# Research Papers — 2025-10 · bundle page 27 of 217

> Full-text markdown of papers #1301–1350 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/27
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/26.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/28.md)

### Retrieval- and Argumentation-Enhanced Multi-Agent LLMs for Judgmental Forecasting (Extended Version with Supplementary Material)

Authors: Deniz Gorur, Antonio Rago, Francesca Toni
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24303v3

Judgmental forecasting is the task of making predictions about future events based on human judgment. This task can be seen as a form of claim verification, where the claim corresponds to a future event and the task is to assess the plausibility of that event. In this paper, we propose a novel multi-agent framework for claim verification, whereby different agents may disagree on claim veracity and bring specific evidence for and against the claims, represented as quantitative bipolar argumentation frameworks (QBAFs). We then instantiate the framework for supporting claim verification, with a variety of agents realised with Large Language Models (LLMs): (1) ArgLLM agents, an existing approach for claim verification that generates and evaluates QBAFs; (2) RbAM agents, whereby LLM-empowered Relation-based Argument Mining (RbAM) from external sources is used to generate QBAFs; (3) RAG-ArgLLM agents, extending ArgLLM agents with a form of Retrieval-Augmented Generation (RAG) of arguments from external sources. Finally, we conduct experiments with two standard judgmental forecasting datasets, with instances of our framework with two or three agents, empowered by six different base LLMs. We observe that combining evidence from agents can improve forecasting accuracy, especially in the case of three agents, while providing an explainable combination of evidence for claim verification.

---

### Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards

Authors: Shangyu Xing, Siyuan Wang, Chenyuan Yang, Xinyu Dai, Xiang Ren
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24302v3

Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the reasoning capabilities of large language models. However, a critical bottleneck in current pipelines lies in the limited diversity of sampled trajectories during group rollouts. Homogeneous trajectories and their associated rewards would diminish the return signals for policy updates, thereby hindering effective policy learning. This lack of diversity stems primarily from token-level stochastic sampling, where local variations are likely to collapse into near-identical reasoning paths. To address this limitation, we propose Lookahead Tree-Based Rollouts (LATR), a novel rollout strategy designed to explicitly promotes trajectory-level diversity by enforcing branching into different candidate tokens likely to yield distinct continuations. Specifically, LATR iteratively operates in three stages: (1) branching at high-uncertainty generation steps, (2) performing lookahead simulation for each new branch, and (3) pruning branches that exhibits prolonged similarity during simulation. Compared with stochastic Sampling, LATR accelerates policy learning by 131% on average and improves final pass@1 performance by 4.2% on both GRPO and Dynamic sAmpling Policy Optimization (DAPO) algorithms across different reasoning tasks. Our code and data are publicly available at https://github.com/starreeze/latr.

---

### Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank

Authors: Jiayu Liu, Wei Dai, Zhenya Huang, Ning Miao, Enhong Chen
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24299v1

Despite the strong reasoning ability of large language models~(LLMs), they are prone to errors and hallucinations. As a result, how to check their outputs effectively and efficiently has become a critical problem in their applications. Existing checking methods heavily rely on external resources, such as trained verifiers (e.g., process/outcome reward models) or elaborate prompts, which lead to high computational overhead and are only applicable to specific domains. In this paper, we investigate whether the internal behaviors of LLMs have already implied the credibility of their reasoning paths. Specifically, we find that the rank of the correlation matrix between the input problem and the output reasoning path is a robust indicator of reasoning correctness. Different from other correctness indicators for LLMs, the calculation of the correlation matrix only relies on the LLM itself, which avoids the hassle of training a separate model or designing complicated prompts. Based on it, we design a simple, plug-and-play Self-Indicator method to reweight candidate reasoning paths, which achieves significant performance improvements than other voting and verification methods with very few computational overhead. Our experiments across multiple LLMs of varying scales and model families have further shown the effectiveness of Self-Indicator. It achieves over 75% accuracy in distinguishing correct reasoning paths from incorrect ones, and, in turn, improves the accuracies on three reasoning benchmarks by more than 8%.

---

### Investigating Intra-Abstraction Policies For Non-exact Abstraction Algorithms

Authors: Robin Schmöcker, Alexander Dockhorn, Bodo Rosenhahn
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24297v1

One weakness of Monte Carlo Tree Search (MCTS) is its sample efficiency which can be addressed by building and using state and/or action abstractions in parallel to the tree search such that information can be shared among nodes of the same layer. The primary usage of abstractions for MCTS is to enhance the Upper Confidence Bound (UCB) value during the tree policy by aggregating visits and returns of an abstract node. However, this direct usage of abstractions does not take the case into account where multiple actions with the same parent might be in the same abstract node, as these would then all have the same UCB value, thus requiring a tiebreak rule. In state-of-the-art abstraction algorithms such as pruned On the Go Abstractions (pruned OGA), this case has not been noticed, and a random tiebreak rule was implicitly chosen. In this paper, we propose and empirically evaluate several alternative intra-abstraction policies, several of which outperform the random policy across a majority of environments and parameter settings.

---

### MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference

Authors: Mădălina Zgreabăn, Tejaswini Deoskar, Lasha Abzianidze
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24295v3

As many benchmarks have become saturated, it is increasingly important to create new datasets that evaluate the generalization capacity of current state-of-the-art models in reasoning. However, creating high-quality reasoning datasets is challenging: manual construction is costly, and automatic generation is error-prone, with the community therefore relying on synthetic datasets with limited scope. In this paper, we propose the Minimal Expression Replacement GEneralization (MERGE) test, to evaluate the robustness of reasoning models against minimal and non-adversarial variants of existing evaluation datasets. First, high-quality variants are automatically obtained from the original instances using Masked Language Models (MLMs) for generation together with safeguarding filters, called Minimal Expression Replacement (MERE). We then apply the MERGE test to Natural Language Inference (NLI), a popular reasoning task, by using MERE on two popular existing NLI datasets. We evaluate multiple strong NLI models and LLMs, and the results indicate they generalize poorly: both struggle to consistently and correctly classify variants minimally different in form, but similar in reasoning, from the original ones. We also analyze how aspects of variant generation, such as word class and source MLMs, affect model performance.

---

### Problem-Parameter-Free Decentralized Bilevel Optimization

Authors: Zhiwei Zhai, Wenjing Yan, Ying-Jun Angela Zhang
Published: 2025-10-28
Categories: math.OC, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.24288v1

Decentralized bilevel optimization has garnered significant attention due to its critical role in solving large-scale machine learning problems. However, existing methods often rely on prior knowledge of problem parameters-such as smoothness, convexity, or communication network topologies-to determine appropriate stepsizes. In practice, these problem parameters are typically unavailable, leading to substantial manual effort for hyperparameter tuning. In this paper, we propose AdaSDBO, a fully problem-parameter-free algorithm for decentralized bilevel optimization with a single-loop structure. AdaSDBO leverages adaptive stepsizes based on cumulative gradient norms to update all variables simultaneously, dynamically adjusting its progress and eliminating the need for problem-specific hyperparameter tuning. Through rigorous theoretical analysis, we establish that AdaSDBO achieves a convergence rate of $\widetilde{\mathcal{O}}\left(\frac{1}{T}\right)$, matching the performance of well-tuned state-of-the-art methods up to polylogarithmic factors. Extensive numerical experiments demonstrate that AdaSDBO delivers competitive performance compared to existing decentralized bilevel optimization methods while exhibiting remarkable robustness across diverse stepsize configurations.

---

### Towards actionable hypotension prediction -- predicting catecholamine therapy initiation in the intensive care unit

Authors: Richard Koebe, Noah Saibel, Juan Miguel Lopez Alcaraz, Simon Schäfer, Nils Strodthoff
Published: 2025-10-28
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2510.24287v1

Hypotension in critically ill ICU patients is common and life-threatening. Escalation to catecholamine therapy marks a key management step, with both undertreatment and overtreatment posing risks. Most machine learning (ML) models predict hypotension using fixed MAP thresholds or MAP forecasting, overlooking the clinical decision behind treatment escalation. Predicting catecholamine initiation, the start of vasoactive or inotropic agent administration offers a more clinically actionable target reflecting real decision-making. Using the MIMIC-III database, we modeled catecholamine initiation as a binary event within a 15-minute prediction window. Input features included statistical descriptors from a two-hour sliding MAP context window, along with demographics, biometrics, comorbidities, and ongoing treatments. An Extreme Gradient Boosting (XGBoost) model was trained and interpreted via SHapley Additive exPlanations (SHAP). The model achieved an AUROC of 0.822 (0.813-0.830), outperforming the hypotension baseline (MAP < 65, AUROC 0.686 (0.675-0.699)). SHAP analysis highlighted recent MAP values, MAP trends, and ongoing treatments (e.g., sedatives, electrolytes) as dominant predictors. Subgroup analysis showed higher performance in males, younger patients (<53 years), those with higher BMI (>32), and patients without comorbidities or concurrent medications. Predicting catecholamine initiation based on MAP dynamics, treatment context, and patient characteristics supports the critical decision of when to escalate therapy, shifting focus from threshold-based alarms to actionable decision support. This approach is feasible across a broad ICU cohort under natural event imbalance. Future work should enrich temporal and physiological context, extend label definitions to include therapy escalation, and benchmark against existing hypotension prediction systems.

---

### ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model

Authors: Juntian Zhang, Song Jin, Chuanqi Cheng, Yuhan Liu, Yankai Lin, Xun Zhang, Yufei Zhang, Fei Jiang, Guojun Yin, Wei Lin, Rui Yan
Published: 2025-10-28
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.24285v1

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations of existing methods: supervised fine-tuning (SFT) often compromises general capabilities, while reinforcement fine-tuning (RFT) prioritizes textual reasoning over visual perception. To bridge this gap, we propose a novel two-stage task that structures visual perception learning as a coarse-to-fine progressive process. Based on this task formulation, we develop ViPER, a self-bootstrapping framework specifically designed to enable iterative evolution through self-critiquing and self-prediction. By synergistically integrating image-level and instance-level reconstruction with a two-stage reinforcement learning strategy, ViPER establishes a closed-loop training paradigm, where internally synthesized data directly fuel the enhancement of perceptual ability. Applied to the Qwen2.5-VL family, ViPER produces the Qwen-Viper series. With an average gain of 1.7% on seven comprehensive benchmarks spanning various tasks and up to 6.0% on fine-grained perception, Qwen-Viper consistently demonstrates superior performance across different vision-language scenarios while maintaining generalizability. Beyond enabling self-improvement in perceptual capabilities, ViPER provides concrete evidence for the reciprocal relationship between generation and understanding, a breakthrough to developing more autonomous and capable VLMs.

---

### MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools

Authors: Wenhao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen, Jian Du, Yaxin Du, Xianghe Pang, Keduan Huang, Yanfeng Wang, Qiang Yan, Siheng Chen
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24284v3

Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing MCP research covers few servers, depends on costly manual curation, and lacks training support, hindering progress toward real-world deployment. To overcome these limitations, we introduce MCP-Flow, an automated web-agent-driven pipeline for large-scale server discovery, data synthesis, and model training. MCP-Flow collects and filters data from 1166 servers and 11536 tools, producing 68733 high-quality instruction-function call pairs and 6439 trajectories, far exceeding prior work in scale and diversity. Extensive experiments demonstrate MCP-Flow's effectiveness in driving superior MCP tool selection, function-call generation, and enhanced agentic task performance. MCP-Flow thus provides a scalable foundation for advancing LLM agents' proficiency in real-world MCP environments. MCP-Flow is publicly available at https://github.com/wwh0411/MCP-Flow.

---

### HergNet: a Fast Neural Surrogate Model for Sound Field Predictions via Superposition of Plane Waves

Authors: Matteo Calafà, Yuanxin Xia, Cheol-Ho Jeong
Published: 2025-10-28
Categories: cs.SD, cs.CE, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.24279v1

We present a novel neural network architecture for the efficient prediction of sound fields in two and three dimensions. The network is designed to automatically satisfy the Helmholtz equation, ensuring that the outputs are physically valid. Therefore, the method can effectively learn solutions to boundary-value problems in various wave phenomena, such as acoustics, optics, and electromagnetism. Numerical experiments show that the proposed strategy can potentially outperform state-of-the-art methods in room acoustics simulation, in particular in the range of mid to high frequencies.

---

### Training-free Source Attribution of AI-generated Images via Resynthesis

Authors: Pietro Bongini, Valentina Molinari, Andrea Costanzo, Benedetta Tondi, Mauro Barni
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24278v1

Synthetic image source attribution is a challenging task, especially in data scarcity conditions requiring few-shot or zero-shot classification capabilities. We present a new training-free one-shot attribution method based on image resynthesis. A prompt describing the image under analysis is generated, then it is used to resynthesize the image with all the candidate sources. The image is attributed to the model which produced the resynthesis closest to the original image in a proper feature space. We also introduce a new dataset for synthetic image attribution consisting of face images from commercial and open-source text-to-image generators. The dataset provides a challenging attribution framework, useful for developing new attribution models and testing their capabilities on different generative architectures. The dataset structure allows to test approaches based on resynthesis and to compare them to few-shot methods. Results from state-of-the-art few-shot approaches and other baselines show that the proposed resynthesis method outperforms existing techniques when only a few samples are available for training or fine-tuning. The experiments also demonstrate that the new dataset is a challenging one and represents a valuable benchmark for developing and evaluating future few-shot and zero-shot methods.

---

### SALS: Sparse Attention in Latent Space for KV cache Compression

Authors: Junlin Mu, Hantao Huang, Jihang Zhang, Minghui Yu, Tao Wang, Yidong Li
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24273v1

Large Language Models capable of handling extended contexts are in high demand, yet their inference remains challenging due to substantial Key-Value cache size and high memory bandwidth requirements. Previous research has demonstrated that KV cache exhibits low-rank characteristics within the hidden dimension, suggesting the potential for effective compression. However, due to the widely adopted Rotary Position Embedding mechanism in modern LLMs, naive low-rank compression suffers severe accuracy degradation or creates a new speed bottleneck, as the low-rank cache must first be reconstructed in order to apply RoPE. In this paper, we introduce two key insights: first, the application of RoPE to the key vectors increases their variance, which in turn results in a higher rank; second, after the key vectors are transformed into the latent space, they largely maintain their representation across most layers. Based on these insights, we propose the Sparse Attention in Latent Space framework. SALS projects the KV cache into a compact latent space via low-rank projection, and performs sparse token selection using RoPE-free query-key interactions in this space. By reconstructing only a small subset of important tokens, it avoids the overhead of full KV cache reconstruction. We comprehensively evaluate SALS on various tasks using two large-scale models: LLaMA2-7b-chat and Mistral-7b, and additionally verify its scalability on the RULER-128k benchmark with LLaMA3.1-8B-Instruct. Experimental results demonstrate that SALS achieves SOTA performance by maintaining competitive accuracy. Under different settings, SALS achieves 6.4-fold KV cache compression and 5.7-fold speed-up in the attention operator compared to FlashAttention2 on the 4K sequence. For the end-to-end throughput performance, we achieves 1.4-fold and 4.5-fold improvement compared to GPT-fast on 4k and 32K sequences, respectively.

---

### Survey and Tutorial of Reinforcement Learning Methods in Process Systems Engineering

Authors: Maximilian Bloor, Max Mowbray, Ehecatl Antonio Del Rio Chanona, Calvin Tsay
Published: 2025-10-28
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2510.24272v1

Sequential decision making under uncertainty is central to many Process Systems Engineering (PSE) challenges, where traditional methods often face limitations related to controlling and optimizing complex and stochastic systems. Reinforcement Learning (RL) offers a data-driven approach to derive control policies for such challenges. This paper presents a survey and tutorial on RL methods, tailored for the PSE community. We deliver a tutorial on RL, covering fundamental concepts and key algorithmic families including value-based, policy-based and actor-critic methods. Subsequently, we survey existing applications of these RL techniques across various PSE domains, such as in fed-batch and continuous process control, process optimization, and supply chains. We conclude with PSE focused discussion of specialized techniques and emerging directions. By synthesizing the current state of RL algorithm development and implications for PSE this work identifies successes, challenges, trends, and outlines avenues for future research at the interface of these fields.

---

### UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

Authors: Jiyu Guo, Shuo Yang, Yiming Huang, Yancheng Long, Xiaobo Xia, Xiu Su, Bo Zhao, Zeke Xie, Liqiang Nie
Published: 2025-10-28
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.24262v1

Data augmentation using generative models has emerged as a powerful paradigm for enhancing performance in computer vision tasks. However, most existing augmentation approaches primarily focus on optimizing intrinsic data attributes -- such as fidelity and diversity -- to generate visually high-quality synthetic data, while often neglecting task-specific requirements. Yet, it is essential for data generators to account for the needs of downstream tasks, as training data requirements can vary significantly across different tasks and network architectures. To address these limitations, we propose UtilGen, a novel utility-centric data augmentation framework that adaptively optimizes the data generation process to produce task-specific, high-utility training data via downstream task feedback. Specifically, we first introduce a weight allocation network to evaluate the task-specific utility of each synthetic sample. Guided by these evaluations, UtilGen iteratively refines the data generation process using a dual-level optimization strategy to maximize the synthetic data utility: (1) model-level optimization tailors the generative model to the downstream task, and (2) instance-level optimization adjusts generation policies -- such as prompt embeddings and initial noise -- at each generation round. Extensive experiments on eight benchmark datasets of varying complexity and granularity demonstrate that UtilGen consistently achieves superior performance, with an average accuracy improvement of 3.87% over previous SOTA. Further analysis of data influence and distribution reveals that UtilGen produces more impactful and task-relevant synthetic data, validating the effectiveness of the paradigm shift from visual characteristics-centric to task utility-centric data augmentation.

---

### DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation

Authors: Jingyi Tian, Le Wang, Sanping Zhou, Sen Wang, Jiayi Li, Gang Hua
Published: 2025-10-28
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.24261v1

Learning generalizable robotic manipulation policies remains a key challenge due to the scarcity of diverse real-world training data. While recent approaches have attempted to mitigate this through self-supervised representation learning, most either rely on 2D vision pretraining paradigms such as masked image modeling, which primarily focus on static semantics or scene geometry, or utilize large-scale video prediction models that emphasize 2D dynamics, thus failing to jointly learn the geometry, semantics, and dynamics required for effective manipulation. In this paper, we present DynaRend, a representation learning framework that learns 3D-aware and dynamics-informed triplane features via masked reconstruction and future prediction using differentiable volumetric rendering. By pretraining on multi-view RGB-D video data, DynaRend jointly captures spatial geometry, future dynamics, and task semantics in a unified triplane representation. The learned representations can be effectively transferred to downstream robotic manipulation tasks via action value map prediction. We evaluate DynaRend on two challenging benchmarks, RLBench and Colosseum, as well as in real-world robotic experiments, demonstrating substantial improvements in policy success rate, generalization to environmental perturbations, and real-world applicability across diverse manipulation tasks.

---

### DeshadowMamba: Deshadowing as 1D Sequential Similarity

Authors: Zhaotong Yang, Yi Chen, Yanying Li, Shengfeng He, Yangyang Xu, Junyu Dong, Jian Yang, Yong Du
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24260v1

Recent deep models for image shadow removal often rely on attention-based architectures to capture long-range dependencies. However, their fixed attention patterns tend to mix illumination cues from irrelevant regions, leading to distorted structures and inconsistent colors. In this work, we revisit shadow removal from a sequence modeling perspective and explore the use of Mamba, a selective state space model that propagates global context through directional state transitions. These transitions yield an efficient global receptive field while preserving positional continuity. Despite its potential, directly applying Mamba to image data is suboptimal, since it lacks awareness of shadow-non-shadow semantics and remains susceptible to color interference from nearby regions. To address these limitations, we propose CrossGate, a directional modulation mechanism that injects shadow-aware similarity into Mamba's input gate, allowing selective integration of relevant context along transition axes. To further ensure appearance fidelity, we introduce ColorShift regularization, a contrastive learning objective driven by global color statistics. By synthesizing structured informative negatives, it guides the model to suppress color contamination and achieve robust color restoration. Together, these components adapt sequence modeling to the structural integrity and chromatic consistency required for shadow removal. Extensive experiments on public benchmarks demonstrate that DeshadowMamba achieves state-of-the-art visual quality and strong quantitative performance.

---

### Can LLMs Translate Human Instructions into a Reinforcement Learning Agent's Internal Emergent Symbolic Representation?

Authors: Ziqi Ma, Sao Mai Nguyen, Philippe Xu
Published: 2025-10-28
Categories: cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2510.24259v1

Emergent symbolic representations are critical for enabling developmental learning agents to plan and generalize across tasks. In this work, we investigate whether large language models (LLMs) can translate human natural language instructions into the internal symbolic representations that emerge during hierarchical reinforcement learning. We apply a structured evaluation framework to measure the translation performance of commonly seen LLMs -- GPT, Claude, Deepseek and Grok -- across different internal symbolic partitions generated by a hierarchical reinforcement learning algorithm in the Ant Maze and Ant Fall environments. Our findings reveal that although LLMs demonstrate some ability to translate natural language into a symbolic representation of the environment dynamics, their performance is highly sensitive to partition granularity and task complexity. The results expose limitations in current LLMs capacity for representation alignment, highlighting the need for further research on robust alignment between language and internal agent representations.

---

### From Memorization to Reasoning in the Spectrum of Loss Curvature

Authors: Jack Merullo, Srihita Vatsavaya, Lucius Bushnaq, Owen Lewis
Published: 2025-10-28
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.24256v2

We characterize how memorization is represented in transformer models and show that it can be disentangled in the weights of both language models (LMs) and vision transformers (ViTs) using a decomposition based on the loss landscape curvature. This insight is based on prior theoretical and empirical work showing that the curvature for memorized training points is much sharper than non memorized, meaning ordering weight components from high to low curvature can reveal a distinction without explicit labels. This motivates a weight editing procedure that suppresses far more recitation of untargeted memorized data more effectively than a recent unlearning method (BalancedSubnet), while maintaining lower perplexity. Since the basis of curvature has a natural interpretation for shared structure in model weights, we analyze the editing procedure extensively on its effect on downstream tasks in LMs, and find that fact retrieval and arithmetic are specifically and consistently negatively affected, even though open book fact retrieval and general logical reasoning is conserved. We posit these tasks rely heavily on specialized directions in weight space rather than general purpose mechanisms, regardless of whether those individual datapoints are memorized. We support this by showing a correspondence between task data's activation strength with low curvature components that we edit out, and the drop in task performance after the edit. Our work enhances the understanding of memorization in neural networks with practical applications towards removing it, and provides evidence for idiosyncratic, narrowly-used structures involved in solving tasks like math and fact retrieval.

---

### Trajectory Design for UAV-Based Low-Altitude Wireless Networks in Unknown Environments: A Digital Twin-Assisted TD3 Approach

Authors: Jihao Luo, Zesong Fei, Xinyi Wang, Le Zhao, Yuanhao Cui, Guangxu Zhu, Dusit Niyato
Published: 2025-10-28
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2510.24255v1

Unmanned aerial vehicles (UAVs) are emerging as key enablers for low-altitude wireless network (LAWN), particularly when terrestrial networks are unavailable. In such scenarios, the environmental topology is typically unknown; hence, designing efficient and safe UAV trajectories is essential yet challenging. To address this, we propose a digital twin (DT)-assisted training and deployment framework. In this framework, the UAV transmits integrated sensing and communication signals to provide communication services to ground users, while simultaneously collecting echoes that are uploaded to the DT server to progressively construct virtual environments (VEs). These VEs accelerate model training and are continuously updated with real-time UAV sensing data during deployment, supporting decision-making and enhancing flight safety. Based on this framework, we further develop a trajectory design scheme that integrates simulated annealing for efficient user scheduling with the twin-delayed deep deterministic policy gradient algorithm for continuous trajectory design, aiming to minimize mission completion time while ensuring obstacle avoidance. Simulation results demonstrate that the proposed approach achieves faster convergence, higher flight safety, and shorter mission completion time compared with baseline methods, providing a robust and efficient solution for LAWN deployment in unknown environments.

---

### Forecasting precipitation in the Arctic using probabilistic machine learning informed by causal climate drivers

Authors: Madhurima Panja, Dhiman Das, Tanujit Chakraborty, Arnob Ray, R. Athulya, Chittaranjan Hens, Syamal K. Dana, Nuncio Murukesh, Dibakar Ghosh
Published: 2025-10-28
Categories: physics.ao-ph, cs.LG, physics.data-an
arXiv: https://arxiv.org/abs/2510.24254v1

Understanding and forecasting precipitation events in the Arctic maritime environments, such as Bear Island and Ny-Ålesund, is crucial for assessing climate risk and developing early warning systems in vulnerable marine regions. This study proposes a probabilistic machine learning framework for modeling and predicting the dynamics and severity of precipitation. We begin by analyzing the scale-dependent relationships between precipitation and key atmospheric drivers (e.g., temperature, relative humidity, cloud cover, and air pressure) using wavelet coherence, which captures localized dependencies across time and frequency domains. To assess joint causal influences, we employ Synergistic-Unique-Redundant Decomposition, which quantifies the impact of interaction effects among each variable on future precipitation dynamics. These insights inform the development of data-driven forecasting models that incorporate both historical precipitation and causal climate drivers. To account for uncertainty, we employ the conformal prediction method, which enables the generation of calibrated non-parametric prediction intervals. Our results underscore the importance of utilizing a comprehensive framework that combines causal analysis with probabilistic forecasting to enhance the reliability and interpretability of precipitation predictions in Arctic marine environments.

---

### Evaluating LLMs on Generating Age-Appropriate Child-Like Conversations

Authors: Syed Zohaib Hassan, Pål Halvorsen, Miriam S. Johnson, Pierre Lison
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24250v1

Large Language Models (LLMs), predominantly trained on adult conversational data, face significant challenges when generating authentic, child-like dialogue for specialized applications. We present a comparative study evaluating five different LLMs (GPT-4, RUTER-LLAMA-2-13b, GPTSW, NorMistral-7b, and NorBloom-7b) to generate age-appropriate Norwegian conversations for children aged 5 and 9 years. Through a blind evaluation by eleven education professionals using both real child interview data and LLM-generated text samples, we assessed authenticity and developmental appropriateness. Our results show that evaluators achieved strong inter-rater reliability (ICC=0.75) and demonstrated higher accuracy in age prediction for younger children (5-year-olds) compared to older children (9-year-olds). While GPT-4 and NorBloom-7b performed relatively well, most models generated language perceived as more linguistically advanced than the target age groups. These findings highlight critical data-related challenges in developing LLM systems for specialized applications involving children, particularly in low-resource languages where comprehensive age-appropriate lexical resources are scarce.

---

### Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations

Authors: Ahmad Ghannam, Naif Alharthi, Faris Alasmary, Kholood Al Tabash, Shouq Sadah, Lahouari Ghouti
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24247v1

In this work, we tackle the Diacritic Restoration (DR) task for Arabic dialectal sentences using a multimodal approach that combines both textual and speech information. We propose a model that represents the text modality using an encoder extracted from our own pre-trained model named CATT. The speech component is handled by the encoder module of the OpenAI Whisper base model. Our solution is designed following two integration strategies. The former consists of fusing the speech tokens with the input at an early stage, where the 1500 frames of the audio segment are averaged over 10 consecutive frames, resulting in 150 speech tokens. To ensure embedding compatibility, these averaged tokens are processed through a linear projection layer prior to merging them with the text tokens. Contextual encoding is guaranteed by the CATT encoder module. The latter strategy relies on cross-attention, where text and speech embeddings are fused. The cross-attention output is then fed to the CATT classification head for token-level diacritic prediction. To further improve model robustness, we randomly deactivate the speech input during training, allowing the model to perform well with or without speech. Our experiments show that the proposed approach achieves a word error rate (WER) of 0.25 and a character error rate (CER) of 0.9 on the development set. On the test set, our model achieved WER and CER scores of 0.55 and 0.13, respectively.

---

### Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Models

Authors: Zihan Li, Jiahao Yang, Yuxin Zhang, Zhe Chen, Yue Gao
Published: 2025-10-28
Categories: cs.NI, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.24242v1

Large vision-language models (LVLMs) have recently demonstrated great potential in remote sensing (RS) tasks (e.g., disaster monitoring) conducted by low Earth orbit (LEO) satellites. However, their deployment in real-world LEO satellite systems remains largely unexplored, hindered by limited onboard computing resources and brief satellite-ground contacts. We propose Grace, a satellite-ground collaborative system designed for near-realtime LVLM inference in RS tasks. Accordingly, we deploy compact LVLM on satellites for realtime inference, but larger ones on ground stations (GSs) to guarantee end-to-end performance. Grace is comprised of two main phases that are asynchronous satellite-GS Retrieval-Augmented Generation (RAG), and a task dispatch algorithm. Firstly, we still the knowledge archive of GS RAG to satellite archive with tailored adaptive update algorithm during limited satellite-ground data exchange period. Secondly, propose a confidence-based test algorithm that either processes the task onboard the satellite or offloads it to the GS. Extensive experiments based on real-world satellite orbital data show that Grace reduces the average latency by 76-95% compared to state-of-the-art methods, without compromising inference accuracy.

---

### MAGNET: A Multi-Graph Attentional Network for Code Clone Detection

Authors: Zixian Zhang, Takfarinas Saber
Published: 2025-10-28
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.24241v1

Code clone detection is a fundamental task in software engineering that underpins refactoring, debugging, plagiarism detection, and vulnerability analysis. Existing methods often rely on singular representations such as abstract syntax trees (ASTs), control flow graphs (CFGs), and data flow graphs (DFGs), which capture only partial aspects of code semantics. Hybrid approaches have emerged, but their fusion strategies are typically handcrafted and ineffective. In this study, we propose MAGNET, a multi-graph attentional framework that jointly leverages AST, CFG, and DFG representations to capture syntactic and semantic features of source code. MAGNET integrates residual graph neural networks with node-level self-attention to learn both local and long-range dependencies, introduces a gated cross-attention mechanism for fine-grained inter-graph interactions, and employs Set2Set pooling to fuse multi-graph embeddings into unified program-level representations. Extensive experiments on BigCloneBench and Google Code Jam demonstrate that MAGNET achieves state-of-the-art performance with an overall F1 score of 96.5\% and 99.2\% on the two datasets, respectively. Ablation studies confirm the critical contributions of multi-graph fusion and each attentional component. Our code is available at https://github.com/ZixianReid/Multigraph_match

---

### Temporal Knowledge Graph Hyperedge Forecasting: Exploring Entity-to-Category Link Prediction

Authors: Edward Markai, Sina Molavipour
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24240v1

Temporal Knowledge Graphs have emerged as a powerful way of not only modeling static relationships between entities but also the dynamics of how relations evolve over time. As these informational structures can be used to store information from a real-world setting, such as a news flow, predicting future graph components to a certain extent equates predicting real-world events. Most of the research in this field focuses on embedding-based methods, often leveraging convolutional neural net architectures. These solutions act as black boxes, limiting insight. In this paper, we explore an extension to an established rule-based framework, TLogic, that yields a high accuracy in combination with explainable predictions. This offers transparency and allows the end-user to critically evaluate the rules applied at the end of the prediction stage. The new rule format incorporates entity category as a key component with the purpose of limiting rule application only to relevant entities. When categories are unknown for building the graph, we propose a data-driven method to generate them with an LLM-based approach. Additionally, we investigate the choice of aggregation method for scores of retrieved entities when performing category prediction.

---

### Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?

Authors: Teague McMillan, Gabriele Dominici, Martin Gjoreski, Marc Langheinrich
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24236v2

Large Language Models (LLMs) often produce explanations that do not faithfully reflect the factors driving their predictions. In healthcare settings, such unfaithfulness is especially problematic: explanations that omit salient clinical cues or mask spurious shortcuts can undermine clinician trust and lead to unsafe decision support. We study how inference and training-time choices shape explanation faithfulness, focusing on factors practitioners can control at deployment. We evaluate three LLMs (GPT-4.1-mini, LLaMA 70B, LLaMA 8B) on two datasets-BBQ (social bias) and MedQA (medical licensing questions), and manipulate the number and type of few-shot examples, prompting strategies, and training procedure. Our results show: (i) both the quantity and quality of few-shot examples significantly impact model faithfulness; (ii) faithfulness is sensitive to prompting design; (iii) the instruction-tuning phase improves measured faithfulness on MedQA. These findings offer insights into strategies for enhancing the interpretability and trustworthiness of LLMs in sensitive domains.

---

### PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling

Authors: Ai Jian, Jingqing Ruan, Xing Ma, Xiaoyun Zhang, Dailin Li, Weipeng Zhang, Ke Zeng, Xunliang Cai
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.24235v3

Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human preferences. Generative reward models (GRMs) provide greater interpretability than traditional scalar RMs, but they come with a critical trade-off: pairwise methods are hindered by a training-inference mismatch, while pointwise methods require expensive absolute annotations. To bridge this gap, we propose the Preference-aware Task-adaptive Reward Model (PaTaRM). Unlike prior approaches, PaTaRM enables robust pointwise training using readily available pairwise data via a novel Preference-Aware Reward (PAR) mechanism, eliminating the need for explicit rating labels. Furthermore, it incorporates a Task-Adaptive Rubric system that dynamically generates instance-specific criteria for precise evaluation. Extensive experiments demonstrate that PATRM achieves a 8.7% average improvement on RewardBench and RMBench across Qwen3-8B/14B models. Crucially, it boosts downstream RLHF performance by an average relative improvement of 13.6% across IFEval and InFoBench, validating its effectiveness for policy alignment. Our code is available at https://github.com/JaneEyre0530/PaTaRM.

---

### Sparse Optimistic Information Directed Sampling

Authors: Ludovic Schwartz, Hamish Flynn, Gergely Neu
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24234v1

Many high-dimensional online decision-making problems can be modeled as stochastic sparse linear bandits. Most existing algorithms are designed to achieve optimal worst-case regret in either the data-rich regime, where polynomial dependence on the ambient dimension is unavoidable, or the data-poor regime, where dimension-independence is possible at the cost of worse dependence on the number of rounds. In contrast, the sparse Information Directed Sampling (IDS) algorithm satisfies a Bayesian regret bound that has the optimal rate in both regimes simultaneously. In this work, we explore the use of Sparse Optimistic Information Directed Sampling (SOIDS) to achieve the same adaptivity in the worst-case setting, without Bayesian assumptions. Through a novel analysis that enables the use of a time-dependent learning rate, we show that SOIDS can optimally balance information and regret. Our results extend the theoretical guarantees of IDS, providing the first algorithm that simultaneously achieves optimal worst-case regret in both the data-rich and data-poor regimes. We empirically demonstrate the good performance of SOIDS.

---

### PRIVET: PRoximIty leakage detection Via Extreme value Theory

Authors: Antoine Szatkownik, Aurélien Decelle, Beatriz Seoane, Nicolas Béreux, Léo Planche, Guillaume Charpiat, Burak Yelmen, Flora Jay, Cyril Furtlehner
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24233v2

Deep generative models are often trained on sensitive data, such as genetic sequences, health data, or more broadly, any copyrighted, licensed or protected content. This raises critical concerns around privacy-preserving synthetic data, and more specifically around privacy leakage, an issue closely tied to overfitting. Existing proximity-based methods mostly assess privacy risk through global criteria, which quantify a model's overall behaviour but cannot attribute risk to an individual record. Sample-level outputs do exist but they are either uncalibrated, discontinuous, or blind to leakage occurring while the model is globally underfit, which limits their practical use. Using extreme value statistics on nearest-neighbor distances, we propose PRIVET, a generic sample-based, modality-agnostic algorithm that assigns an individual proximity leak score to each synthetic sample. These are evaluated under a chosen representation and distance, each synthetic sample being assigned a continuous score measuring how improbable its proximity to the training set is under a no-leakage model. We empirically demonstrate that PRIVET detects memorization and more subtle forms of proximity-based data leakage across diverse data modalities, including settings with very high dimensionality and limited sample sizes such as genetic data, and in underfitting regimes that overfitting-based diagnostics cannot reach by construction. Our analysis further shows that the representation bounds what any distance-based evaluation can detect, existing computer vision embeddings failing to yield perceptually meaningful distances for near-duplicate samples. Accordingly, a low score is evidence of leakage in the chosen metric, while its absence is not a certificate of privacy.

---

### Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy

Authors: Qing Zhao, Weijian Deng, Pengxu Wei, ZiYi Dong, Hannan Lu, Xiangyang Ji, Liang Lin
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24232v3

To improve detection robustness in adverse conditions (e.g., haze and low light), image restoration is commonly applied as a pre-processing step to enhance image quality for the detector. However, the functional mismatch between restoration and detection networks can introduce instability and hinder effective integration -- an issue that remains underexplored. We revisit this limitation through the lens of Lipschitz continuity, analyzing the functional differences between restoration and detection networks in both the input space and the parameter space. Our analysis shows that restoration networks perform smooth, continuous transformations, while object detectors operate with discontinuous decision boundaries, making them highly sensitive to minor perturbations. This mismatch introduces instability in traditional cascade frameworks, where even imperceptible noise from restoration is amplified during detection, disrupting gradient flow and hindering optimization. To address this, we propose Lipschitz-regularized object detection (LROD), a simple yet effective framework that integrates image restoration directly into the detector's feature learning, harmonizing the Lipschitz continuity of both tasks during training. We implement this framework as Lipschitz-regularized YOLO (LR-YOLO), extending seamlessly to existing YOLO detectors. Extensive experiments on haze and low-light benchmarks demonstrate that LR-YOLO consistently improves detection stability, optimization smoothness, and overall accuracy.

---

### Benchmarking Microsaccade Recognition with Event Cameras: A Novel Dataset and Evaluation

Authors: Waseem Shariff, Timothy Hanley, Maciej Stec, Hossein Javidnia, Peter Corcoran
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24231v1

Microsaccades are small, involuntary eye movements vital for visual perception and neural processing. Traditional microsaccade studies typically use eye trackers or frame-based analysis, which, while precise, are costly and limited in scalability and temporal resolution. Event-based sensing offers a high-speed, low-latency alternative by capturing fine-grained spatiotemporal changes efficiently. This work introduces a pioneering event-based microsaccade dataset to support research on small eye movement dynamics in cognitive computing. Using Blender, we render high-fidelity eye movement scenarios and simulate microsaccades with angular displacements from 0.5 to 2.0 degrees, divided into seven distinct classes. These are converted to event streams using v2e, preserving the natural temporal dynamics of microsaccades, with durations ranging from 0.25 ms to 2.25 ms. We evaluate the dataset using Spiking-VGG11, Spiking-VGG13, and Spiking-VGG16, and propose Spiking-VGG16Flow, an optical-flow-enhanced variant implemented in SpikingJelly. The models achieve around 90 percent average accuracy, successfully classifying microsaccades by angular displacement, independent of event count or duration. These results demonstrate the potential of spiking neural networks for fine motion recognition and establish a benchmark for event-based vision research. The dataset, code, and trained models will be publicly available at https://waseemshariff126.github.io/microsaccades/ .

---

### A comparison between joint and dual UKF implementations for state estimation and leak localization in water distribution networks

Authors: Luis Romero-Ben, Paul Irofti, Florin Stoican, Vicenç Puig
Published: 2025-10-28
Categories: eess.SY, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.24228v1

The sustainability of modern cities highly depends on efficient water distribution management, including effective pressure control and leak detection and localization. Accurate information about the network hydraulic state is therefore essential. This article presents a comparison between two data-driven state estimation methods based on the Unscented Kalman Filter (UKF), fusing pressure, demand and flow data for head and flow estimation. One approach uses a joint state vector with a single estimator, while the other uses a dual-estimator scheme. We analyse their main characteristics, discussing differences, advantages and limitations, and compare them theoretically in terms of accuracy and complexity. Finally, we show several estimation results for the L-TOWN benchmark, allowing to discuss their properties in a real implementation.

---

### HACK: Hallucinations Along Certainty and Knowledge Axes

Authors: Adi Simhi, Jonathan Herzig, Itay Itzhak, Dana Arad, Zorik Gekhman, Roi Reichart, Fazl Barez, Gabriel Stanovsky, Idan Szpektor, Yonatan Belinkov
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24222v1

Hallucinations in LLMs present a critical barrier to their reliable usage. Existing research usually categorizes hallucination by their external properties rather than by the LLMs' underlying internal properties. This external focus overlooks that hallucinations may require tailored mitigation strategies based on their underlying mechanism. We propose a framework for categorizing hallucinations along two axes: knowledge and certainty. Since parametric knowledge and certainty may vary across models, our categorization method involves a model-specific dataset construction process that differentiates between those types of hallucinations. Along the knowledge axis, we distinguish between hallucinations caused by a lack of knowledge and those occurring despite the model having the knowledge of the correct response. To validate our framework along the knowledge axis, we apply steering mitigation, which relies on the existence of parametric knowledge to manipulate model activations. This addresses the lack of existing methods to validate knowledge categorization by showing a significant difference between the two hallucination types. We further analyze the distinct knowledge and hallucination patterns between models, showing that different hallucinations do occur despite shared parametric knowledge. Turning to the certainty axis, we identify a particularly concerning subset of hallucinations where models hallucinate with certainty despite having the correct knowledge internally. We introduce a new evaluation metric to measure the effectiveness of mitigation methods on this subset, revealing that while some methods perform well on average, they fail disproportionately on these critical cases. Our findings highlight the importance of considering both knowledge and certainty in hallucination analysis and call for targeted mitigation approaches that consider the hallucination underlying factors.

---

### Closing Gaps: An Imputation Analysis of ICU Vital Signs

Authors: Alisher Turubayev, Anna Shopova, Fabian Lange, Mahmut Kamalak, Paul Mattes, Victoria Ayvasky, Bert Arnrich, Bjarne Pfitzner, Robin P. van de Water
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.24217v1

As more Intensive Care Unit (ICU) data becomes available, the interest in developing clinical prediction models to improve healthcare protocols increases. However, the lack of data quality still hinders clinical prediction using Machine Learning (ML). Many vital sign measurements, such as heart rate, contain sizeable missing segments, leaving gaps in the data that could negatively impact prediction performance. Previous works have introduced numerous time-series imputation techniques. Nevertheless, more comprehensive work is needed to compare a representative set of methods for imputing ICU vital signs and determine the best practice. In reality, ad-hoc imputation techniques that could decrease prediction accuracy, like zero imputation, are still used. In this work, we compare established imputation techniques to guide researchers in improving the performance of clinical prediction models by selecting the most accurate imputation technique. We introduce an extensible and reusable benchmark with currently 15 imputation and 4 amputation methods, created for benchmarking on major ICU datasets. We hope to provide a comparative basis and facilitate further ML development to bring more models into clinical practice.

---

### Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation

Authors: Fan Xu, Hao Wu, Kun Wang, Nan Wang, Qingsong Wen, Xian Wu, Wei Gong, Xibin Zhao
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24216v1

In dynamical system modeling, traditional numerical methods are limited by high computational costs, while modern data-driven approaches struggle with data scarcity and distribution shifts. To address these fundamental limitations, we first propose SPARK, a physics-guided quantitative augmentation plugin. Specifically, SPARK utilizes a reconstruction autoencoder to integrate physical parameters into a physics-rich discrete state dictionary. This state dictionary then acts as a structured dictionary of physical states, enabling the creation of new, physically-plausible training samples via principled interpolation in the latent space. Further, for downstream prediction, these augmented representations are seamlessly integrated with a Fourier-enhanced Graph ODE, a combination designed to robustly model the enriched data distribution while capturing long-term temporal dependencies. Extensive experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines, particularly in challenging out-of-distribution scenarios and data-scarce regimes, proving the efficacy of our physics-guided augmentation paradigm.

---

### Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery

Authors: Vishal Halder, Alexandre Reiffers-Masson, Abdeldjalil Aïssa-El-Bey, Gugan Thoppe
Published: 2025-10-28
Categories: cs.IT, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.24215v5

Recovery from linear measurements under sparse adversarial corruption is typically formulated as an exact-recovery problem: one seeks structural conditions on $\mathbf{A}$ (e.g., restricted isometry property) guaranteeing unique recovery of $\mathbf{x}^\star$ from $\mathbf{y} = \mathbf{A}\mathbf{x}^\star + \mathbf{e}$ with $\|\mathbf{e}\|_0 \leq q$. However, these guarantees provide no guidance once exact recovery fails. This limitation obscures simple robustness phenomena -- for instance, repeated rows in $\mathbf{A}$ can preserve nontrivial information about $\mathbf{x}^\star$ under sparse corruption. In this paper, we study what information about $\mathbf{x}^\star$ can be \emph{uniformly} recovered from $\mathbf{y} = \mathbf{A}\mathbf{x}^\star + \mathbf{e}$ for arbitrary $\mathbf{A}\in\mathbb{R}^{m\times n}$ and \emph{any} $q$-sparse $\mathbf{e}$. We show that the robust information is precisely $\mathbf{x}^\star + \ker(\mathbf{U})$, where $\mathbf{U}$ is the orthogonal projection onto the intersection of rowspaces of all submatrices of $\mathbf{A}$ obtained by deleting $2q$ rows. This clarifies how the row structure of $\mathbf{A}$ governs whether a $q$-sparse corruption allows exact, partial, or only trivial recovery. We further prove every $\mathbf{x}$ minimizing $\|\mathbf{y} - \mathbf{A} \mathbf{x}\|_0$ belongs to $\mathbf{x}^\star + \ker(\mathbf{U})$, yielding a constructive approach to recover this set. For i.i.d. Gaussian matrices, we establish a sharp phase transition between exact and trivial recovery. We sketch two applications: robust network tomography and signal reconstruction from oversampled DCT.

---

### SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs

Authors: Jinhong Deng, Wen Li, Joey Tianyi Zhou, Yang He
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24214v1

Multimodal Large Language Models (MLLMs) typically process a large number of visual tokens, leading to considerable computational overhead, even though many of these tokens are redundant. Existing visual token pruning methods primarily focus on selecting the most salient tokens based on attention scores, resulting in the semantic incompleteness of the selected tokens. In this paper, we propose a novel visual token pruning strategy, called \textbf{S}aliency-\textbf{C}overage \textbf{O}riented token \textbf{P}runing for \textbf{E}fficient MLLMs (SCOPE), to jointly model both the saliency and coverage of the selected visual tokens to better preserve semantic completeness. Specifically, we introduce a set-coverage for a given set of selected tokens, computed based on the token relationships. We then define a token-coverage gain for each unselected token, quantifying how much additional coverage would be obtained by including it. By integrating the saliency score into the token-coverage gain, we propose our SCOPE score and iteratively select the token with the highest SCOPE score. We conduct extensive experiments on multiple vision-language understanding benchmarks using the LLaVA-1.5 and LLaVA-Next models. Experimental results demonstrate that our method consistently outperforms prior approaches. Our code is available at \href{https://github.com/kinredon/SCOPE}{https://github.com/kinredon/SCOPE}.

---

### Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization

Authors: Haoxin Yang, Yihong Lin, Jingdan Kang, Xuemiao Xu, Yue Li, Cheng Xu, Shengfeng He
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24213v1

Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied post-training to suppress identity features. These interventions often introduce distribution shifts and entangle identity with non-identity attributes, degrading visual fidelity and data utility. To address this, we propose \textbf{ID\textsuperscript{2}Face}, a training-centric anonymization framework that removes the need for inference-time optimization. The rationale of our method is to learn a structured latent space where identity and non-identity information are explicitly disentangled, enabling direct and controllable anonymization at inference. To this end, we design a conditional diffusion model with an identity-masked learning scheme. An Identity-Decoupled Latent Recomposer uses an Identity Variational Autoencoder to model identity features, while non-identity attributes are extracted from same-identity pairs and aligned through bidirectional latent alignment. An Identity-Guided Latent Harmonizer then fuses these representations via soft-gating conditioned on noisy feature prediction. The model is trained with a recomposition-based reconstruction loss to enforce disentanglement. At inference, anonymization is achieved by sampling a random identity vector from the learned identity space. To further suppress identity leakage, we introduce an Orthogonal Identity Mapping strategy that enforces orthogonality between sampled and source identity vectors. Experiments demonstrate that ID\textsuperscript{2}Face outperforms existing methods in visual quality, identity suppression, and utility preservation.

---

### Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation

Authors: Junhyuk So, Hyunho Kook, Chaeyeon Jang, Eunhyeok Park
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24211v2

Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrained by the slow inference speed of per-token generation, which often requires thousands of steps to produce a single sample. While several Speculative Decoding (SD)-based methods have been proposed to solve this problem by generating multiple tokens in a single forward step, they suffer from limited speedup, degraded quality, or require the training of a draft model. To solve these problems, we propose a new training-free, lossless SD framework, Speculative Coupled Decoding (SCD), by extending the recently proposed Speculative Jacobi Decoding (SJD). While SJD shows strong potential for accelerating AR generation by combining Jacobi iteration and SD, we found that its acceptance rate is still significantly limited due to the instability arising from the independent sampling process used during draft token generation. To overcome this, we introduce an information-theoretic approach, Coupling, which stabilizes the drafting trajectory of SJD by maximizing the probability of sampling identical draft tokens across consecutive iterations, significantly enhancing the acceptance rate while preserving its lossless property. Remarkably, this method requires only a single-line modification to the existing algorithm with almost zero overhead, yet achieves substantial performance gains, delivering up to a 4.2x speedup in image generation and 13.6x speedup in video generation compared to standard AR decoding, without any degradation or the need for additional training. The source code is available at https://github.com/junhyukso/SCD

---

### Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment

Authors: Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
Published: 2025-10-28
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.24208v2

Language Models (LMs) encode substantial knowledge in their parameters, yet it remains unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A central challenge is to make cross-scale transfer effective and efficient when source and target models differ in architecture and parameterization, making direct parameter reuse strongly limited by neural incompatibility. In this paper, we identify latent semantic alignment as the key prerequisite for cross-scale knowledge transfer. Instead of directly moving layer parameters, our approach uses activations as the transfer medium. \textsc{SemAlign} has two stages: an \emph{layer attribution} stage that attributes task-relevant source layers and selects exactly one source layer for each target layer, and a \emph{semantic alignment} stage that pairs them layer by layer and optimizes the target with source-side semantic supervision. The alignment is carried out in latent space through semantic decomposition and recomposition. During the shallow-to-deep transfer, only the frontier target layer is trainable. The layer objective supervises the residual contribution of that layer by matching centered token-token relation geometry against an aligned supervisory residual, while output KL preserves source-level predictive behavior. The transferred medium is therefore neither a parameter block nor an absolute hidden state, but target-space residual geometry induced by paired source-layer supervision. Evaluations on four benchmarks demonstrate the efficacy of \textsc{SemAlign}, and further analysis confirms that semantic decomposition and recomposition provide a stable mechanism for cross-scale knowledge transfer.

---

### CLFSeg: A Fuzzy-Logic based Solution for Boundary Clarity and Uncertainty Reduction in Medical Image Segmentation

Authors: Anshul Kaushal, Kunal Jangid, Vinod K. Kurmi
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24202v1

Accurate polyp and cardiac segmentation for early detection and treatment is essential for the diagnosis and treatment planning of cancer-like diseases. Traditional convolutional neural network (CNN) based models have represented limited generalizability, robustness, and inability to handle uncertainty, which affects the segmentation performance. To solve these problems, this paper introduces CLFSeg, an encoder-decoder based framework that aggregates the Fuzzy-Convolutional (FC) module leveraging convolutional layers and fuzzy logic. This module enhances the segmentation performance by identifying local and global features while minimizing the uncertainty, noise, and ambiguity in boundary regions, ensuring computing efficiency. In order to handle class imbalance problem while focusing on the areas of interest with tiny and boundary regions, binary cross-entropy (BCE) with dice loss is incorporated. Our proposed model exhibits exceptional performance on four publicly available datasets, including CVC-ColonDB, CVC-ClinicDB, EtisLaribPolypDB, and ACDC. Extensive experiments and visual studies show CLFSeg surpasses the existing SOTA performance and focuses on relevant regions of interest in anatomical structures. The proposed CLFSeg improves performance while ensuring computing efficiency, which makes it a potential solution for real-world medical diagnostic scenarios. Project page is available at https://visdomlab.github.io/CLFSeg/

---

### SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning

Authors: Alexander Bakarsky, Dimitar I. Dimitrov, Maximilian Baader, Martin Vechev
Published: 2025-10-28
Categories: cs.LG, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2510.24200v1

Federated Learning has seen an increased deployment in real-world scenarios recently, as it enables the distributed training of machine learning models without explicit data sharing between individual clients. Yet, the introduction of the so-called gradient inversion attacks has fundamentally challenged its privacy-preserving properties. Unfortunately, as these attacks mostly rely on direct data optimization without any formal guarantees, the vulnerability of real-world systems remains in dispute and requires tedious testing for each new federated deployment. To overcome these issues, recently the SPEAR attack was introduced, which is based on a theoretical analysis of the gradients of linear layers with ReLU activations. While SPEAR is an important theoretical breakthrough, the attack's practicality was severely limited by its exponential runtime in the batch size b. In this work, we fill this gap by applying State-of-the-Art techniques from Sparsely-Used Dictionary Learning to make the problem of gradient inversion on linear layers with ReLU activations tractable. Our experiments demonstrate that our new attack, SPEAR++, retains all desirable properties of SPEAR, such as robustness to DP noise and FedAvg aggregation, while being applicable to 10x bigger batch sizes.

---

### Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2

Authors: Ziqi Zhou, Yifan Hu, Yufei Song, Zijing Li, Shengshan Hu, Leo Yu Zhang, Dezhong Yao, Long Zheng, Hai Jin
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24195v1

Recent studies reveal the vulnerability of the image segmentation foundation model SAM to adversarial examples. Its successor, SAM2, has attracted significant attention due to its strong generalization capability in video segmentation. However, its robustness remains unexplored, and it is unclear whether existing attacks on SAM can be directly transferred to SAM2. In this paper, we first analyze the performance gap of existing attacks between SAM and SAM2 and highlight two key challenges arising from their architectural differences: directional guidance from the prompt and semantic entanglement across consecutive frames. To address these issues, we propose UAP-SAM2, the first cross-prompt universal adversarial attack against SAM2 driven by dual semantic deviation. For cross-prompt transferability, we begin by designing a target-scanning strategy that divides each frame into k regions, each randomly assigned a prompt, to reduce prompt dependency during optimization. For effectiveness, we design a dual semantic deviation framework that optimizes a UAP by distorting the semantics within the current frame and disrupting the semantic consistency across consecutive frames. Extensive experiments on six datasets across two segmentation tasks demonstrate the effectiveness of the proposed method for SAM2. The comparative results show that UAP-SAM2 significantly outperforms state-of-the-art (SOTA) attacks by a large margin.

---

### Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames

Authors: Ev Zisselman, Mirco Mutti, Shelly Francis-Meretzki, Elisei Shafer, Aviv Tamar
Published: 2025-10-28
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.24194v1

Behavioral cloning is a simple yet effective technique for learning sequential decision-making from demonstrations. Recently, it has gained prominence as the core of foundation models for the physical world, where achieving generalization requires countless demonstrations of a multitude of tasks. Typically, a human expert with full information on the task demonstrates a (nearly) optimal behavior. In this paper, we propose to hide some of the task's information from the demonstrator. This ``blindfolded'' expert is compelled to employ non-trivial exploration to solve the task. We show that cloning the blindfolded expert generalizes better to unseen tasks than its fully-informed counterpart. We conduct experiments of real-world robot peg insertion tasks with (limited) human demonstrations, alongside videogames from the Procgen benchmark. Additionally, we support our findings with theoretical analysis, which confirms that the generalization error scales with $\sqrt{I/m}$, where $I$ measures the amount of task information available to the demonstrator, and $m$ is the number of demonstrated tasks. Both theory and practice indicate that cloning blindfolded experts generalizes better with fewer demonstrated tasks. Project page with videos and code: https://sites.google.com/view/blindfoldedexperts/home

---

### Self-Concordant Perturbations for Linear Bandits

Authors: Lucas Lévy, Jean-Lou Valeau, Arya Akhavan, Patrick Rebeschini
Published: 2025-10-28
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.24187v3

We consider the adversarial linear bandits setting and present a unified algorithmic framework that bridges Follow-the-Regularized-Leader (FTRL) and Follow-the-Perturbed-Leader (FTPL) methods, extending the known connection between them from the full-information setting. Within this framework, we introduce self-concordant perturbations, a family of probability distributions that mirror the role of self-concordant barriers previously employed in the FTRL-based SCRiBLe algorithm. Using this idea, we design a novel FTPL-based algorithm that combines self-concordant regularization with efficient stochastic exploration. Our approach achieves a regret of $\mathcal{O}(d\sqrt{n \ln n})$ on both the $d$-dimensional hypercube and the $\ell_2$ ball. On the $\ell_2$ ball, this matches the rate attained by SCRiBLe. For the hypercube, this represents a $\sqrt{d}$ improvement over these methods and matches the optimal bound up to logarithmic factors.

---

### V-SAT: Video Subtitle Annotation Tool

Authors: Arpita Kundu, Joyita Chakraborty, Anindita Desarkar, Aritra Sen, Srushti Anil Patil, Vishwanathan Raman
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24180v1

The surge of audiovisual content on streaming platforms and social media has heightened the demand for accurate and accessible subtitles. However, existing subtitle generation methods primarily speech-based transcription or OCR-based extraction suffer from several shortcomings, including poor synchronization, incorrect or harmful text, inconsistent formatting, inappropriate reading speeds, and the inability to adapt to dynamic audio-visual contexts. Current approaches often address isolated issues, leaving post-editing as a labor-intensive and time-consuming process. In this paper, we introduce V-SAT (Video Subtitle Annotation Tool), a unified framework that automatically detects and corrects a wide range of subtitle quality issues. By combining Large Language Models(LLMs), Vision-Language Models (VLMs), Image Processing, and Automatic Speech Recognition (ASR), V-SAT leverages contextual cues from both audio and video. Subtitle quality improved, with the SUBER score reduced from 9.6 to 3.54 after resolving all language mode issues and F1-scores of ~0.80 for image mode issues. Human-in-the-loop validation ensures high-quality results, providing the first comprehensive solution for robust subtitle annotation.

---

### Exploring the Influence of Relevant Knowledge for Natural Language Generation Interpretability

Authors: Iván Martínez-Murillo, Paloma Moreda, Elena Lloret
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24179v1

This paper explores the influence of external knowledge integration in Natural Language Generation (NLG), focusing on a commonsense generation task. We extend the CommonGen dataset by creating KITGI, a benchmark that pairs input concept sets with retrieved semantic relations from ConceptNet and includes manually annotated outputs. Using the T5-Large model, we compare sentence generation under two conditions: with full external knowledge and with filtered knowledge where highly relevant relations were deliberately removed. Our interpretability benchmark follows a three-stage method: (1) identifying and removing key knowledge, (2) regenerating sentences, and (3) manually assessing outputs for commonsense plausibility and concept coverage. Results show that sentences generated with full knowledge achieved 91\% correctness across both criteria, while filtering reduced performance drastically to 6\%. These findings demonstrate that relevant external knowledge is critical for maintaining both coherence and concept coverage in NLG. This work highlights the importance of designing interpretable, knowledge-enhanced NLG systems and calls for evaluation frameworks that capture the underlying reasoning beyond surface-level metrics.

---

### MuSaG: A Multimodal German Sarcasm Dataset with Full-Modal Annotations

Authors: Aaron Scott, Maike Züfle, Jan Niehues
Published: 2025-10-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.24178v2

Sarcasm is a complex form of figurative language in which the intended meaning contradicts the literal one. Its prevalence in social media and popular culture poses persistent challenges for natural language understanding, sentiment analysis, and content moderation. With the emergence of multimodal large language models, sarcasm detection extends beyond text and requires integrating cues from audio and vision. We present MuSaG, the first German multimodal sarcasm detection dataset, consisting of 33 minutes of manually selected and human-annotated statements from German television shows. Each instance provides aligned text, audio, and video modalities, annotated separately by humans, enabling evaluation in unimodal and multimodal settings. We benchmark nine open-source and commercial models, spanning text, audio, vision, and multimodal architectures, and compare their performance to human annotations. Our results show that while humans rely heavily on audio in conversational settings, models perform best on text. This highlights a gap in current multimodal models and motivates the use of MuSaG for developing models better suited to realistic scenarios. We release MuSaG publicly to support future research on multimodal sarcasm detection and human-model alignment.

---

### EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale

Authors: Yiheng Du, Aditi S. Krishnapriyan
Published: 2025-10-28
Categories: cs.LG, math.DS, math.NA, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.24173v1

Computationally resolving turbulence remains a central challenge in fluid dynamics due to its multi-scale interactions. Fully resolving large-scale turbulence through direct numerical simulation (DNS) is computationally prohibitive, motivating data-driven machine learning alternatives. In this work, we propose EddyFormer, a Transformer-based spectral-element (SEM) architecture for large-scale turbulence simulation that combines the accuracy of spectral methods with the scalability of the attention mechanism. We introduce an SEM tokenization that decomposes the flow into grid-scale and subgrid-scale components, enabling capture of both local and global features. We create a new three-dimensional isotropic turbulence dataset and train EddyFormer to achieves DNS-level accuracy at 256^3 resolution, providing a 30x speedup over DNS. When applied to unseen domains up to 4x larger than in training, EddyFormer preserves accuracy on physics-invariant metrics-energy spectra, correlation functions, and structure functions-showing domain generalization. On The Well benchmark suite of diverse turbulent flows, EddyFormer resolves cases where prior ML models fail to converge, accurately reproducing complex dynamics across a wide range of physical conditions.

---

### SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning

Authors: Hong Wang, Jie Wang, Minghao Ma, Haoran Shao, Haoyang Liu
Published: 2025-10-28
Categories: math.NA, cs.AI
arXiv: https://arxiv.org/abs/2510.24170v2

Matrix preconditioning is a critical technique to accelerate the solution of linear systems, where performance heavily depends on the selection of preconditioning parameters. Traditional parameter selection approaches often define fixed constants for specific scenarios. However, they rely on domain expertise and fail to consider the instance-wise features for individual problems, limiting their performance. In contrast, machine learning (ML) approaches, though promising, are hindered by high inference costs and limited interpretability. To combine the strengths of both approaches, we propose a symbolic discovery framework-namely, Symbolic Matrix Preconditioning (SymMaP)-to learn efficient symbolic expressions for preconditioning parameters. Specifically, we employ a neural network to search the high-dimensional discrete space for expressions that can accurately predict the optimal parameters. The learned expression allows for high inference efficiency and excellent interpretability (expressed in concise symbolic formulas), making it simple and reliable for deployment. Experimental results show that SymMaP consistently outperforms traditional strategies across various benchmarks.

---