# Research Papers — 2025-11 · bundle page 84 of 197 > Full-text markdown of papers #4151–4200 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/84 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/83.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/85.md) ### Biased Minds Meet Biased AI: How Class Imbalance Shapes Appropriate Reliance and Interacts with Human Base Rate Neglect Authors: Nick von Felten, Johannes Schöning, Klaus Opwis, Nicolas Scharowski Published: 2025-11-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.14591v2 Humans increasingly interact with artificial intelligence (AI) in decision-making. However, both AI and humans are prone to biases. While AI and human biases have been studied extensively in isolation, this paper examines their complex interaction. Specifically, we examined how class imbalance as an AI bias affects people's ability to appropriately rely on an AI-based decision-support system, and how it interacts with base rate neglect as a human bias. In a within-subject online study (N= 46), participants classified three diseases using an AI-based decision-support system trained on either a balanced or unbalanced dataset. We found that class imbalance disrupted participants' calibration of AI reliance. Moreover, we observed mutually reinforcing effects between class imbalance and base rate neglect, offering evidence of a compound human-AI bias. Based on these findings, we advocate for an interactionist perspective and further research into the mutually reinforcing effects of biases in human-AI interaction. --- ### Biased Minds Meet Biased AI: How Class Imbalance Shapes Appropriate Reliance and Interacts with Human Base Rate Neglect Authors: Nick von Felten, Johannes Schöning, Klaus Opwis, Nicolas Scharowksi Published: 2025-11-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.14591v1 Humans increasingly interact with artificial intelligence (AI) in decision-making. However, both AI and humans are prone to biases. While AI and human biases have been studied extensively in isolation, this paper examines their complex interaction. Specifically, we examined how class imbalance as an AI bias affects people's ability to appropriately rely on an AI-based decision-support system, and how it interacts with base rate neglect as a human bias. In a within-subject online study (N= 46), participants classified three diseases using an AI-based decision-support system trained on either a balanced or unbalanced dataset. We found that class imbalance disrupted participants' calibration of AI reliance. Moreover, we observed mutually reinforcing effects between class imbalance and base rate neglect, offering evidence of a compound human-AI bias. Based on these findings, we advocate for an interactionist perspective and further research into the mutually reinforcing effects of biases in human-AI interaction. --- ### Deep Learning-Based Regional White Matter Hyperintensity Mapping as a Robust Biomarker for Alzheimer's Disease Authors: Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14588v1 White matter hyperintensities (WMH) are key imaging markers in cognitive aging, Alzheimer's disease (AD), and related dementias. Although automated methods for WMH segmentation have advanced, most provide only global lesion load and overlook their spatial distribution across distinct white matter regions. We propose a deep learning framework for robust WMH segmentation and localization, evaluated across public datasets and an independent Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our results show that the predicted lesion loads are in line with the reference WMH estimates, confirming the robustness to variations in lesion load, acquisition, and demographics. Beyond accurate segmentation, we quantify WMH load within anatomically defined regions and combine these measures with brain structure volumes to assess diagnostic value. Regional WMH volumes consistently outperform global lesion burden for disease classification, and integration with brain atrophy metrics further improves performance, reaching area under the curve (AUC) values up to 0.97. Several spatially distinct regions, particularly within anterior white matter tracts, are reproducibly associated with diagnostic status, indicating localized vulnerability in AD. These results highlight the added value of regional WMH quantification. Incorporating localized lesion metrics alongside atrophy markers may enhance early diagnosis and stratification in neurodegenerative disorders. --- ### ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing Authors: Ankush Kadu, Aswanth Krishnan Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14584v4 We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the information to escape -- but no published architecture acts on it within a single episode. ReflexGrad routes between a fast process (TextGrad-style continuous refinement every $k{=}3$ steps) and a slow process (Reflexion-style causal diagnosis when $m{=}5$ consecutive low-progress scores fire a routing gate). A deterministic priority merge keeps the natural-language policy coherent, and each slow activation emits three observable artifacts: a reproducible trigger, a causal diagnostic, and a verified fix. On ALFWorld 134 tasks, $n{=}10$ seeds, no demonstrations, ReflexGrad lifts Qwen-3-8B from $35.1\%$ to $75.4\%$ ($+40.3$pp), beating compute-matched 1-shot LATS by $+2.7$pp ($p{\approx}0.01$), ToT by $+5.7$pp ($p{<}10^{-4}$), and Self-Refine by $+6.7$pp ($p{<}10^{-5}$); on GPT-5 the lift is $46.3{\to}88.1\%$ ($+41.8$pp). The $1.5$pp cross-model difference is within seed noise ($p{\approx}0.13$), suggesting that the routing mechanism, rather than model scale, is the primary source of the gain. Code, prompts, per-seed logs, and sensitivity sweeps are released. --- ### ReflexGrad: Three-Way Synergistic Architecture for Zero-Shot Generalization in LLM Agents Authors: Ankush Kadu, Ashwanth Krishnan Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14584v1 Enabling agents to learn from experience and generalize across diverse tasks without task-specific training remains a fundamental challenge in reinforcement learning and decision-making. While recent approaches have explored episodic memory (Reflexion), gradient-based prompt optimization (TextGrad),and hierarchical task decomposition independently, their potential for synergistic integration remains unexplored. We introduce ReflexGrad, a novel architecture that tightly couples three complementary mechanisms: (1) LLM-based hierarchical TODO decomposition for strategic planning, (2) history-aware causal reflection that analyzes recent action patterns to identify failure root causes and enable within-trial learning, and (3) gradient-based optimization for systematic improvement. Unlike prior work relying on few-shot demonstrations, our system achieves true zero-shot generalization through pure LLM semantic reasoning,requiring no task-specific examples, fine-tuning, or hardcoded similarity metrics. Evaluated on ALFWorld benchmark tasks, ReflexGrad demonstrates 67% zero-shot success rate on Trial 0 without any prior task experience or demonstrations, establishing effective performance on first exposure. Through empirical analysis, we identify the architectural mechanisms underlying stable convergence (zero action loops) and effective cross-task transfer (67% to 78% improvement).Our work demonstrates that synergistic integration of complementary learning mechanisms enables robust zero-shot generalization that approaches few-shot baselines from prior work. --- ### OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models Authors: Keda Tao, Kele Shao, Bohan Yu, Weiqiang Wang, Jian liu, Huan Wang Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14582v2 Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of processing longer joint audio-video token sequences has become a key bottleneck. Existing token compression methods have not addressed the emerging need to jointly compress multimodal tokens. To bridge this gap, we present OmniZip, a training-free, audio-guided audio-visual token-compression framework that optimizes multimodal token representation and accelerates model inference. Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information density, thereby dynamically guiding video token pruning and preserving cues from audio anchors enhanced by cross-modal similarity. For each time window, OmniZip compresses the video tokens using an interleaved spatio-temporal scheme. Extensive results demonstrate the merits of OmniZip: it achieves a 3.42X inference speedup and a 1.4X memory reduction over other top-performing counterparts, while maintaining the performance of OmniLLMs without training. --- ### OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models Authors: Keda Tao, Kele Shao, Bohan Yu, Weiqiang Wang, Jian liu, Huan Wang Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14582v1 Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding, wherein processing audio-video token sequences creates a significant computational bottleneck, however. Existing token compression methods have yet to accommodate this emerging need of jointly compressing multimodal tokens. To bridge this gap, we present OmniZip, a training-free, audio-guided audio-visual token-compression framework that optimizes multimodal token representation and accelerates inference. Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information density, thereby dynamically guiding video token pruning and preserving cues from audio anchors enhanced by cross-modal similarity. For each time window, OmniZip compresses the video tokens using an interleaved spatio-temporal scheme. Extensive empirical results demonstrate the merits of OmniZip - it achieves 3.42X inference speedup and 1.4X memory reduction over other top-performing counterparts, while maintaining performance with no training. --- ### Online learning of subgrid-scale models for quasi-geostrophic turbulence in planetary interiors Authors: Hugo Frezat, Thomas Gastine, Alexandre Fournier Published: 2025-11-18 Categories: physics.flu-dyn, astro-ph.EP, cs.LG arXiv: https://arxiv.org/abs/2511.14581v2 Machine learning approaches to subgrid-scale (SGS) modelling are now well established in atmospheric and oceanic applications. Among these, online end-to-end learning, where the differentiable solver participates in the training, has shown particular promise. Yet, existing studies are largely restricted to idealised periodic domains, with no mechanical boundaries, precluding them from addressing the dynamics of bounded rotating flows relevant to planetary interiors. Here we consider two-dimensional quasi-geostrophic turbulence in a rapidly rotating annular bounded domain. We examine three configurations varying the geometry of the container and the rotation rate. The system exhibit key features such as zonal jets, Rossby waves, and, in the spherical shell geometry, a slow quasi-periodic inward drift of the jets. The spectral properties of the zonal and non-zonal flow can be understood in the framework of zonostrophic turbulence theory. We develop a differentiable solver for this system, which allows us to train SGS models online, over a time span of one turnover time, using coarse-grained data from direct numerical simulations. In all cases, a SGS model trained on a single turnover time accurately reproduce global integrated diagnostics, energy spectra as well as long-term dynamical behaviours ---such as jet migration--- occurring on timescales which exceed the training window by one order of magnitude. The online-trained model further outperforms classical hyperdiffusivity and Leith closure schemes, for which reducing the radial resolution is impractical. The resulting speed-up paves the way to further investigations of long-term geophysical fluid processes beyond the reach of direct numerical simulations. --- ### Online learning of subgrid-scale models for quasi-geostrophic turbulence in planetary interiors Authors: Hugo Frezat, Thomas Gastine, Alexandre Fournier Published: 2025-11-18 Categories: physics.flu-dyn, astro-ph.EP, cs.LG arXiv: https://arxiv.org/abs/2511.14581v1 The use of machine learning to represent subgrid-scale (SGS) dynamics is now well established in weather forecasting and climate modelling. Recent advances have demonstrated that SGS models trained via ``online'' end-to-end learning -- where the dynamical solver operating on the filtered equations participates in the training -- can outperform traditional physics-based approaches. Most studies, however, have focused on idealised periodic domains, neglecting the mechanical boundaries present e.g. in planetary interiors. To address this issue, we consider two-dimensional quasi-geostrophic turbulent flow in an axisymmetric bounded domain that we model using a pseudo-spectral differentiable solver, thereby enabling online learning. We examine three configurations, varying the geometry (between an exponential container and a spherical shell) and the rotation rate. Flow is driven by a prescribed analytical forcing, allowing for precise control over the energy injection scale and an exact estimate of the power input. We evaluate the accuracy of the online-trained SGS model against the reference direct numerical simulation using integral quantities and spectral diagnostics. In all configurations, we show that an SGS model trained on data spanning only one turnover time remains stable and accurate over integrations at least a hundred times longer than the training period. Moreover, we demonstrate the model's remarkable ability to reproduce slow processes occurring on time scales far exceeding the training duration, such as the inward drift of jets in the spherical shell. These results suggest a promising path towards developing SGS models for planetary and stellar interior dynamics, including dynamo processes. --- ### Task Addition and Weight Disentanglement in Closed-Vocabulary Models Authors: Adam Hazimeh, Alessandro Favero, Pascal Frossard Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14569v1 Task arithmetic has recently emerged as a promising method for editing pre-trained \textit{open-vocabulary} models, offering a cost-effective alternative to standard multi-task fine-tuning. However, despite the abundance of \textit{closed-vocabulary} models that are not pre-trained with language supervision, applying task arithmetic to these models remains unexplored. In this paper, we deploy and study task addition in closed-vocabulary image classification models. We consider different pre-training schemes and find that \textit{weight disentanglement} -- the property enabling task arithmetic -- is a general consequence of pre-training, as it appears in different pre-trained closed-vocabulary models. In fact, we find that pre-trained closed-vocabulary vision transformers can also be edited with task arithmetic, achieving high task addition performance and enabling the efficient deployment of multi-task models. Finally, we demonstrate that simple linear probing is a competitive baseline to task addition. Overall, our findings expand the applicability of task arithmetic to a broader class of pre-trained models and open the way for more efficient use of pre-trained models in diverse settings. --- ### SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering Authors: Chen Chen, Cuong Nguyen, Alexa Siu, Dingzeyu Li, Nadir Weibel Published: 2025-11-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.14567v3 Accessing 3D models remains challenging for Screen Reader (SR) users. While some existing 3D viewers allow creators to provide alternative text, they often lack sufficient detail about the 3D models. Grounded on a formative study, this paper introduces SweeperBot, a system that enables SR users to leverage visual question answering to explore and compare 3D models. SweeperBot answers SR users' visual questions by combining an optimal view selection technique with the strength of generative- and recognition-based foundation models. An expert review with 10 Blind and Low-Vision (BLV) users with SR experience demonstrated the feasibility of using SweeperBot to assist BLV users in exploring and comparing 3D models. The quality of the descriptions generated by SweeperBot was validated by a second survey study with 30 sighted participants. --- ### SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering Authors: Chen Chen, Cuong Nguyen, Alexa Siu, Dingzeyu Li, Nadir Weibel Published: 2025-11-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.14567v1 Accessing 3D models remains challenging for Screen Reader (SR) users. While some existing 3D viewers allow creators to provide alternative text, they often lack sufficient detail about the 3D models. Grounded on a formative study, this paper introduces SweeperBot, a system that enables SR users to leverage visual question answering to explore and compare 3D models. SweeperBot answers SR users' visual questions by combining an optimal view selection technique with the strength of generative- and recognition-based foundation models. An expert review with 10 Blind and Low-Vision (BLV) users with SR experience demonstrated the feasibility of using SweeperBot to assist BLV users in exploring and comparing 3D models. The quality of the descriptions generated by SweeperBot was validated by a second survey study with 30 sighted participants. --- ### Examining the Metrics for Document-Level Claim Extraction in Czech and Slovak Authors: Lucia Makaiova, Martin Fajcik, Antonin Jarolim Published: 2025-11-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14566v2 Document-level claim extraction remains an open challenge in the field of fact-checking, and subsequently, methods for evaluating extracted claims have received limited attention. In this work, we explore approaches to aligning two sets of claims pertaining to the same source document and computing their similarity through an alignment score. We investigate techniques to identify the best possible alignment and evaluation method between claim sets, with the aim of providing a reliable evaluation framework. Our approach enables comparison between model-extracted and human-annotated claim sets, serving as a metric for assessing the extraction performance of models and also as a possible measure of inter-annotator agreement. We conduct experiments on newly collected dataset-claims extracted from comments under Czech and Slovak news articles-domains that pose additional challenges due to the informal language, strong local context, and subtleties of these closely related languages. The results draw attention to the limitations of current evaluation approaches when applied to document-level claim extraction and highlight the need for more advanced methods-ones able to correctly capture semantic similarity and evaluate essential claim properties such as atomicity, checkworthiness, and decontextualization. --- ### Examining the Metrics for Document-Level Claim Extraction in Czech and Slovak Authors: Lucia Makaiová, Martin Fajčík, Antonín Jarolím Published: 2025-11-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14566v1 Document-level claim extraction remains an open challenge in the field of fact-checking, and subsequently, methods for evaluating extracted claims have received limited attention. In this work, we explore approaches to aligning two sets of claims pertaining to the same source document and computing their similarity through an alignment score. We investigate techniques to identify the best possible alignment and evaluation method between claim sets, with the aim of providing a reliable evaluation framework. Our approach enables comparison between model-extracted and human-annotated claim sets, serving as a metric for assessing the extraction performance of models and also as a possible measure of inter-annotator agreement. We conduct experiments on newly collected dataset-claims extracted from comments under Czech and Slovak news articles-domains that pose additional challenges due to the informal language, strong local context, and subtleties of these closely related languages. The results draw attention to the limitations of current evaluation approaches when applied to document-level claim extraction and highlight the need for more advanced methods-ones able to correctly capture semantic similarity and evaluate essential claim properties such as atomicity, checkworthiness, and decontextualization. --- ### Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language Authors: Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler, Andreea Bobu Published: 2025-11-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.14565v2 Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to generalize. This happens because demonstrations show robots how to do a task but not what matters for that task, causing the model to focus on irrelevant state details. Natural language can more directly specify what the robot should focus on, and, in principle, disambiguate between many reward functions consistent with the demonstrations. However, existing language-conditioned reward learning methods typically treat instructions as simple conditioning signals, without fully exploiting their potential to resolve ambiguity. Moreover, real instructions are often ambiguous themselves, so naive conditioning is unreliable. Our key insight is that these two input types carry complementary information: demonstrations show how to act, while language specifies what is important. We propose Masked Inverse Reinforcement Learning (Masked IRL), a framework that uses large language models (LLMs) to combine the strengths of both input types. Masked IRL infers state-relevance masks from language instructions and enforces invariance to irrelevant state components. When instructions are ambiguous, it uses LLM reasoning to clarify them in the context of the demonstrations. In simulation and on a real robot, Masked IRL outperforms prior language-conditioned IRL methods by up to 15% while using up to 4.7 times less data, demonstrating improved sample-efficiency, generalization, and robustness to ambiguous language. Project page: https://MIT-CLEAR-Lab.github.io/Masked-IRL and Code: https://github.com/MIT-CLEAR-Lab/Masked-IRL --- ### Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language Authors: Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler, Andreea Bobu Published: 2025-11-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.14565v1 Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to generalize. This happens because demonstrations show robots how to do a task but not what matters for that task, causing the model to focus on irrelevant state details. Natural language can more directly specify what the robot should focus on, and, in principle, disambiguate between many reward functions consistent with the demonstrations. However, existing language-conditioned reward learning methods typically treat instructions as simple conditioning signals, without fully exploiting their potential to resolve ambiguity. Moreover, real instructions are often ambiguous themselves, so naive conditioning is unreliable. Our key insight is that these two input types carry complementary information: demonstrations show how to act, while language specifies what is important. We propose Masked Inverse Reinforcement Learning (Masked IRL), a framework that uses large language models (LLMs) to combine the strengths of both input types. Masked IRL infers state-relevance masks from language instructions and enforces invariance to irrelevant state components. When instructions are ambiguous, it uses LLM reasoning to clarify them in the context of the demonstrations. In simulation and on a real robot, Masked IRL outperforms prior language-conditioned IRL methods by up to 15% while using up to 4.7 times less data, demonstrating improved sample-efficiency, generalization, and robustness to ambiguous language. Project page: https://MIT-CLEAR-Lab.github.io/Masked-IRL and Code: https://github.com/MIT-CLEAR-Lab/Masked-IRL --- ### Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models Authors: Xinzhe Zheng, Shiyu Jiang, Gustavo Seabra, Chenglong Li, Yanjun Li Published: 2025-11-18 Categories: q-bio.BM, cs.AI, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2511.14559v1 Deep generative models are rapidly advancing structure-based drug design, offering substantial promise for generating small molecule ligands that bind to specific protein targets. However, most current approaches assume a rigid protein binding pocket, neglecting the intrinsic flexibility of proteins and the conformational rearrangements induced by ligand binding, limiting their applicability in practical drug discovery. Here, we propose Apo2Mol, a diffusion-based generative framework for 3D molecule design that explicitly accounts for conformational flexibility in protein binding pockets. To support this, we curate a dataset of over 24,000 experimentally resolved apo-holo structure pairs from the Protein Data Bank, enabling the characterization of protein structure changes associated with ligand binding. Apo2Mol employs a full-atom hierarchical graph-based diffusion model that simultaneously generates 3D ligand molecules and their corresponding holo pocket conformations from input apo states. Empirical studies demonstrate that Apo2Mol can achieve state-of-the-art performance in generating high-affinity ligands and accurately capture realistic protein pocket conformational changes. --- ### Explaining Digital Pathology Models via Clustering Activations Authors: Adam Bajger, Jan Obdržálek, Vojtěch Kůr, Rudolf Nenutil, Petr Holub, Vít Musil, Tomáš Brázdil Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14558v2 We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, such as occlusion, GradCAM, or relevance propagation, which highlight regions that contribute the most to the prediction for a single slide, our method shows the global behaviour of the model under consideration, while also providing more fine-grained information. The result clusters can be visualised not only to understand the model, but also to increase confidence in its operation, leading to faster adoption in clinical practice. We also evaluate the performance of our technique on an existing model for detecting prostate cancer, demonstrating its usefulness. --- ### Explaining Digital Pathology Models via Clustering Activations Authors: Adam Bajger, Jan Obdržálek, Vojtěch Kůr, Rudolf Nenutil, Petr Holub, Vít Musil, Tomáš Brázdil Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14558v1 We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, such as occlusion, GradCAM, or relevance propagation, which highlight regions that contribute the most to the prediction for a single slide, our method shows the global behaviour of the model under consideration, while also providing more fine-grained information. The result clusters can be visualised not only to understand the model, but also to increase confidence in its operation, leading to faster adoption in clinical practice. We also evaluate the performance of our technique on an existing model for detecting prostate cancer, demonstrating its usefulness. --- ### DecNefSimulator: A Modular, Interpretable Framework for Decoded Neurofeedback Simulation Using Generative Models Authors: Alexander Olza, Roberto Santana, David Soto Published: 2025-11-18 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2511.14555v4 Decoded Neurofeedback (DecNef) is a promising non-invasive approach to brain modulation with wide-ranging applications in neuromedicine and cognitive neuroscience. However, progress in DecNef research remains constrained by subject-dependent learning variability, reliance on indirect measures to quantify progress, and the high cost and time demands of experimentation. We present DecNefSimulator, a modular and interpretable simulation framework that formalizes DecNef as a machine learning problem. Beyond providing a virtual laboratory, DecNefSimulator enables researchers to model, analyze and understand neurofeedback dynamics. Using latent variable generative models as simulated participants, DecNefSimulator allows direct observation of internal cognitive states and systematic evaluation of how different protocol designs and subject characteristics influence learning. We demonstrate how this approach can (i) reproduce empirical phenomena of DecNef learning, (ii) identify conditions under which DecNef feedback fails to induce learning, and (iii) guide the design of more robust and reliable DecNef protocols in silico before human implementation. In summary, DecNefSimulator bridges computational modeling and cognitive neuroscience, offering a principled foundation for methodological innovation, robust protocol design, and ultimately, a deeper understanding of DecNef-based brain modulation. --- ### DecNefLab: A Modular and Interpretable Simulation Framework for Decoded Neurofeedback Authors: Alexander Olza, Roberto Santana, David Soto Published: 2025-11-18 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2511.14555v1 Decoded Neurofeedback (DecNef) is a flourishing non-invasive approach to brain modulation with wide-ranging applications in neuromedicine and cognitive neuroscience. However, progress in DecNef research remains constrained by subject-dependent learning variability, reliance on indirect measures to quantify progress, and the high cost and time demands of experimentation. We present DecNefLab, a modular and interpretable simulation framework that formalizes DecNef as a machine learning problem. Beyond providing a virtual laboratory, DecNefLab enables researchers to model, analyze and understand neurofeedback dynamics. Using latent variable generative models as simulated participants, DecNefLab allows direct observation of internal cognitive states and systematic evaluation of how different protocol designs and subject characteristics influence learning. We demonstrate how this approach can (i) reproduce empirical phenomena of DecNef learning, (ii) identify conditions under which DecNef feedback fails to induce learning, and (iii) guide the design of more robust and reliable DecNef protocols in silico before human implementation. In summary, DecNefLab bridges computational modeling and cognitive neuroscience, offering a principled foundation for methodological innovation, robust protocol design, and ultimately, a deeper understanding of DecNef-based brain modulation. --- ### ForensicFlow: A Tri-Modal Adaptive Network for Robust Deepfake Detection Authors: Mohammad Romani Published: 2025-11-18 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2511.14554v2 Modern deepfakes evade detection by leaving subtle, domain-speci c artifacts that single branch networks miss. ForensicFlow addresses this by fusing evidence across three forensic dimensions: global visual inconsistencies (via ConvNeXt-tiny), ne-grained texture anomalies (via Swin Transformer-tiny), and spectral noise patterns (via CNN with channel attention). Our attention-based temporal pooling dynamically prioritizes high-evidence frames, while adaptive fusion weights each branch according to forgery type. Trained on CelebDF(v2) with Focal Loss, the model achieves AUC 0.9752, F1 0.9408, and accuracy 0.9208 out performing single-stream detectors. Ablation studies con rm branch synergy, and Grad-CAM visualizations validate focus on genuine manipulation regions (e.g., facial boundaries). This multi-domain fusion strategy establishes robustness against increasingly sophisticated forgeries. --- ### ForensicFlow: A Tri-Modal Adaptive Network for Robust Deepfake Detection Authors: Mohammad Romani Published: 2025-11-18 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2511.14554v1 Deepfakes generated by advanced GANs and autoencoders severely threaten information integrity and societal stability. Single-stream CNNs fail to capture multi-scale forgery artifacts across spatial, texture, and frequency domains, limiting robustness and generalization. We introduce the ForensicFlow, a tri-modal forensic framework that synergistically fuses RGB, texture, and frequency evidence for video Deepfake detection. The RGB branch (ConvNeXt-tiny) extracts global visual inconsistencies; the texture branch (Swin Transformer-tiny) detects fine-grained blending artifacts; the frequency branch (CNN + SE) identifies periodic spectral noise. Attention-based temporal pooling dynamically prioritizes high-evidence frames, while adaptive attention fusion balances branch contributions.Trained on Celeb-DF (v2) with Focal Loss, ForensicFlow achieves AUC 0.9752, F1-Score 0.9408, and accuracy 0.9208, outperforming single-stream baselines. Ablation validates branch synergy; Grad-CAM confirms forensic focus. This comprehensive feature fusion provides superior resilience against subtle forgeries. --- ### DeepBlip: Estimating Conditional Average Treatment Effects Over Time Authors: Haorui Ma, Dennis Frauen, Stefan Feuerriegel Published: 2025-11-18 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2511.14545v1 Structural nested mean models (SNMMs) are a principled approach to estimate the treatment effects over time. A particular strength of SNMMs is to break the joint effect of treatment sequences over time into localized, time-specific ``blip effects''. This decomposition promotes interpretability through the incremental effects and enables the efficient offline evaluation of optimal treatment policies without re-computation. However, neural frameworks for SNMMs are lacking, as their inherently sequential g-estimation scheme prevents end-to-end, gradient-based training. Here, we propose DeepBlip, the first neural framework for SNMMs, which overcomes this limitation with a novel double optimization trick to enable simultaneous learning of all blip functions. Our DeepBlip seamlessly integrates sequential neural networks like LSTMs or transformers to capture complex temporal dependencies. By design, our method correctly adjusts for time-varying confounding to produce unbiased estimates, and its Neyman-orthogonal loss function ensures robustness to nuisance model misspecification. Finally, we evaluate our DeepBlip across various clinical datasets, where it achieves state-of-the-art performance. --- ### Mind the Gaps: Measuring Visual Artifacts in Dimensionality Reduction Authors: Jaume Ros, Alessio Arleo, Fernando Paulovich Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14544v1 Dimensionality Reduction (DR) techniques are commonly used for the visual exploration and analysis of high-dimensional data due to their ability to project datasets of high-dimensional points onto the 2D plane. However, projecting datasets in lower dimensions often entails some distortion, which is not necessarily easy to recognize but can lead users to misleading conclusions. Several Projection Quality Metrics (PQMs) have been developed as tools to quantify the goodness-of-fit of a DR projection; however, they mostly focus on measuring how well the projection captures the global or local structure of the data, without taking into account the visual distortion of the resulting plots, thus often ignoring the presence of outliers or artifacts that can mislead a visual analysis of the projection. In this work, we introduce the Warping Index (WI), a new metric for measuring the quality of DR projections onto the 2D plane, based on the assumption that the correct preservation of empty regions between points is of crucial importance towards a faithful visual representation of the data. --- ### MissHDD: Hybrid Deterministic Diffusion for Hetrogeneous Incomplete Data Imputation Authors: Youran Zhou, Mohamed Reda Bouadjenek, Sunil Aryal Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14543v1 Incomplete data are common in real-world tabular applications, where numerical, categorical, and discrete attributes coexist within a single dataset. This heterogeneous structure presents significant challenges for existing diffusion-based imputation models, which typically assume a homogeneous feature space and rely on stochastic denoising trajectories. Such assumptions make it difficult to maintain conditional consistency, and they often lead to information collapse for categorical variables or instability when numerical variables require deterministic updates. These limitations indicate that a single diffusion process is insufficient for mixed-type tabular imputation. We propose a hybrid deterministic diffusion framework that separates heterogeneous features into two complementary generative channels. A continuous DDIM-based channel provides efficient and stable deterministic denoising for numerical variables, while a discrete latent-path diffusion channel, inspired by loopholing-based discrete diffusion, models categorical and discrete features without leaving their valid sample manifolds. The two channels are trained under a unified conditional imputation objective, enabling coherent reconstruction of mixed-type incomplete data. Extensive experiments on multiple real-world datasets show that the proposed framework achieves higher imputation accuracy, more stable sampling trajectories, and improved robustness across MCAR, MAR, and MNAR settings compared with existing diffusion-based and classical methods. These results demonstrate the importance of structure-aware diffusion processes for advancing deep learning approaches to incomplete tabular data. --- ### Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction Authors: Hao Tian, Chenyangguang Zhang, Rui Liu, Wen Shen, Xiaolin Qin Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14540v2 This paper focuses on a challenging setting of simultaneously modeling geometry and appearance of hand-object interaction scenes without any object priors. We follow the trend of dynamic 3D Gaussian Splatting based methods, and address several significant challenges. To model complex hand-object interaction with mutual occlusion and edge blur, we present interaction-aware hand-object Gaussians with newly introduced optimizable parameters aiming to adopt piecewise linear hypothesis for clearer structural representation. Moreover, considering the complementarity and tightness of hand shape and object shape during interaction dynamics, we incorporate hand information into object deformation field, constructing interaction-aware dynamic fields to model flexible motions. To further address difficulties in the optimization process, we propose a progressive strategy that handles dynamic regions and static background step by step. Correspondingly, explicit regularizations are designed to stabilize the hand-object representations for smooth motion transition, physical interaction reality, and coherent lighting. Experiments show that our approach surpasses existing dynamic 3D-GS-based methods and achieves state-of-the-art performance in reconstructing dynamic hand-object interaction. --- ### Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction Authors: Hao Tian, Chenyangguang Zhang, Rui Liu, Wen Shen, Xiaolin Qin Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14540v1 This paper focuses on a challenging setting of simultaneously modeling geometry and appearance of hand-object interaction scenes without any object priors. We follow the trend of dynamic 3D Gaussian Splatting based methods, and address several significant challenges. To model complex hand-object interaction with mutual occlusion and edge blur, we present interaction-aware hand-object Gaussians with newly introduced optimizable parameters aiming to adopt piecewise linear hypothesis for clearer structural representation. Moreover, considering the complementarity and tightness of hand shape and object shape during interaction dynamics, we incorporate hand information into object deformation field, constructing interaction-aware dynamic fields to model flexible motions. To further address difficulties in the optimization process, we propose a progressive strategy that handles dynamic regions and static background step by step. Correspondingly, explicit regularizations are designed to stabilize the hand-object representations for smooth motion transition, physical interaction reality, and coherent lighting. Experiments show that our approach surpasses existing dynamic 3D-GS-based methods and achieves state-of-the-art performance in reconstructing dynamic hand-object interaction. --- ### Learning Compact Latent Space for Representing Neural Signed Distance Functions with High-fidelity Geometry Details Authors: Qiang Bai, Bojian Wu, Xi Yang, Zhizhong Han Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14539v1 Neural signed distance functions (SDFs) have been a vital representation to represent 3D shapes or scenes with neural networks. An SDF is an implicit function that can query signed distances at specific coordinates for recovering a 3D surface. Although implicit functions work well on a single shape or scene, they pose obstacles when analyzing multiple SDFs with high-fidelity geometry details, due to the limited information encoded in the latent space for SDFs and the loss of geometry details. To overcome these obstacles, we introduce a method to represent multiple SDFs in a common space, aiming to recover more high-fidelity geometry details with more compact latent representations. Our key idea is to take full advantage of the benefits of generalization-based and overfitting-based learning strategies, which manage to preserve high-fidelity geometry details with compact latent codes. Based on this framework, we also introduce a novel sampling strategy to sample training queries. The sampling can improve the training efficiency and eliminate artifacts caused by the influence of other SDFs. We report numerical and visual evaluations on widely used benchmarks to validate our designs and show advantages over the latest methods in terms of the representative ability and compactness. --- ### A Neuro-Symbolic Framework for Reasoning under Perceptual Uncertainty: Bridging Continuous Perception and Discrete Symbolic Planning Authors: Jiahao Wu, Shengwen Yu Published: 2025-11-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.14533v1 Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty from perception to planning, providing a principled connection between these two abstraction levels. Our approach couples a transformer-based perceptual front-end with graph neural network (GNN) relational reasoning to extract probabilistic symbolic states from visual observations, and an uncertainty-aware symbolic planner that actively gathers information when confidence is low. We demonstrate the framework's effectiveness on tabletop robotic manipulation as a concrete application: the translator processes 10,047 PyBullet-generated scenes (3--10 objects) and outputs probabilistic predicates with calibrated confidences (overall F1=0.68). When embedded in the planner, the system achieves 94\%/90\%/88\% success on Simple Stack, Deep Stack, and Clear+Stack benchmarks (90.7\% average), exceeding the strongest POMDP baseline by 10--14 points while planning within 15\,ms. A probabilistic graphical-model analysis establishes a quantitative link between calibrated uncertainty and planning convergence, providing theoretical guarantees that are validated empirically. The framework is general-purpose and can be applied to any domain requiring uncertainty-aware reasoning from perceptual input to symbolic planning. --- ### LiveRAG: A diverse Q&A dataset with varying difficulty level for RAG evaluation Authors: David Carmel, Simone Filice, Guy Horowitz, Yoelle Maarek, Alex Shtoff, Oren Somekh, Ran Tavory Published: 2025-11-18 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2511.14531v1 With Retrieval Augmented Generation (RAG) becoming more and more prominent in generative AI solutions, there is an emerging need for systematically evaluating their effectiveness. We introduce the LiveRAG benchmark, a publicly available dataset of 895 synthetic questions and answers designed to support systematic evaluation of RAG-based Q&A systems. This synthetic benchmark is derived from the one used during the SIGIR'2025 LiveRAG Challenge, where competitors were evaluated under strict time constraints. It is augmented with information that was not made available to competitors during the Challenge, such as the ground-truth answers, together with their associated supporting claims which were used for evaluating competitors' answers. In addition, each question is associated with estimated difficulty and discriminability scores, derived from applying an Item Response Theory model to competitors' responses. Our analysis highlights the benchmark's questions diversity, the wide range of their difficulty levels, and their usefulness in differentiating between system capabilities. The LiveRAG benchmark will hopefully help the community advance RAG research, conduct systematic evaluation, and develop more robust Q&A systems. --- ### DeCo-VAE: Learning Compact Latents for Video Reconstruction via Decoupled Representation Authors: Xiangchen Yin, Jiahui Yuan, Zhangchi Hu, Wenzhang Sun, Jie Chen, Xiaozhen Qiao, Hao Li, Xiaoyan Sun Published: 2025-11-18 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2511.14530v1 Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled VAE (DeCo-VAE) to achieve compact latent representation. Instead of encoding RGB pixels directly, we decompose video content into distinct components via explicit decoupling: keyframe, motion and residual, and learn dedicated latent representation for each. To avoid cross-component interference, we design dedicated encoders for each decoupled component and adopt a shared 3D decoder to maintain spatiotemporal consistency during reconstruction. We further utilize a decoupled adaptation strategy that freezes partial encoders while training the others sequentially, ensuring stable training and accurate learning of both static and dynamic features. Extensive quantitative and qualitative experiments demonstrate that DeCo-VAE achieves superior video reconstruction performance. --- ### A Generative Data Framework with Authentic Supervision for Underwater Image Restoration and Enhancement Authors: Yufeng Tian, Yifan Chen, Zhe Sun, Libang Chen, Mingyu Dou, Jijun Lu, Ye Zheng, Xuelong Li Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14521v1 Underwater image restoration and enhancement are crucial for correcting color distortion and restoring image details, thereby establishing a fundamental basis for subsequent underwater visual tasks. However, current deep learning methodologies in this area are frequently constrained by the scarcity of high-quality paired datasets. Since it is difficult to obtain pristine reference labels in underwater scenes, existing benchmarks often rely on manually selected results from enhancement algorithms, providing debatable reference images that lack globally consistent color and authentic supervision. This limits the model's capabilities in color restoration, image enhancement, and generalization. To overcome this limitation, we propose using in-air natural images as unambiguous reference targets and translating them into underwater-degraded versions, thereby constructing synthetic datasets that provide authentic supervision signals for model learning. Specifically, we establish a generative data framework based on unpaired image-to-image translation, producing a large-scale dataset that covers 6 representative underwater degradation types. The framework constructs synthetic datasets with precise ground-truth labels, which facilitate the learning of an accurate mapping from degraded underwater images to their pristine scene appearances. Extensive quantitative and qualitative experiments across 6 representative network architectures and 3 independent test sets show that models trained on our synthetic data achieve comparable or superior color restoration and generalization performance to those trained on existing benchmarks. This research provides a reliable and scalable data-driven solution for underwater image restoration and enhancement. The generated dataset is publicly available at: https://github.com/yftian2025/SynUIEDatasets.git. --- ### D-PerceptCT: Deep Perceptual Enhancement for Low-Dose CT Images Authors: Taifour Yousra Nabila, Azeddine Beghdadi, Marie Luong, Zuheng Ming, Habib Zaidi, Faouzi Alaya Cheikh Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14518v1 Low Dose Computed Tomography (LDCT) is widely used as an imaging solution to aid diagnosis and other clinical tasks. However, this comes at the price of a deterioration in image quality due to the low dose of radiation used to reduce the risk of secondary cancer development. While some efficient methods have been proposed to enhance LDCT quality, many overestimate noise and perform excessive smoothing, leading to a loss of critical details. In this paper, we introduce D-PerceptCT, a novel architecture inspired by key principles of the Human Visual System (HVS) to enhance LDCT images. The objective is to guide the model to enhance or preserve perceptually relevant features, thereby providing radiologists with CT images where critical anatomical structures and fine pathological details are perceptu- ally visible. D-PerceptCT consists of two main blocks: 1) a Visual Dual-path Extractor (ViDex), which integrates semantic priors from a pretrained DINOv2 model with local spatial features, allowing the network to incorporate semantic-awareness during enhancement; (2) a Global-Local State-Space block that captures long-range information and multiscale features to preserve the important structures and fine details for diagnosis. In addition, we propose a novel deep perceptual loss, designated as the Deep Perceptual Relevancy Loss Function (DPRLF), which is inspired by human contrast sensitivity, to further emphasize perceptually important features. Extensive experiments on the Mayo2016 dataset demonstrate the effectiveness of D-PerceptCT method for LDCT enhancement, showing better preservation of structural and textural information within LDCT images compared to SOTA methods. --- ### Full-Atom Peptide Design via Riemannian-Euclidean Bayesian Flow Networks Authors: Hao Qian, Shikui Tu, Lei Xu Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14516v2 Diffusion and flow matching models have recently emerged as promising approaches for peptide binder design. Despite their progress, these models still face two major challenges. First, categorical sampling of discrete residue types collapses their continuous parameters into onehot assignments, while continuous variables (e.g., atom positions) evolve smoothly throughout the generation process. This mismatch disrupts the update dynamics and results in suboptimal performance. Second, current models assume unimodal distributions for side-chain torsion angles, which conflicts with the inherently multimodal nature of side chain rotameric states and limits prediction accuracy. To address these limitations, we introduce PepBFN, the first Bayesian flow network for full atom peptide design that directly models parameter distributions in fully continuous space. Specifically, PepBFN models discrete residue types by learning their continuous parameter distributions, enabling joint and smooth Bayesian updates with other continuous structural parameters. It further employs a novel Gaussian mixture based Bayesian flow to capture the multimodal side chain rotameric states and a Matrix Fisher based Riemannian flow to directly model residue orientations on the $\mathrm{SO}(3)$ manifold. Together, these parameter distributions are progressively refined via Bayesian updates, yielding smooth and coherent peptide generation. Experiments on side chain packing, reverse folding, and binder design tasks demonstrate the strong potential of PepBFN in computational peptide design. --- ### Full Atom Peptide Design via Riemannian Euclidean Bayesian Flow Networks Authors: Hao Qian, Shikui Tu, Lei Xu Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14516v1 Diffusion and flow matching models have recently emerged as promising approaches for peptide binder design. Despite their progress, these models still face two major challenges. First, categorical sampling of discrete residue types collapses their continuous parameters into onehot assignments, while continuous variables (e.g., atom positions) evolve smoothly throughout the generation process. This mismatch disrupts the update dynamics and results in suboptimal performance. Second, current models assume unimodal distributions for side-chain torsion angles, which conflicts with the inherently multimodal nature of side chain rotameric states and limits prediction accuracy. To address these limitations, we introduce PepBFN, the first Bayesian flow network for full atom peptide design that directly models parameter distributions in fully continuous space. Specifically, PepBFN models discrete residue types by learning their continuous parameter distributions, enabling joint and smooth Bayesian updates with other continuous structural parameters. It further employs a novel Gaussian mixture based Bayesian flow to capture the multimodal side chain rotameric states and a Matrix Fisher based Riemannian flow to directly model residue orientations on the $\mathrm{SO}(3)$ manifold. Together, these parameter distributions are progressively refined via Bayesian updates, yielding smooth and coherent peptide generation. Experiments on side chain packing, reverse folding, and binder design tasks demonstrate the strong potential of PepBFN in computational peptide design. --- ### IMSE: Efficient U-Net-based Speech Enhancement using Inception Depthwise Convolution and Amplitude-Aware Linear Attention Authors: Xinxin Tang, Bin Qin, Yufang Li Published: 2025-11-18 Categories: cs.SD, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.14515v2 Achieving a balance between lightweight design and high performance remains a significant challenge for speech enhancement (SE) tasks on resource-constrained devices. Existing state-of-the-art methods, such as MUSE, have established a strong baseline with only 0.51M parameters by introducing a Multi-path Enhanced Taylor (MET) transformer and Deformable Embedding (DE). However, an in-depth analysis reveals that MUSE still suffers from efficiency bottlenecks: the MET module relies on a complex "approximate-compensate" mechanism to mitigate the limitations of Taylor-expansion-based attention, while the offset calculation for deformable embedding introduces additional computational burden. This paper proposes IMSE, a systematically optimized and ultra-lightweight network. We introduce two core innovations: 1) Replacing the MET module with Amplitude-Aware Linear Attention (MALA). MALA fundamentally rectifies the "amplitude-ignoring" problem in linear attention by explicitly preserving the norm information of query vectors in the attention calculation, achieving efficient global modeling without an auxiliary compensation branch. 2) Replacing the DE module with Inception Depthwise Convolution (IDConv). IDConv borrows the Inception concept, decomposing large-kernel operations into efficient parallel branches (square, horizontal, and vertical strips), thereby capturing spectrogram features with extremely low parameter redundancy. Extensive experiments on the VoiceBank+DEMAND dataset demonstrate that, compared to the MUSE baseline, IMSE significantly reduces the parameter count by 16.8\% (from 0.513M to 0.427M) while achieving competitive performance comparable to the state-of-the-art on the PESQ metric (3.373). This study sets a new benchmark for the trade-off between model size and speech quality in ultra-lightweight speech enhancement. --- ### IMSE: Efficient U-Net-based Speech Enhancement using Inception Depthwise Convolution and Amplitude-Aware Linear Attention Authors: Xinxin Tang, Bin Qin, Yufang Li Published: 2025-11-18 Categories: cs.SD, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.14515v1 Achieving a balance between lightweight design and high performance remains a significant challenge for speech enhancement (SE) tasks on resource-constrained devices. Existing state-of-the-art methods, such as MUSE, have established a strong baseline with only 0.51M parameters by introducing a Multi-path Enhanced Taylor (MET) transformer and Deformable Embedding (DE). However, an in-depth analysis reveals that MUSE still suffers from efficiency bottlenecks: the MET module relies on a complex "approximate-compensate" mechanism to mitigate the limitations of Taylor-expansion-based attention, while the offset calculation for deformable embedding introduces additional computational burden. This paper proposes IMSE, a systematically optimized and ultra-lightweight network. We introduce two core innovations: 1) Replacing the MET module with Amplitude-Aware Linear Attention (MALA). MALA fundamentally rectifies the "amplitude-ignoring" problem in linear attention by explicitly preserving the norm information of query vectors in the attention calculation, achieving efficient global modeling without an auxiliary compensation branch. 2) Replacing the DE module with Inception Depthwise Convolution (IDConv). IDConv borrows the Inception concept, decomposing large-kernel operations into efficient parallel branches (square, horizontal, and vertical strips), thereby capturing spectrogram features with extremely low parameter redundancy. Extensive experiments on the VoiceBank+DEMAND dataset demonstrate that, compared to the MUSE baseline, IMSE significantly reduces the parameter count by 16.8\% (from 0.513M to 0.427M) while achieving competitive performance comparable to the state-of-the-art on the PESQ metric (3.373). This study sets a new benchmark for the trade-off between model size and speech quality in ultra-lightweight speech enhancement. --- ### LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference Authors: Jiawei Yi, Ping Gong, Youhui Bai, Zewen Jin, Shengnan Wang, Jiaqi Ruan, Jia He, Jiaan Zhu, Pengcheng Wang, Haibo Wang, Weiguang Wang, Xia Zhu et al. Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14510v2 During LLM inference, KVCache memory usage grows linearly with sequence length and batch size and often exceeds GPU capacity. Recent proposals offload KV states to host memory and reduce transfers using top-k attention. But their CPU-centric management of the on-GPU cache and CPU-GPU data movement incurs high overhead and fragments the bulk GPU execution that CUDA Graph relies on. To close this gap, we observe that adjacent queries within the same attention head exhibit strong directional similarity and retrieve highly overlapping top-k KV states. This insight enables a simple head granularity cache algorithm, QSAC, in which each head reuses its previously cached KV states whenever the current query is sufficiently similar to the prior one. QSAC further simplifies cache management primitives and cuts CPU involvement almost entirely. We develop LiteCache, a KVCache subsystem that incorporates QSAC. LiteCache introduces a GPU-centric synchronization controller and speculative sparse prefetching, enabling fully overlapped data movement and computation. These mechanisms produce a stable and predictable execution pattern that remains compatible with the bulk execution mode required by CUDA Graphs. Evaluation on two widely-used LLMs indicates that LiteCache achieves comparable accuracy to baselines, while sharply minimizing CPU overhead, fully utilizing PCIe bandwidth, thus improving decoding throughput by 10.7-224.2% on both H100 and A40 GPUs and easily supporting sequence lengths beyond 1M. We opensource LiteCache at https://anonymous.4open.science/r/LiteCache-888D. --- ### CLO: Efficient LLM Inference System with CPU-Light KVCache Offloading via Algorithm-System Co-Design Authors: Jiawei Yi, Ping Gong, Youhui Bai, Jiaqi Ruan, Shengnan Wang, Pengcheng Wang, Haibo Wang, Weiguang Wang, Xia Zhu, Feng Wu, Cheng Li Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14510v1 The growth of million-token LLMs exposes the scalability limits of inference systems, where the KVCache dominates memory usage and data transfer overhead. Recent offloading systems migrate the KVCache to CPU memory and incorporate top-k attention to reduce the volume of data transferred from the CPU, while further applying system-level optimizations such as on-GPU caching and prefetching to lower transfer overhead. However, they overlook the CPU bottleneck in three aspects: (1) substantial overhead of fine-grained dynamic cache management performed on the CPU side, (2) significant transfer overhead from poor PCIe bandwidth utilization caused by heavy gathering operations at the CPU side, and (3) GPU runtime bubbles introduced by coarse-grained CPU-centric synchronization. To address these challenges, we propose CLO, a CPU-light KVCache offloading system via algorithm-system co-design. CLO features: (1) a coarse-grained head-wise approximate on-GPU caching strategy with negligible cache management cost, (2) seamless combination of data prefetching and on-GPU persistent caching for lower transfer overhead, (3) a zero-copy transfer engine to fully exploit PCIe bandwidth, and a GPU-centric synchronization method to eliminate GPU stalls. Evaluation on two widely-used LLMs demonstrates that CLO achieves comparable accuracy to state-of-the-art systems, while substantially minimizing CPU overhead, fully utilizing PCIe bandwidth, thus improving decoding throughput by 9.3%-66.6%. Our results highlight that algorithm-system co-design is essential for memory-constrained LLM inference on modern GPU platforms. We open source CLO at https://github.com/CommediaJW/CLO. --- ### Parameter Aware Mamba Model for Multi-task Dense Prediction Authors: Xinzhuo Yu, Yunzhi Zhuge, Sitong Gong, Lu Zhang, Pingping Zhang, Huchuan Lu Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14503v1 Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this work, we introduce a novel decoder-based framework, Parameter Aware Mamba Model (PAMM), specifically designed for dense prediction in multi-task learning setting. Distinct from approaches that employ Transformers to model holistic task relationships, PAMM leverages the rich, scalable parameters of state space models to enhance task interconnectivity. It features dual state space parameter experts that integrate and set task-specific parameter priors, capturing the intrinsic properties of each task. This approach not only facilitates precise multi-task interactions but also allows for the global integration of task priors through the structured state space sequence model (S4). Furthermore, we employ the Multi-Directional Hilbert Scanning method to construct multi-angle feature sequences, thereby enhancing the sequence model's perceptual capabilities for 2D data. Extensive experiments on the NYUD-v2 and PASCAL-Context benchmarks demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/CQC-gogopro/PAMM. --- ### Improved Convergence in Parameter-Agnostic Error Feedback through Momentum Authors: Abdurakhmon Sadiev, Yury Demidovich, Igor Sokolov, Grigory Malinovsky, Sarit Khirirat, Peter Richtárik Published: 2025-11-18 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2511.14501v1 Communication compression is essential for scalable distributed training of modern machine learning models, but it often degrades convergence due to the noise it introduces. Error Feedback (EF) mechanisms are widely adopted to mitigate this issue of distributed compression algorithms. Despite their popularity and training efficiency, existing distributed EF algorithms often require prior knowledge of problem parameters (e.g., smoothness constants) to fine-tune stepsizes. This limits their practical applicability especially in large-scale neural network training. In this paper, we study normalized error feedback algorithms that combine EF with normalized updates, various momentum variants, and parameter-agnostic, time-varying stepsizes, thus eliminating the need for problem-dependent tuning. We analyze the convergence of these algorithms for minimizing smooth functions, and establish parameter-agnostic complexity bounds that are close to the best-known bounds with carefully-tuned problem-dependent stepsizes. Specifically, we show that normalized EF21 achieve the convergence rate of near ${O}(1/T^{1/4})$ for Polyak's heavy-ball momentum, ${O}(1/T^{2/7})$ for Iterative Gradient Transport (IGT), and ${O}(1/T^{1/3})$ for STORM and Hessian-corrected momentum. Our results hold with decreasing stepsizes and small mini-batches. Finally, our empirical experiments confirm our theoretical insights. --- ### Enhancing End-to-End Autonomous Driving with Risk Semantic Distillaion from VLM Authors: Jack Qin, Zhitao Wang, Yinan Zheng, Keyu Chen, Yang Zhou, Yuanxin Zhong, Siyuan Cheng Published: 2025-11-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.14499v1 The autonomous driving (AD) system has exhibited remarkable performance in complex driving scenarios. However, generalization is still a key limitation for the current system, which refers to the ability to handle unseen scenarios or unfamiliar sensor configurations.Related works have explored the use of Vision-Language Models (VLMs) to address few-shot or zero-shot tasks. While promising, these methods introduce a new challenge: the emergence of a hybrid AD system, where two distinct systems are used to plan a trajectory, leading to potential inconsistencies. Alternative research directions have explored Vision-Language-Action (VLA) frameworks that generate control actions from VLM directly. However, these end-to-end solutions demonstrate prohibitive computational demands. To overcome these challenges, we introduce Risk Semantic Distillation (RSD), a novel framework that leverages VLMs to enhance the training of End-to-End (E2E) AD backbones. By providing risk attention for key objects, RSD addresses the issue of generalization. Specifically, we introduce RiskHead, a plug-in module that distills causal risk estimates from Vision-Language Models into Bird's-Eye-View (BEV) features, yielding interpretable risk-attention maps.This approach allows BEV features to learn richer and more nuanced risk attention representations, which directly enhance the model's ability to handle spatial boundaries and risky objects.By focusing on risk attention, RSD aligns better with human-like driving behavior, which is essential to navigate in complex and dynamic environments. Our experiments on the Bench2Drive benchmark demonstrate the effectiveness of RSD in managing complex and unpredictable driving conditions. Due to the enhanced BEV representations enabled by RSD, we observed a significant improvement in both perception and planning capabilities. --- ### Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching Authors: Jintao Zhang, Mingyue Cheng, Zirui Liu, Xianquan Wang, Yitong Zhou, Qi Liu Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14488v1 Time series generation is critical for a wide range of applications, which greatly supports downstream analytical and decision-making tasks. However, the inherent temporal heterogeneous induced by localized perturbations present significant challenges for generating structurally consistent time series. While flow matching provides a promising paradigm by modeling temporal dynamics through trajectory-level supervision, it fails to adequately capture abrupt transitions in perturbed time series, as the use of globally shared parameters constrains the velocity field to a unified representation. To address these limitations, we introduce \textbf{PAFM}, a \textbf{P}erturbation-\textbf{A}ware \textbf{F}low \textbf{M}atching framework that models perturbed trajectories to ensure stable and structurally consistent time series generation. The framework incorporates perturbation-guided training to simulate localized disturbances and leverages a dual-path velocity field to capture trajectory deviations under perturbation, enabling refined modeling of perturbed behavior to enhance the structural coherence. In order to further improve sensitivity to trajectory perturbations while enhancing expressiveness, a mixture-of-experts decoder with flow routing dynamically allocates modeling capacity in response to different trajectory dynamics. Extensive experiments on both unconditional and conditional generation tasks demonstrate that PAFM consistently outperforms strong baselines. Code is available at https://anonymous.4open.science/r/PAFM-03B2. --- ### Notes on Kernel Methods in Machine Learning Authors: Diego Armando Pérez-Rosero, Danna Valentina Salazar-Dubois, Juan Camilo Lugo-Rojas, Andrés Marino Álvarez-Meza, Germán Castellanos-Dominguez Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14485v1 These notes provide a self-contained introduction to kernel methods and their geometric foundations in machine learning. Starting from the construction of Hilbert spaces, we develop the theory of positive definite kernels, reproducing kernel Hilbert spaces (RKHS), and Hilbert-Schmidt operators, emphasizing their role in statistical estimation and representation of probability measures. Classical concepts such as covariance, regression, and information measures are revisited through the lens of Hilbert space geometry. We also introduce kernel density estimation, kernel embeddings of distributions, and the Maximum Mean Discrepancy (MMD). The exposition is designed to serve as a foundation for more advanced topics, including Gaussian processes, kernel Bayesian inference, and functional analytic approaches to modern machine learning. --- ### Towards a Comprehensive Theory of Reservoir Computing Authors: Denis Kleyko, Christopher J. Kymn, E. Paxon Frady, Amy Loutfi, Friedrich T. Sommer Published: 2025-11-18 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.14484v2 In reservoir computing, an input sequence is processed by a recurrent neural network, the reservoir, which transforms it into a spatial pattern that a shallow readout network can then exploit for tasks such as memorization and time-series prediction or classification. Echo state networks (ESN) are a model class in which the reservoir is a traditional artificial neural network. This class contains many model types, each with sets of hyperparameters. Selecting models and parameter settings for particular applications requires a theory for predicting and comparing performances. Here, we demonstrate that recent developments of perceptron theory can be used to predict the memory capacity and accuracy of a wide variety of ESN models, including reservoirs with linear neurons, sigmoid nonlinear neurons, different types of recurrent matrices, and different types of readout networks. Across thirty variants of ESNs, we show that empirical results consistently confirm the theory's predictions. As a practical demonstration, the theory is used to optimize memory capacity of an ESN in the entire joint parameter space. Further, guided by the theory, we propose a novel ESN model with a readout network that does not require training, and which outperforms earlier ESN models without training. Finally, we characterize the geometry of the readout networks in ESNs, which reveals that many ESN models exhibit a similar regular simplex geometry as has been observed in the output weights of deep neural networks. --- ### Towards a Comprehensive Theory of Reservoir Computing Authors: Denis Kleyko, Christopher J. Kymn, E. Paxon Frady, Amy Loutfi, Friedrich T. Sommer Published: 2025-11-18 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.14484v1 In reservoir computing, an input sequence is processed by a recurrent neural network, the reservoir, which transforms it into a spatial pattern that a shallow readout network can then exploit for tasks such as memorization and time-series prediction or classification. Echo state networks (ESN) are a model class in which the reservoir is a traditional artificial neural network. This class contains many model types, each with sets of hyperparameters. Selecting models and parameter settings for particular applications requires a theory for predicting and comparing performances. Here, we demonstrate that recent developments of perceptron theory can be used to predict the memory capacity and accuracy of a wide variety of ESN models, including reservoirs with linear neurons, sigmoid nonlinear neurons, different types of recurrent matrices, and different types of readout networks. Across thirty variants of ESNs, we show that empirical results consistently confirm the theory's predictions. As a practical demonstration, the theory is used to optimize memory capacity of an ESN in the entire joint parameter space. Further, guided by the theory, we propose a novel ESN model with a readout network that does not require training, and which outperforms earlier ESN models without training. Finally, we characterize the geometry of the readout networks in ESNs, which reveals that many ESN models exhibit a similar regular simplex geometry as has been observed in the output weights of deep neural networks. --- ### Gradient-Based Join Ordering Authors: Tim Schwabe, Maribel Acosta Published: 2025-11-18 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2511.14482v2 Join ordering is the NP-hard problem of selecting the most efficient order in which to evaluate joins (conjunctive, binary operators) in a database query. Because query execution performance critically depends on this choice, join ordering lies at the core of query optimization. Traditional approaches cast this problem as a discrete combinatorial search over binary trees guided by a cost model, but they have trade-offs between effectiveness and efficiency. We show that when the cost model is differentiable, query plans can be continuously relaxed into a soft adjacency matrix that represents a superposition of plans. This continuous relaxation, combined with differentiable constraints that enforce plan validity, enables a gradient-based search for low-cost plans within this relaxed space. Using a Graph Neural Network as the cost model, we demonstrate that this gradient-based approach can find comparable and even lower-cost plans compared to traditional discrete search methods on two different graph datasets. Furthermore, we empirically show that the runtime of this approach scales better than discrete search algorithms. We believe this first step towards gradient-based join ordering can lead to more effective and efficient query optimizers in the future. --- ### Gradient-Based Join Ordering Authors: Tim Schwabe, Maribel Acosta Published: 2025-11-18 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2511.14482v1 Join ordering is the NP-hard problem of selecting the most efficient sequence in which to evaluate joins (conjunctive, binary operators) in a database query. As the performance of query execution critically depends on this choice, join ordering lies at the core of query optimization. Traditional approaches cast this problem as a discrete combinatorial search over binary trees guided by a cost model, but they often suffer from high computational complexity and limited scalability. We show that, when the cost model is differentiable, the query plans can be continuously relaxed into a soft adjacency matrix representing a superposition of plans. This continuous relaxation, together with a Gumbel-Softmax parameterization of the adjacency matrix and differentiable constraints enforcing plan validity, enables gradient-based search for plans within this relaxed space. Using a learned Graph Neural Network as the cost model, we demonstrate that this gradient-based approach can find comparable and even lower-cost plans compared to traditional discrete local search methods on two different graph datasets. Furthermore, we empirically show that the runtime of this approach scales linearly with query size, in contrast to quadratic or exponential runtimes of classical approaches. We believe this first step towards gradient-based join ordering can lead to more effective and efficient query optimizers in the future. --- ### Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary Delineation Authors: Aditi Agarwal, Anjali Jain, Nikita Saxena, Ishan Deshpande, Michal Kazmierski, Abigail Annkah, Nadav Sherman, Karthikeyan Shanmugam, Alok Talekar, Vaibhav Rajan Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14481v1 Delineating farm boundaries through segmentation of satellite images is a fundamental step in many agricultural applications. The task is particularly challenging for smallholder farms, where accurate delineation requires the use of high resolution (HR) imagery which are available only at low revisit frequencies (e.g., annually). To support more frequent (sub-) seasonal monitoring, HR images could be combined as references (ref) with low resolution (LR) images -- having higher revisit frequency (e.g., weekly) -- using reference-based super-resolution (Ref-SR) methods. However, current Ref-SR methods optimize perceptual quality and smooth over crucial features needed for downstream tasks, and are unable to meet the large scale-factor requirements for this task. Further, previous two-step approaches of SR followed by segmentation do not effectively utilize diverse satellite sources as inputs. We address these problems through a new approach, $\textbf{SEED-SR}$, which uses a combination of conditional latent diffusion models and large-scale multi-spectral, multi-source geo-spatial foundation models. Our key innovation is to bypass the explicit SR task in the pixel space and instead perform SR in a segmentation-aware latent space. This unique approach enables us to generate segmentation maps at an unprecedented 20$\times$ scale factor, and rigorous experiments on two large, real datasets demonstrate up to $\textbf{25.5}$ and $\textbf{12.9}$ relative improvement in instance and semantic segmentation metrics respectively over approaches based on state-of-the-art Ref-SR methods. ---