# Research Papers — 2025-10 · bundle page 136 of 217

> Full-text markdown of papers #6751–6800 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/136
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/135.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/137.md)

### Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs

Authors: Suyang Xi, Chenxi Yang, Hong Ding, Yiqing Ni, Catherine C. Liu, Yunhao Liu, Chengqi Zhang
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10426v1

Multimodal large language models (MLLMs) often fail in fine-grained visual question answering, producing hallucinations about object identities, positions, and relations because textual queries are not explicitly anchored to visual referents. Retrieval-augmented generation (RAG) alleviates some errors, but it fails to align with human-like processing at both the retrieval and augmentation levels. Specifically, it focuses only on global-level image information but lacks local detail and limits reasoning about fine-grained interactions. To overcome this limitation, we present Human-Like Retrieval-Augmented Generation (HuLiRAG), a framework that stages multimodal reasoning as a ``what--where--reweight'' cascade. Queries are first anchored to candidate referents via open-vocabulary detection (what), then spatially resolved with SAM-derived masks to recover fine-grained precision (where), and adaptively prioritized through the trade-off between local and global alignment (reweight). Mask-guided fine-tuning further injects spatial evidence into the generation process, transforming grounding from a passive bias into an explicit constraint on answer formulation. Extensive experiments demonstrate that this human-like cascade improves grounding fidelity and factual consistency while reducing hallucinations, advancing multimodal question answering toward trustworthy reasoning.

---

### Softmax $\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent

Authors: Sara Dragutinović, Andrew M. Saxe, Aaditya K. Singh
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10425v1

The remarkable ability of transformers to learn new concepts solely by reading examples within the input prompt, termed in-context learning (ICL), is a crucial aspect of intelligent behavior. Here, we focus on understanding the learning algorithm transformers use to learn from context. Existing theoretical work, often based on simplifying assumptions, has primarily focused on linear self-attention and continuous regression tasks, finding transformers can learn in-context by gradient descent. Given that transformers are typically trained on discrete and complex tasks, we bridge the gap from this existing work to the setting of classification, with non-linear (importantly, softmax) activation. We find that transformers still learn to do gradient descent in-context, though on functionals in the kernel feature space and with a context-adaptive learning rate in the case of softmax transformer. These theoretical findings suggest a greater adaptability to context for softmax attention, which we empirically verify and study through ablations. Overall, we hope this enhances theoretical understanding of in-context learning algorithms in more realistic settings, pushes forward our intuitions and enables further theory bridging to larger models.

---

### Towards Cybersickness Severity Classification from VR Gameplay Videos Using Transfer Learning and Temporal Modeling

Authors: Jyotirmay Nag Setu, Kevin Desai, John Quarles
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10422v1

With the rapid advancement of virtual reality (VR) technology, its adoption across domains such as healthcare, education, and entertainment has grown significantly. However, the persistent issue of cybersickness, marked by symptoms resembling motion sickness, continues to hinder widespread acceptance of VR. While recent research has explored multimodal deep learning approaches leveraging data from integrated VR sensors like eye and head tracking, there remains limited investigation into the use of video-based features for predicting cybersickness. In this study, we address this gap by utilizing transfer learning to extract high-level visual features from VR gameplay videos using the InceptionV3 model pretrained on the ImageNet dataset. These features are then passed to a Long Short-Term Memory (LSTM) network to capture the temporal dynamics of the VR experience and predict cybersickness severity over time. Our approach effectively leverages the time-series nature of video data, achieving a 68.4% classification accuracy for cybersickness severity. This surpasses the performance of existing models trained solely on video data, providing a practical tool for VR developers to evaluate and mitigate cybersickness in virtual environments. Furthermore, this work lays the foundation for future research on video-based temporal modeling for enhancing user comfort in VR applications.

---

### Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis

Authors: Zhao-Yang Wang, Zhimin Shao, Anirudh Nanduri, Basudha Pal, Laura McDaniel, Jieneng Chen, Rama Chellappa
Published: 2025-10-12
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10417v2

Gait recognition is an important biometric for human identification at a distance, particularly under low-resolution or unconstrained environments. Current works typically focus on either 2D representations (e.g., silhouettes and skeletons) or 3D representations (e.g., meshes and SMPLs), but relying on a single modality often fails to capture the full geometric and dynamic complexity of human walking patterns. In this paper, we propose a multi-modal and multi-task framework that combines 2D temporal silhouettes with 3D SMPL features for robust gait analysis. Beyond identification, we introduce a multitask learning strategy that jointly performs gait recognition and human attribute estimation, including age, body mass index (BMI), and gender. A unified transformer is employed to effectively fuse multi-modal gait features and better learn attribute-related representations, while preserving discriminative identity cues. Extensive experiments on the large-scale BRIAR datasets, collected under challenging conditions such as long-range distances (up to 1 km) and extreme pitch angles (up to 50°), demonstrate that our approach outperforms state-of-the-art methods in gait recognition and provides accurate human attribute estimation. These results highlight the promise of multi-modal and multitask learning for advancing gait-based human understanding in real-world scenarios.

---

### CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints

Authors: Federica Bologna, Tiffany Pan, Matthew Wilkens, Yue Guo, Lucy Lu Wang
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10415v3

Evaluating multi-paragraph clinical question answering (QA) systems is resource-intensive and challenging: accurate judgments require medical expertise and achieving consistent human judgments over multi-paragraph text is difficult. We introduce CQA-Eval, an evaluation framework and set of evaluation recommendations for limited-resource and high-expertise settings. Based on physician annotations of 300 real patient questions answered by physicians and LLMs, we compare coarse answer-level versus fine-grained sentence-level evaluation over the dimensions of correctness, relevance, and risk disclosure. We find that inter-annotator agreement (IAA) varies by dimension: fine-grained annotation improves agreement on correctness, coarse improves agreement on relevance, and judgments on communicates-risks remain inconsistent. Additionally, annotating only a small subset of sentences can provide reliability comparable to coarse annotations, reducing cost and effort.

---

### Guided Image Feature Matching using Feature Spatial Order

Authors: Chin-Hung Teng, Ben-Jian Dong
Published: 2025-10-12
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2510.10414v1

Image feature matching plays a vital role in many computer vision tasks. Although many image feature detection and matching techniques have been proposed over the past few decades, it is still time-consuming to match feature points in two images, especially for images with a large number of detected features. Feature spatial order can estimate the probability that a pair of features is correct. Since it is a completely independent concept from epipolar geometry, it can be used to complement epipolar geometry in guiding feature match in a target region so as to improve matching efficiency. In this paper, we integrate the concept of feature spatial order into a progressive matching framework. We use some of the initially matched features to build a computational model of feature spatial order and employs it to calculates the possible spatial range of subsequent feature matches, thus filtering out unnecessary feature matches. We also integrate it with epipolar geometry to further improve matching efficiency and accuracy. Since the spatial order of feature points is affected by image rotation, we propose a suitable image alignment method from the fundamental matrix of epipolar geometry to remove the effect of image rotation. To verify the feasibility of the proposed method, we conduct a series of experiments, including a standard benchmark dataset, self-generated simulated images, and real images. The results demonstrate that our proposed method is significantly more efficient and has more accurate feature matching than the traditional method.

---

### Trace Length is a Simple Uncertainty Signal in Reasoning Models

Authors: Siddartha Devic, Charlotte Peale, Arwen Bradley, Sinead Williamson, Preetum Nakkiran, Aravind Gollakota
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10409v1

Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence estimator in large reasoning models. Through comprehensive experiments across multiple models, datasets, and prompts, we show that trace length performs in comparable but complementary ways to other zero-shot confidence estimators such as verbalized confidence. Our work reveals that reasoning post-training fundamentally alters the relationship between trace length and accuracy, going beyond prior work that had shown that post-training causes traces to grow longer in general (e.g., "overthinking"). We investigate the mechanisms behind trace length's performance as a confidence signal, observing that the effect remains even after adjusting for confounders such as problem difficulty and GRPO-induced length bias. We identify high-entropy or "forking" tokens as playing a key role in the mechanism. Our findings demonstrate that reasoning post-training enhances uncertainty quantification beyond verbal expressions, and establish trace length as a practical confidence measure for large reasoning models.

---

### Mesh-Gait: A Unified Framework for Gait Recognition Through Multi-Modal Representation Learning from 2D Silhouettes

Authors: Zhao-Yang Wang, Jieneng Chen, Jiang Liu, Yuxiang Guo, Rama Chellappa
Published: 2025-10-12
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10406v1

Gait recognition, a fundamental biometric technology, leverages unique walking patterns for individual identification, typically using 2D representations such as silhouettes or skeletons. However, these methods often struggle with viewpoint variations, occlusions, and noise. Multi-modal approaches that incorporate 3D body shape information offer improved robustness but are computationally expensive, limiting their feasibility for real-time applications. To address these challenges, we introduce Mesh-Gait, a novel end-to-end multi-modal gait recognition framework that directly reconstructs 3D representations from 2D silhouettes, effectively combining the strengths of both modalities. Compared to existing methods, directly learning 3D features from 3D joints or meshes is complex and difficult to fuse with silhouette-based gait features. To overcome this, Mesh-Gait reconstructs 3D heatmaps as an intermediate representation, enabling the model to effectively capture 3D geometric information while maintaining simplicity and computational efficiency. During training, the intermediate 3D heatmaps are gradually reconstructed and become increasingly accurate under supervised learning, where the loss is calculated between the reconstructed 3D joints, virtual markers, and 3D meshes and their corresponding ground truth, ensuring precise spatial alignment and consistent 3D structure. Mesh-Gait extracts discriminative features from both silhouettes and reconstructed 3D heatmaps in a computationally efficient manner. This design enables the model to capture spatial and structural gait characteristics while avoiding the heavy overhead of direct 3D reconstruction from RGB videos, allowing the network to focus on motion dynamics rather than irrelevant visual details. Extensive experiments demonstrate that Mesh-Gait achieves state-of-the-art accuracy. The code will be released upon acceptance of the paper.

---

### Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance

Authors: Jiachi Zhao, Zehong Wang, Yamei Liao, Chuxu Zhang, Yanfang Ye
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2510.10402v2

Graph generation is a fundamental problem in graph learning with broad applications across Web-scale systems, knowledge graphs, and scientific domains such as drug and material discovery. Recent approaches leverage diffusion models for step-by-step generation, yet unconditional diffusion offers little control over desired properties, often leading to unstable quality and difficulty in incorporating new objectives. Inference-time guidance methods mitigate these issues by adjusting the sampling process without retraining, but they remain inherently local, heuristic, and limited in controllability. To overcome these limitations, we propose TreeDiff, a Monte Carlo Tree Search (MCTS) guided dual-space diffusion framework for controllable graph generation. TreeDiff is a plug-and-play inference-time method that expands the search space while keeping computation tractable. Specifically, TreeDiff introduces three key designs to make it practical and scalable: (1) a macro-step expansion strategy that groups multiple denoising updates into a single transition, reducing tree depth and enabling long-horizon exploration; (2) a dual-space denoising mechanism that couples efficient latent-space denoising with lightweight discrete correction in graph space, ensuring both scalability and structural fidelity; and (3) a dual-space verifier that predicts long-term rewards from partially denoised graphs, enabling early value estimation and removing the need for full rollouts. Extensive experiments on 2D and 3D molecular generation benchmarks, under both unconditional and conditional settings, demonstrate that TreeDiff achieves state-of-the-art performance. Notably, TreeDiff exhibits favorable inference-time scaling: it continues to improve with additional computation, while existing inference-time methods plateau early under limited resources.

---

### STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models

Authors: Geunyeong Jeong, Juoh Sun, Seonghee Lee, Harksoo Kim
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10398v1

Large Language Models store extensive factual knowledge acquired during large-scale pre-training. However, this knowledge is inherently static, reflecting only the state of the world at the time of training. Knowledge editing has emerged as a promising solution for updating outdated or incorrect facts without full retraining. However, most existing locate-and-edit methods primarily focus on token-level likelihood optimization without addressing semantic coherence. Our analysis reveals that such edited knowledge is often encoded as isolated residual streams in the model's latent space, distinct from pre-existing knowledge and bypassing natural reasoning process. To address this, we propose \textsc{Steam}, a semantic-level knowledge editing framework that enhances integration of updated knowledge into the model's knowledge structure. \textsc{Steam} first identifies target representations as semantic anchors for the updated factual association, then guides the internal representation of the edited fact towards these anchors through an alignment loss during optimization. Experimental results demonstrate that \textsc{Steam} improves model's ability to reason with edited knowledge and enhances semantic coherence, underscoring the importance of latent-space alignment for reliable and coherent knowledge editing. The code is available at https://github.com/GY-Jeong/STEAM.

---

### AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval

Authors: Kai Zhang, Xinyuan Zhang, Ejaz Ahmed, Hongda Jiang, Caleb Kumar, Kai Sun, Zhaojiang Lin, Sanat Sharma, Shereen Oraby, Aaron Colak, Ahmed Aly, Anuj Kumar et al.
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10397v1

Accurate recall from large scale memories remains a core challenge for memory augmented AI assistants performing question answering (QA), especially in similarity dense scenarios where existing methods mainly rely on semantic distance to the query for retrieval. Inspired by how humans link information associatively, we propose AssoMem, a novel framework constructing an associative memory graph that anchors dialogue utterances to automatically extracted clues. This structure provides a rich organizational view of the conversational context and facilitates importance aware ranking. Further, AssoMem integrates multi-dimensional retrieval signals-relevance, importance, and temporal alignment using an adaptive mutual information (MI) driven fusion strategy. Extensive experiments across three benchmarks and a newly introduced dataset, MeetingQA, demonstrate that AssoMem consistently outperforms SOTA baselines, verifying its superiority in context-aware memory recall.

---

### AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

Authors: Xinlong Chen, Yue Ding, Weihong Lin, Jingyun Hua, Linli Yao, Yang Shi, Bozhou Li, Yuanxing Zhang, Qiang Liu, Pengfei Wan, Liang Wang, Tieniu Tan
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10395v1

Audiovisual video captioning aims to generate semantically rich descriptions with temporal alignment between visual and auditory events, thereby benefiting both video understanding and generation. In this paper, we present AVoCaDO, a powerful audiovisual video captioner driven by the temporal orchestration between audio and visual modalities. We propose a two-stage post-training pipeline: (1) AVoCaDO SFT, which fine-tunes the model on a newly curated dataset of 107K high-quality, temporally-aligned audiovisual captions; and (2) AVoCaDO GRPO, which leverages tailored reward functions to further enhance temporal coherence and dialogue accuracy while regularizing caption length and reducing collapse. Experimental results demonstrate that AVoCaDO significantly outperforms existing open-source models across four audiovisual video captioning benchmarks, and also achieves competitive performance on the VDC and DREAM-1K benchmark under visual-only settings.

---

### RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models

Authors: Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer, Virginia Smith, Mona T. Diab
Published: 2025-10-12
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10390v1

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, with refusal accuracy dropping below 50% on multi-document tasks, while exhibiting either dangerous overconfidence or overcaution. Static benchmarks fail to reliably evaluate this capability, as models exploit dataset-specific artifacts and memorize test instances. We introduce RefusalBench, a generative methodology that programmatically creates diagnostic test cases through controlled linguistic perturbation. Our framework employs 176 distinct perturbation strategies across six categories of informational uncertainty and three intensity levels. Evaluation of over 30 models uncovers systematic failure patterns: refusal comprises separable detection and categorization skills, and neither scale nor extended reasoning improves performance. We find that selective refusal is a trainable, alignment-sensitive capability, offering a clear path for improvement. We release two benchmarks -- RefusalBench-NQ (single document) and RefusalBench-GaRAGe (multi-document) -- and our complete generation framework to enable continued, dynamic evaluation of this critical capability.

---

### ASC analyzer: A Python package for measuring argument structure construction usage in English texts

Authors: Hakyung Sung, Kristopher Kyle
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10384v1

Argument structure constructions (ASCs) offer a theoretically grounded lens for analyzing second language (L2) proficiency, yet scalable and systematic tools for measuring their usage remain limited. This paper introduces the ASC analyzer, a publicly available Python package designed to address this gap. The analyzer automatically tags ASCs and computes 50 indices that capture diversity, proportion, frequency, and ASC-verb lemma association strength. To demonstrate its utility, we conduct both bivariate and multivariate analyses that examine the relationship between ASC-based indices and L2 writing scores.

---

### Identifying bias in CNN image classification using image scrambling and transforms

Authors: Sai Teja Erukude
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10383v1

CNNs are now prevalent as the primary choice for most machine vision problems due to their superior rate of classification and the availability of user-friendly libraries. These networks effortlessly identify and select features in a non-intuitive data-driven manner, making it difficult to determine which features were most influential. That leads to a ``black box", where users cannot know how the image data are analyzed but rely on empirical results. Therefore the decision-making process can be biased by background information that is difficult to detect. Here we discuss examples of such hidden biases and propose techniques for identifying them, methods to distinguish between contextual information and background noise, and explore whether CNNs learn from irrelevant features. One effective approach to identify dataset bias is to classify blank background parts of the images. However, in some situations a blank background in the images is not available, making it more difficult to separate the foreground information from the blank background. Such parts of the image can also be considered contextual learning, not necessarily bias. To overcome this, we propose two approaches that were tested on six different datasets, including natural, synthetic, and hybrid datasets. The first method involves dividing images into smaller, non-overlapping tiles of various sizes, which are then shuffled randomly, making classification more challenging. The second method involves the application of several image transforms, including Fourier, Wavelet transforms, and Median filter, and their combinations. These transforms help recover background noise information used by CNN to classify images. Results indicate that this method can effectively distinguish between contextual information and background noise, and alert on the presence of background noise even without the need to use background information.

---

### FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes

Authors: Shouxu Lin, Zimeng Pan, Yuhang Yao, Haeyoung Noh, Pei Zhang, Carlee Joe-Wong
Published: 2025-10-12
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2510.10380v1

Multi-Model Federated Learning (MMFL) is an emerging direction in Federated Learning (FL) where multiple models are trained in parallel, generally on various datasets. Optimizing the models' accuracies and training times in the MMFL setting requires adapting to data and system heterogeneity across clients as in single-model FL; these challenges are amplified in the MMFL setting due to additional heterogeneity across models. Neither existing solutions nor naïve extensions of single-model FL frameworks efficiently address these challenges. To bridge this gap, we propose FLAMMABLE, a comprehensive MMFL training framework. FLAMMABLE optimizes model training by intelligently adapting client batch sizes while engaging them to train multiple carefully chosen models, depending on their system capabilities, in each training round. To evaluate FLAMMABLE, we develop the first benchmark platform for the MMFL setting, which may enable future reproducible MMFL research. Extensive evaluations on multiple datasets and models show that FLAMMABLE boosts the MMFL time-to-accuracy performance by 1.1$\sim$10.0$\times$ while improving the final model accuracy by 1.3$\sim$5.4\% compared to several known baselines.

---

### RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning

Authors: Rohan Gupta, Trevor Asbery, Zain Merchant, Abrar Anwar, Jesse Thomason
Published: 2025-10-12
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.10379v1

Coordinating heterogeneous robot fleets to achieve multiple goals is challenging in multi-robot systems. We introduce an open-source and extensible framework for centralized multi-robot task planning and scheduling that leverages LLMs to enable fleets of heterogeneous robots to accomplish multiple tasks. RobotFleet provides abstractions for planning, scheduling, and execution across robots deployed as containerized services to simplify fleet scaling and management. The framework maintains a shared declarative world state and two-way communication for task execution and replanning. By modularizing each layer of the autonomy stack and using LLMs for open-world reasoning, RobotFleet lowers the barrier to building scalable multi-robot systems. The code can be found here: https://github.com/therohangupta/robot-fleet.

---

### Self-Supervised Multi-Scale Transformer with Attention-Guided Fusion for Efficient Crack Detection

Authors: Blessing Agyei Kyem, Joshua Kofi Asamoah, Eugene Denteh, Andrews Danyo, Armstrong Aboah
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10378v1

Pavement crack detection has long depended on costly and time-intensive pixel-level annotations, which limit its scalability for large-scale infrastructure monitoring. To overcome this barrier, this paper examines the feasibility of achieving effective pixel-level crack segmentation entirely without manual annotations. Building on this objective, a fully self-supervised framework, Crack-Segmenter, is developed, integrating three complementary modules: the Scale-Adaptive Embedder (SAE) for robust multi-scale feature extraction, the Directional Attention Transformer (DAT) for maintaining linear crack continuity, and the Attention-Guided Fusion (AGF) module for adaptive feature integration. Through evaluations on ten public datasets, Crack-Segmenter consistently outperforms 13 state-of-the-art supervised methods across all major metrics, including mean Intersection over Union (mIoU), Dice score, XOR, and Hausdorff Distance (HD). These findings demonstrate that annotation-free crack detection is not only feasible but also superior, enabling transportation agencies and infrastructure managers to conduct scalable and cost-effective monitoring. This work advances self-supervised learning and motivates pavement cracks detection research.

---

### Applying non-negative matrix factorization with covariates to label matrix for classification

Authors: Kenichi Satoh
Published: 2025-10-12
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.10375v1

Non-negative matrix factorization (NMF) is widely used for dimensionality reduction and interpretable analysis, but standard formulations are unsupervised and cannot directly exploit class labels. Existing supervised or semi-supervised extensions usually incorporate labels only via penalties or graph constraints, still requiring an external classifier. We propose \textit{NMF-LAB} (Non-negative Matrix Factorization for Label Matrix), which redefines classification as the inverse problem of non-negative matrix tri-factorization (tri-NMF). Unlike joint NMF methods, which reconstruct both features and labels, NMF-LAB directly factorizes the label matrix $Y$ as the observation, while covariates $A$ are treated as given explanatory variables. This yields a direct probabilistic mapping from covariates to labels, distinguishing our method from label-matrix factorization approaches that mainly model label correlations or impute missing labels. Our inversion offers two key advantages: (i) class-membership probabilities are obtained directly from the factorization without a separate classifier, and (ii) covariates, including kernel-based similarities, can be seamlessly integrated to generalize predictions to unseen samples. In addition, unlabeled data can be encoded as uniform distributions, supporting semi-supervised learning. Experiments on diverse datasets, from small-scale benchmarks to the large-scale MNIST dataset, demonstrate that NMF-LAB achieves competitive predictive accuracy, robustness to noisy or incomplete labels, and scalability to high-dimensional problems, while preserving interpretability. By unifying regression and classification within the tri-NMF framework, NMF-LAB provides a novel, probabilistic, and scalable approach to modern classification tasks.

---

### Exploration-free Algorithms for Multi-group Mean Estimation

Authors: Ziyi Wei, Huaiyang Zhong, Xiaocheng Li
Published: 2025-10-12
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.10374v1

We address the problem of multi-group mean estimation, which seeks to allocate a finite sampling budget across multiple groups to obtain uniformly accurate estimates of their means. Unlike classical multi-armed bandits, whose objective is to minimize regret by identifying and exploiting the best arm, the optimal allocation in this setting requires sampling every group on the order of $Θ(T)$ times. This fundamental distinction makes exploration-free algorithms both natural and effective. Our work makes three contributions. First, we strengthen the existing results on subgaussian variance concentration using the Hanson-Wright inequality and identify a class of strictly subgaussian distributions that yield sharper guarantees. Second, we design exploration-free non-adaptive and adaptive algorithms, and we establish tighter regret bounds than the existing results. Third, we extend the framework to contextual bandit settings, an underexplored direction, and propose algorithms that leverage side information with provable guarantees. Overall, these results position exploration-free allocation as a principled and efficient approach to multi-group mean estimation, with potential applications in experimental design, personalization, and other domains requiring accurate multi-group inference.

---

### RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

Authors: Rongyang Zhang, Yuqing Huang, Chengqiang Lu, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Yin Xu, Wei Wang, Hao Wang, Enhong Chen
Published: 2025-10-11
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.05119v1

In real-world scenarios, providing user queries with visually enhanced responses can considerably benefit understanding and memory, underscoring the great value of interleaved image-text generation. Despite recent progress, like the visual autoregressive model that unifies text and image processing in a single transformer architecture, generating high-quality interleaved content remains challenging. Moreover, evaluations of these interleaved sequences largely remain underexplored, with existing benchmarks often limited by unimodal metrics that inadequately assess the intricacies of combined image-text outputs. To address these issues, we present RAG-IGBench, a thorough benchmark designed specifically to evaluate the task of Interleaved Generation based on Retrieval-Augmented Generation (RAG-IG) in open-domain question answering. RAG-IG integrates multimodal large language models (MLLMs) with retrieval mechanisms, enabling the models to access external image-text information for generating coherent multimodal content. Distinct from previous datasets, RAG-IGBench draws on the latest publicly available content from social platforms and introduces innovative evaluation metrics that measure the quality of text and images, as well as their consistency. Through extensive experiments with state-of-the-art MLLMs (both open-source and proprietary) on RAG-IGBench, we provide an in-depth analysis examining the capabilities and limitations of these models. Additionally, we validate our evaluation metrics by demonstrating their high correlation with human assessments. Models fine-tuned on RAG-IGBench's training set exhibit improved performance across multiple benchmarks, confirming both the quality and practical utility of our dataset. Our benchmark is available at https://github.com/USTC-StarTeam/RAG-IGBench.

---

### Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects

Authors: Raziyeh Zall, Alireza Kheyrkhah, Erik Cambria, Zahra Naseri, M. Reza Kangavari
Published: 2025-10-11
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.20657v2

The development of agents with emotional intelligence is becoming increasingly vital due to their significant role in human-computer interaction and the growing integration of computer systems across various sectors of society. Affective computing aims to design intelligent systems that can recognize, evoke, and express human emotions, thereby emulating human emotional intelligence. While previous reviews have focused on specific aspects of this field, there has been limited comprehensive research that encompasses emotion understanding, elicitation, and expression, along with the related challenges. This survey addresses this gap by providing a holistic overview of core components of artificial emotion intelligence. It covers emotion understanding through multimodal data processing, as well as affective cognition, which includes cognitive appraisal, emotion mapping, and adaptive modulation in decision-making, learning, and reasoning. Additionally, it addresses the synthesis of emotional expression across text, speech, and facial modalities to enhance human-agent interaction. This paper identifies and analyzes the key challenges and issues encountered in the development of affective systems, covering state-of-the-art methodologies designed to address them. Finally, we highlight promising future directions, with particular emphasis on the potential of generative technologies to advance affective computing.

---

### Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge

Authors: Kabir Khan, Manju Sarkar, Anita Kar, Suresh Ghosh
Published: 2025-10-11
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2511.11585v3

Large generative models (for example, language and diffusion models) enable high-quality text and image synthesis but are hard to train or adapt in cross-device federated settings due to heavy computation and communication and statistical/system heterogeneity. We propose FedGen-Edge, a framework that decouples a frozen, pre-trained global backbone from lightweight client-side adapters and federates only the adapters. Using Low-Rank Adaptation (LoRA) constrains client updates to a compact subspace, which reduces uplink traffic by more than 99 percent versus full-model FedAvg, stabilizes aggregation under non-IID data, and naturally supports personalization because each client can keep a locally tuned adapter. On language modeling (PTB) and image generation (CIFAR-10), FedGen-Edge achieves lower perplexity/FID and faster convergence than strong baselines while retaining a simple FedAvg-style server. A brief ablation shows diminishing returns beyond moderate LoRA rank and a trade-off between local epochs and client drift. FedGen-Edge offers a practical path toward privacy-preserving, resource-aware, and personalized generative AI on heterogeneous edge devices.

---

### Output Supervision Can Obfuscate the Chain of Thought

Authors: Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner
Published: 2025-10-11
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.11584v1

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can still cause obfuscated CoTs via two mechanisms. First, when a model is trained to produce a safe-looking output, that model may generalize to making its CoTs look safe. Second, since later tokens are conditioned on earlier ones, safe-looking CoTs may increase the likelihood of safe outputs, causing safe-looking CoTs to be reinforced. We introduce two mitigations to address these two issues, which achieve a Pareto improvement in terms of monitorability and task performance compared to regular training.

---

### Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review

Authors: Kumater Ter, Abolanle Adetifa, Daniel Udekwe
Published: 2025-10-11
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.21758v4

Reinforcement learning (RL) has become a foundational approach for enabling intelligent robotic behavior in dynamic and uncertain environments. This work presents an in-depth review of RL principles, advanced deep reinforcement learning (DRL) algorithms, and their integration into robotic and control systems. Beginning with the formalism of Markov Decision Processes (MDPs), the study outlines essential elements of the agent-environment interaction and explores core algorithmic strategies including actor-critic methods, value-based learning, and policy gradients. Emphasis is placed on modern DRL techniques such as DDPG, TD3, PPO, and SAC, which have shown promise in solving high-dimensional, continuous control tasks. A structured taxonomy is introduced to categorize RL applications across domains such as locomotion, manipulation, multi-agent coordination, and human-robot interaction, along with training methodologies and deployment readiness levels. The review synthesizes recent research efforts, highlighting technical trends, design patterns, and the growing maturity of RL in real-world robotics. Overall, this work aims to bridge theoretical advances with practical implementations, providing a consolidated perspective on the evolving role of RL in autonomous robotic systems.

---

### Agro-Consensus: Semantic Self-Consistency in Vision-Language Models for Crop Disease Management in Developing Countries

Authors: Mihir Gupta, Pratik Desai, Ross Greer
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21757v1

Agricultural disease management in developing countries such as India, Kenya, and Nigeria faces significant challenges due to limited access to expert plant pathologists, unreliable internet connectivity, and cost constraints that hinder the deployment of large-scale AI systems. This work introduces a cost-effective self-consistency framework to improve vision-language model (VLM) reliability for agricultural image captioning. The proposed method employs semantic clustering, using a lightweight (80MB) pre-trained embedding model to group multiple candidate responses. It then selects the most coherent caption -- containing a diagnosis, symptoms, analysis, treatment, and prevention recommendations -- through a cosine similarity-based consensus. A practical human-in-the-loop (HITL) component is incorporated, wherein user confirmation of the crop type filters erroneous generations, ensuring higher-quality input for the consensus mechanism. Applied to the publicly available PlantVillage dataset using a fine-tuned 3B-parameter PaliGemma model, our framework demonstrates improvements over standard decoding methods. Evaluated on 800 crop disease images with up to 21 generations per image, our single-cluster consensus method achieves a peak accuracy of 83.1% with 10 candidate generations, compared to the 77.5% baseline accuracy of greedy decoding. The framework's effectiveness is further demonstrated when considering multiple clusters; accuracy rises to 94.0% when a correct response is found within any of the top four candidate clusters, outperforming the 88.5% achieved by a top-4 selection from the baseline.

---

### BACE: Behavior-Adaptive Connectivity Estimation for Interpretable Graphs of Neural Dynamics

Authors: Mehrnaz Asadi, Sina Javadzadeh, Rahil Soroushmojdehi, S. Alireza Seyyed Mousavi, Terence D. Sanger
Published: 2025-10-11
Categories: q-bio.NC, cs.LG
arXiv: https://arxiv.org/abs/2510.20831v1

Understanding how distributed brain regions coordinate to produce behavior requires models that are both predictive and interpretable. We introduce Behavior-Adaptive Connectivity Estimation (BACE), an end-to-end framework that learns phase-specific, directed inter-regional connectivity directly from multi-region intracranial local field potentials (LFP). BACE aggregates many micro-contacts within each anatomical region via per-region temporal encoders, applies a learnable adjacency specific to each behavioral phase, and is trained on a forecasting objective. On synthetic multivariate time series with known graphs, BACE accurately recovers ground-truth directed interactions while achieving forecasting performance comparable to state-of-the-art baselines. Applied to human subcortical LFP recorded simultaneously from eight regions during a cued reaching task, BACE yields an explicit connectivity matrix for each within-trial behavioral phase. The resulting behavioral phase-specific graphs reveal behavior-aligned reconfiguration of inter-regional influence and provide compact, interpretable adjacency matrices for comparing network organization across behavioral phases. By linking predictive success to explicit connectivity estimates, BACE offers a practical tool for generating data-driven hypotheses about the dynamic coordination of subcortical regions during behavior.

---

### CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization

Authors: Yichen Yan, Ming Zhong, Qi Zhu, Xiaoling Gu, Jinpeng Chen, Huan Li
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17847v1

Multimodal large language models (MLLMs) rely heavily on instruction tuning to align vision and language capabilities, yet the computational cost of training on large-scale datasets remains a major bottleneck. Existing data selection methods aim to mitigate this by selecting important and diverse subsets, but they often suffer from two critical drawbacks: high computational overhead from processing the entire dataset and suboptimal data selection due to separate treatment of importance and diversity. We introduce CoIDO, a novel dual-objective framework that jointly optimizes data importance and diversity to overcome these challenges. Unlike existing approaches that require costly evaluations across the whole dataset, CoIDO employs a lightweight plug-in scorer. This scorer is trained on just a small random sample of data to learn the distribution of the candidate set, drastically reducing computational demands. By leveraging a homoscedastic uncertainty-based formulation, CoIDO effectively balances importance and diversity during training, enabling efficient and scalable data selection. In our experiments, we trained the CoIDO scorer using only 20 percent of randomly sampled data. Once trained, CoIDO was applied to the entire dataset to select a 20 percent subset for instruction tuning. On the widely used LLaVA-1.5-7B model across ten downstream tasks, this selected subset achieved an impressive 98.2 percent of the performance of full-data fine-tuning, on average.

---

### ESCA: Contextualizing Embodied Agents via Scene-Graph Generation

Authors: Jiani Huang, Amish Sethi, Matthew Kuo, Mayank Keoliya, Neelay Velingker, JungHo Jung, Ser-Nam Lim, Ziyang Li, Mayur Naik
Published: 2025-10-11
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.15963v2

Multi-modal large language models (MLLMs) are making rapid progress toward general-purpose embodied agents. However, existing MLLMs do not reliably capture fine-grained links between low-level visual features and high-level textual semantics, leading to weak grounding and inaccurate perception. To overcome this challenge, we propose ESCA, a framework that contextualizes embodied agents by grounding their perception in spatial-temporal scene graphs. At its core is SGCLIP, a novel, open-domain, promptable foundation model for generating scene graphs that is based on CLIP. SGCLIP is trained on 87K+ open-domain videos using a neurosymbolic pipeline that aligns automatically generated captions with scene graphs produced by the model itself, eliminating the need for human-labeled annotations. We demonstrate that SGCLIP excels in both prompt-based inference and task-specific fine-tuning, achieving state-of-the-art results on scene graph generation and action localization benchmarks. ESCA with SGCLIP improves perception for embodied agents based on both open-source and commercial MLLMs, achieving state of-the-art performance across two embodied environments. Notably, ESCA significantly reduces agent perception errors and enables open-source models to surpass proprietary baselines. We release the source code for SGCLIP model training at https://github.com/video-fm/LASER and for the embodied agent at https://github.com/video-fm/ESCA.

---

### CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models

Authors: Zhuxuanzi Wang, Mingqiao Mo, Xi Xiao, Chen Liu, Chenrui Ma, Yunbei Zhang, Xiao Wang, Smita Krishnaswamy, Tianyang Wang
Published: 2025-10-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15962v1

Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods improve efficiency through low-rank updates, quantization, or heuristic budget reallocation, they often decouple the allocation of capacity from the way updates evolve during training. In this work, we introduce CTR-LoRA, a framework guided by curvature trust region that integrates rank scheduling with stability-aware optimization. CTR-LoRA allocates parameters based on marginal utility derived from lightweight second-order proxies and constrains updates using a Fisher/Hessian-metric trust region. Experiments on multiple open-source backbones (7B-13B), evaluated on both in-distribution and out-of-distribution benchmarks, show consistent improvements over strong PEFT baselines. In addition to increased accuracy, CTR-LoRA enhances training stability, reduces memory requirements, and achieves higher throughput, positioning it on the Pareto frontier of performance and efficiency. These results highlight a principled path toward more robust and deployable PEFT.

---

### Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use

Authors: Yiyang Li, Zehong Wang, Zhengqing Yuan, Zheyuan Zhang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye
Published: 2025-10-11
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.15961v1

Illicit drug use among teenagers and young adults (TYAs) remains a pressing public health concern, with rising prevalence and long-term impacts on health and well-being. To detect illicit drug use among TYAs, researchers analyze large-scale surveys such as the Youth Risk Behavior Survey (YRBS) and the National Survey on Drug Use and Health (NSDUH), which preserve rich demographic, psychological, and environmental factors related to substance use. However, existing modeling methods treat survey variables independently, overlooking latent and interconnected structures among them. To address this limitation, we propose LAMI (LAtent relation Mining with bi-modal Interpretability), a novel joint graph-language modeling framework for detecting illicit drug use and interpreting behavioral risk factors among TYAs. LAMI represents individual responses as relational graphs, learns latent connections through a specialized graph structure learning layer, and integrates a large language model to generate natural language explanations grounded in both graph structures and survey semantics. Experiments on the YRBS and NSDUH datasets show that LAMI outperforms competitive baselines in predictive accuracy. Interpretability analyses further demonstrate that LAMI reveals meaningful behavioral substructures and psychosocial pathways, such as family dynamics, peer influence, and school-related distress, that align with established risk factors for substance use.

---

### Hydrogen production from blended waste biomass: pyrolysis, thermodynamic-kinetic analysis and AI-based modelling

Authors: Sana Kordoghli, Abdelhakim Settar, Oumayma Belaati, Mohammad Alkhatib, Khaled Chetehouna, Zakaria Mansouri
Published: 2025-10-11
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2510.15960v2

This work contributes to advancing sustainable energy and waste management strategies by investigating the thermochemical conversion of food-based biomass through pyrolysis, highlighting the role of artificial intelligence (AI) in enhancing process modelling accuracy and optimization efficiency. The main objective is to explore the potential of underutilized biomass resources, such as spent coffee grounds (SCG) and date seeds (DS), for sustainable hydrogen production. Specifically, it aims to optimize the pyrolysis process while evaluating the performance of these resources both individually and as blends. Proximate, ultimate, fibre, TGA/DTG, kinetic, thermodynamic, and Py-Micro GC analyses were conducted for pure DS, SCG, and blends (75% DS - 25% SCG, 50% DS - 50% SCG, 25% DS - 75% SCG). Blend 3 offered superior hydrogen yield potential but had the highest activation energy (Ea: 313.24 kJ/mol), while Blend 1 exhibited the best activation energy value (Ea: 161.75 kJ/mol). The kinetic modelling based on isoconversional methods (KAS, FWO, Friedman) identified KAS as the most accurate. These approaches provide a detailed understanding of the pyrolysis process, with particular emphasis on the integration of artificial intelligence. An LSTM model trained with lignocellulosic data predicted TGA curves with exceptional accuracy (R^2: 0.9996-0.9998).

---

### Exploring the Potential of Citiverses for Regulatory Learning

Authors: Isabelle Hupont, Marisa Ponti, Sven Schade
Published: 2025-10-11
Categories: cs.AI, cs.CY, cs.ET, cs.HC
arXiv: https://arxiv.org/abs/2510.15959v1

Citiverses hold the potential to support regulatory learning by offering immersive, virtual environments for experimenting with policy scenarios and technologies. This paper proposes a science-for-policy agenda to explore the potential of citiverses as experimentation spaces for regulatory learning, grounded in a consultation with a high-level panel of experts, including policymakers from the European Commission, national government science advisers and leading researchers in digital regulation and virtual worlds. It identifies key research areas, including scalability, real-time feedback, complexity modelling, cross-border collaboration, risk reduction, citizen participation, ethical considerations and the integration of emerging technologies. In addition, the paper analyses a set of experimental topics, spanning transportation, urban planning and the environment/climate crisis, that could be tested in citiverse platforms to advance regulatory learning in these areas. The proposed work is designed to inform future research for policy and emphasizes a responsible approach to developing and using citiverses. It prioritizes careful consideration of the ethical, economic, ecological and social dimensions of different regulations. The paper also explores essential preliminary steps necessary for integrating citiverses into the broader ecosystems of experimentation spaces, including test beds, living labs and regulatory sandboxes

---

### BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation

Authors: Fabian Wenz, Omar Bouattour, Devin Yang, Justin Choi, Cecil Gregg, Nesime Tatbul, Çağatay Demiralp
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.DB, cs.HC
arXiv: https://arxiv.org/abs/2510.13853v2

Large language models (LLMs) have been successfully applied to many tasks, including text-to-SQL generation. However, much of this work has focused on publicly available datasets, such as Fiben, Spider, and Bird. Our earlier work showed that LLMs are much less effective in querying large private enterprise data warehouses and released Beaver, the first private enterprise text-to-SQL benchmark. To create Beaver, we leveraged SQL logs, which are often readily available. However, manually annotating these logs to identify which natural language questions they answer is a daunting task. Asking database administrators, who are highly trained experts, to take on additional work to construct and validate corresponding natural language utterances is not only challenging but also quite costly. To address this challenge, we introduce BenchPress, a human-in-the-loop system designed to accelerate the creation of domain-specific text-to-SQL benchmarks. Given a SQL query, BenchPress uses retrieval-augmented generation (RAG) and LLMs to propose multiple natural language descriptions. Human experts then select, rank, or edit these drafts to ensure accuracy and domain alignment. We evaluated BenchPress on annotated enterprise SQL logs, demonstrating that LLM-assisted annotation drastically reduces the time and effort required to create high-quality benchmarks. Our results show that combining human verification with LLM-generated suggestions enhances annotation accuracy, benchmark reliability, and model evaluation robustness. By streamlining the creation of custom benchmarks, BenchPress offers researchers and practitioners a mechanism for assessing text-to-SQL models on a given domain-specific workload. BenchPress is freely available via our public GitHub repository at https://github.com/fabian-wenz/enterprise-txt2sql and is also accessible on our website at http://dsg-mcgraw.csail.mit.edu:5000.

---

### ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups

Authors: Peter Banyas, Shristi Sharma, Alistair Simmons, Atharva Vispute
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.13852v3

Is an LLM telling you different facts than it's telling me? This paper introduces ConsistencyAI, an independent benchmark for measuring the factual consistency of large language models (LLMs) for different personas. ConsistencyAI tests whether, when users of different demographics ask identical questions, the model responds with factually inconsistent answers. Designed without involvement from LLM providers, this benchmark offers impartial evaluation and accountability. In our experiment, we queried 19 LLMs with prompts that requested 5 facts for each of 15 topics. We repeated this query 100 times for each LLM, each time adding prompt context from a different persona selected from a subset of personas modeling the general population. We processed the responses into sentence embeddings, computed cross-persona cosine similarity, and computed the weighted average of cross-persona cosine similarity to calculate factual consistency scores. In 100-persona experiments, scores ranged from 0.9065 to 0.7896, and the mean was 0.8656, which we adopt as a benchmark threshold. xAI's Grok-3 is most consistent, while several lightweight models rank lowest. Consistency varies by topic: the job market is least consistent, G7 world leaders most consistent, and issues like vaccines or the Israeli-Palestinian conflict diverge by provider. These results show that both the provider and the topic shape the factual consistency. We release our code and interactive demo to support reproducible evaluation and encourage persona-invariant prompting strategies.

---

### EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing

Authors: Sicheng Lyu, Yu Gu, Xinyu Wang, Jerry Huang, Sitao Luan, Yufei Cui, Xiao-Wen Chang, Peng Lu
Published: 2025-10-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.13851v2

Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modifications without the computational burden of full retraining. Existing approaches are mainly based on a locate-then-edit framework. However, in sequential editing contexts, where multiple updates are applied over time, they exhibit significant limitations and suffer from catastrophic interference, i.e., new edits compromise previously integrated updates and degrade preserved knowledge. To address these challenges, we introduce EvoEdit, a novel editing strategy that mitigates catastrophic interference through sequential null-space alignment, enabling stable and efficient model editing. By performing sequential null-space alignment for each incoming edit, EvoEdit preserves both original and previously modified knowledge representations and maintains output invariance on preserved knowledge even across long edit sequences, effectively mitigating interference. Evaluations on real-world sequential knowledge-editing benchmarks show that EvoEdit achieves better or comparable performance than prior state-of-the-art locate-then-edit techniques, with up to 3.53 times speedup. Overall, these results underscore the necessity of developing more principled approaches for designing LLMs in dynamically evolving information settings, while providing a simple yet effective solution with strong theoretical guarantees.

---

### Revisiting the UID Hypothesis in LLM Reasoning Traces

Authors: Minju Gwak, Guijin Son, Jaehyung Kim
Published: 2025-10-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13850v1

Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret. Inspired by the Uniform Information Density (UID) hypothesis in psycholinguistics -- which posits that humans communicate by maintaining a stable flow of information -- we introduce entropy-based metrics to analyze the information flow within reasoning traces. Surprisingly, across three challenging mathematical benchmarks, we find that successful reasoning in LLMs is globally non-uniform: correct solutions are characterized by uneven swings in information density, in stark contrast to human communication patterns. This result challenges assumptions about machine reasoning and suggests new directions for designing interpretable and adaptive reasoning models.

---

### Language steering in latent space to mitigate unintended code-switching

Authors: Andrey Goncharov, Nikolai Kondusov, Alexey Zaytsev
Published: 2025-10-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.13849v3

Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that identifies language directions via Principal Component Analysis (PCA) on parallel translations and steers token embeddings along these axes to control language identity. Our approach mitigates code-switching while preserving semantics with negligible computational overhead and requires only minimal parallel data for calibration. Empirically, we achieve 95-99\% language classification accuracy using a single principal component and reduce next-token distributional divergence by up to 55\% across multiple language pairs on Qwen2.5 and Llama-3.2 models. Generation-based evaluation on Llama-3.2 further demonstrates 63--99\% reduction in Code-Switching Index across four language pairs ($p < 0.001$). We further analyze the layer-wise evolution of language representations, revealing that language identity concentrates in final layers with near-perfect linear separability.

---

### On-device System of Compositional Multi-tasking in Large Language Models

Authors: Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitris Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyeng-Hun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay et al.
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13848v1

Large language models (LLMs) are commonly adapted for diverse downstream tasks via parameter-efficient fine-tuning techniques such as Low-Rank Adapters (LoRA). While adapters can be combined to handle multiple tasks separately, standard approaches struggle when targeting the simultaneous execution of complex tasks, such as generating a translated summary from a long conversation. To address this challenge, we propose a novel approach tailored specifically for compositional multi-tasking scenarios involving summarization and translation. Our technique involves adding a learnable projection layer on top of the combined summarization and translation adapters. This design enables effective integration while maintaining efficiency through reduced computational overhead compared to alternative strategies requiring extensive retraining or sequential processing. We demonstrate the practical viability of our method within an on-device environment by developing an Android app capable of executing compositional tasks seamlessly. Experimental results indicate our solution performs well and is fast in both cloud-based and on-device implementations, highlighting the potential benefits of adopting our framework in real-world applications demanding high-speed operation alongside resource constraints.

---

### DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models

Authors: Jinbin Zhang, Nasib Ullah, Erik Schultheis, Rohit Babbar
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13847v3

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is largely unchanged, but the drafter can become bottlenecked by its O(|V|d) output projection. Recent approaches (e.g., FR-Spec, VocabTrim) mitigate this by restricting drafting to a fixed, frequency-ranked shortlist; however, such static truncation is corpus-dependent and suppresses rare or domain-specific tokens, reducing acceptance and limiting speedups. We propose DynaSpec, a context-dependent dynamic shortlisting mechanism for large-vocabulary speculative decoding. DynaSpec trains lightweight meta-classifiers that route each context to a small set of coarse token clusters; the union of the top-selected clusters defines the drafter's shortlist, while the target model still verifies over the full vocabulary, preserving exactness. Systems-wise, routing is overlapped with draft computation via parallel execution streams, reducing end-to-end overhead. Across standard speculative decoding benchmarks, DynaSpec consistently improves mean accepted length-recovering 98.4% of full-vocabulary performance for Llama-3-8B versus 93.6% for fixed-shortlist baselines-and achieves up to a 2.23x throughput gain compared to 1.91x for static approaches on the dataset with rare tokens.

---

### Information flow in multilayer perceptrons: an in-depth analysis

Authors: Giuliano Armano
Published: 2025-10-11
Categories: cs.IT, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2510.13846v1

Analysing how information flows along the layers of a multilayer perceptron is a topic of paramount importance in the field of artificial neural networks. After framing the problem from the point of view of information theory, in this position article a specific investigation is conducted on the way information is processed, with particular reference to the requirements imposed by supervised learning. To this end, the concept of information matrix is devised and then used as formal framework for understanding the aetiology of optimisation strategies and for studying the information flow. The underlying research for this article has also produced several key outcomes: i) the definition of a parametric optimisation strategy, ii) the finding that the optimisation strategy proposed in the information bottleneck framework shares strong similarities with the one derived from the information matrix, and iii) the insight that a multilayer perceptron serves as a kind of "adaptor", meant to process the input according to the given objective.

---

### Serialized EHR make for good text representations

Authors: Zhirong Chou, Quan Qin, Shi Li
Published: 2025-10-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13843v1

The emergence of foundation models in healthcare has opened new avenues for learning generalizable representations from large scale clinical data. Yet, existing approaches often struggle to reconcile the tabular and event based nature of Electronic Health Records (EHRs) with the sequential priors of natural language models. This structural mismatch limits their ability to capture longitudinal dependencies across patient encounters. We introduce SerialBEHRT, a domain aligned foundation model that extends SciBERT through additional pretraining on structured EHR sequences. SerialBEHRT is designed to encode temporal and contextual relationships among clinical events, thereby producing richer patient representations. We evaluate its effectiveness on the task of antibiotic susceptibility prediction, a clinically meaningful problem in antibiotic stewardship. Through extensive benchmarking against state of the art EHR representation strategies, we demonstrate that SerialBEHRT achieves superior and more consistent performance, highlighting the importance of temporal serialization in foundation model pretraining for healthcare.

---

### ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking

Authors: Yutao Wu, Xiao Liu, Yinghui Li, Yifeng Gao, Yifan Ding, Jiale Ding, Xiang Zheng, Xingjun Ma
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.13842v2

Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases, tricking Large Language Models (LLMs) into producing attacker-controlled outputs grounded in manipulated context. Prior work highlights LLMs' susceptibility to misleading or malicious retrieved content. However, real-world fact-checking scenarios are more challenging, as credible evidence typically dominates the retrieval pool. To investigate this problem, we extend knowledge poisoning to the fact-checking setting, where retrieved context includes authentic supporting or refuting evidence. We propose \textbf{ADMIT} (\textbf{AD}versarial \textbf{M}ulti-\textbf{I}njection \textbf{T}echnique), a few-shot, semantically aligned poisoning attack that flips fact-checking decisions and induces deceptive justifications, all without access to the target LLMs, retrievers, or token-level control. Extensive experiments show that ADMIT transfers effectively across 4 retrievers, 11 LLMs, and 4 cross-domain benchmarks, achieving an average attack success rate (ASR) of 86\% at an extremely low poisoning rate of $0.93 \times 10^{-6}$, and remaining robust even in the presence of strong counter-evidence. Compared with prior state-of-the-art attacks, ADMIT improves ASR by 11.2\% across all settings, exposing significant vulnerabilities in real-world RAG-based fact-checking systems.

---

### Identifying Autism-Related Neurobiomarkers Using Hybrid Deep Learning Models

Authors: Ashley Chen
Published: 2025-10-11
Categories: q-bio.NC, cs.LG
arXiv: https://arxiv.org/abs/2510.13841v2

Autism spectrum disorder (ASD) has been associated with structural alterations across cortical and subcortical regions. Quantitative neuroimaging enables large-scale analysis of these neuroanatomical patterns. This project used structural MRI (T1-weighted) data from the publicly available ABIDE I dataset (n = 1,112) to classify ASD and control participants using a hybrid model. A 3D convolutional neural network (CNN) was trained to learn neuroanatomical feature representations, which were then passed to a support vector machine (SVM) for final classification. Gradient-weighted class activation mapping (Grad-CAM) was applied to the CNN to visualize the brain regions that contributed most to the model predictions. The Grad-CAM difference maps showed strongest relevance along cortical boundary regions, with additional emphasis in midline frontal-temporal-parietal areas, which is broadly consistent with prior ASD neuroimaging findings.

---

### Meronymic Ontology Extraction via Large Language Models

Authors: Dekai Zhang, Simone Conia, Antonio Rago
Published: 2025-10-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13839v2

Ontologies have become essential in today's digital age as a way of organising the vast amount of readily available unstructured text. In providing formal structure to this information, ontologies have immense value and application across various domains, e.g., e-commerce, where countless product listings necessitate proper product organisation. However, the manual construction of these ontologies is a time-consuming, expensive and laborious process. In this paper, we harness the recent advancements in large language models (LLMs) to develop a fully-automated method of extracting product ontologies, in the form of meronymies, from raw review texts. We demonstrate that the ontologies produced by our method surpass an existing, BERT-based baseline when evaluating using an LLM-as-a-judge. Our investigation provides the groundwork for LLMs to be used more generally in (product or otherwise) ontology extraction.

---

### Seeing Hate Differently: Hate Subspace Modeling for Culture-Aware Hate Speech Detection

Authors: Weibin Cai, Reza Zafarani
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2510.13837v1

Hate speech detection has been extensively studied, yet existing methods often overlook a real-world complexity: training labels are biased, and interpretations of what is considered hate vary across individuals with different cultural backgrounds. We first analyze these challenges, including data sparsity, cultural entanglement, and ambiguous labeling. To address them, we propose a culture-aware framework that constructs individuals' hate subspaces. To alleviate data sparsity, we model combinations of cultural attributes. For cultural entanglement and ambiguous labels, we use label propagation to capture distinctive features of each combination. Finally, individual hate subspaces, which in turn can further enhance classification performance. Experiments show our method outperforms state-of-the-art by 1.05\% on average across all metrics.

---

### EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection

Authors: Huaizhi Qu, Ruichen Zhang, Shuqing Luo, Luchao Qi, Zhihao Zhang, Xiaoming Liu, Roni Sengupta, Tianlong Chen
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13652v1

Recent advances in foundation models have driven remarkable progress in image editing, yet their extension to 3D editing remains underexplored. A natural approach is to replace the image editing modules in existing workflows with foundation models. However, their heavy computational demands and the restrictions and costs of closed-source APIs make plugging these models into existing iterative editing strategies impractical. To address this limitation, we propose EditCast3D, a pipeline that employs video generation foundation models to propagate edits from a single first frame across the entire dataset prior to reconstruction. While editing propagation enables dataset-level editing via video models, its consistency remains suboptimal for 3D reconstruction, where multi-view alignment is essential. To overcome this, EditCast3D introduces a view selection strategy that explicitly identifies consistent and reconstruction-friendly views and adopts feedforward reconstruction without requiring costly refinement. In combination, the pipeline both minimizes reliance on expensive image editing and mitigates prompt ambiguities that arise when applying foundation models independently across images. We evaluate EditCast3D on commonly used 3D editing datasets and compare it against state-of-the-art 3D editing baselines, demonstrating superior editing quality and high efficiency. These results establish EditCast3D as a scalable and general paradigm for integrating foundation models into 3D editing pipelines. The code is available at https://github.com/UNITES-Lab/EditCast3D

---

### Local-Global Context-Aware and Structure-Preserving Image Super-Resolution

Authors: Sanchar Palit, Subhasis Chaudhuri, Biplab Banerjee
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13649v1

Diffusion models have recently achieved significant success in various image manipulation tasks, including image super-resolution and perceptual quality enhancement. Pretrained text-to-image models, such as Stable Diffusion, have exhibited strong capabilities in synthesizing realistic image content, which makes them particularly attractive for addressing super-resolution tasks. While some existing approaches leverage these models to achieve state-of-the-art results, they often struggle when applied to diverse and highly degraded images, leading to noise amplification or incorrect content generation. To address these limitations, we propose a contextually precise image super-resolution framework that effectively maintains both local and global pixel relationships through Local-Global Context-Aware Attention, enabling the generation of high-quality images. Furthermore, we propose a distribution- and perceptual-aligned conditioning mechanism in the pixel space to enhance perceptual fidelity. This mechanism captures fine-grained pixel-level representations while progressively preserving and refining structural information, transitioning from local content details to the global structural composition. During inference, our method generates high-quality images that are structurally consistent with the original content, mitigating artifacts and ensuring realistic detail restoration. Extensive experiments on multiple super-resolution benchmarks demonstrate the effectiveness of our approach in producing high-fidelity, perceptually accurate reconstructions.

---

### Mathematics with large language models as provers and verifiers

Authors: Hieu Le Duc, Leo Liberti
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2510.12829v3

During 2024 and 2025 the discussion about the theorem-proving capabilities of large language models started reporting interesting success stories, mostly to do with difficult exercises (such as problems from the International Mathematical Olympiad), but also with conjectures (Feldman & Karbasi, arXiv:2509.18383v1) formulated for the purpose of verifying whether the artificial intelligence could prove it. In this paper we report a theorem proving feat achieved by ChatGPT by using a protocol involving different prover and verifier instances of the gpt-5 model working collaboratively. To make sure that the produced proofs do not suffer from hallucinations, the final proof is formally verified by the lean proof assistant, and the conformance of premises and conclusion of the lean code is verified by a human. Our methodology is by no means complete or exact. It was nonetheless able to solve five out of six 2025 IMO problems, and close about a third of the sixty-six number theory conjectures in (Cohen, Journal of Integer Sequences, 2025).

---

### SimKey: A Semantically Aware Key Module for Watermarking Language Models

Authors: Shingo Kodama, Haya Diwan, Lucas Rosenblatt, R. Teal Witter, Niv Cohen
Published: 2025-10-11
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.12828v2

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible signal into generated text, marking its origin. Most leading approaches seed an LLM's next-token sampling with a pseudo-random key that can later be recovered to identify the text as machine-generated, while only minimally altering the model's output distribution. However, these methods suffer from two related issues: (i) watermarks are brittle to simple surface-level edits such as paraphrasing or reordering; and (ii) adversaries can append unrelated, potentially harmful text that inherits the watermark, risking reputational damage to model owners. To address these issues, we introduce SimKey, a semantic key module that strengthens watermark robustness by tying key generation to the meaning of prior context. SimKey uses locality-sensitive hashing over semantic embeddings to ensure that paraphrased text yields the same watermark key, while unrelated or semantically shifted text produces a different one. Integrated with state-of-the-art watermarking schemes, SimKey improves watermark robustness to paraphrasing and translation while preventing harmful content from false attribution, establishing semantic-aware keying as a practical and extensible watermarking direction.

---