# Research Papers — 2025-10 · bundle page 83 of 217

> Full-text markdown of papers #4101–4150 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/83
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/82.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/84.md)

### High-Level Multi-Robot Trajectory Planning And Spurious Behavior Detection

Authors: Fernando Salanova, Jesús Roche, Cristian Mahulea, Eduardo Montijano
Published: 2025-10-20
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.17261v2

The reliable execution of high-level missions in multi-robot systems with heterogeneous agents, requires robust methods for detecting spurious behaviors. In this paper, we address the challenge of identifying spurious executions of plans specified as a Linear Temporal Logic (LTL) formula, as incorrect task sequences, violations of spatial constraints, timing inconsistencies, or deviations from intended mission semantics. To tackle this, we introduce a structured data generation framework based on the Nets-within-Nets (NWN) paradigm, which coordinates robot actions with LTL-derived global mission specifications. We further propose a Transformer-based anomaly detection pipeline that classifies robot trajectories as normal or anomalous. Experimental evaluations show that our method achieves high accuracy (91.3%) in identifying execution inefficiencies, and demonstrates robust detection capabilities for core mission violations (88.3%) and constraint-based adaptive anomalies (66.8%). An ablation experiment of the embedding and architecture was carried out, obtaining successful results where our novel proposition performs better than simpler representations.

---

### Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations

Authors: Shahin Atakishiyev, Housam K. B. Babiker, Jiayi Dai, Nawshad Farruque, Teruaki Hayashi, Nafisa Sadaf Hriti, Md Abed Rahman, Iain Smith, Mi-Young Kim, Osmar R. Zaïane, Randy Goebel
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17256v2

Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable by humans. Furthermore, these models often make errors in prediction and reasoning, known as hallucinations. These errors underscore the urgent need to better understand and interpret the intricate inner workings of language models and how they generate predictive outputs. Motivated by this gap, this paper investigates local explainability and mechanistic interpretability within Transformer-based large language models to foster trust in such models. In this regard, our paper aims to make three key contributions. First, we present a review of local explainability and mechanistic interpretability approaches and insights from relevant studies in the literature. Furthermore, we describe experimental studies on explainability and reasoning with large language models in two critical domains -- healthcare and autonomous driving -- and analyze the trust implications of such explanations for explanation receivers. Finally, we summarize current unaddressed issues in the evolving landscape of LLM explainability and outline the opportunities, critical challenges, and future directions toward generating human-aligned, trustworthy LLM explanations.

---

### Augmented Web Usage Mining and User Experience Optimization with CAWAL's Enriched Analytics Data

Authors: Özkan Canay, {Ü}mit Kocabıcak
Published: 2025-10-20
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.17253v1

Understanding user behavior on the web is increasingly critical for optimizing user experience (UX). This study introduces Augmented Web Usage Mining (AWUM), a methodology designed to enhance web usage mining and improve UX by enriching the interaction data provided by CAWAL (Combined Application Log and Web Analytics), a framework for advanced web analytics. Over 1.2 million session records collected in one month (~8.5GB of data) were processed and transformed into enriched datasets. AWUM analyzes session structures, page requests, service interactions, and exit methods. Results show that 87.16% of sessions involved multiple pages, contributing 98.05% of total pageviews; 40% of users accessed various services and 50% opted for secure exits. Association rule mining revealed patterns of frequently accessed services, highlighting CAWAL's precision and efficiency over conventional methods. AWUM offers a comprehensive understanding of user behavior and strong potential for large-scale UX optimization.

---

### Quantifying Affective Bias in Low-Resource Media: Large-Scale Emotion Profiling of Bengali Headlines

Authors: Mohd Ruhul Ameen, Akif Islam, Ayesha Siddiqua, Abu Saleh Musa Miah, Jungpil Shin
Published: 2025-10-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.17252v2

News media can influence readers not only through the events they report but also through the emotional tone used to present them. This issue is especially important in digital news environments, where headlines often shape first impressions before readers open the full article. This study examines affective framing in Bengali digital journalism through corpus level emotion analysis of news headlines. Using zero shot inference with Gemma 3 4B, we analyzed 300,000 Bengali news headlines to estimate the dominant emotion and overall affective tone of each headline. The results show that negative emotion labels, particularly anger, sadness, disappointment, and fear, appear frequently in the analyzed corpus. A small pilot validation on 200 manually reviewed headlines suggests that the model can provide useful emotion estimates, although the results should be interpreted as computational estimates rather than a complete benchmark. Based on these findings, we propose a conceptual bias sensitive news interface that visualizes emotional cues across news sources and helps readers notice affective framing patterns in daily news.

---

### A Prototypical Network with an Attention-based Encoder for Drivers Identification Application

Authors: Wei-Hsun Lee, Che-Yu Chang, Kuang-Yu Li
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17250v1

Driver identification has become an area of increasing interest in recent years, especially for data- driven applications, because biometric-based technologies may incur privacy issues. This study proposes a deep learning neural network architecture, an attention-based encoder (AttEnc), which uses an attention mechanism for driver identification and uses fewer model parameters than current methods. Most studies do not address the issue of data shortages for driver identification, and most of them are inflexible when encountering unknown drivers. In this study, an architecture that combines a prototypical network and an attention-based encoder (P-AttEnc) is proposed. It applies few-shot learning to overcome the data shortage issues and to enhance model generalizations. The experiments showed that the attention-based encoder can identify drivers with accuracies of 99.3%, 99.0% and 99.9% in three different datasets and has a prediction time that is 44% to 79% faster because it significantly reduces, on average, 87.6% of the model parameters. P-AttEnc identifies drivers based on few shot data, extracts driver fingerprints to address the issue of data shortages, and is able to classify unknown drivers. The first experiment showed that P-AttEnc can identify drivers with an accuracy of 69.8% in the one-shot scenario. The second experiment showed that P-AttEnc, in the 1-shot scenario, can classify unknown drivers with an average accuracy of 65.7%.

---

### From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models

Authors: Zefan Cai, Haoyi Qiu, Haozhe Zhao, Ke Wan, Jiachen Li, Jiuxiang Gu, Wen Xiao, Nanyun Peng, Junjie Hu
Published: 2025-10-20
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.17247v2

Recent advances in video diffusion models have significantly enhanced text-to-video generation, particularly through alignment tuning using reward models trained on human preferences. While these methods improve visual quality, they can unintentionally encode and amplify social biases. To systematically trace how such biases evolve throughout the alignment pipeline, we introduce VideoBiasEval, a comprehensive diagnostic framework for evaluating social representation in video generation. Grounded in established social bias taxonomies, VideoBiasEval employs an event-based prompting strategy to disentangle semantic content (actions and contexts) from actor attributes (gender and ethnicity). It further introduces multi-granular metrics to evaluate (1) overall ethnicity bias, (2) gender bias conditioned on ethnicity, (3) distributional shifts in social attributes across model variants, and (4) the temporal persistence of bias within videos. Using this framework, we conduct the first end-to-end analysis connecting biases in human preference datasets, their amplification in reward models, and their propagation through alignment-tuned video diffusion models. Our results reveal that alignment tuning not only strengthens representational biases but also makes them temporally stable, producing smoother yet more stereotyped portrayals. These findings highlight the need for bias-aware evaluation and mitigation throughout the alignment process to ensure fair and socially responsible video generation.

---

### Visibility Allocation Systems: How Algorithmic Design Shapes Online Visibility and Societal Outcomes

Authors: Stefania Ionescu, Robin Forsberg, Elsa Lichtenegger, Salima Jaoua, Kshitijaa Jaglan, Florian Dorfler, Aniko Hannak
Published: 2025-10-20
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.17241v1

Throughout application domains, we now rely extensively on algorithmic systems to engage with ever-expanding datasets of information. Despite their benefits, these systems are often complex (comprising of many intricate tools, e.g., moderation, recommender systems, prediction models), of unknown structure (due to the lack of accompanying documentation), and having hard-to-predict yet potentially severe downstream consequences (due to the extensive use, systematic enactment of existing errors, and many comprising feedback loops). As such, understanding and evaluating these systems as a whole remains a challenge for both researchers and legislators. To aid ongoing efforts, we introduce a formal framework for such visibility allocation systems (VASs) which we define as (semi-)automated systems deciding which (processed) data to present a human user with. We review typical tools comprising VASs and define the associated computational problems they solve. By doing so, VASs can be decomposed into sub-processes and illustrated via data flow diagrams. Moreover, we survey metrics for evaluating VASs throughout the pipeline, thus aiding system diagnostics. Using forecasting-based recommendations in school choice as a case study, we demonstrate how our framework can support VAS evaluation. We also discuss how our framework can support ongoing AI-legislative efforts to locate obligations, quantify systemic risks, and enable adaptive compliance.

---

### StreamingThinker: Large Language Models Can Think While Reading

Authors: Junlong Tong, Yingqi Fan, Anhao Zhao, Yunpu Ma, Xiaoyu Shen
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17238v3

Large language models (LLMs) have demonstrated remarkable capabilities in chain of thought (CoT) reasoning. However, the current LLM reasoning paradigm initiates thinking only after the entire input is available, which introduces unnecessary latency and weakens attention to earlier information in dynamic scenarios. Inspired by human cognition of thinking while reading, we first design a \textit{\textbf{streaming thinking}} paradigm for LLMs, where reasoning unfolds in the order of input and further adjusts its depth once reading is complete. We instantiate this paradigm with \textit{StreamingThinker}, a framework that enables LLMs to think while reading through the integration of streaming CoT generation, streaming-constraint training, and streaming parallel inference. Specifically, StreamingThinker employs streaming reasoning units with quality control for CoT generation, enforces order-preserving reasoning through streaming attention masks and position encoding, and leverages parallel KV caches that decouple input encoding from reasoning generation, thereby ensuring alignment and enabling true concurrency. We evaluate StreamingThinker on the Qwen3 model family across math reasoning, logical reasoning, and context-based QA reasoning tasks. Experimental results show that the StreamingThinker preserves performance comparable to batch thinking, while yielding an 80\% reduction in token waiting before the onset of reasoning and a more than 60\% reduction in time-level latency for producing the final answer, demonstrating the effectiveness of the streaming paradigm for LLM reasoning. Code is publicly available at https://github.com/EIT-NLP/StreamingLLM/tree/main/StreamingThinker.

---

### Coinvisor: An RL-Enhanced Chatbot Agent for Interactive Cryptocurrency Investment Analysis

Authors: Chong Chen, Ze Liu, Lingfeng Bao, Yanlin Wang, Ting Chen, Daoyuan Wu, Jiachi Chen
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.17235v1

The cryptocurrency market offers significant investment opportunities but faces challenges including high volatility and fragmented information. Data integration and analysis are essential for informed investment decisions. Currently, investors use three main approaches: (1) Manual analysis across various sources, which depends heavily on individual experience and is time-consuming and prone to bias; (2) Data aggregation platforms-limited in functionality and depth of analysis; (3) Large language model agents-based on static pretrained models, lacking real-time data integration and multi-step reasoning capabilities. To address these limitations, we present Coinvisor, a reinforcement learning-based chatbot that provides comprehensive analytical support for cryptocurrency investment through a multi-agent framework. Coinvisor integrates diverse analytical capabilities through specialized tools. Its key innovation is a reinforcement learning-based tool selection mechanism that enables multi-step planning and flexible integration of diverse data sources. This design supports real-time interaction and adaptive analysis of dynamic content, delivering accurate and actionable investment insights. We evaluated Coinvisor through automated benchmarks on tool calling accuracy and user studies with 20 cryptocurrency investors using our interface. Results show that Coinvisor improves recall by 40.7% and F1 score by 26.6% over the base model in tool orchestration. User studies show high satisfaction (4.64/5), with participants preferring Coinvisor to both general LLMs and existing crypto platforms (4.62/5).

---

### Taming Modality Entanglement in Continual Audio-Visual Segmentation

Authors: Yuyang Hong, Qi Yang, Tao Zhang, Zili Wang, Zhaojin Fu, Kun Ding, Bin Fan, Shiming Xiang
Published: 2025-10-20
Categories: cs.MM, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.17234v3

Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previously learned ones. However, existing methods mainly focus on coarse-grained tasks, with limitations in addressing modality entanglement in fine-grained continual learning settings. To bridge this gap, we introduce a novel Continual Audio-Visual Segmentation (CAVS) task, aiming to continuously segment new classes guided by audio. Through comprehensive analysis, two critical challenges are identified: 1) multi-modal semantic drift, where a sounding objects is labeled as background in sequential tasks; 2) co-occurrence confusion, where frequent co-occurring classes tend to be confused. In this work, a Collision-based Multi-modal Rehearsal (CMR) framework is designed to address these challenges. Specifically, for multi-modal semantic drift, a Multi-modal Sample Selection (MSS) strategy is proposed to select samples with high modal consistency for rehearsal. Meanwhile, for co-occurence confusion, a Collision-based Sample Rehearsal (CSR) mechanism is designed, allowing for the increase of rehearsal sample frequency of those confusable classes during training process. Moreover, we construct three audio-visual incremental scenarios to verify effectiveness of our method. Comprehensive experiments demonstrate that our method significantly outperforms single-modal continual learning methods. Code can be seen at https://github.com/cqu-student/CAVS-CMR.

---

### When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions

Authors: Zhuo Cao, Heming Du, Bingqing Zhang, Xin Yu, Xue Li, Sen Wang
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17218v1

Existing Moment retrieval (MR) methods focus on Single-Moment Retrieval (SMR). However, one query can correspond to multiple relevant moments in real-world applications. This makes the existing datasets and methods insufficient for video temporal grounding. By revisiting the gap between current MR tasks and real-world applications, we introduce a high-quality datasets called QVHighlights Multi-Moment Dataset (QV-M$^2$), along with new evaluation metrics tailored for multi-moment retrieval (MMR). QV-M$^2$ consists of 2,212 annotations covering 6,384 video segments. Building on existing efforts in MMR, we propose a framework called FlashMMR. Specifically, we propose a Multi-moment Post-verification module to refine the moment boundaries. We introduce constrained temporal adjustment and subsequently leverage a verification module to re-evaluate the candidate segments. Through this sophisticated filtering pipeline, low-confidence proposals are pruned, and robust multi-moment alignment is achieved. We retrain and evaluate 6 existing MR methods on QV-M$^2$ and QVHighlights under both SMR and MMR settings. Results show that QV-M$^2$ serves as an effective benchmark for training and evaluating MMR models, while FlashMMR provides a strong baseline. Specifically, on QV-M$^2$, it achieves improvements over prior SOTA method by 3.00% on G-mAP, 2.70% on mAP@3+tgt, and 2.56% on mR@3. The proposed benchmark and method establish a foundation for advancing research in more realistic and challenging video temporal grounding scenarios. Code is released at https://github.com/Zhuo-Cao/QV-M2.

---

### Diagnosis of Fuel Cell Health Status with Deep Sparse Auto-Encoder Neural Network

Authors: Chenyan Fei, Dalin Zhang, Chen Melinda Dang
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17214v1

Effective and accurate diagnosis of fuel cell health status is crucial for ensuring the stable operation of fuel cell stacks. Among various parameters, high-frequency impedance serves as a critical indicator for assessing fuel cell state and health conditions. However, its online testing is prohibitively complex and costly. This paper employs a deep sparse auto-encoding network for the prediction and classification of high-frequency impedance in fuel cells, achieving metric of accuracy rate above 92\%. The network is further deployed on an FPGA, attaining a hardware-based recognition rate almost 90\%.

---

### D2C-HRHR: Discrete Actions with Double Distributional Critics for High-Risk-High-Return Tasks

Authors: Jundong Zhang, Yuhui Situ, Fanji Zhang, Rongji Deng, Tianqi Wei
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17212v1

Tasks involving high-risk-high-return (HRHR) actions, such as obstacle crossing, often exhibit multimodal action distributions and stochastic returns. Most reinforcement learning (RL) methods assume unimodal Gaussian policies and rely on scalar-valued critics, which limits their effectiveness in HRHR settings. We formally define HRHR tasks and theoretically show that Gaussian policies cannot guarantee convergence to the optimal solution. To address this, we propose a reinforcement learning framework that (i) discretizes continuous action spaces to approximate multimodal distributions, (ii) employs entropy-regularized exploration to improve coverage of risky but rewarding actions, and (iii) introduces a dual-critic architecture for more accurate discrete value distribution estimation. The framework scales to high-dimensional action spaces, supporting complex control domains. Experiments on locomotion and manipulation benchmarks with high risks of failure demonstrate that our method outperforms baselines, underscoring the importance of explicitly modeling multimodality and risk in RL.

---

### Temporally Detailed Hypergraph Neural ODEs for Disease Progression Modeling

Authors: Tingsong Xiao, Yao An Lee, Zelin Xu, Yupu Zhang, Zibo Liu, Yu Huang, Jiang Bian, Jingchuan Guo, Zhe Jiang
Published: 2025-10-20
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17211v2

Disease progression modeling aims to characterize and predict how a patient's disease complications worsen over time based on longitudinal electronic health records (EHRs). For diseases such as type 2 diabetes, accurate progression modeling can enhance patient sub-phenotyping and inform effective and timely interventions. However, the problem is challenging due to the need to learn continuous-time progression dynamics from irregularly sampled clinical events amid patient heterogeneity (e.g., different progression rates and pathways). Existing mechanistic and data-driven methods either lack adaptability to learn from real-world data or fail to capture complex continuous-time dynamics on progression trajectories. To address these limitations, we propose Temporally Detailed Hypergraph Neural Ordinary Differential Equation (TD-HNODE), which represents disease progression on clinically recognized trajectories as a temporally detailed hypergraph and learns the continuous-time progression dynamics via a neural ODE framework. TD-HNODE contains a learnable TD-Hypergraph Laplacian that captures the interdependency of disease complication markers within both intra- and inter-progression trajectories. Experiments on two real-world clinical datasets demonstrate that TD-HNODE outperforms multiple baselines in modeling the progression of type 2 diabetes and related cardiovascular diseases.

---

### Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting

Authors: Chenchen Tan, Youyang Qu, Xinghao Li, Hui Zhang, Shujie Cui, Cunjian Chen, Longxiang Gao
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17210v3

The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing research into machine unlearning. However, existing unlearning approaches face a critical dilemma: Aggressive unlearning compromises model utility, while conservative strategies preserve utility but risk hallucinated responses. This significantly limits LLMs' reliability in knowledge-intensive applications. To address this, we introduce a novel Attention-Shifting (AS) framework for selective unlearning. AS is driven by two design objectives: (1) context-preserving suppression that attenuates attention to fact-bearing tokens without disrupting LLMs' linguistic structure; and (2) hallucination-resistant response shaping that discourages fabricated completions when queried about unlearning content. AS realizes these objectives through two attention-level interventions, which are importance-aware suppression applied to the unlearning set to reduce reliance on memorized knowledge and attention-guided retention enhancement that reinforces attention toward semantically essential tokens in the retained dataset to mitigate unintended degradation. These two components are jointly optimized via a dual-loss objective, which forms a soft boundary that localizes unlearning while preserving unrelated knowledge under representation superposition. Experimental results show that AS improves performance preservation over the state-of-the-art unlearning methods, achieving up to 15% higher accuracy on the ToFU benchmark and 10% on the TDEC benchmark, while maintaining competitive hallucination-free unlearning effectiveness. Compared to existing methods, AS demonstrates a superior balance between unlearning effectiveness, generalization, and response reliability.

---

### Soft-Masked Diffusion Language Models

Authors: Michael Hersche, Samuel Moor-Smith, Thomas Hofmann, Abbas Rahimi
Published: 2025-10-20
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.17206v2

Diffusion models have demonstrated strong potential in language modeling, offering various advantages over traditional autoregressive approaches. Their ability to generate and revise entire responses in parallel enables faster generation and built-in self-correction mechanisms. Most modern diffusion-based language models employ masked diffusion, where decoding involves iteratively processing masked tokens based on a binary decision: either retaining the mask or replacing it with the predicted token. However, this binary choice discards valuable predictive information when the mask is retained. To address this limitation, we introduce soft-masking (SM), a novel method that dynamically blends the embedding of the mask token with the embeddings of the top-k predicted tokens from the previous decoding step, for each retained mask. This provides the model with a more informative prior, preserving context from earlier computations and allowing partial information about masked tokens to propagate beyond a single step. We propose a training methodology that efficiently adapts masked diffusion language models to incorporate SM. We demonstrate that training a 169M parameter model from scratch with SM yields superior perplexity and MAUVE scores compared to binary masking baselines. Similarly, a pretrained model can be enhanced with SM through continued pretraining. Finally, we finetune two state-of-the-art diffusion models, Dream-7B and Dream-Coder-7B, with SM. SM consistently improves performance across multiple coding benchmarks, particularly in high-throughput settings. The code is available at https://github.com/IBM/soft-masked-diffusion-language-models.

---

### $\mathcal{V}isi\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs

Authors: Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, Xiaoyu Shen
Published: 2025-10-20
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.17205v1

Multimodal Large Language Models (MLLMs) have achieved strong performance across vision-language tasks, but suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens. Though efforts have been made to prune tokens in MLLMs, \textit{they lack a fundamental understanding of how MLLMs process and fuse multimodal information.} Through systematic analysis, we uncover a \textbf{three-stage} cross-modal interaction process: (1) Shallow layers recognize task intent, with visual tokens acting as passive attention sinks; (2) Cross-modal fusion occurs abruptly in middle layers, driven by a few critical visual tokens; (3) Deep layers discard vision tokens, focusing solely on linguistic refinement. Based on these findings, we propose \emph{VisiPruner}, a training-free pruning framework that reduces up to 99\% of vision-related attention computations and 53.9\% of FLOPs on LLaVA-v1.5 7B. It significantly outperforms existing token pruning methods and generalizes across diverse MLLMs. Beyond pruning, our insights further provide actionable guidelines for training efficient MLLMs by aligning model architecture with its intrinsic layer-wise processing dynamics. Our code is available at: https://github.com/EIT-NLP/VisiPruner.

---

### Optimizing DINOv2 with Registers for Face Anti-Spoofing

Authors: Mika Feng, Pierre Gallin-Martel, Koichi Ito, Takafumi Aoki
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17201v2

Face recognition systems are designed to be robust against variations in head pose, illumination, and image blur during capture. However, malicious actors can exploit these systems by presenting a face photo of a registered user, potentially bypassing the authentication process. Such spoofing attacks must be detected prior to face recognition. In this paper, we propose a DINOv2-based spoofing attack detection method to discern minute differences between live and spoofed face images. Specifically, we employ DINOv2 with registers to extract generalizable features and to suppress perturbations in the attention mechanism, which enables focused attention on essential and minute features. We demonstrate the effectiveness of the proposed method through experiments conducted on the dataset provided by ``The 6th Face Anti-Spoofing Workshop: Unified Physical-Digital Attacks Detection@ICCV2025'' and SiW dataset. The project page is available at: https://gsisaoki.github.io/FAS-DINOv2-ICCVW/ .

---

### EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification

Authors: Bingrong Liu, Jun Shi, Yushan Zheng
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17200v1

Class-incremental learning (CIL) for endoscopic image analysis is crucial for real-world clinical applications, where diagnostic models should continuously adapt to evolving clinical data while retaining performance on previously learned ones. However, existing replay-based CIL methods fail to effectively mitigate catastrophic forgetting due to severe domain discrepancies and class imbalance inherent in endoscopic imaging. To tackle these challenges, we propose EndoCIL, a novel and unified CIL framework specifically tailored for endoscopic image diagnosis. EndoCIL incorporates three key components: Maximum Mean Discrepancy Based Replay (MDBR), employing a distribution-aligned greedy strategy to select diverse and representative exemplars, Prior Regularized Class Balanced Loss (PRCBL), designed to alleviate both inter-phase and intra-phase class imbalance by integrating prior class distributions and balance weights into the loss function, and Calibration of Fully-Connected Gradients (CFG), which adjusts the classifier gradients to mitigate bias toward new classes. Extensive experiments conducted on four public endoscopic datasets demonstrate that EndoCIL generally outperforms state-of-the-art CIL methods across varying buffer sizes and evaluation metrics. The proposed framework effectively balances stability and plasticity in lifelong endoscopic diagnosis, showing promising potential for clinical scalability and deployment.

---

### Round Outcome Prediction in VALORANT Using Tactical Features from Video Analysis

Authors: Nirai Hayakawa, Kazumasa Shimari, Kazuma Yamasaki, Hirotatsu Hoshikawa, Rikuto Tsuchida, Kenichi Matsumoto
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17199v1

Recently, research on predicting match outcomes in esports has been actively conducted, but much of it is based on match log data and statistical information. This research targets the FPS game VALORANT, which requires complex strategies, and aims to build a round outcome prediction model by analyzing minimap information in match footage. Specifically, based on the video recognition model TimeSformer, we attempt to improve prediction accuracy by incorporating detailed tactical features extracted from minimap information, such as character position information and other in-game events. This paper reports preliminary results showing that a model trained on a dataset augmented with such tactical event labels achieved approximately 81% prediction accuracy, especially from the middle phases of a round onward, significantly outperforming a model trained on a dataset with the minimap information itself. This suggests that leveraging tactical features from match footage is highly effective for predicting round outcomes in VALORANT.

---

### Riverbank Erosion Analysis in Bangladesh Using Spatiotemporal Segmentation

Authors: M. Saifuzzaman Rafat, Akif Islam, Mohd Ruhul Ameen, Momen Khandoker Ope, Abu Saleh Musa Miah, Jungpil Shin
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17198v2

Riverbank erosion is a serious environmental problem in Bangladesh, causing land loss, damage to infrastructure, and displacement of local communities. Manual analysis of satellite images is often slow and difficult to apply consistently across large river networks. This study uses a parameter-efficient adaptation of the Segment Anything Model (SAM) to detect and measure riverbank erosion from historical Google Earth images. A dataset of 500 image pairs from 2003 to 2025 was prepared from erosion-prone areas, including Mokterer Char, Kedarpur, and Chowhali Upazila, with pixel-level labels for river, stable land, and eroded regions. During training, the ViT-H image encoder and prompt encoder were kept frozen, while only the lightweight mask decoder was fine-tuned for riverine segmentation. The adapted model achieved an erosion-class IoU of 0.867 and an F1-score of 0.928 on the primary held-out test set. Evaluation on unseen riverbank regions also showed that the model could generalize to new geographic areas, although detecting accreted land from RGB-only images remained difficult. The estimated erosion area differed from the ground truth by only 0.17%, showing that the model can produce reliable area measurements. Overall, this study demonstrates that adapted foundation segmentation models can support faster and more consistent riverbank erosion monitoring, with future scope for using multi-modal remote sensing data in broader environmental assessment.

---

### ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models

Authors: Pu Zhang, Yuwei Li, Xingyuan Xian, Guoming Tang
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17197v1

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim to reduce these costs by pruning visual tokens, existing approaches, whether based on attention or diversity, typically neglect the guidance of the text prompt and thus fail to prioritize task relevance. In this work, we propose a novel, zero-shot method that reframes the problem by introducing a prompt-aware perspective, explicitly modeling visual token pruning as a balance between task relevance and information diversity. Our hierarchical approach first selects a core set of task-relevant visual tokens and then supplements them with diversity tokens to preserve broader context. Experiments across multiple models and benchmarks show that our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss, even when pruning up to 90\% of the tokens. Furthermore, these gains are accompanied by significant reductions in GPU memory footprint and inference latency.

---

### Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models

Authors: Jiaqi Leng, Xiang Hu, Junxiong Wang, Jianguo Li, Wei Wu, Yucheng Lu
Published: 2025-10-20
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17196v3

Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alternative architectures like sliding window attention and state space models sacrifice the ability to effectively utilize the full context due to their fixed-size memory. Chunk-based sparse attention has emerged as a promising paradigm for extreme length generalization, yet the key architectural principles underpinning its success are not yet fully understood. In this work, we present a systematic dissection of these models to identify the core components driving their performance. Through a unified framework and comprehensive ablation studies, we demonstrate that a combination of three design principles is critical: (1) an expressive, non-linear Chunk Encoder with a dedicated CLS token to produce representations for retrieval; (2) a Bypassing Residual Path to stably integrate retrieved global information without it being overridden by the local residual stream; and (3) enforced selection sparsity during pre-training to bridge the train-test distribution gap. We provide a theoretical motivation for intra-chunk information processing and landmark generation. By combining these principles, we establish a new state-of-the-art for training-free length extrapolation, successfully generalizing models trained on a 4K context to 32 million tokens on RULER and BABILong. Our findings provide a clear and empirically-grounded set of design principles for developing future, highly-capable long-context language models.

---

### SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Driving

Authors: Peiru Zheng, Yun Zhao, Zhan Gong, Hong Zhu, Shaohua Wu
Published: 2025-10-20
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.17191v2

End-to-end autonomous driving has emerged as a promising paradigm for achieving robust and intelligent driving policies. However, existing end-to-end methods still face significant challenges, such as suboptimal decision-making in complex scenarios. In this paper,we propose SimpleVSF (Simple VLM-Scoring Fusion), a novel framework that enhances end-to-end planning by leveraging the cognitive capabilities of Vision-Language Models (VLMs) and advanced trajectory fusion techniques. We utilize the conventional scorers and the novel VLM-enhanced scorers. And we leverage a robust weight fusioner for quantitative aggregation and a powerful VLM-based fusioner for qualitative, context-aware decision-making. As the leading approach in the ICCV 2025 NAVSIM v2 End-to-End Driving Challenge, our SimpleVSF framework demonstrates state-of-the-art performance, achieving a superior balance between safety, comfort, and efficiency.

---

### SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference

Authors: Wenxun Wang, Shuchang Zhou, Wenyu Sun, Peiqin Sun, Yongpan Liu
Published: 2025-10-20
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2510.17189v1

Transformers have shown remarkable performance in both natural language processing (NLP) and computer vision (CV) tasks. However, their real-time inference speed and efficiency are limited due to the inefficiency in Softmax and Layer Normalization (LayerNorm). Previous works based on function approximation suffer from inefficient implementation as they place emphasis on computation while disregarding memory overhead concerns. Moreover, such methods rely on retraining to compensate for approximation error which can be costly and inconvenient. In this paper, we present SOLE, a hardware-software co-design for Softmax and LayerNorm which is composed of E2Softmax and AILayerNorm. E2Softmax utilizes log2 quantization of exponent function and log-based division to approximate Softmax while AILayerNorm adopts low-precision statistic calculation. Compared with state-of-the-art designs, we achieve both low-precision calculation and low bit-width storage on Softmax and LayerNorm. Experiments show that SOLE maintains inference accuracy without retraining while offering orders of magnitude speedup and energy savings over GPU, achieving 3.04x, 3.86x energy-efficiency improvements and 2.82x, 3.32x area-efficiency improvements over prior state-of-the-art custom hardware for Softmax and LayerNorm, respectively.

---

### HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery

Authors: Vaibhav Rathore, Divyam Gupta, Biplab Banerjee
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17188v1

Generalized Category Discovery (GCD) aims to classify test-time samples into either seen categories** -- available during training -- or novel ones, without relying on label supervision. Most existing GCD methods assume simultaneous access to labeled and unlabeled data during training and arising from the same domain, limiting applicability in open-world scenarios involving distribution shifts. Domain Generalization with GCD (DG-GCD) lifts this constraint by requiring models to generalize to unseen domains containing novel categories, without accessing targetdomain data during training. The only prior DG-GCD method, DG2CD-Net, relies on episodic training with multiple synthetic domains and task vector aggregation, incurring high computational cost and error accumulation. We propose HIDISC, a hyperbolic representation learning framework that achieves domain and category-level generalization without episodic simulation. To expose the model to minimal but diverse domain variations, we augment the source domain using GPT-guided diffusion, avoiding overfitting while maintaining efficiency. To structure the representation space, we introduce Tangent CutMix, a curvature-aware interpolation that synthesizes pseudo-novel samples in tangent space, preserving manifold consistency. A unified loss -- combining penalized Busemann alignment, hybrid hyperbolic contrastive regularization, and adaptive outlier repulsion -- **facilitates compact, semantically structured embeddings. A learnable curvature parameter further adapts the geometry to dataset complexity. HIDISC achieves state-of-the-art results on PACS , Office-Home , and DomainNet, consistently outperforming the existing Euclidean and hyperbolic (DG)-GCD baselines.

---

### A Standardized Benchmark for Machine-Learned Molecular Dynamics using Weighted Ensemble Sampling

Authors: Alexander Aghili, Andy Bruce, Daniel Sabo, Sanya Murdeshwar, Kevin Bachelor, Ionut Mistreanu, Ashwin Lokapally, Razvan Marinescu
Published: 2025-10-20
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2510.17187v1

The rapid evolution of molecular dynamics (MD) methods, including machine-learned dynamics, has outpaced the development of standardized tools for method validation. Objective comparison between simulation approaches is often hindered by inconsistent evaluation metrics, insufficient sampling of rare conformational states, and the absence of reproducible benchmarks. To address these challenges, we introduce a modular benchmarking framework that systematically evaluates protein MD methods using enhanced sampling analysis. Our approach uses weighted ensemble (WE) sampling via The Weighted Ensemble Simulation Toolkit with Parallelization and Analysis (WESTPA), based on progress coordinates derived from Time-lagged Independent Component Analysis (TICA), enabling fast and efficient exploration of protein conformational space. The framework includes a flexible, lightweight propagator interface that supports arbitrary simulation engines, allowing both classical force fields and machine learning-based models. Additionally, the framework offers a comprehensive evaluation suite capable of computing more than 19 different metrics and visualizations across a variety of domains. We further contribute a dataset of nine diverse proteins, ranging from 10 to 224 residues, that span a variety of folding complexities and topologies. Each protein has been extensively simulated at 300K for one million MD steps per starting point (4 ns). To demonstrate the utility of our framework, we perform validation tests using classic MD simulations with implicit solvent and compare protein conformational sampling using a fully trained versus under-trained CGSchNet model. By standardizing evaluation protocols and enabling direct, reproducible comparisons across MD approaches, our open-source platform lays the groundwork for consistent, rigorous benchmarking across the molecular simulation community.

---

### Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses

Authors: Runlin Lei, Lu Yi, Mingguo He, Pengyu Qiu, Zhewei Wei, Yongchao Liu, Chuntao Hong
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17185v1

While Graph Neural Networks (GNNs) and Large Language Models (LLMs) are powerful approaches for learning on Text-Attributed Graphs (TAGs), a comprehensive understanding of their robustness remains elusive. Current evaluations are fragmented, failing to systematically investigate the distinct effects of textual and structural perturbations across diverse models and attack scenarios. To address these limitations, we introduce a unified and comprehensive framework to evaluate robustness in TAG learning. Our framework evaluates classical GNNs, robust GNNs (RGNNs), and GraphLLMs across ten datasets from four domains, under diverse text-based, structure-based, and hybrid perturbations in both poisoning and evasion scenarios. Our extensive analysis reveals multiple findings, among which three are particularly noteworthy: 1) models have inherent robustness trade-offs between text and structure, 2) the performance of GNNs and RGNNs depends heavily on the text encoder and attack type, and 3) GraphLLMs are particularly vulnerable to training data corruption. To overcome the identified trade-offs, we introduce SFT-auto, a novel framework that delivers superior and balanced robustness against both textual and structural attacks within a single model. Our work establishes a foundation for future research on TAG security and offers practical solutions for robust TAG learning in adversarial environments. Our code is available at: https://github.com/Leirunlin/TGRB.

---

### Capturing Head Avatar with Hand Contacts from a Monocular Video

Authors: Haonan He, Yufeng Zheng, Jie Song
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17181v1

Photorealistic 3D head avatars are vital for telepresence, gaming, and VR. However, most methods focus solely on facial regions, ignoring natural hand-face interactions, such as a hand resting on the chin or fingers gently touching the cheek, which convey cognitive states like pondering. In this work, we present a novel framework that jointly learns detailed head avatars and the non-rigid deformations induced by hand-face interactions. There are two principal challenges in this task. First, naively tracking hand and face separately fails to capture their relative poses. To overcome this, we propose to combine depth order loss with contact regularization during pose tracking, ensuring correct spatial relationships between the face and hand. Second, no publicly available priors exist for hand-induced deformations, making them non-trivial to learn from monocular videos. To address this, we learn a PCA basis specific to hand-induced facial deformations from a face-hand interaction dataset. This reduces the problem to estimating a compact set of PCA parameters rather than a full spatial deformation field. Furthermore, inspired by physics-based simulation, we incorporate a contact loss that provides additional supervision, significantly reducing interpenetration artifacts and enhancing the physical plausibility of the results. We evaluate our approach on RGB(D) videos captured by an iPhone. Additionally, to better evaluate the reconstructed geometry, we construct a synthetic dataset of avatars with various types of hand interactions. We show that our method can capture better appearance and more accurate deforming geometry of the face than SOTA surface reconstruction methods.

---

### Benchmarking Out-of-Distribution Detection for Plankton Recognition: A Systematic Evaluation of Advanced Methods in Marine Ecological Monitoring

Authors: Yingzi Han, Jiakai He, Chuanlong Xie, Jianping Li
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17179v1

Automated plankton recognition models face significant challenges during real-world deployment due to distribution shifts (Out-of-Distribution, OoD) between training and test data. This stems from plankton's complex morphologies, vast species diversity, and the continuous discovery of novel species, which leads to unpredictable errors during inference. Despite rapid advancements in OoD detection methods in recent years, the field of plankton recognition still lacks a systematic integration of the latest computer vision developments and a unified benchmark for large-scale evaluation. To address this, this paper meticulously designed a series of OoD benchmarks simulating various distribution shift scenarios based on the DYB-PlanktonNet dataset \cite{875n-f104-21}, and systematically evaluated twenty-two OoD detection methods. Extensive experimental results demonstrate that the ViM \cite{wang2022vim} method significantly outperforms other approaches in our constructed benchmarks, particularly excelling in Far-OoD scenarios with substantial improvements in key metrics. This comprehensive evaluation not only provides a reliable reference for algorithm selection in automated plankton recognition but also lays a solid foundation for future research in plankton OoD detection. To our knowledge, this study marks the first large-scale, systematic evaluation and analysis of Out-of-Distribution data detection methods in plankton recognition. Code is available at https://github.com/BlackJack0083/PlanktonOoD.

---

### QRïS: A Preemptive Novel Method for Quishing Detection Through Structural Features of QR

Authors: Muhammad Wahid Akram, Keshav Sood, Muneeb Ul Hassan
Published: 2025-10-20
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.17175v1

Globally, individuals and organizations employ Quick Response (QR) codes for swift and convenient communication. Leveraging this, cybercriminals embed falsify and misleading information in QR codes to launch various phishing attacks which termed as Quishing. Many former studies have introduced defensive approaches to preclude Quishing such as by classifying the embedded content of QR codes and then label the QR codes accordingly, whereas other studies classify them using visual features (i.e., deep features, histogram density analysis features). However, these approaches mainly rely on black-box techniques which do not clearly provide interpretability and transparency to fully comprehend and reproduce the intrinsic decision process; therefore, having certain obvious limitations includes the approaches' trust, accountability, issues in bias detection, and many more. We proposed QRïS, the pioneer method to classify QR codes through the comprehensive structural analysis of a QR code which helps to identify phishing QR codes beforehand. Our classification method is clearly transparent which makes it reproducible, scalable, and easy to comprehend. First, we generated QR codes dataset (i.e. 400,000 samples) using recently published URLs datasets (1), (2). Then, unlike black-box models, we developed a simple algorithm to extract 24 structural features from layout patterns present in QR codes. Later, we train the machine learning models on the harvested features and obtained accuracy of up to 83.18%. To further evaluate the effectiveness of our approach, we perform the comparative analysis of proposed method with relevant contemporary studies. Lastly, for real-world deployment and validation, we developed a mobile app which assures the feasibility of the proposed solution in real-world scenarios which eventually strengthen the applicability of the study.

---

### Offline Policy Evaluation of Multi-Turn LLM Health Coaching with Real Users

Authors: Melik Ozolcer, Sang Won Bae
Published: 2025-10-20
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.17173v2

We study a web-deployed, tool-augmented LLM health coach with real users. In a pilot with seven users (280 rated turns), offline policy evaluation (OPE) over factorized decision heads (Tool/Style) shows that a uniform heavy-tool policy raises average value on logs but harms specific subgroups, most notably low-health-literacy/high-self-efficacy users. A lightweight simulator with hidden archetypes further shows that adding a small early information-gain bonus reliably shortens trait identification and improves goal success and pass@3. Together, these early findings indicate an evaluation-first path to personalization: freeze the generator, learn subgroup-aware decision heads on typed rewards (objective tool outcomes and satisfaction), and always report per-archetype metrics to surface subgroup harms that averages obscure.

---

### Combining ECG Foundation Model and XGBoost to Predict In-Hospital Malignant Ventricular Arrhythmias in AMI Patients

Authors: Shun Huang, Wenlu Xing, Shijia Geng, Hailong Wang, Guangkun Nie, Gongzheng Tang, Chenyang He, Shenda Hong
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.17172v1

Malignant ventricular arrhythmias (VT/VF) following acute myocardial infarction (AMI) are a major cause of in-hospital death, yet early identification remains a clinical challenge. While traditional risk scores have limited performance, end-to-end deep learning models often lack the interpretability needed for clinical trust. This study aimed to develop a hybrid predictive framework that integrates a large-scale electrocardiogram (ECG) foundation model (ECGFounder) with an interpretable XGBoost classifier to improve both accuracy and interpretability. We analyzed 6,634 ECG recordings from AMI patients, among whom 175 experienced in-hospital VT/VF. The ECGFounder model was used to extract 150-dimensional diagnostic probability features , which were then refined through feature selection to train the XGBoost classifier. Model performance was evaluated using AUC and F1-score , and the SHAP method was used for interpretability. The ECGFounder + XGBoost hybrid model achieved an AUC of 0.801 , outperforming KNN (AUC 0.677), RNN (AUC 0.676), and an end-to-end 1D-CNN (AUC 0.720). SHAP analysis revealed that model-identified key features, such as "premature ventricular complexes" (risk predictor) and "normal sinus rhythm" (protective factor), were highly consistent with clinical knowledge. We conclude that this hybrid framework provides a novel paradigm for VT/VF risk prediction by validating the use of foundation model outputs as effective, automated feature engineering for building trustworthy, explainable AI-based clinical decision support systems.

---

### Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling

Authors: Feihong Yan, Peiru Wang, Yao Zhu, Kaiyu Pang, Qingyan Wei, Huiqi Li, Linfeng Zhang
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17171v2

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of spatially correlated visual tokens in a single step. To address this limitation, we introduce Generation then Reconstruction (GtR), a training-free hierarchical sampling strategy that decomposes generation into two stages: structure generation establishing global semantic scaffolding, followed by detail reconstruction efficiently completing remaining tokens. Assuming that it is more difficult to create an image from scratch than to complement images based on a basic image framework, GtR is designed to achieve acceleration by computing the reconstruction stage quickly while maintaining the generation quality by computing the generation stage slowly. Moreover, observing that tokens on the details of an image often carry more semantic information than tokens in the salient regions, we further propose Frequency-Weighted Token Selection (FTS) to offer more computation budget to tokens on image details, which are localized based on the energy of high frequency information. Extensive experiments on ImageNet class-conditional and text-to-image generation demonstrate 3.72x speedup on MAR-H while maintaining comparable quality (e.g., FID: 1.59, IS: 304.4 vs. original 1.59, 299.1), substantially outperforming existing acceleration methods across various model scales and generation tasks. Our codes will be released in https://github.com/feihongyan1/GtR.

---

### Investigating Adversarial Robustness against Preprocessing used in Blackbox Face Recognition

Authors: Roland Croft, Brian Du, Darcy Joseph, Sharath Kumar
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17169v1

Face Recognition (FR) models have been shown to be vulnerable to adversarial examples that subtly alter benign facial images, exposing blind spots in these systems, as well as protecting user privacy. End-to-end FR systems first obtain preprocessed faces from diverse facial imagery prior to computing the similarity of the deep feature embeddings. Whilst face preprocessing is a critical component of FR systems, and hence adversarial attacks against them, we observe that this preprocessing is often overlooked in blackbox settings. Our study seeks to investigate the transferability of several out-of-the-box state-of-the-art adversarial attacks against FR when applied against different preprocessing techniques used in a blackbox setting. We observe that the choice of face detection model can degrade the attack success rate by up to 78%, whereas choice of interpolation method during downsampling has relatively minimal impacts. Furthermore, we find that the requirement for facial preprocessing even degrades attack strength in a whitebox setting, due to the unintended interaction of produced noise vectors against face detection models. Based on these findings, we propose a preprocessing-invariant method using input transformations that improves the transferability of the studied attacks by up to 27%. Our findings highlight the importance of preprocessing in FR systems, and the need for its consideration towards improving the adversarial generalisation of facial adversarial examples.

---

### Neural Dynamics of AI-attributed Irony Reveal a Partial Intentional Stance

Authors: Xiaohui Rao, Hanlin Wu, Zhenguang G. Cai
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17168v2

As Large Language Models (LLMs) are increasingly deployed as social agents and trained to produce humor and irony, a question emerges: when encountering witty AI remarks, do people interpret them as deliberate communicative acts? This study investigated whether people adopt an intentional stance, ascribing mental states to explain behavior, when comprehending AI-attributed irony. Irony provides a testbed because understanding it requires distinguishing intentional contradictions from unintended errors through pragmatic reanalysis. Using electroencephalography (EEG) to measure event-related potentials (ERPs), we compared behavioral and neural responses to identical ironic utterances attributed to either an AI companion or a human. We found that people do not fully adopt an intentional stance towards AI communication. Participants interpreted contextually incongruent utterances as irony significantly less often when attributed to an AI than when attributed to a human. Correspondingly, we observed attenuated neural responses to AI-attributed irony compared to human-attributed irony during both initial semantic processing (P200) and pragmatic reanalysis (P600). In addition, these neural responses were modulated by individual perceptions of AI sincerity and trustworthiness, with positive perceptions facilitating pragmatic comprehension by reducing cognitive effort. This suggests that adopting an intentional stance toward AI is a flexible and adaptive process, dynamically shaped by people's mental models of artificial agents. These findings reveal that despite advances in communicative competence, AI systems face a barrier to social agency: humans process input from artificial interlocutors with reduced ascription of intentionality. This has important implications for understanding human social cognition and for designing AI systems intended for social interaction.

---

### Discovering Causal Relationships using Proxy Variables under Unmeasured Confounding

Authors: Yong Wu, Yanwei Fu, Shouyan Wang, Yizhou Wang, Xinwei Sun
Published: 2025-10-20
Categories: stat.ME, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.17167v1

Inferring causal relationships between variable pairs in the observational study is crucial but challenging, due to the presence of unmeasured confounding. While previous methods employed the negative controls to adjust for the confounding bias, they were either restricted to the discrete setting (i.e., all variables are discrete) or relied on strong assumptions for identification. To address these problems, we develop a general nonparametric approach that accommodates both discrete and continuous settings for testing causal hypothesis under unmeasured confounders. By using only a single negative control outcome (NCO), we establish a new identification result based on a newly proposed integral equation that links the outcome and NCO, requiring only the completeness and mild regularity conditions. We then propose a kernel-based testing procedure that is more efficient than existing moment-restriction methods. We derive the asymptotic level and power properties for our tests. Furthermore, we examine cases where our procedure using only NCO fails to achieve identification, and introduce a new procedure that incorporates a negative control exposure (NCE) to restore identifiability. We demonstrate the effectiveness of our approach through extensive simulations and real-world data from the Intensive Care Data and World Values Survey.

---

### TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework

Authors: Shuzheng Gao, Eric John Li, Man Ho Lam, Jingyu Xiao, Yuxuan Wan, Chaozheng Wang, Ng Man Tik, Michael R. Lyu
Published: 2025-10-20
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.17163v1

Large foundation models are fundamentally transforming the software engineering landscape, demonstrating exceptional capabilities across diverse tasks such as code generation, debugging, and testing. Despite this rapid progress, a significant gap remains in how to comprehensively evaluate these models' trustworthiness in real-world software engineering scenarios. Existing benchmarks suffer from limited task scope and fail to incorporate critical evaluation aspects such as the robustness and reliability of models. To bridge this gap, we present an evaluation framework called TREAT (Code LLMs Trustworthiness / Reliability Evaluation And Testing) that provides a holistic assessment of model performance in code intelligence tasks. Our evaluation framework addresses key limitations in existing approaches with four main improvements: (1) Multi-Task Holistic Evaluation that spans diverse software engineering activities rather than limited coding tasks; (2) Multi-Language and Multi-Modality Assessment that extends beyond traditional single-language, text-only benchmarks to include multi-modality coding tasks; (3) Robustness Assessment that evaluates model reliability under semantically-preserving code transformations; and (4) Rigorous Evaluation Methodology that enhances the trustworthiness of evaluation results through diverse evaluation prompts and adaptive solution extraction. Based on this evaluation framework, we assess 26 state-of-the-art models and uncover both their strengths and limitations, yielding several key insights:(1) Current models show substantial performance variation across programming tasks; (2) Multi-modal language models demonstrate specific performance limitations in UI code generation and edit;

---

### ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing

Authors: Guanjie Cheng, Siyang Liu, Xinkui Zhao, Yishan Chen, Junqin Huang, Linghe Kong, Shiguang Deng
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17162v2

Mobile edge crowdsensing (MECS) enables large-scale real-time sensing services, but its continuous data collection and transmission pipeline exposes terminal devices to dynamic privacy risks. Existing privacy protection schemes in MECS typically rely on static configurations or coarse-grained adaptation, making them difficult to balance privacy, data utility, and device overhead under changing channel conditions, data sensitivity, and resource availability. To address this problem, we propose ALPINE, a lightweight closed-loop framework for adaptive privacy budget allocation in MECS. ALPINE performs multi-dimensional risk perception on terminal devices by jointly modeling channel, semantic, contextual, and resource risks, and maps the resulting risk state to a privacy budget through an offline-trained TD3 policy. The selected budget is then used to drive local differential privacy perturbation before data transmission, while edge-side privacy-utility evaluation provides feedback for policy switching and periodic refinement. In this way, ALPINE forms a terminal-edge collaborative control loop that enables real-time, risk-adaptive privacy protection with low online overhead. Extensive experiments on multiple real-world datasets show that ALPINE achieves a better privacy-utility trade-off than representative baselines, reduces the effectiveness of membership inference, property inference, and reconstruction attacks, and preserves robust downstream task performance under dynamic risk conditions. Prototype deployment further demonstrates that ALPINE introduces only modest runtime overhead on resource-constrained devices.

---

### Learning After Model Deployment

Authors: Derda Kaymak, Gyuhak Kim, Tomoya Kaichi, Tatsuya Konishi, Bing Liu
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17160v1

In classic supervised learning, once a model is deployed in an application, it is fixed. No updates will be made to it during the application. This is inappropriate for many dynamic and open environments, where unexpected samples from unseen classes may appear. In such an environment, the model should be able to detect these novel samples from unseen classes and learn them after they are labeled. We call this paradigm Autonomous Learning after Model Deployment (ALMD). The learning here is continuous and involves no human engineers. Labeling in this scenario is performed by human co-workers or other knowledgeable agents, which is similar to what humans do when they encounter an unfamiliar object and ask another person for its name. In ALMD, the detection of novel samples is dynamic and differs from traditional out-of-distribution (OOD) detection in that the set of in-distribution (ID) classes expands as new classes are learned during application, whereas ID classes is fixed in traditional OOD detection. Learning is also different from classic supervised learning because in ALMD, we learn the encountered new classes immediately and incrementally. It is difficult to retrain the model from scratch using all the past data from the ID classes and the novel samples from newly discovered classes, as this would be resource- and time-consuming. Apart from these two challenges, ALMD faces the data scarcity issue because instances of new classes often appear sporadically in real-life applications. To address these issues, we propose a novel method, PLDA, which performs dynamic OOD detection and incremental learning of new classes on the fly. Empirical evaluations will demonstrate the effectiveness of PLDA.

---

### GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image

Authors: Yinghui Wang, Xinyu Zhang, Peng Du
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17157v1

Generating editable, parametric CAD models from a single image holds great potential to lower the barriers of industrial concept design. However, current multi-modal large language models (MLLMs) still struggle with accurately inferring 3D geometry from 2D images due to limited spatial reasoning capabilities. We address this limitation by introducing GACO-CAD, a novel two-stage post-training framework. It is designed to achieve a joint objective: simultaneously improving the geometric accuracy of the generated CAD models and encouraging the use of more concise modeling procedures. First, during supervised fine-tuning, we leverage depth and surface normal maps as dense geometric priors, combining them with the RGB image to form a multi-channel input. In the context of single-view reconstruction, these priors provide complementary spatial cues that help the MLLM more reliably recover 3D geometry from 2D observations. Second, during reinforcement learning, we introduce a group length reward that, while preserving high geometric fidelity, promotes the generation of more compact and less redundant parametric modeling sequences. A simple dynamic weighting strategy is adopted to stabilize training. Experiments on the DeepCAD and Fusion360 datasets show that GACO-CAD achieves state-of-the-art performance under the same MLLM backbone, consistently outperforming existing methods in terms of code validity, geometric accuracy, and modeling conciseness.

---

### HyperSearch: Prediction of New Hyperedges through Unconstrained yet Efficient Search

Authors: Hyunjin Choo, Fanchen Bu, Hyunjin Hwang, Young-Gyu Yoon, Kijung Shin
Published: 2025-10-20
Categories: cs.SI, cs.LG
arXiv: https://arxiv.org/abs/2510.17153v1

Higher-order interactions (HOIs) in complex systems, such as scientific collaborations, multi-protein complexes, and multi-user communications, are commonly modeled as hypergraphs, where each hyperedge (i.e., a subset of nodes) represents an HOI among the nodes. Given a hypergraph, hyperedge prediction aims to identify hyperedges that are either missing or likely to form in the future, and it has broad applications, including recommending interest-based social groups, predicting collaborations, and uncovering functional complexes in biological systems. However, the vast search space of hyperedge candidates (i.e., all possible subsets of nodes) poses a significant computational challenge, making naive exhaustive search infeasible. As a result, existing approaches rely on either heuristic sampling to obtain constrained candidate sets or ungrounded assumptions on hypergraph structure to select promising hyperedges. In this work, we propose HyperSearch, a search-based algorithm for hyperedge prediction that efficiently evaluates unconstrained candidate sets, by incorporating two key components: (1) an empirically grounded scoring function derived from observations in real-world hypergraphs and (2) an efficient search mechanism, where we derive and use an anti-monotonic upper bound of the original scoring function (which is not antimonotonic) to prune the search space. This pruning comes with theoretical guarantees, ensuring that discarded candidates are never better than the kept ones w.r.t. the original scoring function. In extensive experiments on 10 real-world hypergraphs across five domains, HyperSearch consistently outperforms state-of-the-art baselines, achieving higher accuracy in predicting new (i.e., not in the training set) hyperedges.

---

### ProtocolBench: Which LLM MultiAgent Protocol to Choose?

Authors: Hongyi Du, Jiaqi Su, Jisen Li, Lijie Ding, Yingxuan Yang, Peixuan Han, Xiangru Tang, Kunlun Zhu, Jiaxuan You
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.17149v3

As large-scale multi-agent systems evolve, the communication protocol layer has become a critical yet under-evaluated factor shaping performance and reliability. Despite the existence of diverse protocols (A2A, ACP, ANP, Agora, etc.), selection is often intuition-driven and lacks standardized guidance. We introduce ProtocolBench, a benchmark that systematically compares agent protocols along four measurable axes: task success, end-to-end latency, message or byte overhead, and robustness under failures. On ProtocolBench, protocol choice significantly influences system behavior. In the Streaming Queue scenario, overall completion time varies by up to 36.5% across protocols, and mean end-to-end latency differs by 3.48 s. Under Fail-Storm Recovery, resilience also differs consistently across protocols. Beyond evaluation, we present ProtocolRouter, a learnable protocol router that selects per-scenario (or per-module) protocols from requirement and runtime signals. ProtocolRouter reduces Fail-Storm recovery time by up to 18.1% versus the best single-protocol baseline, and achieves scenario-specific gains such as higher success in GAIA. We also release ProtocolRouterBench to standardize protocol evaluation and improve reliability at scale.

---

### DiffVLA++: Bridging Cognitive Reasoning and End-to-End Driving through Metric-Guided Alignment

Authors: Yu Gao, Anqing Jiang, Yiru Wang, Wang Jijun, Hao Jiang, Zhigang Sun, Heng Yuwen, Wang Shuo, Hao Zhao, Sun Hao
Published: 2025-10-20
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.17148v4

Conventional end-to-end (E2E) driving models are effective at generating physically plausible trajectories, but often fail to generalize to long-tail scenarios due to the lack of essential world knowledge to understand and reason about surrounding environments. In contrast, Vision-Language-Action (VLA) models leverage world knowledge to handle challenging cases, but their limited 3D reasoning capability can lead to physically infeasible actions. In this work we introduce DiffVLA++, an enhanced autonomous driving framework that explicitly bridges cognitive reasoning and E2E planning through metric-guided alignment. First, we build a VLA module directly generating semantically grounded driving trajectories. Second, we design an E2E module with a dense trajectory vocabulary that ensures physical feasibility. Third, and most critically, we introduce a metric-guided trajectory scorer that guides and aligns the outputs of the VLA and E2E modules, thereby integrating their complementary strengths. The experiment on the ICCV 2025 Autonomous Grand Challenge leaderboard shows that DiffVLA++ achieves EPDMS of 49.12.

---

### Physics-Informed Large Language Models for HVAC Anomaly Detection with Autonomous Rule Generation

Authors: Subin Lin, Chuanbo Hua
Published: 2025-10-20
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2510.17146v1

Heating, Ventilation, and Air-Conditioning (HVAC) systems account for a substantial share of global building energy use, making reliable anomaly detection essential for improving efficiency and reducing emissions. Classical rule-based approaches offer explainability but lack adaptability, while deep learning methods provide predictive power at the cost of transparency, efficiency, and physical plausibility. Recent attempts to use Large Language Models (LLMs) for anomaly detection improve interpretability but largely ignore the physical principles that govern HVAC operations. We present PILLM, a Physics-Informed LLM framework that operates within an evolutionary loop to automatically generate, evaluate, and refine anomaly detection rules. Our approach introduces physics-informed reflection and crossover operators that embed thermodynamic and control-theoretic constraints, enabling rules that are both adaptive and physically grounded. Experiments on the public Building Fault Detection dataset show that PILLM achieves state-of-the-art performance while producing diagnostic rules that are interpretable and actionable, advancing trustworthy and deployable AI for smart building systems.

---

### Enhanced Fish Freshness Classification with Incremental Handcrafted Feature Fusion

Authors: Phi-Hung Hoang, Nam-Thuan Trinh, Van-Manh Tran, Thi-Thu-Hong Phan
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.17145v2

Accurate assessment of fish freshness remains a major challenge in the food industry, with direct consequences for product quality, market value, and consumer health. Conventional sensory evaluation is inherently subjective, inconsistent, and difficult to standardize across contexts, often limited by subtle, species-dependent spoilage cues. To address these limitations, we propose a handcrafted feature-based approach that systematically extracts and incrementally fuses complementary descriptors, including color statistics, histograms across multiple color spaces, and texture features such as Local Binary Patterns (LBP) and Gray-Level Co-occurrence Matrices (GLCM), from fish eye images. Our method captures global chromatic variations from full images and localized degradations from ROI segments, fusing each independently to evaluate their effectiveness in assessing freshness. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate the approach's effectiveness: in a standard train-test setting, a LightGBM classifier achieved 77.56% accuracy, a 14.35% improvement over the previous deep learning baseline of 63.21%. With augmented data, an Artificial Neural Network (ANN) reached 97.49% accuracy, surpassing the prior best of 77.3% by 20.19%. These results demonstrate that carefully engineered, handcrafted features, when strategically processed, yield a robust, interpretable, and reliable solution for automated fish freshness assessment, providing valuable insights for practical applications in food quality monitoring.

---

### Rethinking On-policy Optimization for Query Augmentation

Authors: Zhichao Xu, Shengyao Zhuang, Xueguang Ma, Bingsen Chen, Yijun Tian, Fengran Mo, Tao Li, Jie Cao, Vivek Srikumar
Published: 2025-10-20
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.17139v3

Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main approaches have emerged. The first prompts LLMs to generate answers or pseudo-documents that serve as new queries, relying purely on the model's parametric knowledge or contextual information. The second applies reinforcement learning (RL) to fine-tune LLMs for query rewriting, directly optimizing retrieval metrics. While having respective advantages and limitations, the two approaches have not been compared under consistent experimental conditions. In this work, we present the first systematic comparison of prompting-based and RL-based query augmentation across diverse benchmarks, including evidence-seeking, ad hoc, and tool retrieval. Our key finding is that under a compute-aware comparison setting, simple, training-free query augmentation often performs on par with, or even surpasses, more expensive RL-based counterparts, especially when using powerful LLMs. Motivated by this discovery, we introduce a novel hybrid method, On-policy Pseudo-document Query Expansion (OPQE), in which the LLM policy learns to generate a pseudo-document that maximizes retrieval performance, rather than rewriting the query, thus merging the flexibility and generative structure of prompting with the targeted optimization of RL. We show OPQE outperforms both standalone prompting and RL-based rewriting, demonstrating that a synergistic approach yields the best results. We open source our implementation to facilitate reproducibility.

---

### KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation

Authors: WenBo Xu, Liu Liu, Li Zhang, Ran Zhang, Hao Wu, Dan Guo, Meng Wang
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17137v1

Articulated objects, such as laptops and drawers, exhibit significant challenges for 3D reconstruction and pose estimation due to their multi-part geometries and variable joint configurations, which introduce structural diversity across different states. To address these challenges, we propose KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation, a unified framework for reconstructing diverse articulated instances and pose estimation from single view input. Specifically, we first encode complete geometry (SDFs), joint angles, and part segmentation into a structured latent space via a novel Kinematic-Aware VAE (KA-VAE). In addition, we employ two conditional diffusion models: one for regressing global pose (SE(3)) and joint parameters, and another for generating the kinematic-aware latent code from partial observations. Finally, we produce an iterative optimization module that bidirectionally refines reconstruction accuracy and kinematic parameters via Chamfer-distance minimization while preserving articulation constraints. Experimental results on synthetic, semi-synthetic, and real-world datasets demonstrate the effectiveness of our approach in accurately reconstructing articulated objects and estimating their kinematic properties.

---

### In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models

Authors: Enhao Gu, Haolin Hou
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17136v2

The generation of high-quality, diverse, and prompt-aligned images is a central goal in image-generating diffusion models. The popular classifier-free guidance (CFG) approach improves quality and alignment at the cost of reduced variation, creating an inherent entanglement of these effects. Recent work has successfully disentangled these properties by guiding a model with a separately trained, inferior counterpart; however, this solution introduces the considerable overhead of requiring an auxiliary model. We challenge this prerequisite by introducing In-situ Autoguidance, a method that elicits guidance from the model itself without any auxiliary components. Our approach dynamically generates an inferior prediction on the fly using a stochastic forward pass, reframing guidance as a form of inference-time self-correction. We demonstrate that this zero-cost approach is not only viable but also establishes a powerful new baseline for cost-efficient guidance, proving that the benefits of self-guidance can be achieved without external models.

---

### Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction

Authors: Ioannis Tsaknakis, Bingqing Song, Shuyu Gan, Dongyeop Kang, Alfredo Garcia, Gaowen Liu, Charles Fleming, Mingyi Hong
Published: 2025-10-20
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.17132v1

Large Language Models (LLMs) excel at producing broadly relevant text, but this generality becomes a limitation when user-specific preferences are required, such as recommending restaurants or planning travel. In these scenarios, users rarely articulate every preference explicitly; instead, much of what they care about remains latent, waiting to be inferred. This raises a fundamental question: Can LLMs uncover and reason about such latent information through conversation? We address this problem by introducing a unified benchmark for evaluating latent information discovery - the ability of LLMs to reveal and utilize hidden user attributes through multi-turn interaction. The benchmark spans three progressively realistic settings: the classic 20 Questions game, Personalized Question Answering, and Personalized Text Summarization. All tasks share a tri-agent framework (User, Assistant, Judge) enabling turn-level evaluation of elicitation and adaptation. Our results reveal that while LLMs can indeed surface latent information through dialogue, their success varies dramatically with context: from 32% to 98%, depending on task complexity, topic, and number of hidden attributes. This benchmark provides the first systematic framework for studying latent information discovery in personalized interaction, highlighting that effective preference inference remains an open frontier for building truly adaptive AI systems.

---