structured data remains largely unevaluated and underdeveloped. To address this gap, we introduce PlotCraft, a new benchmark featuring 1k challenging visualization tasks that cover a wide range of topics, such as finance, scientific research, and sociology. The benchmark is structured around seven high-level visualization tasks and encompasses 48 distinct chart types. Crucially, it is the first to systematically evaluate both single-turn generation and multi-turn refinement across a diverse spectrum of task complexities. Our comprehensive evaluation of 23 leading LLMs on PlotCraft reveals obvious performance deficiencies in handling sophisticated visualization tasks. To bridge this performance gap, we develope SynthVis-30K, a large-scale, high-quality dataset of complex visualization code synthesized via a collaborative agent framework. Building upon this dataset, we develope PlotCraftor, a novel code generation model that achieves strong capabilities in complex data visualization with a remarkably small size. Across VisEval, PandasPlotBench, and our proposed PlotCraft, PlotCraftor shows performance comparable to that of leading proprietary approaches. Especially, on hard task, Our model achieves over 50% performance improvement. We will release the benchmark, dataset, and code at https://github.com/Speakn0w/PlotCraft-Benchmark. --- ### PulseFi: A Low Cost Robust Machine Learning System for Accurate Cardiopulmonary and Apnea Monitoring Using Channel State Information Authors: Pranay Kocheta, Nayan Sanjay Bhatia, Katia Obraczka Published: 2025-10-15 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2510.24744v1 Non-intrusive monitoring of vital signs has become increasingly important in a variety of healthcare settings. In this paper, we present PulseFi, a novel low-cost non-intrusive system that uses Wi-Fi sensing and artificial intelligence to accurately and continuously monitor heart rate and breathing rate, as well as detect apnea events. PulseFi operates using low-cost commodity devices, making it more accessible and cost-effective. It uses a signal processing pipeline to process Wi-Fi telemetry data, specifically Channel State Information (CSI), that is fed into a custom low-compute Long Short-Term Memory (LSTM) neural network model. We evaluate PulseFi using two datasets: one that we collected locally using ESP32 devices and another that contains recordings of 118 participants collected using the Raspberry Pi 4B, making the latter the most comprehensive data set of its kind. Our results show that PulseFi can effectively estimate heart rate and breathing rate in a seemless non-intrusive way with comparable or better accuracy than multiple antenna systems that can be expensive and less accessible. --- ### Comparative Analysis of Data Augmentation for Clinical ECG Classification with STAR Authors: Nader Nemati Published: 2025-10-15 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2510.24740v1 Clinical 12-lead ECG classification remains difficult because of diverse recording conditions, overlapping pathologies, and pronounced label imbalance hinder generalization, while unconstrained augmentations risk distorting diagnostically critical morphology. In this study, Sinusoidal Time--Amplitude Resampling (STAR) is introduced as a beat-wise augmentation that operates strictly between successive R-peaks to apply controlled time warping and amplitude scaling to each R--R segment, preserving the canonical P--QRS--T order and leaving the head and tail of the trace unchanged. STAR is designed for practical pipelines and offers: (i) morphology-faithful variability that broadens training diversity without corrupting peaks or intervals; (ii) source-resilient training, improving stability across devices, sites, and cohorts without dataset-specific tuning; (iii) model-agnostic integration with common 1D SE--ResNet-style ECG encoders backbone; and (iv) better learning on rare classes via beat-level augmentation, reducing overfitting by resampling informative beats instead of duplicating whole records. In contrast to global crops, large shifts, or additive noise, STAR avoids transformations that suppress or misalign clinical landmarks. A complete Python implementation and a transparent training workflow are released, aligned with a source-aware, stratified five-fold protocol over a multi-institutional 12-lead corpus, thereby facilitating inspection and reuse. Taken together, STAR provides a simple and controllable augmentation for clinical ECG classification where trustworthy morphology, operational simplicity, and cross-source durability are essential. ---