# Research Papers — 2025-10 · bundle page 215 of 217

> Full-text markdown of papers #10701–10750 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/215
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/214.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/216.md)

### Unsupervised Unfolded rPCA (U2-rPCA): Deep Interpretable Clutter Filtering for Ultrasound Microvascular Imaging

Authors: Huaying Li, Chuling Ye, Manfei Liao, Xiaobo Qu, Liansheng Wang, Yinran Chen
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00660v2

High-sensitivity clutter filtering is a fundamental step in ultrasound microvascular imaging. Singular value decomposition (SVD) and robust principal component analysis (rPCA) are the main clutter filtering strategies. However, both strategies are limited in feature modeling and separation of tissue and blood flow for high-quality microvascular imaging. Recently, deep learning-based clutter filtering has shown potential in more thoroughly separating tissue and blood flow signals. However, the existing supervised filters face the lack of interpretability and the training ground truth. While the interpretability issue can be addressed by algorithm deep unfolding, the training ground truth remains unsolved. This paper proposes an unsupervised unfolded rPCA (U2-rPCA) method that preserves mathematical interpretability and is insusceptible to learning labels. Specifically, U2-rPCA is unfolded from an iteratively reweighted least squares (IRLS) rPCA baseline with intrinsic low-rank and sparse regularization. In addition, a sparse-enhancement unit is plugged into the network to strengthen its capability to capture the sparse micro-flow signals. U2-rPCA is like an adaptive filter that is trained with part of the image sequence and then used for the following frames. Experimental validations on a in-silico dataset and public in-vivo datasets demonstrated the outperformance of U2-rPCA when compared with the SVD filter, the rPCA baseline, and another deep learning-based filter. Particularly, the proposed method improved the contrast-to-noise ratio (CNR) of the power Doppler image by 1.91 dB to 8.48 dB compared to other methods. Furthermore, the effectiveness of the building modules of U2-rPCA was validated through ablation studies.

---

### Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

Authors: Beomsu Kim, Byunghee Cha, Jong Chul Ye
Published: 2025-10-01
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.00658v1

With diffusion and flow matching models achieving state-of-the-art generating performance, the interest of the community now turned to reducing the inference time without sacrificing sample quality. Consistency Models (CMs), which are trained to be consistent on diffusion or probability flow ordinary differential equation (PF-ODE) trajectories, enable one or two-step flow or diffusion sampling. However, CMs typically require prolonged training with large batch sizes to obtain competitive sample quality. In this paper, we examine the training dynamics of CMs near convergence and discover that CM tangents -- CM output update directions -- are quite oscillatory, in the sense that they move parallel to the data manifold, not towards the manifold. To mitigate oscillatory tangents, we propose a new loss function, called the manifold feature distance (MFD), which provides manifold-aligned tangents that point toward the data manifold. Consequently, our method -- dubbed Align Your Tangent (AYT) -- can accelerate CM training by orders of magnitude and even out-perform the learned perceptual image patch similarity metric (LPIPS). Furthermore, we find that our loss enables training with extremely small batch sizes without compromising sample quality. Code: https://github.com/1202kbs/AYT

---

### Weakly Supervised Cloud Detection Combining Spectral Features and Multi-Scale Deep Network

Authors: Shaocong Zhu, Zhiwei Li, Xinghua Li, Huanfeng Shen
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00654v1

Clouds significantly affect the quality of optical satellite images, which seriously limits their precise application. Recently, deep learning has been widely applied to cloud detection and has achieved satisfactory results. However, the lack of distinctive features in thin clouds and the low quality of training samples limit the cloud detection accuracy of deep learning methods, leaving space for further improvements. In this paper, we propose a weakly supervised cloud detection method that combines spectral features and multi-scale scene-level deep network (SpecMCD) to obtain highly accurate pixel-level cloud masks. The method first utilizes a progressive training framework with a multi-scale scene-level dataset to train the multi-scale scene-level cloud detection network. Pixel-level cloud probability maps are then obtained by combining the multi-scale probability maps and cloud thickness map based on the characteristics of clouds in dense cloud coverage and large cloud-area coverage images. Finally, adaptive thresholds are generated based on the differentiated regions of the scene-level cloud masks at different scales and combined with distance-weighted optimization to obtain binary cloud masks. Two datasets, WDCD and GF1MS-WHU, comprising a total of 60 Gaofen-1 multispectral (GF1-MS) images, were used to verify the effectiveness of the proposed method. Compared to the other weakly supervised cloud detection methods such as WDCD and WSFNet, the F1-score of the proposed SpecMCD method shows an improvement of over 7.82%, highlighting the superiority and potential of the SpecMCD method for cloud detection under different cloud coverage conditions.

---

### OTTER: Open-Tagging via Text-Image Representation for Multi-modal Understanding

Authors: Jieer Ouyang, Xiaoneng Xiang, Zheng Wang, Yangkai Ding
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00652v1

We introduce OTTER, a unified open-set multi-label tagging framework that harmonizes the stability of a curated, predefined category set with the adaptability of user-driven open tags. OTTER is built upon a large-scale, hierarchically organized multi-modal dataset, collected from diverse online repositories and annotated through a hybrid pipeline combining automated vision-language labeling with human refinement. By leveraging a multi-head attention architecture, OTTER jointly aligns visual and textual representations with both fixed and open-set label embeddings, enabling dynamic and semantically consistent tagging. OTTER consistently outperforms competitive baselines on two benchmark datasets: it achieves an overall F1 score of 0.81 on Otter and 0.75 on Favorite, surpassing the next-best results by margins of 0.10 and 0.02, respectively. OTTER attains near-perfect performance on open-set labels, with F1 of 0.99 on Otter and 0.97 on Favorite, while maintaining competitive accuracy on predefined labels. These results demonstrate OTTER's effectiveness in bridging closed-set consistency with open-vocabulary flexibility for multi-modal tagging applications.

---

### FIN: Fast Inference Network for Map Segmentation

Authors: Ruan Bispo, Tim Brophy, Reenu Mohandas, Anthony Scanlan, Ciarán Eising
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00651v1

Multi-sensor fusion in autonomous vehicles is becoming more common to offer a more robust alternative for several perception tasks. This need arises from the unique contribution of each sensor in collecting data: camera-radar fusion offers a cost-effective solution by combining rich semantic information from cameras with accurate distance measurements from radar, without incurring excessive financial costs or overwhelming data processing requirements. Map segmentation is a critical task for enabling effective vehicle behaviour in its environment, yet it continues to face significant challenges in achieving high accuracy and meeting real-time performance requirements. Therefore, this work presents a novel and efficient map segmentation architecture, using cameras and radars, in the \acrfull{bev} space. Our model introduces a real-time map segmentation architecture considering aspects such as high accuracy, per-class balancing, and inference time. To accomplish this, we use an advanced loss set together with a new lightweight head to improve the perception results. Our results show that, with these modifications, our approach achieves results comparable to large models, reaching 53.5 mIoU, while also setting a new benchmark for inference time, improving it by 260\% over the strongest baseline models.

---

### MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation

Authors: Jinlan Fu, Shenzhen Huangfu, Hao Fei, Yichong Huang, Xiaoyu Shen, Xipeng Qiu, See-Kiong Ng
Published: 2025-10-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.00647v1

The alt-text generation task produces concise, context-relevant descriptions of images, enabling blind and low-vision users to access online images. Despite the capabilities of large vision-language models, alt-text generation performance remains limited due to noisy user annotations, inconsistent standards, and MLLMs' insensitivity to contextual information. Previous efforts to fine-tune MLLMs using supervised fine-tuning (SFT) have struggled, as SFT relies on accurate target annotations, which are often flawed in user-generated alt-text. To address this, we propose Multi-faceted Cross-modal Direct Preference Optimization (MCM-DPO), which improves alt-text generation by learning to identify better options in preference pairs without requiring precise annotations. MCM-DPO optimizes preferences across single, paired, and multi-preference dimensions, covering textual, visual, and cross-modal factors. In light of the scarcity of high-quality annotated and preference-labeled datasets for alt-text, we constructed two large-scale, high-quality datasets named TAlt and PAlt, sourced from Twitter and Pinterest. These datasets include 202k annotated alt-text samples and 18k preference pairs that cover diverse preference dimensions, aiming to support further research in this domain. Experimental results show that our proposed MCM-DPO method consistently outperforms both DPO and SFT, establishing a new state of the art in alt-text generation. We release the code and data here: https://github.com/LVUGAI/MCM-DPO

---

### Error Feedback for Muon and Friends

Authors: Kaja Gruntkowska, Alexander Gaponov, Zhirayr Tovmasyan, Peter Richtárik
Published: 2025-10-01
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2510.00643v1

Recent optimizers like Muon, Scion, and Gluon have pushed the frontier of large-scale deep learning by exploiting layer-wise linear minimization oracles (LMOs) over non-Euclidean norm balls, capturing neural network structure in ways traditional algorithms cannot. Yet, no principled distributed framework exists for these methods, and communication bottlenecks remain unaddressed. The very few distributed variants are heuristic, with no convergence guarantees in sight. We introduce EF21-Muon, the first communication-efficient, non-Euclidean LMO-based optimizer with rigorous convergence guarantees. EF21-Muon supports stochastic gradients, momentum, and bidirectional compression with error feedback-marking the first extension of error feedback beyond the Euclidean setting. It recovers Muon/Scion/Gluon when compression is off and specific norms are chosen, providing the first efficient distributed implementation of this powerful family. Our theory covers non-Euclidean smooth and the more general $(L^0, L^1)$-smooth setting, matching best-known Euclidean rates and enabling faster convergence under suitable norm choices. We further extend the analysis to layer-wise (generalized) smoothness regimes, capturing the anisotropic structure of deep networks. Experiments on NanoGPT benchmarking EF21-Muon against uncompressed Muon/Scion/Gluon demonstrate up to $7\times$ communication savings with no accuracy degradation.

---

### Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution

Authors: Alessio Devoto, Maximilian Jeblick, Simon Jégou
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.00636v1

Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-score-based KV cache pruning shows promise, it faces critical practical limitations: attention scores from future tokens are unavailable during compression, and modern implementations like Flash Attention do not materialize the full attention matrix, making past scores inaccessible. To overcome these challenges, we introduce $\textbf{Expected Attention, a training-free compression method}$ that estimates KV pairs importance by predicting how future queries will attend to them. Our approach leverages the distributional properties of LLM activations to compute expected attention scores in closed form for each KV pair. These scores enable principled ranking and pruning of KV pairs with minimal impact on the residual stream, achieving effective compression without performance degradation. Importantly, our method operates seamlessly across both prefilling and decoding phases, consistently outperforming state-of-the-art baselines in both scenarios. Finally, $\textbf{we release KVPress, a comprehensive library to enable researchers to implement and benchmark KV cache compression methods, already including more than 20 techniques}$.

---

### Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack

Authors: Nanxiang Jiang, Zhaoxin Fan, Enhan Kang, Daiheng Gao, Yun Zhou, Yanxia Chang, Zheng Zhu, Yeying Jin, Wenjun Wu
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00635v5

Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to produce harmful or undesirable content. While concept erasure has been explored as a mitigation strategy, most existing approaches and corresponding attack evaluations are tailored to Stable Diffusion (SD) and exhibit limited effectiveness when transferred to next-generation rectified flow transformers such as Flux. In this work, we present ReFlux, the first concept attack method specifically designed to assess the robustness of concept erasure in the latest rectified flow-based T2I framework. Our approach is motivated by the observation that existing concept erasure techniques, when applied to Flux, fundamentally rely on a phenomenon known as attention localization. Building on this insight, we propose a simple yet effective attack strategy that specifically targets this property. At its core, a reverse-attention optimization strategy is introduced to effectively reactivate suppressed signals while stabilizing attention. This is further reinforced by a velocity-guided dynamic that enhances the robustness of concept reactivation by steering the flow matching process, and a consistency-preserving objective that maintains the global layout and preserves unrelated content. Extensive experiments consistently demonstrate the effectiveness and efficiency of the proposed attack method, establishing a reliable benchmark for evaluating the robustness of concept erasure strategies in rectified flow transformers.

---

### LAKAN: Landmark-assisted Adaptive Kolmogorov-Arnold Network for Face Forgery Detection

Authors: Jiayao Jiang, Bin Liu, Qi Chu, Nenghai Yu
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00634v3

The rapid development of deepfake generation techniques necessitates robust face forgery detection algorithms. While methods based on Convolutional Neural Networks (CNNs) and Transformers are effective, there is still room for improvement in modeling the highly complex and non-linear nature of forgery artifacts. To address this issue, we propose a novel detection method based on the Kolmogorov-Arnold Network (KAN). By replacing fixed activation functions with learnable splines, our KAN-based approach is better suited to this challenge. Furthermore, to guide the network's focus towards critical facial areas, we introduce a Landmark-assisted Adaptive Kolmogorov-Arnold Network (LAKAN) module. This module uses facial landmarks as a structural prior to dynamically generate the internal parameters of the KAN, creating an instance-specific signal that steers a general-purpose image encoder towards the most informative facial regions with artifacts. This core innovation creates a powerful combination between geometric priors and the network's learning process. Extensive experiments on multiple public datasets show that our proposed method achieves superior performance.

---

### Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset

Authors: Yannick Hauri, Luca A. Lanzendörfer, Till Aczel
Published: 2025-10-01
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.00633v1

Fashion image generation has so far focused on narrow tasks such as virtual try-on, where garments appear in clean studio environments. In contrast, editorial fashion presents garments through dynamic poses, diverse locations, and carefully crafted visual narratives. We introduce the task of virtual fashion photo-shoot, which seeks to capture this richness by transforming standardized garment images into contextually grounded editorial imagery. To enable this new direction, we construct the first large-scale dataset of garment-lookbook pairs, bridging the gap between e-commerce and fashion media. Because such pairs are not readily available, we design an automated retrieval pipeline that aligns garments across domains, combining visual-language reasoning with object-level localization. We construct a dataset with three garment-lookbook pair accuracy levels: high quality (10,000 pairs), medium quality (50,000 pairs), and low quality (300,000 pairs). This dataset offers a foundation for models that move beyond catalog-style generation and toward fashion imagery that reflects creativity, atmosphere, and storytelling.

---

### Tenyidie Syllabification corpus creation and deep learning applications

Authors: Teisovi Angami, Kevisino Khate
Published: 2025-10-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.00629v2

The Tenyidie language is a low-resource language of the Tibeto-Burman family spoken by the Tenyimia Community of Nagaland in the north-eastern part of India and is considered a major language in Nagaland. It is tonal, Subject-Object-Verb, and highly agglutinative in nature. Being a low-resource language, very limited research on Natural Language Processing (NLP) has been conducted. To the best of our knowledge, no work on syllabification has been reported for this language. Among the many NLP tasks, syllabification or syllabication is an important task in which the given word syllables are identified. The contribution of this work is the creation of 10,120 syllabified Tenyidie words and the application of the Deep Learning techniques on the created corpus. In this paper, we have applied LSTM, BLSTM, BLSTM+CRF, and Encoder-decoder deep learning architectures on our created dataset. In our dataset split of 80:10:10 (train:validation:test) set, we achieved the highest accuracy of 99.21% with BLSTM model on the test set. This work will find its application in numerous other NLP applications, such as morphological analysis, part-of-speech tagging, machine translation, etc, for the Tenyidie Language. Keywords: Tenyidie; NLP; syllabification; deep learning; LSTM; BLSTM; CRF; Encoder-decoder

---

### Hearing the Order: Investigating Position Bias in Large Audio-Language Models

Authors: Yu-Xiang Lin, Chen-An Li, Sheng-Lun Wei, Po-Chun Chen, Hsin-Hsi Chen, Hung-yi Lee
Published: 2025-10-01
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2510.00628v3

Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their predictions are influenced by the order of answer choices, which would indicate a form of position bias and undermine their reliability. In this paper, we identify and analyze this problem in LALMs. We demonstrate that no model is immune to this bias through extensive experiments on six LALMs across three widely used benchmarks and their spoken counterparts. Shuffling the order of answer options can cause performance fluctuations of up to 24% and even change model rankings, raising concerns about the reliability of current evaluation practices. We also study permutation-based strategies and show that they can mitigate bias in most cases. Our work represents the first systematic investigation of this issue in LALMs, and we hope it raises awareness and motivates further research in this direction.

---

### Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory Prediction

Authors: Bingzhang Wang, Kehua Chen, Yinhai Wang
Published: 2025-10-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.00627v1

Trajectory prediction is a fundamental task in Autonomous Vehicles (AVs) and Intelligent Transportation Systems (ITS), supporting efficient motion planning and real-time traffic safety management. Diffusion models have recently demonstrated strong performance in probabilistic trajectory prediction, but their large model size and slow sampling process hinder real-world deployment. This paper proposes Collaborative-Distilled Diffusion Models (CDDM), a novel method for real-time and lightweight trajectory prediction. Built upon Collaborative Progressive Distillation (CPD), CDDM progressively transfers knowledge from a high-capacity teacher diffusion model to a lightweight student model, jointly reducing both the number of sampling steps and the model size across distillation iterations. A dual-signal regularized distillation loss is further introduced to incorporate guidance from both the teacher and ground-truth data, mitigating potential overfitting and ensuring robust performance. Extensive experiments on the ETH-UCY pedestrian benchmark and the nuScenes vehicle benchmark demonstrate that CDDM achieves state-of-the-art prediction accuracy. The well-distilled CDDM retains 96.2% and 95.5% of the baseline model's ADE and FDE performance on pedestrian trajectories, while requiring only 231K parameters and 4 or 2 sampling steps, corresponding to 161x compression, 31x acceleration, and 9 ms latency. Qualitative results further show that CDDM generates diverse and accurate trajectories under dynamic agent behaviors and complex social interactions. By bridging high-performing generative models with practical deployment constraints, CDDM enables resource-efficient probabilistic prediction for AVs and ITS. Code is available at https://github.com/bingzhangw/CDDM.

---

### When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models

Authors: Chen-An Li, Tzu-Han Lin, Hung-yi Lee
Published: 2025-10-01
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2510.00626v3

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds, affects text reasoning tasks where audio is unnecessary. Across three text-based benchmarks, we find that even non-informative audio reduces accuracy and increases prediction volatility; the severity of interference scales with longer durations, higher amplitudes, and elevated decoding temperatures. Silence, often assumed neutral, destabilizes outputs as strongly as synthetic noise. While larger models show greater resilience, vulnerabilities persist across all evaluated systems. We further test mitigation strategies and find that prompting shows limited effectiveness, whereas self-consistency improves stability at the cost of increased computation. Our results reveal cross-modal interference as a key robustness challenge and highlight the need for efficient fusion strategies that preserve reasoning performance in the presence of irrelevant inputs.

---

### Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundation

Authors: Wei Liu, Haomei Xu, Bingqing Liu, Zhiying Deng, Haozhao Wang, Jun Wang, Ruixuan Li, Yee Whye Teh, Wee Sun Lee
Published: 2025-10-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.00625v1

Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a promising paradigm: by precisely editing a small subset of parameters such that a specific fact is updated while preserving other knowledge. Despite its great success reported in previous papers, we find the apparent reliability of editing rests on a fragile foundation and the current literature is largely driven by illusory success. The fundamental goal of steering the model's output toward a target with minimal modification would encourage exploiting hidden shortcuts, rather than utilizing real semantics. This problem directly challenges the feasibility of the current model editing literature at its very foundation, as shortcuts are inherently at odds with robust knowledge integration. Coincidentally, this issue has long been obscured by evaluation frameworks that lack the design of negative examples. To uncover it, we systematically develop a suite of new evaluation methods. Strikingly, we find that state-of-the-art approaches collapse even under the simplest negation queries. Our empirical evidence shows that editing is likely to be based on shortcuts rather than full semantics, calling for an urgent reconsideration of the very basis of model editing before further advancements can be meaningfully pursued.

---

### UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs

Authors: Mengfei Xia, Nan Xue, Jiapeng Zhu, Yujun Shen
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00624v1

Adversarial training turns out to be the key to one-step generation, especially for Generative Adversarial Network (GAN) and diffusion model distillation. Yet in practice, GAN training hardly converges properly and struggles in mode collapse. In this work, we quantitatively analyze the extent of Nash equilibrium in GAN training, and conclude that redundant shortcuts by inputting condition in $D$ disables meaningful knowledge extraction. We thereby propose to employ an unconditional discriminator (UCD), in which $D$ is enforced to extract more comprehensive and robust features with no condition injection. In this way, $D$ is able to leverage better knowledge to supervise $G$, which promotes Nash equilibrium in GAN literature. Theoretical guarantee on compatibility with vanilla GAN theory indicates that UCD can be implemented in a plug-in manner. Extensive experiments confirm the significant performance improvements with high efficiency. For instance, we achieved \textbf{1.47 FID} on the ImageNet-64 dataset, surpassing StyleGAN-XL and several state-of-the-art one-step diffusion models. The code will be made publicly available.

---

### FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression

Authors: Yifei Gao, Yong Chen, Chen Zhang
Published: 2025-10-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.00621v1

Functional data play a pivotal role across science and engineering, yet their infinite-dimensional nature makes representation learning challenging. Conventional statistical models depend on pre-chosen basis expansions or kernels, limiting the flexibility of data-driven discovery, while many deep-learning pipelines treat functions as fixed-grid vectors, ignoring inherent continuity. In this paper, we introduce Functional Attention with a Mixture-of-Experts (FAME), an end-to-end, fully data-driven framework for function-on-function regression. FAME forms continuous attention by coupling a bidirectional neural controlled differential equation with MoE-driven vector fields to capture intra-functional continuity, and further fuses change to inter-functional dependencies via multi-head cross attention. Extensive experiments on synthetic and real-world functional-regression benchmarks show that FAME achieves state-of-the-art accuracy, strong robustness to arbitrarily sampled discrete observations of functions.

---

### HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation

Authors: Rosni Vasu, Peter Jansen, Pao Siangliulue, Cristina Sarasua, Abraham Bernstein, Peter Clark, Bhavana Dalvi Mishra
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.00620v1

While there has been a surge of interest in automated scientific discovery (ASD), especially with the emergence of LLMs, it remains challenging for tools to generate hypotheses that are both testable and grounded in the scientific literature. Additionally, existing ideation tools are not adaptive to prior experimental outcomes. We developed HARPA to address these challenges by incorporating the ideation workflow inspired by human researchers. HARPA first identifies emerging research trends through literature mining, then explores hypothesis design spaces, and finally converges on precise, testable hypotheses by pinpointing research gaps and justifying design choices. Our evaluations show that HARPA-generated hypothesis-driven research proposals perform comparably to a strong baseline AI-researcher across most qualitative dimensions (e.g., specificity, novelty, overall quality), but achieve significant gains in feasibility(+0.78, p$<0.05$, bootstrap) and groundedness (+0.85, p$<0.01$, bootstrap) on a 10-point Likert scale. When tested with the ASD agent (CodeScientist), HARPA produced more successful executions (20 vs. 11 out of 40) and fewer failures (16 vs. 21 out of 40), showing that expert feasibility judgments track with actual execution success. Furthermore, to simulate how researchers continuously refine their understanding of what hypotheses are both testable and potentially interesting from experience, HARPA learns a reward model that scores new hypotheses based on prior experimental outcomes, achieving approx. a 28\% absolute gain over HARPA's untrained baseline scorer. Together, these methods represent a step forward in the field of AI-driven scientific discovery.

---

### What Did I Learn? Operational Competence Assessment for AI-Based Trajectory Planners

Authors: Michiel Braat, Maren Buermann, Marijke van Weperen, Jan-Pieter Paardekooper
Published: 2025-10-01
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.00619v1

Automated driving functions increasingly rely on machine learning for tasks like perception and trajectory planning, requiring large, relevant datasets. The performance of these algorithms depends on how closely the training data matches the task. To ensure reliable functioning, it is crucial to know what is included in the dataset to assess the trained model's operational risk. We aim to enhance the safe use of machine learning in automated driving by developing a method to recognize situations that an automated vehicle has not been sufficiently trained on. This method also improves explainability by describing the dataset at a human-understandable level. We propose modeling driving data as knowledge graphs, representing driving scenes with entities and their relationships. These graphs are queried for specific sub-scene configurations to check their occurrence in the dataset. We estimate a vehicle's competence in a driving scene by considering the coverage and complexity of sub-scene configurations in the training set. Higher complexity scenes require greater coverage for high competence. We apply this method to the NuPlan dataset, modeling it with knowledge graphs and analyzing the coverage of specific driving scenes. This approach helps monitor the competence of machine learning models trained on the dataset, which is essential for trustworthy AI to be deployed in automated driving.

---

### Robust Context-Aware Object Recognition

Authors: Klara Janouskova, Cristian Gavrus, Jiri Matas
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00618v1

In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended over-reliance on the BG, known as shortcut learning of spurious correlations, limiting model robustness in real-world deployment settings. In the literature, the problem is mainly addressed by suppressing the BG, sacrificing context information for improved generalization. We propose RCOR -- Robust Context-Aware Object Recognition -- the first approach that jointly achieves robustness and context-awareness without compromising either. RCOR treats localization as an integral part of recognition to decouple object-centric and context-aware modelling, followed by a robust, non-parametric fusion. It improves the performance of both supervised models and VLM on datasets with both in-domain and out-of-domain BG, even without fine-tuning. The results confirm that localization before recognition is now possible even in complex scenes as in ImageNet-1k.

---

### ACON: Optimizing Context Compression for Long-horizon LLM Agents

Authors: Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin A. Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, Saravan Rajmohan
Published: 2025-10-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.00615v3

Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observations. However, the resulting unbounded context growth in long-horizon agentic tasks makes two critical bottlenecks: prohibitive inference memory costs and reasoning degradation due to irrelevant information. Existing compression methods fail to fully address this, often relying on brittle heuristics or requiring parameter updates impractical for proprietary or large-scale LLMs. We introduce Agent Context Optimization (ACON), a unified framework that optimally compresses both observations and history into concise, informative representations. Distinct from prior works, ACON employs an optimization in natural language space: it iteratively refines compression guidelines based on failure analysis of the agent, ensuring critical state information is preserved without model fine-tuning. To further minimize computational overhead, we distill the optimized compressor into smaller models. Experiments on AppWorld, OfficeBench, and Multi-objective QA demonstrate that ACON reduces peak token usage by 26-54% while improving task success over existing compression baselines. Notably, it enables smaller LMs to function effectively as long-horizon agents, achieving up to 46% performance improvement by mitigating context distraction. Our code is available at https://github.com/microsoft/acon.

---

### Disentangling Foreground and Background for vision-Language Navigation via Online Augmentation

Authors: Yunbo Xu, Xuesong Zhang, Jia Li, Zhenzhen Hu, Richang Hong
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00604v1

Following language instructions, vision-language navigation (VLN) agents are tasked with navigating unseen environments. While augmenting multifaceted visual representations has propelled advancements in VLN, the significance of foreground and background in visual observations remains underexplored. Intuitively, foreground regions provide semantic cues, whereas the background encompasses spatial connectivity information. Inspired on this insight, we propose a Consensus-driven Online Feature Augmentation strategy (COFA) with alternative foreground and background features to facilitate the navigable generalization. Specifically, we first leverage semantically-enhanced landmark identification to disentangle foreground and background as candidate augmented features. Subsequently, a consensus-driven online augmentation strategy encourages the agent to consolidate two-stage voting results on feature preferences according to diverse instructions and navigational locations. Experiments on REVERIE and R2R demonstrate that our online foreground-background augmentation boosts the generalization of baseline and attains state-of-the-art performance.

---

### LVLMs as inspectors: an agentic framework for category-level structural defect annotation

Authors: Sheng Jiang, Yuanmin Ning, Bingxi Huang, Peiyin Chen, Zhaohui Chen
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00603v1

Automated structural defect annotation is essential for ensuring infrastructure safety while minimizing the high costs and inefficiencies of manual labeling. A novel agentic annotation framework, Agent-based Defect Pattern Tagger (ADPT), is introduced that integrates Large Vision-Language Models (LVLMs) with a semantic pattern matching module and an iterative self-questioning refinement mechanism. By leveraging optimized domain-specific prompting and a recursive verification process, ADPT transforms raw visual data into high-quality, semantically labeled defect datasets without any manual supervision. Experimental results demonstrate that ADPT achieves up to 98% accuracy in distinguishing defective from non-defective images, and 85%-98% annotation accuracy across four defect categories under class-balanced settings, with 80%-92% accuracy on class-imbalanced datasets. The framework offers a scalable and cost-effective solution for high-fidelity dataset construction, providing strong support for downstream tasks such as transfer learning and domain adaptation in structural damage assessment.

---

### Multi-Agent Stage-wise Conservative Linear Bandits

Authors: Amirhossein Afsharrad, Ahmadreza Moradipari, Sanjay Lall
Published: 2025-10-01
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.00602v3

In many real-world applications such as recommendation systems, multiple learning agents must balance exploration and exploitation while maintaining safety guarantees to avoid catastrophic failures. We study the stochastic linear bandit problem in a multi-agent networked setting where agents must satisfy stage-wise conservative constraints. A network of $N$ agents collaboratively maximizes cumulative reward while ensuring that the expected reward at every round is no less than $(1-α)$ times that of a baseline policy. Each agent observes local rewards with unknown parameters, but the network optimizes for the global parameter (average of local parameters). Agents communicate only with immediate neighbors, and each communication round incurs additional regret. We propose MA-SCLUCB (Multi-Agent Stage-wise Conservative Linear UCB), an episodic algorithm alternating between action selection and consensus-building phases. We prove that MA-SCLUCB achieves regret $\tilde{O}\left(\frac{d}{\sqrt{N}}\sqrt{T}\cdot\frac{\log(NT)}{\sqrt{\log(1/|λ_2|)}}\right)$ with high probability, where $d$ is the dimension, $T$ is the horizon, and $|λ_2|$ is the network's second largest eigenvalue magnitude. Our analysis shows: (i) collaboration yields $\frac{1}{\sqrt{N}}$ improvement despite local communication, (ii) communication overhead grows only logarithmically for well-connected networks, and (iii) stage-wise safety adds only lower-order regret. Thus, distributed learning with safety guarantees achieves near-optimal performance in reasonably connected networks.

---

### Hybrid Training for Vision-Language-Action Models

Authors: Pietro Mazzaglia, Cansu Sancaktar, Markus Peschl, Daniel Dijkman
Published: 2025-10-01
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.00600v2

Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language tasks. In robotics, similar embodied CoT strategies, generating thoughts before actions, have also been shown to lead to improved performance when using Vision-Language-Action models (VLAs). As these techniques increase the length of the model's generated outputs to include the thoughts, the inference time is negatively affected. Delaying an agent's actions in real-world executions, as in robotic manipulation settings, strongly affects the usability of a method, as tasks require long sequences of actions. However, is the generation of long chains-of-thought a strong prerequisite for achieving performance improvements? In this work, we explore the idea of Hybrid Training (HyT), a framework that enables VLAs to learn from thoughts and benefit from the associated performance gains, while enabling the possibility to leave out CoT generation during inference. Furthermore, by learning to conditionally predict a diverse set of outputs, HyT supports flexibility at inference time, enabling the model to either predict actions directly, generate thoughts or follow instructions. We evaluate the proposed method in a series of simulated benchmarks and real-world experiments.

---

### Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport

Authors: Ahmad-Reza Ehyaei, Golnoosh Farnadi, Samira Samadi
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.00599v1

Distributionally robust optimization tackles out-of-sample issues like overfitting and distribution shifts by adopting an adversarial approach over a range of possible data distributions, known as the ambiguity set. To balance conservatism and accuracy, these sets must include realistic probability distributions by leveraging information from the nominal distribution. Assuming that nominal distributions arise from a structural causal model with a directed acyclic graph $\mathcal{G}$ and structural equations, previous methods such as adapted and $\mathcal{G}$-causal optimal transport have only utilized causal graph information in designing ambiguity sets. In this work, we propose incorporating structural equations, which include causal graph information, to enhance ambiguity sets, resulting in more realistic distributions. We introduce structural causal optimal transport and its associated ambiguity set, demonstrating their advantages and connections to previous methods. A key benefit of our approach is a relaxed version, where a regularization term replaces the complex causal constraints, enabling an efficient algorithm via difference-of-convex programming to solve structural causal optimal transport. We also show that when structural information is absent and must be estimated, our approach remains effective and provides finite sample guarantees. Lastly, we address the radius of ambiguity sets, illustrating how our method overcomes the curse of dimensionality in optimal transport problems, achieving faster shrinkage with dimension-free order.

---

### Probability calibration for precipitation nowcasting

Authors: Lauri Kurki, Yaniel Cabrera, Samu Karanko
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.00594v2

Reliable precipitation nowcasting is critical for weather-sensitive decision-making, yet neural weather models (NWMs) can produce poorly calibrated probabilistic forecasts. Standard calibration metrics such as the expected calibration error (ECE) fail to capture miscalibration across precipitation thresholds. We introduce the expected thresholded calibration error (ETCE), a new metric that better captures miscalibration in ordered classes like precipitation amounts. We extend post-processing techniques from computer vision to the forecasting domain. Our results show that selective scaling with lead time conditioning reduces model miscalibration without reducing the forecast quality.

---

### Multi-level Dynamic Style Transfer for NeRFs

Authors: Zesheng Li, Shuaibo Li, Wei Ma, Jianwei Guo, Hongbin Zha
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00592v1

As the application of neural radiance fields (NeRFs) in various 3D vision tasks continues to expand, numerous NeRF-based style transfer techniques have been developed. However, existing methods typically integrate style statistics into the original NeRF pipeline, often leading to suboptimal results in both content preservation and artistic stylization. In this paper, we present multi-level dynamic style transfer for NeRFs (MDS-NeRF), a novel approach that reengineers the NeRF pipeline specifically for stylization and incorporates an innovative dynamic style injection module. Particularly, we propose a multi-level feature adaptor that helps generate a multi-level feature grid representation from the content radiance field, effectively capturing the multi-scale spatial structure of the scene. In addition, we present a dynamic style injection module that learns to extract relevant style features and adaptively integrates them into the content patterns. The stylized multi-level features are then transformed into the final stylized view through our proposed multi-level cascade decoder. Furthermore, we extend our 3D style transfer method to support omni-view style transfer using 3D style references. Extensive experiments demonstrate that MDS-NeRF achieves outstanding performance for 3D style transfer, preserving multi-scale spatial structures while effectively transferring stylistic characteristics.

---

### AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation

Authors: Liyi Cai, Yijie Ren, Yitong Zhang, Jia Li
Published: 2025-10-01
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.00591v1

Software automation has long been a central goal of software engineering, striving for software development that proceeds without human intervention. Recent efforts have leveraged Artificial Intelligence (AI) to advance software automation with notable progress. However, current AI functions primarily as assistants to human developers, leaving software development still dependent on explicit human intervention. This raises a fundamental question: Can AI move beyond its role as an assistant to become a core component of software, thereby enabling genuine software automation? To investigate this vision, we introduce AI-Driven Self-Evolving Software, a new form of software that evolves continuously through direct interaction with users. We demonstrate the feasibility of this idea with a lightweight prototype built on a multi-agent architecture that autonomously interprets user requirements, generates and validates code, and integrates new functionalities. Case studies across multiple representative scenarios show that the prototype can reliably construct and reuse functionality, providing early evidence that such software systems can scale to more sophisticated applications and pave the way toward truly automated software development. We make code and cases in this work publicly available at https://anonymous.4open.science/r/live-software.

---

### Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

Authors: Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen
Published: 2025-10-01
Categories: cs.LG, cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2510.00586v3

Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase. We introduce Eyes-on-Me, a modular attack that decomposes an adversarial document into reusable **Attention Attractors** and **Focus Regions**. Attractors are optimized to direct attention to the Focus Region. Attackers can then insert semantic baits for the retriever or malicious instructions for the generator, adapting to new targets at near zero cost. This is achieved by steering a small subset of attention heads that we empirically identify as strongly correlated with attack success. Across 18 end-to-end RAG settings (3 datasets $\times$ 2 retrievers $\times$ 3 generators), Eyes-on-Me raises average attack success rates from 21.9 to 57.8 (+35.9 points, 2.6$\times$ over prior work). A single optimized attractor transfers to unseen black box retrievers and generators without retraining. Our findings establish a scalable paradigm for RAG data poisoning and show that modular, reusable components pose a practical threat to modern AI systems. They also contribute to interpretability research by revealing a strong link between attention concentration and model outputs.

---

### U-DFA: A Unified DINOv2-Unet with Dual Fusion Attention for Multi-Dataset Medical Segmentation

Authors: Zulkaif Sajjad, Furqan Shaukat, Junaid Mir
Published: 2025-10-01
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.00585v1

Accurate medical image segmentation plays a crucial role in overall diagnosis and is one of the most essential tasks in the diagnostic pipeline. CNN-based models, despite their extensive use, suffer from a local receptive field and fail to capture the global context. A common approach that combines CNNs with transformers attempts to bridge this gap but fails to effectively fuse the local and global features. With the recent emergence of VLMs and foundation models, they have been adapted for downstream medical imaging tasks; however, they suffer from an inherent domain gap and high computational cost. To this end, we propose U-DFA, a unified DINOv2-Unet encoder-decoder architecture that integrates a novel Local-Global Fusion Adapter (LGFA) to enhance segmentation performance. LGFA modules inject spatial features from a CNN-based Spatial Pattern Adapter (SPA) module into frozen DINOv2 blocks at multiple stages, enabling effective fusion of high-level semantic and spatial features. Our method achieves state-of-the-art performance on the Synapse and ACDC datasets with only 33\% of the trainable model parameters. These results demonstrate that U-DFA is a robust and scalable framework for medical image segmentation across multiple modalities.

---

### Color Models in Image Processing: A Review and Experimental Comparison

Authors: Muragul Muratbekova, Nuray Toganas, Ayan Igali, Maksat Shagyrov, Elnara Kadyrgali, Adilet Yerkin, Pakizar Shamoi
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00584v1

Color representation is essential in computer vision and human-computer interaction. There are multiple color models available. The choice of a suitable color model is critical for various applications. This paper presents a review of color models and spaces, analyzing their theoretical foundations, computational properties, and practical applications. We explore traditional models such as RGB, CMYK, and YUV, perceptually uniform spaces like CIELAB and CIELUV, and fuzzy-based approaches as well. Additionally, we conduct a series of experiments to evaluate color models from various perspectives, like device dependency, chromatic consistency, and computational complexity. Our experimental results reveal gaps in existing color models and show that the HS* family is the most aligned with human perception. The review also identifies key strengths and limitations of different models and outlines open challenges and future directions This study provides a reference for researchers in image processing, perceptual computing, digital media, and any other color-related field.

---

### SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation

Authors: Sangmin Lee, Woongjib Choi, Jihyun Kim, Hong-Goo Kang
Published: 2025-10-01
Categories: cs.CL, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2510.00582v1

In this paper, we present a neural spoken language diarization model that supports an unconstrained span of languages within a single framework. Our approach integrates a learnable query-based architecture grounded in multilingual awareness, with large-scale pretraining on simulated code-switching data. By jointly leveraging these two components, our method overcomes the limitations of conventional approaches in data scarcity and architecture optimization, and generalizes effectively to real-world multilingual settings across diverse environments. Experimental results demonstrate that our approach achieves state-of-the-art performance on several language diarization benchmarks, with a relative performance improvement of 23% to 52% over previous methods. We believe that this work not only advances research in language diarization but also establishes a foundational framework for code-switching speech technologies.

---

### CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs

Authors: Li Li, Ziyi Wang, Yongliang Wu, Jianfei Cai, Xu Yang
Published: 2025-10-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.00579v1

Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient. To improve CoT reasoning at a lower cost, and inspired by the task vector paradigm, we introduce CoT Vectors, compact representations that encode task-general, multi-step reasoning knowledge. Through experiments with Extracted CoT Vectors, we observe pronounced layer-wise instability, manifesting as a U-shaped performance curve that reflects a systematic three-stage reasoning process in LLMs. To address this limitation, we propose Learnable CoT Vectors, optimized under a teacher-student framework to provide more stable and robust guidance. Extensive evaluations across diverse benchmarks and models demonstrate that CoT Vectors not only outperform existing baselines but also achieve performance comparable to parameter-efficient fine-tuning methods, while requiring fewer trainable parameters. Moreover, by treating CoT Vectors as a probe, we uncover how their effectiveness varies due to latent space structure, information density, acquisition mechanisms, and pre-training differences, offering new insights into the functional organization of multi-step reasoning in LLMs. The source code will be released.

---

### Arbitrary Generative Video Interpolation

Authors: Guozhen Zhang, Haiguang Wang, Chunyu Wang, Yuan Zhou, Qinglin Lu, Limin Wang
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00578v3

Video frame interpolation (VFI), which generates intermediate frames from given start and end frames, has become a fundamental function in video generation applications. However, existing generative VFI methods are constrained to synthesize a fixed number of intermediate frames, lacking the flexibility to adjust generated frame rates or total sequence duration. In this work, we present ArbInterp, a novel generative VFI framework that enables efficient interpolation at any timestamp and of any length. Specifically, to support interpolation at any timestamp, we propose the Timestamp-aware Rotary Position Embedding (TaRoPE), which modulates positions in temporal RoPE to align generated frames with target normalized timestamps. This design enables fine-grained control over frame timestamps, addressing the inflexibility of fixed-position paradigms in prior work. For any-length interpolation, we decompose long-sequence generation into segment-wise frame synthesis. We further design a novel appearance-motion decoupled conditioning strategy: it leverages prior segment endpoints to enforce appearance consistency and temporal semantics to maintain motion coherence, ensuring seamless spatiotemporal transitions across segments. Experimentally, we build comprehensive benchmarks for multi-scale frame interpolation (2x to 32x) to assess generalizability across arbitrary interpolation factors. Results show that ArbInterp outperforms prior methods across all scenarios with higher fidelity and more seamless spatiotemporal continuity. Project website: https://mcg-nju.github.io/ArbInterp-Web/.

---

### Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings

Authors: Bo Li, Wei Wang, Peng Ye
Published: 2025-10-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.00574v2

We revisit the problem of private online learning, in which a learner receives a sequence of $T$ data points and has to respond at each time-step a hypothesis. It is required that the entire stream of output hypotheses should satisfy differential privacy. Prior work of Golowich and Livni (2021) established that every concept class $\mathcal{H}$ with finite Littlestone dimension $d$ is privately online learnable in the realizable setting. In particular, they proposed an algorithm that achieves an $O_{d}(\log T)$ mistake bound against an oblivious adversary. However, their approach yields a suboptimal $\tilde{O}_{d}(\sqrt{T})$ bound against an adaptive adversary. In this work, we present a new algorithm with a mistake bound of $O_{d}(\log T)$ against an adaptive adversary, closing this gap. We further investigate the problem in the agnostic setting, which is more general than the realizable setting as it does not impose any assumptions on the data. We give an algorithm that obtains a sublinear regret of $\tilde{O}_d(\sqrt{T})$ for generic Littlestone classes, demonstrating that they are also privately online learnable in the agnostic setting.

---

### IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection

Authors: Ahsan Farabi, Muhaiminul Rashid Shad, Israt Khandaker
Published: 2025-10-01
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.00572v2

Intrusion Detection Systems (IDS) face persistent challenges due to evolving cyberattacks, high-dimensional traffic data, and severe class imbalance in benchmark datasets such as NSL-KDD. To address these issues, we propose IntrusionX, a hybrid deep learning framework that integrates Convolutional Neural Networks (CNNs) for local feature extraction and Long Short-Term Memory (LSTM) networks for temporal modeling. The architecture is further optimized using the Squirrel Search Algorithm (SSA), enabling effective hyperparameter tuning while maintaining computational efficiency. Our pipeline incorporates rigorous preprocessing, stratified data splitting, and dynamic class weighting to enhance the detection of rare classes. Experimental evaluation on NSL-KDD demonstrates that IntrusionX achieves 98% accuracy in binary classification and 87% in 5-class classification, with significant improvements in minority class recall (U2R: 71%, R2L: 93%). The novelty of IntrusionX lies in its reproducible, imbalance-aware design with metaheuristic optimization.

---

### Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning

Authors: Minghao Yang, Ren Togo, Guang Li, Takahiro Ogawa, Miki Haseyama
Published: 2025-10-01
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.00570v1

Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge sharing during the transition from single-task to multi-task learning (STL to MTL). To address these limitations, we propose adaptive shared experts (ASE) within a low-rank adaptation (LoRA) based MoE, where shared experts are assigned router-computed gating weights jointly normalized with sparse experts. This design facilitates STL to MTL transition, enhances expert specialization, and cooperation. Furthermore, we incorporate fine-grained experts by increasing the number of LoRA experts while proportionally reducing their rank, enabling more effective knowledge sharing under a comparable parameter budget. Extensive experiments on the PASCAL-Context benchmark, under unified training settings, demonstrate that ASE consistently improves performance across diverse configurations and validates the effectiveness of fine-grained designs for MTL.

---

### Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold

Authors: Ke Xu, Yuefeng Han
Published: 2025-10-01
Categories: stat.ML, cs.LG, math.OC, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2510.00569v1

Recovering a low-CP-rank tensor from noisy linear measurements is a central challenge in high-dimensional data analysis, with applications spanning tensor PCA, tensor regression, and beyond. We exploit the intrinsic geometry of rank-one tensors by casting the recovery task as an optimization problem over the Segre manifold, the smooth Riemannian manifold of rank-one tensors. This geometric viewpoint yields two powerful algorithms: Riemannian Gradient Descent (RGD) and Riemannian Gauss-Newton (RGN), each of which preserves feasibility at every iteration. Under mild noise assumptions, we prove that RGD converges at a local linear rate, while RGN exhibits an initial local quadratic convergence phase that transitions to a linear rate as the iterates approach the statistical noise floor. Extensive synthetic experiments validate these convergence guarantees and demonstrate the practical effectiveness of our methods.

---

### ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards

Authors: Shiyu Li, Yang Tang, Yifan Wang, Peiming Li, Xi Chen
Published: 2025-10-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.00568v3

Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning (RL) has emerged as a powerful paradigm for training these agents to perform complex, multi-step reasoning. However, prior RL-based methods often rely on sparse or rule-based rewards, which can lead agents to commit to suboptimal or erroneous reasoning paths without the ability to recover. To address these limitations, we propose ReSeek, a novel self-correcting framework for training search agents. Our framework introduces a self-correction mechanism that empowers the agent to dynamically identify and recover from erroneous search paths during an episode. By invoking a special JUDGE action, the agent can judge the information and re-plan its search strategy. To guide this process, we design a dense, instructive process reward function, which decomposes into a correctness reward for retrieving factual information and a utility reward for finding information genuinely useful for the query. Furthermore, to mitigate the risk of data contamination in existing datasets, we introduce FictionalHot, a new and challenging benchmark with recently curated questions requiring complex reasoning. Being intuitively reasonable and practically simple, extensive experiments show that agents trained with ReSeek significantly outperform SOTA baselines in task success rate and path faithfulness.

---

### Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation

Authors: Yubo Xie, Chenkai Wang, Zongyang Ma, Fahui Miao
Published: 2025-10-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.00567v1

Large language models (LLMs) are trained on vast amounts of text from the Internet, but do they truly understand the viral content that rapidly spreads online -- commonly known as memes? In this paper, we introduce CHIME, a dataset for CHinese Internet Meme Explanation. The dataset comprises popular phrase-based memes from the Chinese Internet, annotated with detailed information on their meaning, origin, example sentences, types, etc. To evaluate whether LLMs understand these memes, we designed two tasks. In the first task, we assessed the models' ability to explain a given meme, identify its origin, and generate appropriate example sentences. The results show that while LLMs can explain the meanings of some memes, their performance declines significantly for culturally and linguistically nuanced meme types. Additionally, they consistently struggle to provide accurate origins for the memes. In the second task, we created a set of multiple-choice questions (MCQs) requiring LLMs to select the most appropriate meme to fill in a blank within a contextual sentence. While the evaluated models were able to provide correct answers, their performance remains noticeably below human levels. We have made CHIME public and hope it will facilitate future research on computational meme understanding.

---

### Panorama: Fast-Track Nearest Neighbors

Authors: Vansh Ramani, Alexis Schlomer, Akash Nayar, Sayan Ranu, Jignesh M. Patel, Panagiotis Karras
Published: 2025-10-01
Categories: cs.LG, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2510.00566v4

Approximate Nearest-Neighbor Search (ANNS) pipelines for high-dimensional neural embeddings spend the bulk of their query time in candidate verification, making it the primary bottleneck in the search process. In this paper, we present PANORAMA, a state-of-the-art refinement technique that accelerates verification by exploiting the inherent spectral decay of these embeddings. Using PCA to compact signal energy, PANORAMA evaluates candidate distances incrementally, computing at each step a strict lower bound on the full-vector distance and dynamically pruning candidates the moment this bound exceeds the running k-th nearest neighbor distance. While PCA's concentration of variance facilitates pruning, it breaks the uniform-variance assumption required by Product Quantization (PQ); we resolve this with a variance-shaping step that redistributes energy across subvectors, rendering accretive refinement compatible with quantized indexes. Optimized for modern memory hierarchies via vectorized bulk-pruning and cache-conscious data layouts, PANORAMA has been upstreamed into the FAISS library across major index families (IVFPQ/Flat, HNSW, and Refine). PANORAMA achieves higher QPS at any target recall with a cost that provably scales inversely with dataset spectral decay, delivering end-to-end speedups of up to 28.9x and outperforming probabilistic methods across all recall bands.

---

### Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability

Authors: Shojiro Yamabe, Jun Sakuma
Published: 2025-10-01
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.00565v2

Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional conditioning. However, the safety risks posed by jailbreak attacks that exploit this inference mechanism are not well understood. In this paper, we reveal that DLMs have a critical vulnerability stemming from their iterative denoising process and propose a countermeasure. Specifically, our investigation shows that if an affirmative token for a harmful query appears at an intermediate step, subsequent denoising can be steered toward a harmful response even in aligned models. As a result, simply injecting such affirmative tokens can readily bypass the safety guardrails. Furthermore, we demonstrate that the vulnerability allows existing optimization-based jailbreak attacks to succeed on DLMs. Building on this analysis, we propose a novel safety alignment method tailored to DLMs that trains models to generate safe responses from contaminated intermediate states that contain affirmative tokens. Our experiments indicate that the proposed method significantly mitigates the vulnerability with minimal impact on task performance. Furthermore, our method improves robustness against conventional jailbreak attacks. Our work underscores the need for DLM-specific safety research. Our code is available at https://github.com/mdl-lab/dlm-priming-vulnerability.

---

### Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models

Authors: JingChuan Guan, Tomoyuki Kubota, Yasuo Kuniyoshi, Kohei Nakajima
Published: 2025-10-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.00563v1

State space models (SSMs) have gained attention by showing potential to outperform Transformers. However, previous studies have not sufficiently addressed the mechanisms underlying their high performance owing to a lack of theoretical explanation of SSMs' learning dynamics. In this study, we provide such an explanation and propose an improved training strategy. The memory capacity of SSMs can be evaluated by examining how input time series are stored in their current state. Such an examination reveals a tradeoff between memory accuracy and length, as well as the theoretical equivalence between the structured state space sequence model (S4) and a simplified S4 with diagonal recurrent weights. This theoretical foundation allows us to elucidate the learning dynamics, proving the importance of initial parameters. Our analytical results suggest that successful learning requires the initial memory structure to be the longest possible even if memory accuracy may deteriorate or the gradient lose the teacher information. Experiments on tasks requiring long memory confirmed that extending memory is difficult, emphasizing the importance of initialization. Furthermore, we found that fixing recurrent weights can be more advantageous than adapting them because it achieves comparable or even higher performance with faster convergence. Our results provide a new theoretical foundation for SSMs and potentially offer a novel optimization strategy.

---

### Assessing Foundation Models for Mold Colony Detection with Limited Training Data

Authors: Henrik Pichler, Janis Keuper, Matthew Copping
Published: 2025-10-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.00561v1

The process of quantifying mold colonies on Petri dish samples is of critical importance for the assessment of indoor air quality, as high colony counts can indicate potential health risks and deficiencies in ventilation systems. Conventionally the automation of such a labor-intensive process, as well as other tasks in microbiology, relies on the manual annotation of large datasets and the subsequent extensive training of models like YoloV9. To demonstrate that exhaustive annotation is not a prerequisite anymore when tackling a new vision task, we compile a representative dataset of 5000 Petri dish images annotated with bounding boxes, simulating both a traditional data collection approach as well as few-shot and low-shot scenarios with well curated subsets with instance level masks. We benchmark three vision foundation models against traditional baselines on task specific metrics, reflecting realistic real-world requirements. Notably, MaskDINO attains near-parity with an extensively trained YoloV9 model while finetuned only on 150 images, retaining competitive performance with as few as 25 images, still being reliable on $\approx$ 70% of the samples. Our results show that data-efficient foundation models can match traditional approaches with only a fraction of the required data, enabling earlier development and faster iterative improvement of automated microbiological systems with a superior upper-bound performance than traditional models would achieve.

---

### Mathematical Theory of Collinearity Effects on Machine Learning Variable Importance Measures

Authors: Kelvyn K. Bladen, D. Richard Cutler, Alan Wisler
Published: 2025-10-01
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.00557v1

In many machine learning problems, understanding variable importance is a central concern. Two common approaches are Permute-and-Predict (PaP), which randomly permutes a feature in a validation set, and Leave-One-Covariate-Out (LOCO), which retrains models after permuting a training feature. Both methods deem a variable important if predictions with the original data substantially outperform those with permutations. In linear regression, empirical studies have linked PaP to regression coefficients and LOCO to $t$-statistics, but a formal theory has been lacking. We derive closed-form expressions for both measures, expressed using square-root transformations. PaP is shown to be proportional to the coefficient and predictor variability: $\text{PaP}_i = β_i \sqrt{2\operatorname{Var}(\mathbf{x}^v_i)}$, while LOCO is proportional to the coefficient but dampened by collinearity (captured by $Δ$): $\text{LOCO}_i = β_i (1 -Δ)\sqrt{1 + c}$. These derivations explain why PaP is largely unaffected by multicollinearity, whereas LOCO is highly sensitive to it. Monte Carlo simulations confirm these findings across varying levels of collinearity. Although derived for linear regression, we also show that these results provide reasonable approximations for models like Random Forests. Overall, this work establishes a theoretical basis for two widely used importance measures, helping analysts understand how they are affected by the true coefficients, dimension, and covariance structure. This work bridges empirical evidence and theory, enhancing the interpretability and application of variable importance measures.

---

### PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering

Authors: Niklas Gutheil, Valentin Mayer, Leopold Müller, Jörg Rommelt, Niklas Kühl
Published: 2025-10-01
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.00555v1

Effective prompt engineering is critical to realizing the promised productivity gains of large language models (LLMs) in knowledge-intensive tasks. Yet, many users struggle to craft prompts that yield high-quality outputs, limiting the practical benefits of LLMs. Existing approaches, such as prompt handbooks or automated optimization pipelines, either require substantial effort, expert knowledge, or lack interactive guidance. To address this gap, we design and evaluate PromptPilot, an interactive prompting assistant grounded in four empirically derived design objectives for LLM-enhanced prompt engineering. We conducted a randomized controlled experiment with 80 participants completing three realistic, work-related writing tasks. Participants supported by PromptPilot achieved significantly higher performance (median: 78.3 vs. 61.7; p = .045, d = 0.56), and reported enhanced efficiency, ease-of-use, and autonomy during interaction. These findings empirically validate the effectiveness of our proposed design objectives, establishing LLM-enhanced prompt engineering as a viable technique for improving human-AI collaboration.

---

### On Predictability of Reinforcement Learning Dynamics for Large Language Models

Authors: Yuchen Cai, Ding Cao, Xin Xu, Zijun Yao, Yuqing Huang, Zhenyu Tan, Benyi Zhang, Guangzhong Sun, Guiquan Liu, Junfeng Fang
Published: 2025-10-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.00553v3

Recent advances in reasoning capabilities of large language models (LLMs) are largely driven by reinforcement learning (RL), yet the underlying parameter dynamics during RL training remain poorly understood. This work identifies two fundamental properties of RL-induced parameter updates in LLMs: (1) Rank-1 Dominance, where the top singular subspace of the parameter update matrix nearly fully determines reasoning improvements, recovering over 99\% of performance gains; and (2) Rank-1 Linear Dynamics, where this dominant subspace evolves linearly throughout training, enabling accurate prediction from early checkpoints. Extensive experiments across 8 LLMs and 7 algorithms validate the generalizability of these properties. More importantly, based on these findings, we propose AlphaRL, a plug-in acceleration framework that extrapolates the final parameter update using a short early training window, achieving up to 2.5 speedup while retaining \textgreater 96\% of reasoning performance without extra modules or hyperparameter tuning. This positions our finding as a versatile and practical tool for large-scale RL, opening a path toward principled, interpretable, and efficient training paradigm for LLMs.

---

### Data Quality Challenges in Retrieval-Augmented Generation

Authors: Leopold Müller, Joshua Holstein, Sarah Bause, Gerhard Satzger, Niklas Kühl
Published: 2025-10-01
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.00552v1

Organizations increasingly adopt Retrieval-Augmented Generation (RAG) to enhance Large Language Models with enterprise-specific knowledge. However, current data quality (DQ) frameworks have been primarily developed for static datasets, and only inadequately address the dynamic, multi-stage nature of RAG systems. This study aims to develop DQ dimensions for this new type of AI-based systems. We conduct 16 semi-structured interviews with practitioners of leading IT service companies. Through a qualitative content analysis, we inductively derive 15 distinct DQ dimensions across the four processing stages of RAG systems: data extraction, data transformation, prompt & search, and generation. Our findings reveal that (1) new dimensions have to be added to traditional DQ frameworks to also cover RAG contexts; (2) these new dimensions are concentrated in early RAG steps, suggesting the need for front-loaded quality management strategies, and (3) DQ issues transform and propagate through the RAG pipeline, necessitating a dynamic, step-aware approach to quality management.

---