# Research Papers — 2025-10 · bundle page 39 of 217

> Full-text markdown of papers #1901–1950 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/39
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/38.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/40.md)

### MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control

Authors: Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Muhammad Awais, Josef Kittler
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22810v1

Audio-driven talking face generation has gained significant attention for applications in digital media and virtual avatars. While recent methods improve audio-lip synchronization, they often struggle with temporal consistency, identity preservation, and customization, especially in long video generation. To address these issues, we propose MAGIC-Talk, a one-shot diffusion-based framework for customizable and temporally stable talking face generation. MAGIC-Talk consists of ReferenceNet, which preserves identity and enables fine-grained facial editing via text prompts, and AnimateNet, which enhances motion coherence using structured motion priors. Unlike previous methods requiring multiple reference images or fine-tuning, MAGIC-Talk maintains identity from a single image while ensuring smooth transitions across frames. Additionally, a progressive latent fusion strategy is introduced to improve long-form video quality by reducing motion inconsistencies and flickering. Extensive experiments demonstrate that MAGIC-Talk outperforms state-of-the-art methods in visual quality, identity preservation, and synchronization accuracy, offering a robust solution for talking face generation.

---

### A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)

Authors: Christopher J. Hazard, Michael Resnick, Jacob Beel, Jack Xia, Cade Mack, Dominic Glennie, Matthew Fulp, David Maze, Andrew Bassett, Martin Koistinen
Published: 2025-10-26
Categories: cs.LG, cs.AI, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.22809v2

Traditional machine learning relies on explicit models and domain assumptions, often limiting flexibility and interpretability. We introduce a "model-free" framework of instance-based learning using surprisal (information theoretic uncertainty) to directly analyze and perform inferences from raw data, eliminating distribution modeling, reducing bias, and enabling efficient updates including direct edits and deletion of training data. By quantifying relevance through uncertainty, the approach enables generalizable inference across tasks including generative inference, causal discovery, anomaly detection, and time series forecasting. Our approach emphasizes traceability, interpretability, and data-driven decision making, offering a unified, human-understandable framework for machine learning, can be adapted to virtually all machine learning tasks, achieving competency across all and state-of-the-art performance on anomaly detection and some supervised tasks. The mathematical foundations create a "physics" of information, which enable these techniques to apply effectively to a wide variety of complex data types, including missing data. Our results suggest that this may be a viable foundation upon which to build scalable machine learning and artificial intelligence that can maintain human understandability of the underlying mechanics.

---

### MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering

Authors: Hai-Dang Nguyen, Minh-Anh Dang, Minh-Tan Le, Minh-Tuan Le
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22803v1

Explainability is critical for the clinical adoption of medical visual question answering (VQA) systems, as physicians require transparent reasoning to trust AI-generated diagnoses. We present MedXplain-VQA, a comprehensive framework integrating five explainable AI components to deliver interpretable medical image analysis. The framework leverages a fine-tuned BLIP-2 backbone, medical query reformulation, enhanced Grad-CAM attention, precise region extraction, and structured chain-of-thought reasoning via multi-modal language models. To evaluate the system, we introduce a medical-domain-specific framework replacing traditional NLP metrics with clinically relevant assessments, including terminology coverage, clinical structure quality, and attention region relevance. Experiments on 500 PathVQA histopathology samples demonstrate substantial improvements, with the enhanced system achieving a composite score of 0.683 compared to 0.378 for baseline methods, while maintaining high reasoning confidence (0.890). Our system identifies 3-5 diagnostically relevant regions per sample and generates structured explanations averaging 57 words with appropriate clinical terminology. Ablation studies reveal that query reformulation provides the most significant initial improvement, while chain-of-thought reasoning enables systematic diagnostic processes. These findings underscore the potential of MedXplain-VQA as a robust, explainable medical VQA system. Future work will focus on validation with medical experts and large-scale clinical datasets to ensure clinical readiness.

---

### Probing the Representational Geometry of Color Qualia: Dissociating Pure Perception from Task Demands in Brains and AI Models

Authors: Jing Xu
Published: 2025-10-26
Categories: cs.NE
arXiv: https://arxiv.org/abs/2510.22800v1

Probing the computational underpinnings of subjective experience, or qualia, remains a central challenge in cognitive neuroscience. This project tackles this question by performing a rigorous comparison of the representational geometry of color qualia between state-of-the-art AI models and the human brain. Using a unique fMRI dataset with a "no-report" paradigm, we use Representational Similarity Analysis (RSA) to compare diverse vision models against neural activity under two conditions: pure perception ("no-report") and task-modulated perception ("report"). Our analysis yields three principal findings. First, nearly all models align better with neural representations of pure perception, suggesting that the cognitive processes involved in task execution are not captured by current feedforward architectures. Second, our analysis reveals a critical interaction between training paradigm and architecture, challenging the simple assumption that Contrastive Language-Image Pre-training(CLIP) training universally improves neural plausibility. In our direct comparison, this multi-modal training method enhanced brain-alignment for a vision transformer(ViT), yet had the opposite effect on a ConvNet. Our work contributes a new benchmark task for color qualia to the field, packaged in a Brain-Score compatible format. This benchmark reveals a fundamental divergence in the inductive biases of artificial and biological vision systems, offering clear guidance for developing more neurally plausible models.

---

### Inductive Transfer Learning for Graph-Based Recommenders

Authors: Florian Grötschla, Elia Trachsel, Luca A. Lanzendörfer, Roger Wattenhofer
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22799v1

Graph-based recommender systems are commonly trained in transductive settings, which limits their applicability to new users, items, or datasets. We propose NBF-Rec, a graph-based recommendation model that supports inductive transfer learning across datasets with disjoint user and item sets. Unlike conventional embedding-based methods that require retraining for each domain, NBF-Rec computes node embeddings dynamically at inference time. We evaluate the method on seven real-world datasets spanning movies, music, e-commerce, and location check-ins. NBF-Rec achieves competitive performance in zero-shot settings, where no target domain data is used for training, and demonstrates further improvements through lightweight fine-tuning. These results show that inductive transfer is feasible in graph-based recommendation and that interaction-level message passing supports generalization across datasets without requiring aligned users or items.

---

### VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions

Authors: Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon, Hyunwook Lee, Hyunmin Song, Sungahn Ko, Taehwan Kim
Published: 2025-10-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.22798v1

Automatically assessing handwritten mathematical solutions is an important problem in educational technology with practical applications, but it remains a significant challenge due to the diverse formats, unstructured layouts, and symbolic complexity of student work. To address this challenge, we introduce VEHME-a Vision-Language Model for Evaluating Handwritten Mathematics Expressions-designed to assess open-form handwritten math responses with high accuracy and interpretable reasoning traces. VEHME integrates a two-phase training pipeline: (i) supervised fine-tuning using structured reasoning data, and (ii) reinforcement learning that aligns model outputs with multi-dimensional grading objectives, including correctness, reasoning depth, and error localization. To enhance spatial understanding, we propose an Expression-Aware Visual Prompting Module, trained on our synthesized multi-line math expressions dataset to robustly guide attention in visually heterogeneous inputs. Evaluated on AIHub and FERMAT datasets, VEHME achieves state-of-the-art performance among open-source models and approaches the accuracy of proprietary systems, demonstrating its potential as a scalable and accessible tool for automated math assessment. Our training and experiment code is publicly available at our GitHub repository.

---

### SAO-Instruct: Free-form Audio Editing using Natural Language Instructions

Authors: Michael Ungersböck, Florian Grötschla, Luca A. Lanzendörfer, June Young Yi, Changho Choi, Roger Wattenhofer
Published: 2025-10-26
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2510.22795v1

Generative models have made significant progress in synthesizing high-fidelity audio from short textual descriptions. However, editing existing audio using natural language has remained largely underexplored. Current approaches either require the complete description of the edited audio or are constrained to predefined edit instructions that lack flexibility. In this work, we introduce SAO-Instruct, a model based on Stable Audio Open capable of editing audio clips using any free-form natural language instruction. To train our model, we create a dataset of audio editing triplets (input audio, edit instruction, output audio) using Prompt-to-Prompt, DDPM inversion, and a manual editing pipeline. Although partially trained on synthetic data, our model generalizes well to real in-the-wild audio clips and unseen edit instructions. We demonstrate that SAO-Instruct achieves competitive performance on objective metrics and outperforms other audio editing approaches in a subjective listening study. To encourage future research, we release our code and model weights.

---

### Collaborative LLM Agents for C4 Software Architecture Design Automation

Authors: Kamil Szczepanik, Jarosław A. Chudziak
Published: 2025-10-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.22787v1

Software architecture design is a fundamental part of creating every software system. Despite its importance, producing a C4 software architecture model, the preferred notation for such architecture, remains manual and time-consuming. We introduce an LLM-based multi-agent system that automates this task by simulating a dialogue between role-specific experts who analyze requirements and generate the Context, Container, and Component views of the C4 model. Quality is assessed with a hybrid evaluation framework: deterministic checks for structural and syntactic integrity and C4 rule consistency, plus semantic and qualitative scoring via an LLM-as-a-Judge approach. Tested on five canonical system briefs, the workflow demonstrates fast C4 model creation, sustains high compilation success, and delivers semantic fidelity. A comparison of four state-of-the-art LLMs shows different strengths relevant to architectural design. This study contributes to automated software architecture design and its evaluation methods.

---

### Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models

Authors: Jiaxiang Liu, Jiawei Du, Xiao Liu, Prayag Tiwari, Mingkun Xu
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22785v1

Pre-trained vision-language models (VLMs) such as CLIP have demonstrated strong zero-shot capabilities across diverse domains, yet remain highly vulnerable to adversarial perturbations that disrupt image-text alignment and compromise reliability. Existing defenses typically rely on adversarial fine-tuning with labeled data, limiting their applicability in zero-shot settings. In this work, we identify two key weaknesses of current CLIP adversarial attacks -- lack of semantic guidance and vulnerability to view variations -- collectively termed semantic and viewpoint fragility. To address these challenges, we propose Self-Calibrated Consistency (SCC), an effective test-time defense. SCC consists of two complementary modules: Semantic consistency, which leverages soft pseudo-labels from counterattack warm-up and multi-view predictions to regularize cross-modal alignment and separate the target embedding from confusable negatives; and Spatial consistency, aligning perturbed visual predictions via augmented views to stabilize inference under adversarial perturbations. Together, these modules form a plug-and-play inference strategy. Extensive experiments on 22 benchmarks under diverse attack settings show that SCC consistently improves the zero-shot robustness of CLIP while maintaining accuracy, and can be seamlessly integrated with other VLMs for further gains. These findings highlight the great potential of establishing an adversarially robust paradigm from CLIP, with implications extending to broader vision-language domains such as BioMedCLIP.

---

### PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language

Authors: Guangyao Shi, Yuwei Wu, Vijay Kumar, Gaurav S. Sukhatme
Published: 2025-10-26
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.22784v1

Enabling robot teams to execute natural language commands requires translating high-level instructions into feasible, efficient multi-robot plans. While Large Language Models (LLMs) combined with Planning Domain Description Language (PDDL) offer promise for single-robot scenarios, existing approaches struggle with multi-robot coordination due to brittle task decomposition, poor scalability, and low coordination efficiency. We introduce PIP-LLM, a language-based coordination framework that consists of PDDL-based team-level planning and Integer Programming (IP) based robot-level planning. PIP-LLMs first decomposes the command by translating the command into a team-level PDDL problem and solves it to obtain a team-level plan, abstracting away robot assignment. Each team-level action represents a subtask to be finished by the team. Next, this plan is translated into a dependency graph representing the subtasks' dependency structure. Such a dependency graph is then used to guide the robot-level planning, in which each subtask node will be formulated as an IP-based task allocation problem, explicitly optimizing travel costs and workload while respecting robot capabilities and user-defined constraints. This separation of planning from assignment allows PIP-LLM to avoid the pitfalls of syntax-based decomposition and scale to larger teams. Experiments across diverse tasks show that PIP-LLM improves plan success rate, reduces maximum and average travel costs, and achieves better load balancing compared to state-of-the-art baselines.

---

### Agentic Meta-Orchestrator for Multi-task Copilots

Authors: Xiaofeng Zhu, Yunshen Zhou
Published: 2025-10-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22781v2

Microsoft Copilot suites serve as the universal entry point for various agents skilled in handling important tasks, ranging from assisting a customer with product purchases to detecting vulnerabilities in corporate programming code. Each agent can be powered by language models, software engineering operations, such as database retrieval, and internal \& external knowledge. The repertoire of a copilot can expand dynamically with new agents. This requires a robust orchestrator that can distribute tasks from user prompts to the right agents. In this work, we propose an Agentic Meta-orchestrator (AMO) for handling multiple tasks and scalable agents in copilot services, which can provide both natural language and action responses. We will also demonstrate the planning that leverages meta-learning, i.e., a trained decision tree model for deciding the best inference strategy among various agents/models. We showcase the effectiveness of our AMO through two production use cases: Microsoft 365 (M365) E-Commerce Copilot and code compliance copilot. M365 E-Commerce Copilot advertises Microsoft products to external customers to promote sales success. The M365 E-Commerce Copilot provides up-to-date product information and connects to multiple agents, such as relational databases and human customer support. The code compliance copilot scans the internal DevOps code to detect known and new compliance issues in pull requests (PR).

---

### How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations

Authors: Zora Zhiruo Wang, Yijia Shao, Omar Shaikh, Daniel Fried, Graham Neubig, Diyi Yang
Published: 2025-10-26
Categories: cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2510.22780v2

AI agents are continually optimized for tasks related to human work, such as software engineering and professional writing, signaling a pressing trend with significant impacts on the human workforce. However, these agent developments have often not been grounded in a clear understanding of how humans execute work, to reveal what expertise agents possess and the roles they can play in diverse workflows. In this work, we study how agents do human work by presenting the first direct comparison of human and agent workers across multiple essential work-related skills: data analysis, engineering, computation, writing, and design. To better understand and compare heterogeneous computer-use activities of workers, we introduce a scalable toolkit to induce interpretable, structured workflows from either human or agent computer-use activities. Using such induced workflows, we compare how humans and agents perform the same tasks and find that: (1) While agents exhibit promise in their alignment to human workflows, they take an overwhelmingly programmatic approach across all work domains, even for open-ended, visually dependent tasks like design, creating a contrast with the UI-centric methods typically used by humans. (2) Agents produce work of inferior quality, yet often mask their deficiencies via data fabrication and misuse of advanced tools. (3) Nonetheless, agents deliver results 88.3% faster and cost 90.4-96.2% less than humans, highlighting the potential for enabling efficient collaboration by delegating easily programmable tasks to agents.

---

### Beyond the Semicircle: Free Diffusion Models with Prescribed Equilibria

Authors: Swagatam Das
Published: 2025-10-26
Categories: math.PR, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.22778v4

A growing class of machine-learning objects -- covariance and Gram matrices, kernel and attention matrices, MIMO channel matrices, density operators -- are naturally spectra rather than coordinate vectors. Building a denoising diffusion model for such data by corrupting eigenvalues coordinatewise is not merely elegant: it converges to the wrong limit, because eigenvalues repel rather than move independently. Free probability theory supplies the correct forward process, with free convolution replacing classical convolution and Voiculescu's conjugate variable replacing the score, but constant-coefficient free diffusions have a hidden limitation of their own: their only possible equilibrium is the semicircular law, whatever the target distribution looks like. We show that state-dependent free volatility removes this restriction. For any sufficiently regular compactly supported target law, we explicitly construct, through a closed-form Hilbert-transform drift, a free Fokker--Planck flow having that law as a stationary spectral distribution. Under an additional convex-potential condition, the construction admits a globally relaxing diffusion interpretation, reverse-time dynamics, and a trainable score. The generalization is genuine rather than cosmetic: no change of spectral variable reduces it to the constant-coefficient case, and it is a Wasserstein gradient flow only for an explicitly characterized family of coefficients that contains no bounded non-constant member. We instantiate the construction on the Marchenko--Pastur law, the limiting spectrum of isotropic sample covariance matrices, and validate it numerically: the free-versus-coordinatewise gap, an exact dimension-independent score driving reverse-time matrix dynamics at several matrix sizes, the designed Marchenko--Pastur equilibrium, and end-to-end generation with a learned score.

---

### SeeDNorm: Self-Rescaled Dynamic Normalization

Authors: Wenrui Cai, Defa Zhu, Qingjie Liu, Qiyang Min
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22777v3

Normalization layer constitutes an essential component in neural networks. In transformers, the predominantly used RMSNorm constrains vectors to a unit hypersphere, followed by dimension-wise rescaling through a learnable scaling coefficient $γ$ to maintain the representational capacity of the model. However, RMSNorm discards the input norm information in forward pass and a static scaling factor $γ$ may be insufficient to accommodate the wide variability of input data and distributional shifts, thereby limiting further performance improvements, particularly in zero-shot scenarios that large language models routinely encounter. To address this limitation, we propose SeeDNorm, which enhances the representational capability of the model by dynamically adjusting the scaling coefficient based on the current input, thereby preserving the input norm information and enabling data-dependent, self-rescaled dynamic normalization. During backpropagation, SeeDNorm retains the ability of RMSNorm to dynamically adjust gradient according to the input norm. We provide a detailed analysis of the training optimization for SeedNorm and proposed corresponding solutions to address potential instability issues that may arise when applying SeeDNorm. We validate the effectiveness of SeeDNorm across models of varying sizes in large language model pre-training as well as supervised and unsupervised computer vision tasks. By introducing a minimal number of parameters and with neglligible impact on model efficiency, SeeDNorm achieves consistently superior performance compared to previously commonly used normalization layers such as RMSNorm and LayerNorm, as well as element-wise activation alternatives to normalization layers like DyT.

---

### Scalable Supervision for Software Agents via Patch Reasoning

Authors: Junjielong Xu, Boyin Tan, Xiaoyuan Liu, Chao Peng, Pengfei Gao, Pinjia He
Published: 2025-10-26
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2510.22775v2

While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. The reason is twofold: (1) high-coverage tests are naturally rare in the wild, and (2) building and running test sandbox is heavy and fragile. To unlock supervision scaling, we propose R4P, a reasoning-based method that provides scaffold-agnostic rewards. R4P uses a group-wise training objective, enabling it to verify multiple patches against each other's modification and gain a dense reward for supervising agents without executing tests or relying on specific agent trajectories. R4P achieves 72.2% Acc. for verifying patches from SWE-bench, competitive with proprietary models. To show the downstream practical utility of R4P, we design and train an execution-free scaffold, Mini-SE, with pure RL via R4P. Mini-SE achieves 26.2% Pass@1, showing a 10.0% improvement over the original Qwen3-32B, and can be further improved to 32.8% with R4P for test-time scaling on patch selection. The stable scaling curves illustrate that though imperfect, R4P can still reliably support downstream tasks at scale.

---

### Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition

Authors: Yizhuo Wu, Francesco Fioranelli, Chang Gao
Published: 2025-10-26
Categories: eess.SP, cs.CV
arXiv: https://arxiv.org/abs/2510.22772v1

Radar-based human activity recognition (HAR) is attractive for unobtrusive and privacy-preserving monitoring, yet many CNN/RNN solutions remain too heavy for edge deployment, and even lightweight ViT/SSM variants often exceed practical compute and memory budgets. We introduce Neural-HAR, a dimension-gated CNN accelerator tailored for real-time radar HAR on resource-constrained platforms. At its core is GateCNN, a parameter-efficient Doppler-temporal network that (i) embeds Doppler vectors to emphasize frequency evolution over time and (ii) applies dual-path gated convolutions that modulate Doppler-aware content features with temporal gates, complemented by a residual path for stable training. On the University of Glasgow UoG2020 continuous radar dataset, GateCNN attains 86.4% accuracy with only 2.7k parameters and 0.28M FLOPs per inference, comparable to CNN-BiGRU at a fraction of the complexity. Our FPGA prototype on Xilinx Zynq-7000 Z-7007S reaches 107.5 $μ$s latency and 15 mW dynamic power using LUT-based ROM and distributed RAM only (zero DSP/BRAM), demonstrating real-time, energy-efficient edge inference. Code and HLS conversion scripts are available at https://github.com/lab-emi/AIRHAR.

---

### Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion

Authors: Haoyi Qiu, Yilun Zhou, Pranav Narayanan Venkit, Kung-Hsiang Huang, Jiaxin Zhang, Nanyun Peng, Chien-Sheng Wu
Published: 2025-10-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.22768v2

As autonomous agents increasingly interact, they inevitably attempt to influence one another. While prior work in text-only settings has explored the dynamics of Agent-to-Agent (A2A) persuasion, the rise of Vision-Language Models (VLMs) introduces a more complex challenge: multimodal content conveys richer information while integrating subtle, hard-to-detect persuasive cues. To study this vulnerability, we present MMPersuade, a unified framework and dataset for A2A multimodal persuasion. We model interactions between a persuader agent, which leverages images and psychological strategies, and a persuadee VLM. Our benchmark spans commercial, subjective and behavioral, and adversarial contexts, and evaluates persuasion via function-calling that capture behavioral shifts beyond verbal responses. Experiments on six VLMs reveal three findings: (1) multimodal inputs consistently outperform text-only persuasion, with raw visual signals uniquely increasing susceptibility in adversarial settings by bypassing text-activated safety defenses; (2) persuadee vulnerability is highly domain- and format-dependent, with realistic and community-style formats driving susceptibility in commercial settings while different formats dominate in adversarial ones; and (3) psychological strategy efficacy varies with context and model architecture, as more capable models resist benign persuasion yet become more susceptible under adversarial multimodal inputs. Our framework provides a foundation for building more robust and aligned VLMs in multi-agent environments.

---

### TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination

Authors: Omar Naim, Krish Sharma, Niyar R Barman, Nicholas Asher
Published: 2025-10-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.22767v3

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that improves task performance by selectively removing layers that are irrelevant or detrimental for a given task. TALE optimizes task-specific performance, yielding a task-optimized architecture without retraining. Across 9 tasks and 5 model families, under both zero-shot and few-shot settings, TALE consistently matches or surpasses baseline performance while simultaneously reducing computational costs. TALE also synergizes with fine-tuning, leading to further performance improvements. Computing TALE for a new task requires modest resources, making it a practical and deployable solution for task-specialized LLM inference.

---

### Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval

Authors: Binxiao Xu, Junyu Feng, Shaolin Lu, Yulin Luo, Shilin Yan, Hao Liang, Ming Lu, Wentao Zhang
Published: 2025-10-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22765v2

The rapid development of Vision-language models (VLMs) enables open-ended perception and reasoning. Recent works have started to investigate how to adapt general-purpose VLMs into personalized assistants. Even commercial models such as ChatGPT now support model personalization by incorporating user-specific information. However, existing methods either learn a set of concept tokens or train a VLM to utilize user-specific information. However, both pipelines struggle to generate accurate answers as personalized assistants. We introduce Jarvis, an innovative framework for a personalized AI assistant through personal KV-Cache retrieval, which stores user-specific information in the KV-Caches of both textual and visual tokens. The textual tokens are created by summarizing user information into metadata, while the visual tokens are produced by extracting distinct image patches from the user's images. When answering a question, Jarvis first retrieves related KV-Caches from personal storage and uses them to ensure accuracy in responses. We also introduce a fine-grained benchmark built with the same distinct image patch mining pipeline, emphasizing accurate question answering based on fine-grained user-specific information. Jarvis is capable of providing more accurate responses, particularly when they depend on specific local details. Jarvis achieves state-of-the-art results in both visual question answering and text-only tasks across multiple datasets, indicating a practical path toward personalized AI assistants. The code and dataset will be released.

---

### Iterative Layer Pruning for Efficient Translation Inference

Authors: Yasmin Moslem, Muhammad Hazim Al Farouq, John D. Kelleher
Published: 2025-10-26
Categories: cs.CL, cs.PF
arXiv: https://arxiv.org/abs/2510.22763v1

Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models.

---

### Understanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions

Authors: Kai Ye, Bowen Liu, Jianghang Lin, Jiayi Ji, Pingyang Dai, Liujuan Cao
Published: 2025-10-26
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.22760v1

Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions in the remote sensing domain is particularly challenging due to the prevalence of small, densely distributed objects and complex backgrounds. This paper introduces a new learning paradigm, Weakly Referring Expression Learning (WREL) for RRSIS, which leverages abundant class names as weakly referring expressions together with a small set of accurate ones to enable efficient training under limited annotation conditions. Furthermore, we provide a theoretical analysis showing that mixed-referring training yields a provable upper bound on the performance gap relative to training with fully annotated referring expressions, thereby establishing the validity of this new setting. We also propose LRB-WREL, which integrates a Learnable Reference Bank (LRB) to refine weakly referring expressions through sample-specific prompt embeddings that enrich coarse class-name inputs. Combined with a teacher-student optimization framework using dynamically scheduled EMA updates, LRB-WREL stabilizes training and enhances cross-modal generalization under noisy weakly referring supervision. Extensive experiments on our newly constructed benchmark with varying weakly referring data ratios validate both the theoretical insights and the practical effectiveness of WREL and LRB-WREL, demonstrating that they can approach or even surpass models trained with fully annotated referring expressions.

---

### EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Authors: Li Zhou, Lutong Yu, You Lyu, Yihang Lin, Zefeng Zhao, Junyi Ao, Yuhao Zhang, Benyou Wang, Haizhou Li
Published: 2025-10-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.22758v2

Speech Language Models (SLMs) have made significant progress in spoken language understanding. Yet it remains unclear whether they can fully perceive non lexical vocal cues alongside spoken words, and respond with empathy that aligns with both emotional and contextual factors. Existing benchmarks typically evaluate linguistic, acoustic, reasoning, or dialogue abilities in isolation, overlooking the integration of these skills that is crucial for human-like, emotionally intelligent conversation. We present EchoMind, the first interrelated, multi-level benchmark that simulates the cognitive process of empathetic dialogue through sequential, context-linked tasks: spoken-content understanding, vocal-cue perception, integrated reasoning, and response generation. All tasks share identical and semantically neutral scripts that are free of explicit emotional or contextual cues, and controlled variations in vocal style are used to test the effect of delivery independent of the transcript. EchoMind is grounded in an empathy-oriented framework spanning 3 coarse and 12 fine-grained dimensions, encompassing 39 vocal attributes, and evaluated using both objective and subjective metrics. Testing 12 advanced SLMs reveals that even state-of-the-art models struggle with high-expressive vocal cues, limiting empathetic response quality. Analyses of prompt strength, speech source, and ideal vocal cue recognition reveal persistent weaknesses in instruction-following, resilience to natural speech variability, and effective use of vocal cues for empathy. These results underscore the need for SLMs that integrate linguistic content with diverse vocal cues to achieve truly empathetic conversational ability.

---

### Distributionally Robust Optimization via Diffusion Ambiguity Modeling

Authors: Jiaqi Wen, Jianyi Yang
Published: 2025-10-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22757v1

This paper studies Distributionally Robust Optimization (DRO), a fundamental framework for enhancing the robustness and generalization of statistical learning and optimization. An effective ambiguity set for DRO must involve distributions that remain consistent with the nominal distribution while being diverse enough to account for a variety of potential scenarios. Moreover, it should lead to tractable DRO solutions. To this end, we propose a diffusion-based ambiguity set design that captures various adversarial distributions beyond the nominal support space while maintaining consistency with the nominal distribution. Building on this ambiguity modeling, we propose Diffusion-based DRO (D-DRO), a tractable DRO algorithm that solves the inner maximization over the parameterized diffusion model space. We formally establish the stationary convergence performance of D-DRO and empirically demonstrate its superior Out-of-Distribution (OOD) generalization performance in a ML prediction task.

---

### Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models

Authors: Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini, Yash Aggarwal, Zoran Tiganj
Published: 2025-10-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.22752v2

In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by separating events that happened at different times, this work probes the ability of various pretrained LLMs, including transformer and state-space models, to differentiate and retrieve temporally separated events. Specifically, we prompted models with sequences containing multiple presentations of the same token, which reappears at the sequence end. By fixing the positions of these repeated tokens and permuting all others, we removed semantic confounds and isolated temporal effects on next-token prediction. Across diverse sequences, models consistently placed the highest probabilities on tokens following a repeated token, but with a notable bias for those nearest the beginning or end of the input. An ablation experiment linked this phenomenon in transformers to induction heads. Extending the analysis to unique semantic contexts with partial overlap further demonstrated that memories embedded in the middle of a prompt are retrieved less reliably. Despite architectural differences, state-space and transformer models showed comparable temporal biases. Our findings deepen the understanding of temporal biases in in-context learning and offer an illustration of how these biases can enable temporal separation and episodic retrieval.

---

### Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models

Authors: Piyushkumar Patel
Published: 2025-10-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.22751v1

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major barrier to deploying these models in real-world applications where accuracy matters. We developed a fact verification framework that catches and corrects these errors in real-time by cross checking LLM outputs against multiple knowledge sources. Our system combines structured databases, live web searches, and academic literature to verify factual claims as they're generated. When we detect inconsistencies, we automatically correct them while preserving the natural flow of the response. Testing across various domains showed we could reduce hallucinations by 67% without sacrificing response quality. Domain experts in healthcare, finance, and scientific research rated our corrected outputs 89% satisfactory a significant improvement over unverified LLM responses. This work offers a practical solution for making LLMs more trustworthy in applications where getting facts wrong isn't an option.

---

### Low-Resource Dialect Adaptation of Large Language Models: A French Dialect Case-Study

Authors: Eeham Khan, Firas Saidani, Owen Van Esbroeck, Richard Khoury, Leila Kosseim
Published: 2025-10-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.22747v3

Despite the widespread adoption of Large Language Models (LLMs), their strongest capabilities remain largely confined to a small number of high-resource languages for which there is abundant training data. Recently, continual pre-training (CPT) has emerged as a means to fine-tune these models to low-resource regional dialects. In this paper, we study the use of CPT for dialect learning under tight data and compute budgets. Using low-rank adaptation (LoRA) and compute-efficient continual pre-training, we adapt three LLMs to the Québec French dialect using a very small dataset and benchmark them on the COLE suite. Our experiments demonstrate an improvement on the minority dialect benchmarks with minimal regression on the prestige language benchmarks with around 1% of model parameters updated. Analysis of the results demonstrate that gains are highly contingent on corpus composition. These findings indicate that CPT with parameter-efficient fine-tuning (PEFT) can narrow the dialect gap by providing cost-effective and sustainable language resource creation, expanding high-quality LLM access to minority linguistic communities. To support reproducibility and broaden access, we release the first Québec French LLMs on Hugging Face.

---

### OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation

Authors: Kanad Pardeshi, Bryan Wilder, Aarti Singh
Published: 2025-10-26
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.22744v1

Online learning algorithms continually update their models as data arrive, making it essential to accurately estimate the expected loss at the current time step. The prequential method is an effective estimation approach which can be practically deployed in various ways. However, theoretical guarantees have previously been established under strong conditions on the algorithm, and practical algorithms have hyperparameters which require careful tuning. We introduce OEUVRE, an estimator that evaluates each incoming sample on the function learned at the current and previous time steps, recursively updating the loss estimate in constant time and memory. We use algorithmic stability, a property satisfied by many popular online learners, for optimal updates and prove consistency, convergence rates, and concentration bounds for our estimator. We design a method to adaptively tune OEUVRE's hyperparameters and test it across diverse online and stochastic tasks. We observe that OEUVRE matches or outperforms other estimators even when their hyperparameters are tuned with oracle access to ground truth.

---

### ConMatFormer: A Multi-attention and Transformer Integrated ConvNext based Deep Learning Model for Enhanced Diabetic Foot Ulcer Classification

Authors: Raihan Ahamed Rifat, Fuyad Hasan Bhoyan, Md Humaion Kabir Mehedi, Md Kaviul Hossain, Md. Jakir Hossen, M. F. Mridha
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22743v1

Diabetic foot ulcer (DFU) detection is a clinically significant yet challenging task due to the scarcity and variability of publicly available datasets. To solve these problems, we propose ConMatFormer, a new hybrid deep learning architecture that combines ConvNeXt blocks, multiple attention mechanisms convolutional block attention module (CBAM) and dual attention network (DANet), and transformer modules in a way that works together. This design facilitates the extraction of better local features and understanding of the global context, which allows us to model small skin patterns across different types of DFU very accurately. To address the class imbalance, we used data augmentation methods. A ConvNeXt block was used to obtain detailed local features in the initial stages. Subsequently, we compiled the model by adding a transformer module to enhance long-range dependency. This enabled us to pinpoint the DFU classes that were underrepresented or constituted minorities. Tests on the DS1 (DFUC2021) and DS2 (diabetic foot ulcer (DFU)) datasets showed that ConMatFormer outperformed state-of-the-art (SOTA) convolutional neural network (CNN) and Vision Transformer (ViT) models in terms of accuracy, reliability, and flexibility. The proposed method achieved an accuracy of 0.8961 and a precision of 0.9160 in a single experiment, which is a significant improvement over the current standards for classifying DFUs. In addition, by 4-fold cross-validation, the proposed model achieved an accuracy of 0.9755 with a standard deviation of only 0.0031. We further applied explainable artificial intelligence (XAI) methods, such as Grad-CAM, Grad-CAM++, and LIME, to consistently monitor the transparency and trustworthiness of the decision-making process.. Our findings set a new benchmark for DFU classification and provide a hybrid attention transformer framework for medical image analysis.

---

### Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAM

Authors: Sai Krishna Ghanta, Ramviyas Parasuraman
Published: 2025-10-26
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.22740v1

We consider the distributed pose-graph optimization (PGO) problem, which is fundamental in accurate trajectory estimation in multi-robot simultaneous localization and mapping (SLAM). Conventional iterative approaches linearize a highly non-convex optimization objective, requiring repeated solving of normal equations, which often converge to local minima and thus produce suboptimal estimates. We propose a scalable, outlier-robust distributed planar PGO framework using Multi-Agent Reinforcement Learning (MARL). We cast distributed PGO as a partially observable Markov game defined on local pose-graphs, where each action refines a single edge's pose estimate. A graph partitioner decomposes the global pose graph, and each robot runs a recurrent edge-conditioned Graph Neural Network (GNN) encoder with adaptive edge-gating to denoise noisy edges. Robots sequentially refine poses through a hybrid policy that utilizes prior action memory and graph embeddings. After local graph correction, a consensus scheme reconciles inter-robot disagreements to produce a globally consistent estimate. Our extensive evaluations on a comprehensive suite of synthetic and real-world datasets demonstrate that our learned MARL-based actors reduce the global objective by an average of 37.5% more than the state-of-the-art distributed PGO framework, while enhancing inference efficiency by at least 6X. We also demonstrate that actor replication allows a single learned policy to scale effortlessly to substantially larger robot teams without any retraining. Code is publicly available at https://github.com/herolab-uga/policies-over-poses.

---

### REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization

Authors: Yiwen Tang, Qiuyu Zhao, Zenghui Sun, Jinsong Lan, Xiaoyong Zhu, Bo Zheng
Published: 2025-10-26
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.22739v2

In Taobao e-commerce visual search, user behavior analysis reveals a large proportion of no-click requests, suggesting diverse and implicit user intents. These intents are expressed in various forms and are difficult to mine and discover, thereby leading to the limited adaptability and lag in platform strategies. This greatly restricts users' ability to express diverse intents and hinders the scalability of the visual search system. This mismatch between user implicit intent expression and system response defines the User-SearchSys Intent Discrepancy. To alleviate the issue, we propose a novel framework REVISION. This framework integrates offline reasoning mining with online decision-making and execution, enabling adaptive strategies to solve implicit user demands. In the offline stage, we construct a periodic pipeline to mine discrepancies from historical no-click requests. Leveraging large models, we analyze implicit intent factors and infer optimal suggestions by jointly reasoning over query and product metadata. These inferred suggestions serve as actionable insights for refining platform strategies. In the online stage, REVISION-R1-3B, trained on the curated offline data, performs holistic analysis over query images and associated historical products to generate optimization plans and adaptively schedule strategies across the search pipeline. Our framework offers a streamlined paradigm for integrating large models with traditional search systems, enabling end-to-end intelligent optimization across information aggregation and user interaction. Experimental results demonstrate that our approach improves the efficiency of implicit intent mining from large-scale search logs and significantly reduces the no-click rate.

---

### Cross-view Localization and Synthesis -- Datasets, Challenges and Opportunities

Authors: Ningli Xu, Rongjun Qin
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22736v2

Cross-view localization and synthesis are two fundamental tasks in cross-view visual understanding, which deals with cross-view datasets: overhead (satellite or aerial) and ground-level imagery. These tasks have gained increasing attention due to their broad applications in autonomous navigation, urban planning, and augmented reality. Cross-view localization aims to estimate the geographic position of ground-level images based on information provided by overhead imagery while cross-view synthesis seeks to generate ground-level images based on information from the overhead imagery. Both tasks remain challenging due to significant differences in viewing perspective, resolution, and occlusion, which are widely embedded in cross-view datasets. Recent years have witnessed rapid progress driven by the availability of large-scale datasets and novel approaches. Typically, cross-view localization is formulated as an image retrieval problem where ground-level features are matched with tiled overhead images feature, extracted by convolutional neural networks (CNNs) or vision transformers (ViTs) for cross-view feature embedding. Cross-view synthesis, on the other hand, seeks to generate ground-level views based on information from overhead imagery, generally using generative adversarial networks (GANs) or diffusion models. This paper presents a comprehensive survey of advances in cross-view localization and synthesis, reviewing widely used datasets, highlighting key challenges, and providing an organized overview of state-of-the-art techniques. Furthermore, it discusses current limitations, offers comparative analyses, and outlines promising directions for future research. We also include the project page via https://github.com/GDAOSU/Awesome-Cross-View-Methods.

---

### Centrum: Model-based Database Auto-tuning with Minimal Distributional Assumptions

Authors: Yuanhao Lai, Pengfei Zheng, Chenpeng Ji, Yan Li, Songhan Zhang, Rutao Zhang, Zhengang Wang, Yunfei Du
Published: 2025-10-26
Categories: cs.LG, cs.DB, stat.ME
arXiv: https://arxiv.org/abs/2510.22734v1

Gaussian-Process-based Bayesian optimization (GP-BO), is a prevailing model-based framework for DBMS auto-tuning. However, recent work shows GP-BO-based DBMS auto-tuners significantly outperformed auto-tuners based on SMAC, which features random forest surrogate models; such results motivate us to rethink and investigate the limitations of GP-BO in auto-tuner design. We find the fundamental assumptions of GP-BO are widely violated when modeling and optimizing DBMS performance, while tree-ensemble-BOs (e.g., SMAC) can avoid the assumption pitfalls and deliver improved tuning efficiency and effectiveness. Moreover, we argue that existing tree-ensemble-BOs restrict further advancement in DBMS auto-tuning. First, existing tree-ensemble-BOs can only achieve distribution-free point estimates, but still impose unrealistic distributional assumptions on uncertainty estimates, compromising surrogate modeling and distort the acquisition function. Second, recent advances in gradient boosting, which can further enhance surrogate modeling against vanilla GP and random forest counterparts, have rarely been applied in optimizing DBMS auto-tuners. To address these issues, we propose a novel model-based DBMS auto-tuner, Centrum. Centrum improves distribution-free point and interval estimation in surrogate modeling with a two-phase learning procedure of stochastic gradient boosting ensembles. Moreover, Centrum adopts a generalized SGBE-estimated locally-adaptive conformal prediction to facilitate a distribution-free uncertainty estimation and acquisition function. To our knowledge, Centrum is the first auto-tuner to realize distribution-freeness, enhancing BO's practicality in DBMS auto-tuning, and the first to seamlessly fuse gradient boosting ensembles and conformal inference in BO. Extensive physical and simulation experiments on two DBMSs and three workloads show Centrum outperforms 21 SOTA methods.

---

### E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search

Authors: Qi Liu, Yanzhao Zhang, Mingxin Li, Dingkun Long, Pengjun Xie, Jiaxin Mao
Published: 2025-10-26
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.22733v3

Text embedding models deliver competitive retrieval performance with high efficiency, but their ranking fidelity remains limited compared to LLM-based listwise rerankers, which capture fine-grained query-document and document-document interactions at high computational cost. We propose E2Rank (Efficient Embedding-based Ranking), a unified framework that extends a single text embedding model to perform both retrieval and listwise reranking via continued training under a listwise ranking objective. The key insight is to treat the listwise prompt---constructed from the query and its top-K candidates---as a pseudo-relevance feedback (PRF) query, enabling reranking via cosine similarity against precomputed document embeddings without autoregressive decoding. Empirically, E2Rank achieves state-of-the-art results on BEIR, competitive performance on the reasoning-intensive BRIGHT benchmark, significantly lower latency than existing LLM-based rerankers, and improved embedding performance on MTEB---all within a single model.

---

### WebATLAS: An LLM Agent with Experience-Driven Memory and Action Simulation

Authors: Jiali Cheng, Anjishnu Kumar, Roshan Lal, Rishi Rajasekaran, Hani Ramezani, Omar Zia Khan, Oleg Rokhlenko, Sunny Chiu-Webster, Gang Hua, Hadi Amiri
Published: 2025-10-26
Categories: cs.LG, cs.AI, cs.CL, cs.IR, cs.MA, cs.RO
arXiv: https://arxiv.org/abs/2510.22732v2

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that experience-driven memory, combined with look-ahead action simulation, is sufficient for LLM agents to adapt to unseen web environments by remembering past failures and predicting the consequences of future actions. We introduce WebATLAS (Actor-Critic Task-completion with Look-ahead Action Simulation), a memory-augmented LLM web agent that learns a lightweight internal model of the environment from interaction experience and performs hypothetical action rollouts before acting in the real world. WebATLAS builds a persistent cognitive map via curiosity-driven exploration, stores interaction outcomes as experience-based memory, and evaluates candidate actions in cognitive space using a planner--simulator--critic loop. This enables the agent to reuse past experience, avoid previously unsuccessful behaviors, and generate more efficient plans. We evaluate WebATLAS on the WebArena-Lite benchmark for autonomous web navigation and demonstrate a success rate of 63%, outperforming the previous state-of-the-art at 53.9%. Unlike previous systems, our modular architecture requires no website-specific LLM fine-tuning. Ablation studies confirm that experience-driven memory, look-ahead action simulation, and hierarchical replanning play complementary roles in enabling robust, training-free web agents.

---

### Critical Insights into Leading Conversational AI Models

Authors: Urja Kohli, Aditi Singh, Arun Sharma
Published: 2025-10-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.22729v1

Big Language Models (LLMs) are changing the way businesses use software, the way people live their lives and the way industries work. Companies like Google, High-Flyer, Anthropic, OpenAI and Meta are making better LLMs. So, it's crucial to look at how each model is different in terms of performance, moral behaviour and usability, as these differences are based on the different ideas that built them. This study compares five top LLMs: Google's Gemini, High-Flyer's DeepSeek, Anthropic's Claude, OpenAI's GPT models and Meta's LLaMA. It performs this by analysing three important factors: Performance and Accuracy, Ethics and Bias Mitigation and Usability and Integration. It was found that Claude has good moral reasoning, Gemini is better at multimodal capabilities and has strong ethical frameworks. DeepSeek is great at reasoning based on facts, LLaMA is good for open applications and ChatGPT delivers balanced performance with a focus on usage. It was concluded that these models are different in terms of how well they work, how easy they are to use and how they treat people ethically, making it a point that each model should be utilised by the user in a way that makes the most of its strengths.

---

### S-Chain: Structured Visual Chain-of-Thought For Medicine

Authors: Khai Le-Duc, Duy M. H. Nguyen, Phuong T. H. Trinh, Tien-Phat Nguyen, Nghiem T. Diep, An Ngo, Tung Vu, Trinh Vuong, Anh-Tien Nguyen, Mau Nguyen, Van Trung Hoang, Khai-Nguyen Nguyen et al.
Published: 2025-10-26
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.22728v1

Faithful reasoning in medical vision-language models (VLMs) requires not only accurate predictions but also transparent alignment between textual rationales and visual evidence. While Chain-of-Thought (CoT) prompting has shown promise in medical visual question answering (VQA), no large-scale expert-level dataset has captured stepwise reasoning with precise visual grounding. We introduce S-Chain, the first large-scale dataset of 12,000 expert-annotated medical images with bounding boxes and structured visual CoT (SV-CoT), explicitly linking visual regions to reasoning steps. The dataset further supports 16 languages, totaling over 700k VQA pairs for broad multilingual applicability. Using S-Chain, we benchmark state-of-the-art medical VLMs (ExGra-Med, LLaVA-Med) and general-purpose VLMs (Qwen2.5-VL, InternVL2.5), showing that SV-CoT supervision significantly improves interpretability, grounding fidelity, and robustness. Beyond benchmarking, we study its synergy with retrieval-augmented generation, revealing how domain knowledge and visual grounding interact during autoregressive reasoning. Finally, we propose a new mechanism that strengthens the alignment between visual evidence and reasoning, improving both reliability and efficiency. S-Chain establishes a new benchmark for grounded medical reasoning and paves the way toward more trustworthy and explainable medical VLMs.

---

### Scalable Neural Decoders for Practical Real-Time Quantum Error Correction

Authors: Changwon Lee, Tak Hur, Daniel K. Park
Published: 2025-10-26
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.22724v1

Real-time, scalable, and accurate decoding is a critical component for realizing a fault-tolerant quantum computer. While Transformer-based neural decoders such as \textit{AlphaQubit} have demonstrated high accuracy, the computational complexity of their core attention mechanism, which scales as $\mathcal{O}(d^4)$ with code distance $d$, results in decoding speeds insufficient for practical real-time applications. In this work, we introduce and evaluate a \textit{Mamba}-based decoder, a state-space model with $\mathcal{O}(d^2)$ complexity. In memory experiments using Sycamore hardware data, our Mamba decoder matches the performance of its Transformer-based counterpart, providing that its superior efficiency does not come at the cost of performance. Crucially, in simulated real-time scenarios that account for decoder-induced noise, the Mamba decoder significantly outperforms the Transformer, exhibiting a higher error threshold of $0.0104$ compared to $0.0097$. These results demonstrate that Mamba decoders offer a compelling balance between speed and accuracy, making them a promising architecture for scalable, real-time quantum error correction.

---

### Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication

Authors: Yujie Wan, Chenxuan Liu, Shuai Wang, Tong Zhang, James Jianqiao Yu, Kejiang Ye, Dusit Niyato, Chengzhong Xu
Published: 2025-10-26
Categories: cs.IT, cs.CV
arXiv: https://arxiv.org/abs/2510.22718v2

Gaussian splatting (GS) struggles with degraded rendering quality on low-cost devices. To address this issue, we present edge collaborative GS (ECO-GS), where each user can switch between a local small GS model to guarantee timeliness and a remote large GS model to guarantee fidelity. However, deciding how to engage the large GS model is nontrivial, due to the interdependency between rendering requirements and resource conditions. To this end, we propose integrated rendering and communication (IRAC), which jointly optimizes collaboration status (i.e., deciding whether to engage large GS) and edge power allocation (i.e., enabling remote rendering) under communication constraints across different users by minimizing a newly-derived GS switching function. Despite the nonconvexity of the problem, we propose an efficient penalty majorization minimization (PMM) algorithm to obtain the critical point solution. Furthermore, we develop an imitation learning optimization (ILO) algorithm, which reduces the computational time by over 100x compared to PMM. Experiments demonstrate the superiority of PMM and the real-time execution capability of ILO.

---

### LRW-Persian: Lip-reading in the Wild Dataset for Persian Language

Authors: Zahra Taghizadeh, Mohammad Shahverdikondori, Arian Noori, Alireza Dadgarnia
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22716v1

Lipreading has emerged as an increasingly important research area for developing robust speech recognition systems and assistive technologies for the hearing-impaired. However, non-English resources for visual speech recognition remain limited. We introduce LRW-Persian, the largest in-the-wild Persian word-level lipreading dataset, comprising $743$ target words and over $414{,}000$ video samples extracted from more than $1{,}900$ hours of footage across $67$ television programs. Designed as a benchmark-ready resource, LRW-Persian provides speaker-disjoint training and test splits, wide regional and dialectal coverage, and rich per-clip metadata including head pose, age, and gender. To ensure large-scale data quality, we establish a fully automated end-to-end curation pipeline encompassing transcription based on Automatic Speech Recognition(ASR), active-speaker localization, quality filtering, and pose/mask screening. We further fine-tune two widely used lipreading architectures on LRW-Persian, establishing reference performance and demonstrating the difficulty of Persian visual speech recognition. By filling a critical gap in low-resource languages, LRW-Persian enables rigorous benchmarking, supports cross-lingual transfer, and provides a foundation for advancing multimodal speech research in underrepresented linguistic contexts. The dataset is publicly available at: https://lrw-persian.vercel.app.

---

### Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles

Authors: Jose Luis Ponton, Eduardo Alvarado, Lin Geng Foo, Nuria Pelechano, Carlos Andujar, Marc Habermann
Published: 2025-10-26
Categories: cs.GR, cs.AI
arXiv: https://arxiv.org/abs/2510.22712v2

Human motion is fundamentally driven by continuous physical interaction with the environment. Whether walking, running, or simply standing, the forces exchanged between our feet and the ground provide crucial insights for understanding and reconstructing human movement. Recent advances in wearable insole devices offer a compelling solution for capturing these forces in diverse, real-world scenarios. Sensor insoles pose no constraint on the users' motion (unlike mocap suits) and are unaffected by line-of-sight limitations (in contrast to optical systems). These qualities make sensor insoles an ideal choice for robust, unconstrained motion capture, particularly in outdoor environments. Surprisingly, leveraging these devices with recent motion reconstruction methods remains largely unexplored. Aiming to fill this gap, we present Step2Motion, the first approach to reconstruct human locomotion from multi-modal insole sensors. Our method utilizes pressure and inertial data-accelerations and angular rates-captured by the insoles to reconstruct human motion. We evaluate the effectiveness of our approach across a range of experiments to show its versatility for diverse locomotion styles, from simple ones like walking or jogging up to moving sideways, on tiptoes, slightly crouching, or dancing.

---

### Identification of Causal Direction under an Arbitrary Number of Latent Confounders

Authors: Wei Chen, Linjun Peng, Zhiyi Huang, Haoyue Dai, Zhifeng Hao, Ruichu Cai, Kun Zhang
Published: 2025-10-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.22711v1

Recovering causal structure in the presence of latent variables is an important but challenging task. While many methods have been proposed to handle it, most of them require strict and/or untestable assumptions on the causal structure. In real-world scenarios, observed variables may be affected by multiple latent variables simultaneously, which, generally speaking, cannot be handled by these methods. In this paper, we consider the linear, non-Gaussian case, and make use of the joint higher-order cumulant matrix of the observed variables constructed in a specific way. We show that, surprisingly, causal asymmetry between two observed variables can be directly seen from the rank deficiency properties of such higher-order cumulant matrices, even in the presence of an arbitrary number of latent confounders. Identifiability results are established, and the corresponding identification methods do not even involve iterative procedures. Experimental results demonstrate the effectiveness and asymptotic correctness of our proposed method.

---

### RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability

Authors: Kaitong Cai, Jusheng Zhang, Yijia Fan, Jing Yang, Keze Wang
Published: 2025-10-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22710v1

Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose RaCoT (Retrieval-aware Contrastive-of-Thought), a novel framework that shifts contrastive thinking to the pre-retrieval stage. By automatically generating a semantically adjacent yet differently answered contrastive question and extracting a $Δ$-Prompt to capture their key differences, RaCoT guides the model to proactively focus on the ``critical details that determine answer divergence." This approach allows it to suppress semantic interference within a single retrieval pass, overcoming the theoretical bottleneck of single-vector queries that struggle to simultaneously encode signals for what to attend to and what to ignore. On six authoritative benchmarks, including PopQA and TriviaQA-unfiltered, RaCoT outperforms strong baselines like RankRAG and Self-RAG by 0.9-2.4 percentage points. It exhibits superior robustness, with a performance drop of only 8.6\% in adversarial tests, far surpassing the over 15\% degradation in other methods. Furthermore, its low latency (3.12s) and token overhead (11.54) place it on the accuracy-efficiency Pareto frontier, while ablation studies validate the necessity of each component. Ultimately, RaCoT reframes the RAG paradigm from ``post-hoc context cleaning" to ``a priori shaping of discriminative reasoning", offering an efficient and robust path toward reliable AI systems for real-time, resource-constrained deployments.

---

### IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

Authors: Hao Li, Zhengyu Zou, Fangfu Liu, Xuanyang Zhang, Fangzhou Hong, Yukang Cao, Yushi Lan, Manyuan Zhang, Gang Yu, Dingwen Zhang, Ziwei Liu
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22706v3

Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions, enabling coherent and accurate understanding of complex scenes. However, most prior approaches prioritize training large geometry models for low-level 3D reconstruction and treat high-level spatial understanding in isolation, overlooking the crucial interplay between these two fundamental aspects of 3D-scene analysis, thereby limiting generalization and leading to poor performance in downstream 3D understanding tasks. Recent attempts have mitigated this issue by simply aligning 3D models with specific language models, thus restricting perception to the aligned model's capacity and limiting adaptability to downstream tasks. In this paper, we propose InstanceGrounded Geometry Transformer (IGGT), an end-to-end large unified transformer to unify the knowledge for both spatial reconstruction and instance-level contextual understanding. Specifically, we design a 3D-Consistent Contrastive Learning strategy that guides IGGT to encode a unified representation with geometric structures and instance-grounded clustering through only 2D visual inputs. This representation supports consistent lifting of 2D visual inputs into a coherent 3D scene with explicitly distinct object instances. To facilitate this task, we further construct InsScene-15K, a large-scale dataset with high-quality RGB images, poses, depth maps, and 3D-consistent instance-level mask annotations with a novel data curation pipeline.

---

### Atlas Urban Index: A VLM-Based Approach for Spatially and Temporally Calibrated Urban Development Monitoring

Authors: Mithul Chander, Sai Pragnya Ranga, Prathamesh Mayekar
Published: 2025-10-26
Categories: cs.AI, cs.CV, cs.ET, eess.IV
arXiv: https://arxiv.org/abs/2510.22702v1

We introduce the {\em Atlas Urban Index} (AUI), a metric for measuring urban development computed using Sentinel-2 \citep{spoto2012sentinel2} satellite imagery. Existing approaches, such as the {\em Normalized Difference Built-up Index} (NDBI), often struggle to accurately capture urban development due to factors like atmospheric noise, seasonal variation, and cloud cover. These limitations hinder large-scale monitoring of human development and urbanization. To address these challenges, we propose an approach that leverages {\em Vision-Language Models }(VLMs) to provide a development score for regions. Specifically, we collect a time series of Sentinel-2 images for each region. Then, we further process the images within fixed time windows to get an image with minimal cloud cover, which serves as the representative image for that time window. To ensure consistent scoring, we adopt two strategies: (i) providing the VLM with a curated set of reference images representing different levels of urbanization, and (ii) supplying the most recent past image to both anchor temporal consistency and mitigate cloud-related noise in the current image. Together, these components enable AUI to overcome the challenges of traditional urbanization indices and produce more reliable and stable development scores. Our qualitative experiments on Bangalore suggest that AUI outperforms standard indices such as NDBI.

---

### WaveMAE: Wavelet decomposition Masked Auto-Encoder for Remote Sensing

Authors: Vittorio Bernuzzi, Leonardo Rossi, Tomaso Fontanini, Massimo Bertozzi, Andrea Prati
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22697v1

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce WaveMAE, a masked autoencoding framework tailored for multispectral satellite imagery. Unlike conventional pixel-based reconstruction, WaveMAE leverages a multi-level Discrete Wavelet Transform (DWT) to disentangle frequency components and guide the encoder toward learning scale-aware high-frequency representations. We further propose a Geo-conditioned Positional Encoding (GPE), which incorporates geographical priors via Spherical Harmonics, encouraging embeddings that respect both semantic and geospatial structure. To ensure fairness in evaluation, all methods are pretrained on the same dataset (fMoW-S2) and systematically evaluated on the diverse downstream tasks of the PANGAEA benchmark, spanning semantic segmentation, regression, change detection, and multilabel classification. Extensive experiments demonstrate that WaveMAE achieves consistent improvements over prior state-of-the-art approaches, with substantial gains on segmentation and regression benchmarks. The effectiveness of WaveMAE pretraining is further demonstrated by showing that even a lightweight variant, containing only 26.4% of the parameters, achieves state-of-the-art performance. Our results establish WaveMAE as a strong and geographically informed foundation model for multispectral remote sensing imagery.

---

### Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation

Authors: Shu Zhao, Tianyi Shen, Nilesh Ahuja, Omesh Tickoo, Vijaykrishnan Narayanan
Published: 2025-10-26
Categories: cs.CV, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.22694v1

Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a promising method to generate factual and up-to-date responses of Multimodal Large Language Models (MLLMs) by incorporating non-parametric knowledge from external knowledge bases. However, existing MRAG approaches suffer from static retrieval strategies, inflexible modality selection, and suboptimal utilization of retrieved information, leading to three critical challenges: determining when to retrieve, what modality to incorporate, and how to utilize retrieved information effectively. To address these challenges, we introduce Windsock, a query-dependent module making decisions on retrieval necessity and modality selection, effectively reducing computational overhead and improving response quality. Additionally, we propose Dynamic Noise-Resistance (DANCE) Instruction Tuning, an adaptive training strategy that enhances MLLMs' ability to utilize retrieved information while maintaining robustness against noise. Moreover, we adopt a self-assessment approach leveraging knowledge within MLLMs to convert question-answering datasets to MRAG training datasets. Extensive experiments demonstrate that our proposed method significantly improves the generation quality by 17.07% while reducing 8.95% retrieval times.

---

### VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree

Authors: Wenlong Li, Yifei Xu, Yuan Rao, Zhenhua Wang, Shuiguang Deng
Published: 2025-10-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22693v3

Video anomaly detection (VAD) focuses on identifying anomalies in videos. Supervised methods demand substantial in-domain training data and fail to deliver clear explanations for anomalies. In contrast, training-free methods leverage the knowledge reserves and language interactivity of large pre-trained models to detect anomalies. However, the current fixed-length temporal window sampling approaches struggle to accurately capture anomalies with varying temporal spans. Therefore, we propose VADTree that utilizes a Hierarchical Granularityaware Tree (HGTree) structure for flexible sampling in VAD. VADTree leverages the knowledge embedded in a pre-trained Generic Event Boundary Detection (GEBD) model to characterize potential anomaly event boundaries. Specifically, VADTree decomposes the video into generic event nodes based on boundary confidence, and performs adaptive coarse-fine hierarchical structuring and redundancy removal to construct the HGTree. Then, the multi-dimensional priors are injected into the visual language models (VLMs) to enhance the node-wise anomaly perception, and anomaly reasoning for generic event nodes is achieved via large language models (LLMs). Finally, an inter-cluster node correlation method is used to integrate the multi-granularity anomaly scores. Extensive experiments on three challenging datasets demonstrate that VADTree achieves state-of-the-art performance in training-free settings while drastically reducing the number of sampled video segments. The code will be available at https://github.com/wenlongli10/VADTree.

---

### SALSA: Single-pass Autoregressive LLM Structured Classification

Authors: Ruslan Berdichevsky, Shai Nahum-Gefen, Elad Ben Zaken
Published: 2025-10-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.22691v1

Despite their impressive generalization capabilities, instruction-tuned Large Language Models often underperform on text classification benchmarks. We introduce SALSA, a coherent pipeline that combines structured prompting, class-to-token mapping, and parameter-efficient fine-tuning, thereby avoiding cold-start training. Each class label is mapped to a distinct output token, and prompts are constructed to elicit a single-token response. During inference, the model's output is projected only onto the logits of the relevant class tokens, enabling efficient and accurate classification in a single forward pass. SALSA achieves state-of-the-art results across diverse benchmarks, demonstrating its robustness and scalability for LLM-based classification applications.

---

### Rule-Based Explanations for Retrieval-Augmented LLM Systems

Authors: Joel Rorseth, Parke Godfrey, Lukasz Golab, Divesh Srivastava, Jarek Szlichta
Published: 2025-10-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.22689v2

If-then rules are widely used to explain machine learning models; e.g., "if employed = no, then loan application = rejected." We present the first proposal to apply rules to explain the emerging class of large language models (LLMs) with retrieval-augmented generation (RAG). Since RAG enables LLM systems to incorporate retrieved information sources at inference time, rules linking the presence or absence of sources can explain output provenance; e.g., "if a Times Higher Education ranking article is retrieved, then the LLM ranks Oxford first." To generate such rules, a brute force approach would probe the LLM with all source combinations and check if the presence or absence of any sources leads to the same output. We propose optimizations to speed up rule generation, inspired by Apriori-like pruning from frequent itemset mining but redefined within the scope of our novel problem. We conclude with qualitative and quantitative experiments demonstrating our solutions' value and efficiency.

---

### FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning

Authors: Shan Zhong, Shutong Ding, He Diao, Xiangyu Wang, Kah Chan Teh, Bei Peng
Published: 2025-10-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.22686v1

Reliable value estimation serves as the cornerstone of reinforcement learning (RL) by evaluating long-term returns and guiding policy improvement, significantly influencing the convergence speed and final performance. Existing works improve the reliability of value function estimation via multi-critic ensembles and distributional RL, yet the former merely combines multi point estimation without capturing distributional information, whereas the latter relies on discretization or quantile regression, limiting the expressiveness of complex value distributions. Inspired by flow matching's success in generative modeling, we propose a generative paradigm for value estimation, named FlowCritic. Departing from conventional regression for deterministic value prediction, FlowCritic leverages flow matching to model value distributions and generate samples for value estimation.

---