# Research Papers — 2025-12 · bundle page 96 of 175 > Full-text markdown of papers #4751–4800 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/96 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/95.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/97.md) ### AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org Authors: Jaehyung Lee, Justin Ely, Kent Zhang, Akshaya Ajith, Charles Rhys Campbell, Kamal Choudhary Published: 2025-12-12 Categories: cs.AI, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2512.11935v2 Agentic AI systems increasingly connect large language models (LLMs) to external scientific tools, yet whether and when tool access improves prediction accuracy remains uncharacterized. We present AGAPI (AtomGPT.org API), an open access platform integrating eight open-source LLMs with 18 REST endpoints (28 agent tools, 50 web apps) spanning materials databases, force fields, tight-binding band structures, X-ray diffraction, and protein structure. A three-evaluation residual decomposition on JARVIS-Leaderboard electronic-structure test sets separates agent pipeline fidelity from inherited density functional theory (DFT) functional bias. For bulk modulus and bandgap the agent reproduces JARVIS-DFT entries to numerical precision, so the experimental-reference degradation is functional bias, not agentic malfunction. On memorization-resistant test sets (57 defective supercells, 60 hypothetical compositions), tool-augmented mean absolute error (MAE) is below 0.005 eV versus 1.25 to 1.86 eV tool-free, confirming tools are indispensable where parametric knowledge is unavailable. We further demonstrate autonomous multi-step workflows including 10-operation defect-engineering pipelines. AGAPI is available at https://github.com/atomgptlab/agapi. --- ### Unveiling User Perceptions in the Generative AI Era: A Sentiment-Driven Evaluation of AI Educational Apps' Role in Digital Transformation of e-Teaching Authors: Adeleh Mazaherian, Erfan Nourbakhsh Published: 2025-12-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.11934v1 The rapid integration of generative artificial intelligence into education has driven digital transformation in e-teaching, yet user perceptions of AI educational apps remain underexplored. This study performs a sentiment-driven evaluation of user reviews from top AI ed-apps on the Google Play Store to assess efficacy, challenges, and pedagogical implications. Our pipeline involved scraping app data and reviews, RoBERTa for binary sentiment classification, GPT-4o for key point extraction, and GPT-5 for synthesizing top positive/negative themes. Apps were categorized into seven types (e.g., homework helpers, math solvers, language tools), with overlaps reflecting multifunctional designs. Results indicate predominantly positive sentiments, with homework apps like Edu AI (95.9% positive) and Answer.AI (92.7%) leading in accuracy, speed, and personalization, while language/LMS apps (e.g., Teacher AI at 21.8% positive) lag due to instability and limited features. Positives emphasize efficiency in brainstorming, problem-solving, and engagement; negatives center on paywalls, inaccuracies, ads, and glitches. Trends show that homework helpers outperform specialized tools, highlighting AI's democratizing potential amid risks of dependency and inequity. The discussion proposes future ecosystems with hybrid AI-human models, VR/AR for immersive learning, and a roadmap for developers (adaptive personalization) and policymakers (monetization regulation for inclusivity). This underscores generative AI's role in advancing e-teaching by enabling ethical refinements that foster equitable, innovative environments. The full dataset is available here(https://github.com/erfan-nourbakhsh/GenAI-EdSent). --- ### The Agentic Regulator: Risks for AI in Finance and a Proposed Agent-based Framework for Governance Authors: Eren Kurshan, Tucker Balch, David Byrd Published: 2025-12-12 Categories: cs.CY, cs.AI, cs.CE, cs.MA, q-fin.GN arXiv: https://arxiv.org/abs/2512.11933v1 Generative and agentic artificial intelligence is entering financial markets faster than existing governance can adapt. Current model-risk frameworks assume static, well-specified algorithms and one-time validations; large language models and multi-agent trading systems violate those assumptions by learning continuously, exchanging latent signals, and exhibiting emergent behavior. Drawing on complex adaptive systems theory, we model these technologies as decentralized ensembles whose risks propagate along multiple time-scales. We then propose a modular governance architecture. The framework decomposes oversight into four layers of "regulatory blocks": (i) self-regulation modules embedded beside each model, (ii) firm-level governance blocks that aggregate local telemetry and enforce policy, (iii) regulator-hosted agents that monitor sector-wide indicators for collusive or destabilizing patterns, and (iv) independent audit blocks that supply third-party assurance. Eight design strategies enable the blocks to evolve as fast as the models they police. A case study on emergent spoofing in multi-agent trading shows how the layered controls quarantine harmful behavior in real time while preserving innovation. The architecture remains compatible with today's model-risk rules yet closes critical observability and control gaps, providing a practical path toward resilient, adaptive AI governance in financial systems. --- ### Mapping AI Risk Mitigations: Evidence Scan and Preliminary AI Risk Mitigation Taxonomy Authors: Alexander K. Saeri, Sophia Lloyd George, Jess Graham, Clelia D. Lacarriere, Peter Slattery, Michael Noetel, Neil Thompson Published: 2025-12-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.11931v1 Organizations and governments that develop, deploy, use, and govern AI must coordinate on effective risk mitigation. However, the landscape of AI risk mitigation frameworks is fragmented, uses inconsistent terminology, and has gaps in coverage. This paper introduces a preliminary AI Risk Mitigation Taxonomy to organize AI risk mitigations and provide a common frame of reference. The Taxonomy was developed through a rapid evidence scan of 13 AI risk mitigation frameworks published between 2023-2025, which were extracted into a living database of 831 AI risk mitigations. The mitigations were iteratively clustered & coded to create the Taxonomy. The preliminary AI Risk Mitigation Taxonomy organizes mitigations into four categories and 23 subcategories: (1) Governance & Oversight: Formal organizational structures and policy frameworks that establish human oversight mechanisms and decision protocols; (2) Technical & Security: Technical, physical, and engineering safeguards that secure AI systems and constrain model behaviors; (3) Operational Process: processes and management frameworks governing AI system deployment, usage, monitoring, incident handling, and validation; and (4) Transparency & Accountability: formal disclosure practices and verification mechanisms that communicate AI system information and enable external scrutiny. The rapid evidence scan and taxonomy construction also revealed several cases where terms like 'risk management' and 'red teaming' are used widely but refer to different responsible actors, actions, and mechanisms of action to reduce risk. This Taxonomy and associated mitigation database, while preliminary, offers a starting point for collation and synthesis of AI risk mitigations. It also offers an accessible, structured way for different actors in the AI ecosystem to discuss and coordinate action to reduce risks from AI. --- ### Evolutionary Reinforcement Learning based AI tutor for Socratic Interdisciplinary Instruction Authors: Mei Jiang, Haihai Shen, Zhuo Luo, Bingdong Li, Wenjing Hong, Ke Tang, Aimin Zhou Published: 2025-12-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.11930v1 Cultivating higher-order cognitive abilities -- such as knowledge integration, critical thinking, and creativity -- in modern STEM education necessitates a pedagogical shift from passive knowledge transmission to active Socratic construction. Although Large Language Models (LLMs) hold promise for STEM Interdisciplinary education, current methodologies employing Prompt Engineering (PE), Supervised Fine-tuning (SFT), or standard Reinforcement Learning (RL) often fall short of supporting this paradigm. Existing methods are hindered by three fundamental challenges: the inability to dynamically model latent student cognitive states; severe reward sparsity and delay inherent in long-term educational goals; and a tendency toward policy collapse lacking strategic diversity due to reliance on behavioral cloning. Recognizing the unobservability and dynamic complexity of these interactions, we formalize the Socratic Interdisciplinary Instructional Problem (SIIP) as a structured Partially Observable Markov Decision Process (POMDP), demanding simultaneous global exploration and fine-grained policy refinement. To this end, we propose ERL4SIIP, a novel Evolutionary Reinforcement Learning (ERL) framework specifically tailored for this domain. ERL4SIIP integrates: (1) a dynamic student simulator grounded in a STEM knowledge graph for latent state modeling; (2) a Hierarchical Reward Mechanism that decomposes long-horizon goals into dense signals; and (3) a LoRA-Division based optimization strategy coupling evolutionary algorithms for population-level global search with PPO for local gradient ascent. --- ### MONET -- Virtual Cell Painting of Brightfield Images and Time Lapses Using Reference Consistent Diffusion Authors: Alexander Peysakhovich, William Berman, Joseph Rufo, Felix Wong, Maxwell Z. Wilson Published: 2025-12-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11928v1 Cell painting is a popular technique for creating human-interpretable, high-contrast images of cell morphology. There are two major issues with cell paint: (1) it is labor-intensive and (2) it requires chemical fixation, making the study of cell dynamics impossible. We train a diffusion model (Morphological Observation Neural Enhancement Tool, or MONET) on a large dataset to predict cell paint channels from brightfield images. We show that model quality improves with scale. The model uses a consistency architecture to generate time-lapse videos, despite the impossibility of obtaining cell paint video training data. In addition, we show that this architecture enables a form of in-context learning, allowing the model to partially transfer to out-of-distribution cell lines and imaging protocols. Virtual cell painting is not intended to replace physical cell painting completely, but to act as a complementary tool enabling novel workflows in biological research. --- ### Gene regulatory network inference algorithm based on spectral signed directed graph convolution Authors: Rijie Xi, Weikang Xu, Wei Xiong, Yuannong Ye, Bin Zhao Published: 2025-12-12 Categories: q-bio.MN, cs.AI arXiv: https://arxiv.org/abs/2512.11927v1 Accurately reconstructing Gene Regulatory Networks (GRNs) is crucial for understanding gene functions and disease mechanisms. Single-cell RNA sequencing (scRNA-seq) technology provides vast data for computational GRN reconstruction. Since GRNs are ideally modeled as signed directed graphs to capture activation/inhibition relationships, the most intuitive and reasonable approach is to design feature extractors based on the topological structure of GRNs to extract structural features, then combine them with biological characteristics for research. However, traditional spectral graph convolution struggles with this representation. Thus, we propose MSGRNLink, a novel framework that explicitly models GRNs as signed directed graphs and employs magnetic signed Laplacian convolution. Experiments across simulated and real datasets demonstrate that MSGRNLink outperforms all baseline models in AUROC. Parameter sensitivity analysis and ablation studies confirmed its robustness and the importance of each module. In a bladder cancer case study, MSGRNLink predicted more known edges and edge signs than benchmark models, further validating its biological relevance. --- ### TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder Authors: Qinghao Meng, Chenming Wu, Liangjun Zhang, Jianbing Shen Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11926v1 3D object detection is essential in autonomous driving, providing vital information about moving objects and obstacles. Detecting objects in distant regions with only a few LiDAR points is still a challenge, and numerous strategies have been developed to address point cloud sparsity through densification.This paper presents a joint completion and detection framework that improves the detection feature in sparse areas while maintaining costs unchanged. Specifically, we propose TransBridge, a novel transformer-based up-sampling block that fuses the features from the detection and completion networks.The detection network can benefit from acquiring implicit completion features derived from the completion network. Additionally, we design the Dynamic-Static Reconstruction (DSRecon) module to produce dense LiDAR data for the completion network, meeting the requirement for dense point cloud ground truth.Furthermore, we employ the transformer mechanism to establish connections between channels and spatial relations, resulting in a high-resolution feature map used for completion purposes.Extensive experiments on the nuScenes and Waymo datasets demonstrate the effectiveness of the proposed framework.The results show that our framework consistently improves end-to-end 3D object detection, with the mean average precision (mAP) ranging from 0.7 to 1.5 across multiple methods, indicating its generalization ability. For the two-stage detection framework, it also boosts the mAP up to 5.78 points. --- ### Moment-Based 3D Gaussian Splatting: Resolving Volumetric Occlusion with Order-Independent Transmittance Authors: Jan U. Müller, Robin Tim Landsgesell, Leif Van Holland, Patrick Stotko, Reinhard Klein Published: 2025-12-12 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2512.11800v1 The recent success of 3D Gaussian Splatting (3DGS) has reshaped novel view synthesis by enabling fast optimization and real-time rendering of high-quality radiance fields. However, it relies on simplified, order-dependent alpha blending and coarse approximations of the density integral within the rasterizer, thereby limiting its ability to render complex, overlapping semi-transparent objects. In this paper, we extend rasterization-based rendering of 3D Gaussian representations with a novel method for high-fidelity transmittance computation, entirely avoiding the need for ray tracing or per-pixel sample sorting. Building on prior work in moment-based order-independent transparency, our key idea is to characterize the density distribution along each camera ray with a compact and continuous representation based on statistical moments. To this end, we analytically derive and compute a set of per-pixel moments from all contributing 3D Gaussians. From these moments, a continuous transmittance function is reconstructed for each ray, which is then independently sampled within each Gaussian. As a result, our method bridges the gap between rasterization and physical accuracy by modeling light attenuation in complex translucent media, significantly improving overall reconstruction and rendering quality. --- ### V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties Authors: Ye Fang, Tong Wu, Valentin Deschaintre, Duygu Ceylan, Iliyan Georgiev, Chun-Hao Paul Huang, Yiwei Hu, Xuelin Chen, Tuanfeng Yang Wang Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11799v1 Large-scale video generation models have shown remarkable potential in modeling photorealistic appearance and lighting interactions in real-world scenes. However, a closed-loop framework that jointly understands intrinsic scene properties (e.g., albedo, normal, material, and irradiance), leverages them for video synthesis, and supports editable intrinsic representations remains unexplored. We present V-RGBX, the first end-to-end framework for intrinsic-aware video editing. V-RGBX unifies three key capabilities: (1) video inverse rendering into intrinsic channels, (2) photorealistic video synthesis from these intrinsic representations, and (3) keyframe-based video editing conditioned on intrinsic channels. At the core of V-RGBX is an interleaved conditioning mechanism that enables intuitive, physically grounded video editing through user-selected keyframes, supporting flexible manipulation of any intrinsic modality. Extensive qualitative and quantitative results show that V-RGBX produces temporally consistent, photorealistic videos while propagating keyframe edits across sequences in a physically plausible manner. We demonstrate its effectiveness in diverse applications, including object appearance editing and scene-level relighting, surpassing the performance of prior methods. --- ### Particulate: Feed-Forward 3D Object Articulation Authors: Ruining Li, Yuxin Yao, Chuanxia Zheng, Christian Rupprecht, Joan Lasenby, Shangzhe Wu, Andrea Vedaldi Published: 2025-12-12 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2512.11798v2 We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion constraints. The model is based on a transformer network, the Part Articulation Transformer, which predicts all these parameters for all joints. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate maps the output of the network back to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate also works on AI-generated 3D assets, enabling the generation of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D model. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Empirically, Particulate significantly outperforms state-of-the-art approaches. --- ### Particulate: Feed-Forward 3D Object Articulation Authors: Ruining Li, Yuxin Yao, Chuanxia Zheng, Christian Rupprecht, Joan Lasenby, Shangzhe Wu, Andrea Vedaldi Published: 2025-12-12 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2512.11798v1 We present Particulate, a feed-forward approach that, given a single static 3D mesh of an everyday object, directly infers all attributes of the underlying articulated structure, including its 3D parts, kinematic structure, and motion constraints. At its core is a transformer network, Part Articulation Transformer, which processes a point cloud of the input mesh using a flexible and scalable architecture to predict all the aforementioned attributes with native multi-joint support. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate lifts the network's feed-forward prediction to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate can also accurately infer the articulated structure of AI-generated 3D assets, enabling full-fledged extraction of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D generator. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Quantitative and qualitative results show that Particulate significantly outperforms state-of-the-art approaches. --- ### AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis Authors: Junjie Ye, Rong Xue, Basile Van Hoorick, Pavel Tokmakov, Muhammad Zubair Irshad, Yue Wang, Vitor Guizilini Published: 2025-12-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.11797v2 The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisition is costly and simulators offer limited diversity and fidelity with pronounced sim-to-real gaps. While generative models present an attractive solution, existing methods often alter only visual appearances without creating new behaviors, or suffer from embodiment inconsistencies that yield implausible motions. To address these limitations, we introduce AnchorDream, an embodiment-aware world model that repurposes pretrained video diffusion models for robot data synthesis. AnchorDream conditions the diffusion process on robot motion renderings, anchoring the embodiment to prevent hallucination while synthesizing objects and environments consistent with the robot's kinematics. Starting from only a handful of human teleoperation demonstrations, our method scales them into large, diverse, high-quality datasets without requiring explicit environment modeling. Experiments show that the generated data leads to consistent improvements in downstream policy learning, with relative gains of 36.4% in simulator benchmarks and nearly double performance in real-world studies. These results suggest that grounding generative world models in robot motion provides a practical path toward scaling imitation learning. --- ### AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis Authors: Junjie Ye, Rong Xue, Basile Van Hoorick, Pavel Tokmakov, Muhammad Zubair Irshad, Yue Wang, Vitor Guizilini Published: 2025-12-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.11797v1 The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisition is costly and simulators offer limited diversity and fidelity with pronounced sim-to-real gaps. While generative models present an attractive solution, existing methods often alter only visual appearances without creating new behaviors, or suffer from embodiment inconsistencies that yield implausible motions. To address these limitations, we introduce AnchorDream, an embodiment-aware world model that repurposes pretrained video diffusion models for robot data synthesis. AnchorDream conditions the diffusion process on robot motion renderings, anchoring the embodiment to prevent hallucination while synthesizing objects and environments consistent with the robot's kinematics. Starting from only a handful of human teleoperation demonstrations, our method scales them into large, diverse, high-quality datasets without requiring explicit environment modeling. Experiments show that the generated data leads to consistent improvements in downstream policy learning, with relative gains of 36.4% in simulator benchmarks and nearly double performance in real-world studies. These results suggest that grounding generative world models in robot motion provides a practical path toward scaling imitation learning. --- ### A General Algorithm for Detecting Higher-Order Interactions via Random Sequential Additions Authors: Ahmad Shamail, Claire McWhite Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11793v1 Many systems exhibit complex interactions between their components: some features or actions amplify each other's effects, others provide redundant information, and some contribute independently. We present a simple geometric method for discovering interactions and redundancies: when elements are added in random sequential orders and their contributions plotted over many trials, characteristic L-shaped patterns emerge that directly reflect interaction structure. The approach quantifies how the contribution of each element depends on those added before it, revealing patterns that distinguish interaction, independence, and redundancy on a unified scale. When pairwise contributions are visualized as two--dimensional point clouds, redundant pairs form L--shaped patterns where only the first-added element contributes, while synergistic pairs form L--shaped patterns where only elements contribute together. Independent elements show order--invariant distributions. We formalize this with the L--score, a continuous measure ranging from $-1$ (perfect synergy, e.g. $Y=X_1X_2$) to $0$ (independence) to $+1$ (perfect redundancy, $X_1 \approx X_2$). The relative scaling of the L--shaped arms reveals feature dominance in which element consistently provides more information. Although computed only from pairwise measurements, higher--order interactions among three or more elements emerge naturally through consistent cross--pair relationships (e.g. AB, AC, BC). The method is metric--agnostic and broadly applicable to any domain where performance can be evaluated incrementally over non-repeating element sequences, providing a unified geometric approach to uncovering interaction structure. --- ### Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation Authors: Yang Fei, George Stoica, Jingyuan Liu, Qifeng Chen, Ranjay Krishna, Xiaojuan Wang, Benlin Liu Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11792v1 Reality is a dance between rigid constraints and deformable structures. For video models, that means generating motion that preserves fidelity as well as structure. Despite progress in diffusion models, producing realistic structure-preserving motion remains challenging, especially for articulated and deformable objects such as humans and animals. Scaling training data alone, so far, has failed to resolve physically implausible transitions. Existing approaches rely on conditioning with noisy motion representations, such as optical flow or skeletons extracted using an external imperfect model. To address these challenges, we introduce an algorithm to distill structure-preserving motion priors from an autoregressive video tracking model (SAM2) into a bidirectional video diffusion model (CogVideoX). With our method, we train SAM2VideoX, which contains two innovations: (1) a bidirectional feature fusion module that extracts global structure-preserving motion priors from a recurrent model like SAM2; (2) a Local Gram Flow loss that aligns how local features move together. Experiments on VBench and in human studies show that SAM2VideoX delivers consistent gains (+2.60\% on VBench, 21-22\% lower FVD, and 71.4\% human preference) over prior baselines. Specifically, on VBench, we achieve 95.51\%, surpassing REPA (92.91\%) by 2.60\%, and reduce FVD to 360.57, a 21.20\% and 22.46\% improvement over REPA- and LoRA-finetuning, respectively. The project website can be found at https://sam2videox.github.io/ . --- ### Uncertainty-Aware Domain Adaptation for Vitiligo Segmentation in Clinical Photographs Authors: Wentao Jiang, Vamsi Varra, Caitlin Perez-Stable, Harrison Zhu, Meredith Apicella, Nicole Nyamongo Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11791v2 Accurately quantifying vitiligo extent in routine clinical photographs is crucial for longitudinal monitoring of treatment response. We propose a trustworthy, frequency-aware segmentation framework built on three synergistic pillars: (1) a data-efficient training strategy combining domain-adaptive pre-training on the ISIC 2019 dataset with an ROI-constrained dual-task loss to suppress background noise; (2) an architectural refinement via a ConvNeXt V2-based encoder enhanced with a novel High-Frequency Spectral Gating (HFSG) module and stem-skip connections to capture subtle textures; and (3) a clinical trust mechanism employing K-fold ensemble and Test-Time Augmentation (TTA) to generate pixel-wise uncertainty maps. Extensive validation on an expert-annotated clinical cohort demonstrates superior performance, achieving a Dice score of 85.05% and significantly reducing boundary error (95% Hausdorff Distance improved from 44.79 px to 29.95 px), consistently outperforming strong CNN (ResNet-50 and UNet++) and Transformer (MiT-B5) baselines. Notably, our framework demonstrates high reliability with zero catastrophic failures and provides interpretable entropy maps to identify ambiguous regions for clinician review. Our approach suggests that the proposed framework establishes a robust and reliable standard for automated vitiligo assessment. --- ### Uncertainty-Aware Domain Adaptation for Vitiligo Segmentation in Clinical Photographs Authors: Wentao Jiang, Vamsi Varra, Caitlin Perez-Stable, Harrison Zhu, Meredith Apicella, Nicole Nyamongo Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11791v1 Accurately quantifying vitiligo extent in routine clinical photographs is crucial for longitudinal monitoring of treatment response. We propose a trustworthy, frequency-aware segmentation framework built on three synergistic pillars: (1) a data-efficient training strategy combining domain-adaptive pre-training on the ISIC 2019 dataset with an ROI-constrained dual-task loss to suppress background noise; (2) an architectural refinement via a ConvNeXt V2-based encoder enhanced with a novel High-Frequency Spectral Gating (HFSG) module and stem-skip connections to capture subtle textures; and (3) a clinical trust mechanism employing K-fold ensemble and Test-Time Augmentation (TTA) to generate pixel-wise uncertainty maps. Extensive validation on an expert-annotated clinical cohort demonstrates superior performance, achieving a Dice score of 85.05% and significantly reducing boundary error (95% Hausdorff Distance improved from 44.79 px to 29.95 px), consistently outperforming strong CNN (ResNet-50 and UNet++) and Transformer (MiT-B5) baselines. Notably, our framework demonstrates high reliability with zero catastrophic failures and provides interpretable entropy maps to identify ambiguous regions for clinician review. Our approach suggests that the proposed framework establishes a robust and reliable standard for automated vitiligo assessment. --- ### Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective Authors: Etienne Boursier, Claire Boyer Published: 2025-12-12 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.11784v2 Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax attention under both finite and infinite prompts. For i.i.d. Gaussian inputs, we lean on the fact that the softmax operator converges in the infinite-prompt limit to a linear operator acting on the underlying input-token measure. Building on this insight, we establish non-asymptotic concentration bounds for the output and gradient of softmax attention, quantifying how rapidly the finite-prompt model approaches its infinite-prompt counterpart, and prove that this concentration remains stable along the entire training trajectory in general in-context learning settings with sub-Gaussian tokens. In the case of in-context linear regression, we use the tractable infinite-prompt dynamics to analyze training at finite prompt length. Our results allow optimization analyses developed for linear attention to transfer directly to softmax attention when prompts are sufficiently long, showing that large-prompt softmax attention inherits the analytical structure of its linear counterpart. This, in turn, provides a principled and broadly applicable toolkit for studying the training dynamics and statistical behavior of softmax attention layers in large prompt regimes. --- ### Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective Authors: Etienne Boursier, Claire Boyer Published: 2025-12-12 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.11784v1 Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax attention under both finite and infinite prompts. For i.i.d. Gaussian inputs, we lean on the fact that the softmax operator converges in the infinite-prompt limit to a linear operator acting on the underlying input-token measure. Building on this insight, we establish non-asymptotic concentration bounds for the output and gradient of softmax attention, quantifying how rapidly the finite-prompt model approaches its infinite-prompt counterpart, and prove that this concentration remains stable along the entire training trajectory in general in-context learning settings with sub-Gaussian tokens. In the case of in-context linear regression, we use the tractable infinite-prompt dynamics to analyze training at finite prompt length. Our results allow optimization analyses developed for linear attention to transfer directly to softmax attention when prompts are sufficiently long, showing that large-prompt softmax attention inherits the analytical structure of its linear counterpart. This, in turn, provides a principled and broadly applicable toolkit for studying the training dynamics and statistical behavior of softmax attention layers in large prompt regimes. --- ### Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously Authors: Andrew Adiletta, Kathryn Adiletta, Kemal Derya, Berk Sunar Published: 2025-12-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.11783v1 The rapid deployment of Large Language Models (LLMs) has created an urgent need for enhanced security and privacy measures in Machine Learning (ML). LLMs are increasingly being used to process untrusted text inputs and even generate executable code, often while having access to sensitive system controls. To address these security concerns, several companies have introduced guard models, which are smaller, specialized models designed to protect text generation models from adversarial or malicious inputs. In this work, we advance the study of adversarial inputs by introducing Super Suffixes, suffixes capable of overriding multiple alignment objectives across various models with different tokenization schemes. We demonstrate their effectiveness, along with our joint optimization technique, by successfully bypassing the protection mechanisms of Llama Prompt Guard 2 on five different text generation models for malicious text and code generation. To the best of our knowledge, this is the first work to reveal that Llama Prompt Guard 2 can be compromised through joint optimization. Additionally, by analyzing the changing similarity of a model's internal state to specific concept directions during token sequence processing, we propose an effective and lightweight method to detect Super Suffix attacks. We show that the cosine similarity between the residual stream and certain concept directions serves as a distinctive fingerprint of model intent. Our proposed countermeasure, DeltaGuard, significantly improves the detection of malicious prompts generated through Super Suffixes. It increases the non-benign classification rate to nearly 100%, making DeltaGuard a valuable addition to the guard model stack and enhancing robustness against adversarial prompt attacks. --- ### MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator Authors: Peiqing Yang, Shangchen Zhou, Kai Hao, Qingyi Tao Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11782v2 Video matting remains limited by the scale and realism of existing datasets. While leveraging segmentation data can enhance semantic stability, the lack of effective boundary supervision often leads to segmentation-like mattes lacking fine details. To this end, we introduce a learned Matting Quality Evaluator (MQE) that assesses semantic and boundary quality of alpha mattes without ground truth. It produces a pixel-wise evaluation map that identifies reliable and erroneous regions, enabling fine-grained quality assessment. The MQE scales up video matting in two ways: (1) as an online matting-quality feedback during training to suppress erroneous regions, providing comprehensive supervision, and (2) as an offline selection module for data curation, improving annotation quality by combining the strengths of leading video and image matting models. This process allows us to build a large-scale real-world video matting dataset, VMReal, containing 28K clips and 2.4M frames. To handle large appearance variations in long videos, we introduce a reference-frame training strategy that incorporates long-range frames beyond the local window for effective training. Our MatAnyone 2 achieves state-of-the-art performance on both synthetic and real-world benchmarks, surpassing prior methods across all metrics. --- ### MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator Authors: Peiqing Yang, Shangchen Zhou, Kai Hao, Qingyi Tao Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11782v1 Video matting remains limited by the scale and realism of existing datasets. While leveraging segmentation data can enhance semantic stability, the lack of effective boundary supervision often leads to segmentation-like mattes lacking fine details. To this end, we introduce a learned Matting Quality Evaluator (MQE) that assesses semantic and boundary quality of alpha mattes without ground truth. It produces a pixel-wise evaluation map that identifies reliable and erroneous regions, enabling fine-grained quality assessment. The MQE scales up video matting in two ways: (1) as an online matting-quality feedback during training to suppress erroneous regions, providing comprehensive supervision, and (2) as an offline selection module for data curation, improving annotation quality by combining the strengths of leading video and image matting models. This process allows us to build a large-scale real-world video matting dataset, VMReal, containing 28K clips and 2.4M frames. To handle large appearance variations in long videos, we introduce a reference-frame training strategy that incorporates long-range frames beyond the local window for effective training. Our MatAnyone 2 achieves state-of-the-art performance on both synthetic and real-world benchmarks, surpassing prior methods across all metrics. --- ### Agile Flight Emerges from Multi-Agent Competitive Racing Authors: Vineet Pasumarti, Lorenzo Bianchi, Antonio Loquercio Published: 2025-12-12 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.11781v2 Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge from agents trained with reinforcement learning. We provide evidence in both simulation and the real world that this approach outperforms the common paradigm of training agents in isolation with rewards that prescribe behavior, e.g., progress on the raceline, in particular when the complexity of the environment increases, e.g., in the presence of obstacles. Moreover, we find that multi-agent competition yields policies that transfer more reliably to the real world than policies trained with a single-agent progress-based reward, despite the two methods using the same simulation environment, randomization strategy, and hardware. In addition to improved sim-to-real transfer, the multi-agent policies also exhibit some degree of generalization to opponents unseen at training time. Overall, our work, following in the tradition of multi-agent competitive game-play in digital domains, shows that sparse task-level rewards are sufficient for training agents capable of advanced low-level control in the physical world. Code: https://github.com/Jirl-upenn/AgileFlight_MultiAgent --- ### Agile Flight Emerges from Multi-Agent Competitive Racing Authors: Vineet Pasumarti, Lorenzo Bianchi, Antonio Loquercio Published: 2025-12-12 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.11781v1 Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge from agents trained with reinforcement learning. We provide evidence in both simulation and the real world that this approach outperforms the common paradigm of training agents in isolation with rewards that prescribe behavior, e.g., progress on the raceline, in particular when the complexity of the environment increases, e.g., in the presence of obstacles. Moreover, we find that multi-agent competition yields policies that transfer more reliably to the real world than policies trained with a single-agent progress-based reward, despite the two methods using the same simulation environment, randomization strategy, and hardware. In addition to improved sim-to-real transfer, the multi-agent policies also exhibit some degree of generalization to opponents unseen at training time. Overall, our work, following in the tradition of multi-agent competitive game-play in digital domains, shows that sparse task-level rewards are sufficient for training agents capable of advanced low-level control in the physical world. Code: https://github.com/Jirl-upenn/AgileFlight_MultiAgent --- ### Conditional Coverage Diagnostics for Conformal Prediction Authors: Sacha Braun, David Holzmüller, Michael I. Jordan, Francis Bach Published: 2025-12-12 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.11779v2 Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on marginal coverage, no method can guarantee to produce sets with correct conditional coverage, leaving practitioners without a clear way to interpret local deviations. To overcome sample-inefficiency and overfitting issues of existing metrics, we cast conditional coverage estimation as a classification problem. Conditional coverage is violated if and only if some classifier can achieve lower risk than the target coverage. Through the choice of a (proper) loss function, the resulting risk difference gives a conservative estimate of natural miscoverage measures such as L1 and L2 distance, and can even separate the effects of over- and under-coverage, and non-constant target coverages. We call the resulting family of metrics excess risk of the target coverage (ERT). We show experimentally that the use of modern classifiers provides much higher statistical power than simple classifiers underlying established metrics like CovGap. Additionally, we use our metric to benchmark different conformal prediction methods. Finally, we release an open-source package for ERT as well as previous conditional coverage metrics. Together, these contributions provide a new lens for understanding, diagnosing, and improving the conditional reliability of predictive systems. --- ### Conditional Coverage Diagnostics for Conformal Prediction Authors: Sacha Braun, David Holzmüller, Michael I. Jordan, Francis Bach Published: 2025-12-12 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.11779v1 Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on marginal coverage, no method can guarantee to produce sets with correct conditional coverage, leaving practitioners without a clear way to interpret local deviations. To overcome sample-inefficiency and overfitting issues of existing metrics, we cast conditional coverage estimation as a classification problem. Conditional coverage is violated if and only if any classifier can achieve lower risk than the target coverage. Through the choice of a (proper) loss function, the resulting risk difference gives a conservative estimate of natural miscoverage measures such as L1 and L2 distance, and can even separate the effects of over- and under-coverage, and non-constant target coverages. We call the resulting family of metrics excess risk of the target coverage (ERT). We show experimentally that the use of modern classifiers provides much higher statistical power than simple classifiers underlying established metrics like CovGap. Additionally, we use our metric to benchmark different conformal prediction methods. Finally, we release an open-source package for ERT as well as previous conditional coverage metrics. Together, these contributions provide a new lens for understanding, diagnosing, and improving the conditional reliability of predictive systems. --- ### The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation Authors: Vladimer Khasia Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11776v1 Coordinate-based neural networks have emerged as a powerful tool for representing continuous physical fields, yet they face two fundamental pathologies: spectral bias, which hinders the learning of high-frequency dynamics, and the curse of dimensionality, which causes parameter explosion in discrete feature grids. We propose the Adaptive Vekua Cascade (AVC), a hybrid architecture that bridges deep learning and classical approximation theory. AVC decouples manifold learning from function approximation by using a deep network to learn a diffeomorphic warping of the physical domain, projecting complex spatiotemporal dynamics onto a latent manifold where the solution is represented by a basis of generalized analytic functions. Crucially, we replace the standard gradient-descent output layer with a differentiable linear solver, allowing the network to optimally resolve spectral coefficients in a closed form during the forward pass. We evaluate AVC on a suite of five rigorous physics benchmarks, including high-frequency Helmholtz wave propagation, sparse medical reconstruction, and unsteady 3D Navier-Stokes turbulence. Our results demonstrate that AVC achieves state-of-the-art accuracy while reducing parameter counts by orders of magnitude (e.g., 840 parameters vs. 4.2 million for 3D grids) and converging 2-3x faster than implicit neural representations. This work establishes a new paradigm for memory-efficient, spectrally accurate scientific machine learning. The code is available at https://github.com/VladimerKhasia/vecua. --- ### Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints Authors: Kai Yao, Marc Juarez Published: 2025-12-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11771v2 Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial settings. We present the first systematic security evaluation of these techniques, formalizing threat models that encompass both white- and black-box access and two attack goals: fingerprint removal, which erases identifying traces to evade attribution, and fingerprint forgery, which seeks to cause misattribution to a target model. We implement five attack strategies and evaluate 14 representative fingerprinting methods across RGB, frequency, and learned-feature domains on 12 state-of-the-art image generators. Our experiments reveal a pronounced gap between clean and adversarial performance. Removal attacks are highly effective, often achieving success rates above 80% in white-box settings and over 50% under black-box access. While forgery is more challenging than removal, its success varies significantly across targeted models. We also observe a utility-robustness trade-off: accurate attribution methods are often vulnerable to attacks and, although some techniques are robust in specific settings, none achieves robustness and accuracy across all evaluated threat models. These findings highlight the need for techniques that balance robustness and accuracy, and we identify the most promising approaches toward this goal. Code available at: https://github.com/kaikaiyao/SmudgedFingerprints. --- ### Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints Authors: Kai Yao, Marc Juarez Published: 2025-12-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11771v1 Model fingerprint detection techniques have emerged as a promising approach for attributing AI-generated images to their source models, but their robustness under adversarial conditions remains largely unexplored. We present the first systematic security evaluation of these techniques, formalizing threat models that encompass both white- and black-box access and two attack goals: fingerprint removal, which erases identifying traces to evade attribution, and fingerprint forgery, which seeks to cause misattribution to a target model. We implement five attack strategies and evaluate 14 representative fingerprinting methods across RGB, frequency, and learned-feature domains on 12 state-of-the-art image generators. Our experiments reveal a pronounced gap between clean and adversarial performance. Removal attacks are highly effective, often achieving success rates above 80% in white-box settings and over 50% under constrained black-box access. While forgery is more challenging than removal, its success significantly varies across targeted models. We also identify a utility-robustness trade-off: methods with the highest attribution accuracy are often vulnerable to attacks. Although some techniques exhibit robustness in specific settings, none achieves high robustness and accuracy across all evaluated threat models. These findings highlight the need for techniques balancing robustness and accuracy, and identify the most promising approaches for advancing this goal. --- ### Learning Minimal Representations of Fermionic Ground States Authors: Felix Frohnert, Emiel Koridon, Stefano Polla Published: 2025-12-12 Categories: quant-ph, cond-mat.str-el, cs.LG arXiv: https://arxiv.org/abs/2512.11767v1 We introduce an unsupervised machine-learning framework that discovers optimally compressed representations of quantum many-body ground states. Using an autoencoder neural network architecture on data from $L$-site Fermi-Hubbard models, we identify minimal latent spaces with a sharp reconstruction quality threshold at $L-1$ latent dimensions, matching the system's intrinsic degrees of freedom. We demonstrate the use of the trained decoder as a differentiable variational ansatz to minimize energy directly within the latent space. Crucially, this approach circumvents the $N$-representability problem, as the learned manifold implicitly restricts the optimization to physically valid quantum states. --- ### Reducing Domain Gap with Diffusion-Based Domain Adaptation for Cell Counting Authors: Mohammad Dehghanmanshadi, Wallapak Tavanapong Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11763v1 Generating realistic synthetic microscopy images is critical for training deep learning models in label-scarce environments, such as cell counting with many cells per image. However, traditional domain adaptation methods often struggle to bridge the domain gap when synthetic images lack the complex textures and visual patterns of real samples. In this work, we adapt the Inversion-Based Style Transfer (InST) framework originally designed for artistic style transfer to biomedical microscopy images. Our method combines latent-space Adaptive Instance Normalization with stochastic inversion in a diffusion model to transfer the style from real fluorescence microscopy images to synthetic ones, while weakly preserving content structure. We evaluate the effectiveness of our InST-based synthetic dataset for downstream cell counting by pre-training and fine-tuning EfficientNet-B0 models on various data sources, including real data, hard-coded synthetic data, and the public Cell200-s dataset. Models trained with our InST-synthesized images achieve up to 37\% lower Mean Absolute Error (MAE) compared to models trained on hard-coded synthetic data, and a 52\% reduction in MAE compared to models trained on Cell200-s (from 53.70 to 25.95 MAE). Notably, our approach also outperforms models trained on real data alone (25.95 vs. 27.74 MAE). Further improvements are achieved when combining InST-synthesized data with lightweight domain adaptation techniques such as DACS with CutMix. These findings demonstrate that InST-based style transfer most effectively reduces the domain gap between synthetic and real microscopy data. Our approach offers a scalable path for enhancing cell counting performance while minimizing manual labeling effort. The source code and resources are publicly available at: https://github.com/MohammadDehghan/InST-Microscopy. --- ### Covariate-assisted graph matching Authors: Trisha Dawn, Jesús Arroyo Published: 2025-12-12 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.11761v1 Data integration is essential across diverse domains, from historical records to biomedical research, facilitating joint statistical inference. A crucial initial step in this process involves merging multiple data sources based on matching individual records, often in the absence of unique identifiers. When the datasets are networks, this problem is typically addressed through graph matching methodologies. For such cases, auxiliary features or covariates associated with nodes or edges can be instrumental in achieving improved accuracy. However, most existing graph matching techniques do not incorporate this information, limiting their performance against non-identifiable and erroneous matches. To overcome these limitations, we propose two novel covariate-assisted seeded graph matching methods, where a partial alignment for a set of nodes, called seeds, is known. The first one solves a quadratic assignment problem (QAP) over the whole graph, while the second one only leverages the local neighborhood structure of seed nodes for computational scalability. Both methods are grounded in a conditional modeling framework, where elements of one graph's adjacency matrix are modeled using a generalized linear model (GLM), given the other graph and the available covariates. We establish theoretical guarantees for model estimation error and exact recovery of the solution of the QAP. The effectiveness of our methods is demonstrated through numerical experiments and in an application to matching the statistics academic genealogy and the collaboration networks. By leveraging additional covariates, we achieve improved alignment accuracy. Our work highlights the power of integrating covariate information in the classical graph matching setup, offering a practical and improved framework for combining network data with wide-ranging applications. --- ### SpectralKrum: A Spectral-Geometric Defense Against Byzantine Attacks in Federated Learning Authors: Aditya Tripathi, Karan Sharma, Rahul Mishra, Tapas Kumar Maiti Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11760v1 Federated Learning (FL) distributes model training across clients who retain their data locally, but this architecture exposes a fundamental vulnerability: Byzantine clients can inject arbitrarily corrupted updates that degrade or subvert the global model. While robust aggregation methods (including Krum, Bulyan, and coordinate-wise defenses) offer theoretical guarantees under idealized assumptions, their effectiveness erodes substantially when client data distributions are heterogeneous (non-IID) and adversaries can observe or approximate the defense mechanism. This paper introduces SpectralKrum, a defense that fuses spectral subspace estimation with geometric neighbor-based selection. The core insight is that benign optimization trajectories, despite per-client heterogeneity, concentrate near a low-dimensional manifold that can be estimated from historical aggregates. SpectralKrum projects incoming updates into this learned subspace, applies Krum selection in compressed coordinates, and filters candidates whose orthogonal residual energy exceeds a data-driven threshold. The method requires no auxiliary data, operates entirely on model updates, and preserves FL privacy properties. We evaluate SpectralKrum against eight robust baselines across seven attack scenarios on CIFAR-10 with Dirichlet-distributed non-IID partitions (alpha = 0.1). Experiments spanning over 56,000 training rounds show that SpectralKrum is competitive against directional and subspace-aware attacks (adaptive-steer, buffer-drift), but offers limited advantage under label-flip and min-max attacks where malicious updates remain spectrally indistinguishable from benign ones. --- ### SUMFORU: An LLM-Based Review Summarization Framework for Personalized Purchase Decision Support Authors: Yuming Feng, Xinrui Jiang Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11755v1 Online product reviews contain rich but noisy signals that overwhelm users and hinder effective decision-making. Existing LLM-based summarizers remain generic and fail to account for individual preferences, limiting their practical utility. We propose SUMFORU, a steerable review summarization framework that aligns outputs with explicit user personas to support personalized purchase decisions. Our approach integrates a high-quality data pipeline built from the Amazon 2023 Review Dataset with a two-stage alignment procedure: (1) persona-aware Supervised Fine-Tuning (SFT) via asymmetric knowledge distillation, and (2) Reinforcement Learning with AI Feedback (RLAIF) using a preference estimator to capture fine-grained, persona-relevant signals. We evaluate the model across rule-based, LLM-based, and human-centered metrics, demonstrating consistent improvements in consistency, grounding, and preference alignment. Our framework achieves the highest performance across all evaluation settings and generalizes effectively to unseen product categories. Our results highlight the promise of steerable pluralistic alignment for building next-generation personalized decision-support systems. --- ### LUCID: Learning-Enabled Uncertainty-Aware Certification of Stochastic Dynamical Systems Authors: Ernesto Casablanca, Oliver Schön, Paolo Zuliani, Sadegh Soudjani Published: 2025-12-12 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2512.11750v1 Ensuring the safety of AI-enabled systems, particularly in high-stakes domains such as autonomous driving and healthcare, has become increasingly critical. Traditional formal verification tools fall short when faced with systems that embed both opaque, black-box AI components and complex stochastic dynamics. To address these challenges, we introduce LUCID (Learning-enabled Uncertainty-aware Certification of stochastIc Dynamical systems), a verification engine for certifying safety of black-box stochastic dynamical systems from a finite dataset of random state transitions. As such, LUCID is the first known tool capable of establishing quantified safety guarantees for such systems. Thanks to its modular architecture and extensive documentation, LUCID is designed for easy extensibility. LUCID employs a data-driven methodology rooted in control barrier certificates, which are learned directly from system transition data, to ensure formal safety guarantees. We use conditional mean embeddings to embed data into a reproducing kernel Hilbert space (RKHS), where an RKHS ambiguity set is constructed that can be inflated to robustify the result to out-of-distribution behavior. A key innovation within LUCID is its use of a finite Fourier kernel expansion to reformulate a semi-infinite non-convex optimization problem into a tractable linear program. The resulting spectral barrier allows us to leverage the fast Fourier transform to generate the relaxed problem efficiently, offering a scalable yet distributionally robust framework for verifying safety. LUCID thus offers a robust and efficient verification framework, able to handle the complexities of modern black-box systems while providing formal guarantees of safety. These unique capabilities are demonstrated on challenging benchmarks. --- ### SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder Authors: Minglei Shi, Haolin Wang, Borui Zhang, Wenzhao Zheng, Bohan Zeng, Ziyang Yuan, Xiaoshi Wu, Yuanxing Zhang, Huan Yang, Xintao Wang, Pengfei Wan, Kun Gai et al. Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11749v1 Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale text-to-image diffusion models entirely within the VFM representation space remains largely unexplored. To bridge this gap, we scale the SVG (Self-supervised representations for Visual Generation) framework, proposing SVG-T2I to support high-quality text-to-image synthesis directly in the VFM feature domain. By leveraging a standard text-to-image diffusion pipeline, SVG-T2I achieves competitive performance, reaching 0.75 on GenEval and 85.78 on DPG-Bench. This performance validates the intrinsic representational power of VFMs for generative tasks. We fully open-source the project, including the autoencoder and generation model, together with their training, inference, evaluation pipelines, and pre-trained weights, to facilitate further research in representation-driven visual generation. --- ### Generative Parametric Design (GPD): A framework for real-time geometry generation and on-the-fly multiparametric approximation Authors: Mohammed El Fallaki Idrissi, Jad Mounayer, Sebastian Rodriguez, Fodil Meraghni, Francisco Chinesta Published: 2025-12-12 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2512.11748v1 This paper presents a novel paradigm in simulation-based engineering sciences by introducing a new framework called Generative Parametric Design (GPD). The GPD framework enables the generation of new designs along with their corresponding parametric solutions given as a reduced basis. To achieve this, two Rank Reduction Autoencoders (RRAEs) are employed, one for encoding and generating the design or geometry, and the other for encoding the sparse Proper Generalized Decomposition (sPGD) mode solutions. These models are linked in the latent space using regression techniques, allowing efficient transitions between design and their associated sPGD modes. By empowering design exploration and optimization, this framework also advances digital and hybrid twin development, enhancing predictive modeling and real-time decision-making in engineering applications. The developed framework is demonstrated on two-phase microstructures, in which the multiparametric solutions account for variations in two key material parameters. --- ### mViSE: A Visual Search Engine for Analyzing Multiplex IHC Brain Tissue Images Authors: Liqiang Huang, Rachel W. Mills, Saikiran Mandula, Lin Bai, Mahtab Jeyhani, John Redell, Hien Van Nguyen, Saurabh Prasad, Dragan Maric, Badrinath Roysam Published: 2025-12-12 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.11745v1 Whole-slide multiplex imaging of brain tissue generates massive information-dense images that are challenging to analyze and require custom software. We present an alternative query-driven programming-free strategy using a multiplex visual search engine (mViSE) that learns the multifaceted brain tissue chemoarchitecture, cytoarchitecture, and myeloarchitecture. Our divide-and-conquer strategy organizes the data into panels of related molecular markers and uses self-supervised learning to train a multiplex encoder for each panel with explicit visual confirmation of successful learning. Multiple panels can be combined to process visual queries for retrieving similar communities of individual cells or multicellular niches using information-theoretic methods. The retrievals can be used for diverse purposes including tissue exploration, delineating brain regions and cortical cell layers, profiling and comparing brain regions without computer programming. We validated mViSE's ability to retrieve single cells, proximal cell pairs, tissue patches, delineate cortical layers, brain regions and sub-regions. mViSE is provided as an open-source QuPath plug-in. --- ### CogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural Networks Authors: Yongsheng Huang, Peibo Duan, Yujie Wu, Kai Sun, Zhipeng Liu, Changsheng Zhang, Bin Zhang, Mingkun Xu Published: 2025-12-12 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2512.11743v1 Spiking neural networks (SNNs), regarded as the third generation of artificial neural networks, are expected to bridge the gap between artificial intelligence and computational neuroscience. However, most mainstream SNN research directly adopts the rigid, chain-like hierarchical architecture of traditional artificial neural networks (ANNs), ignoring key structural characteristics of the brain. Biological neurons are stochastically interconnected, forming complex neural pathways that exhibit Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability. In this paper, we introduce a new SNN paradigm, named Cognition-aware SNN (CogniSNN), by incorporating Random Graph Architecture (RGA). Furthermore, we address the issues of network degradation and dimensional mismatch in deep pathways by introducing an improved pure spiking residual mechanism alongside an adaptive pooling strategy. Then, we design a Key Pathway-based Learning without Forgetting (KP-LwF) approach, which selectively reuses critical neural pathways while retaining historical knowledge, enabling efficient multi-task transfer. Finally, we propose a Dynamic Growth Learning (DGL) algorithm that allows neurons and synapses to grow dynamically along the internal temporal dimension. Extensive experiments demonstrate that CogniSNN achieves performance comparable to, or even surpassing, current state-of-the-art SNNs on neuromorphic datasets and Tiny-ImageNet. The Pathway-Reusability enhances the network's continuous learning capability across different scenarios, while the dynamic growth algorithm improves robustness against interference and mitigates the fixed-timestep constraints during neuromorphic chip deployment. This work demonstrates the potential of SNNs with random graph structures in advancing brain-inspired intelligence and lays the foundation for their practical application on neuromorphic hardware. --- ### ECCO: Leveraging Cross-Camera Correlations for Efficient Live Video Continuous Learning Authors: Yuze He, Ferdi Kossmann, Srinivasan Seshan, Peter Steenkiste Published: 2025-12-12 Categories: cs.DC, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2512.11727v1 Recent advances in video analytics address real-time data drift by continuously retraining specialized, lightweight DNN models for individual cameras. However, the current practice of retraining a separate model for each camera suffers from high compute and communication costs, making it unscalable. We present ECCO, a new video analytics framework designed for resource-efficient continuous learning. The key insight is that the data drift, which necessitates model retraining, often shows temporal and spatial correlations across nearby cameras. By identifying cameras that experience similar drift and retraining a shared model for them, ECCO can substantially reduce the associated compute and communication costs. Specifically, ECCO introduces: (i) a lightweight grouping algorithm that dynamically forms and updates camera groups; (ii) a GPU allocator that dynamically assigns GPU resources across different groups to improve retraining accuracy and ensure fairness; and (iii) a transmission controller at each camera that configures frame sampling and coordinates bandwidth sharing with other cameras based on its assigned GPU resources. We conducted extensive evaluations on three distinctive datasets for two vision tasks. Compared to leading baselines, ECCO improves retraining accuracy by 6.7%-18.1% using the same compute and communication resources, or supports 3.3 times more concurrent cameras at the same accuracy. --- ### From Signal to Turn: Interactional Friction in Modular Speech-to-Speech Pipelines Authors: Tittaya Mairittha, Tanakon Sawanglok, Panuwit Raden, Jirapast Buntub, Thanapat Warunee, Napat Asawachaisuvikrom, Thanaphum Saiwongin Published: 2025-12-12 Categories: cs.HC, cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2512.11724v2 While voice-based AI systems have achieved remarkable generative capabilities, their interactions often feel conversationally broken. This paper examines the interactional friction that emerges in modular Speech-to-Speech Retrieval-Augmented Generation (S2S-RAG) pipelines. By analyzing a representative production system, we move beyond simple latency metrics to identify three recurring patterns of conversational breakdown: (1) Temporal Misalignment, where system delays violate user expectations of conversational rhythm; (2) Expressive Flattening, where the loss of paralinguistic cues leads to literal, inappropriate responses; and (3) Repair Rigidity, where architectural gating prevents users from correcting errors in real-time. Through system-level analysis, we demonstrate that these friction points should not be understood as defects or failures, but as structural consequences of a modular design that prioritizes control over fluidity. We conclude that building natural spoken AI is an infrastructure design challenge, requiring a shift from optimizing isolated components to carefully choreographing the seams between them. --- ### From Signal to Turn: Interactional Friction in Modular Speech-to-Speech Pipelines Authors: Titaya Mairittha, Tanakon Sawanglok, Panuwit Raden, Jirapast Buntub, Thanapat Warunee, Napat Asawachaisuvikrom, Thanaphum Saiwongin Published: 2025-12-12 Categories: cs.HC, cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2512.11724v1 While voice-based AI systems have achieved remarkable generative capabilities, their interactions often feel conversationally broken. This paper examines the interactional friction that emerges in modular Speech-to-Speech Retrieval-Augmented Generation (S2S-RAG) pipelines. By analyzing a representative production system, we move beyond simple latency metrics to identify three recurring patterns of conversational breakdown: (1) Temporal Misalignment, where system delays violate user expectations of conversational rhythm; (2) Expressive Flattening, where the loss of paralinguistic cues leads to literal, inappropriate responses; and (3) Repair Rigidity, where architectural gating prevents users from correcting errors in real-time. Through system-level analysis, we demonstrate that these friction points should not be understood as defects or failures, but as structural consequences of a modular design that prioritizes control over fluidity. We conclude that building natural spoken AI is an infrastructure design challenge, requiring a shift from optimizing isolated components to carefully choreographing the seams between them. --- ### Weak-to-Strong Generalization Enables Fully Automated De Novo Training of Multi-head Mask-RCNN Model for Segmenting Densely Overlapping Cell Nuclei in Multiplex Whole-slice Brain Images Authors: Lin Bai, Xiaoyang Li, Liqiang Huang, Quynh Nguyen, Hien Van Nguyen, Saurabh Prasad, Dragan Maric, John Redell, Pramod Dash, Badrinath Roysam Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11722v1 We present a weak to strong generalization methodology for fully automated training of a multi-head extension of the Mask-RCNN method with efficient channel attention for reliable segmentation of overlapping cell nuclei in multiplex cyclic immunofluorescent (IF) whole-slide images (WSI), and present evidence for pseudo-label correction and coverage expansion, the key phenomena underlying weak to strong generalization. This method can learn to segment de novo a new class of images from a new instrument and/or a new imaging protocol without the need for human annotations. We also present metrics for automated self-diagnosis of segmentation quality in production environments, where human visual proofreading of massive WSI images is unaffordable. Our method was benchmarked against five current widely used methods and showed a significant improvement. The code, sample WSI images, and high-resolution segmentation results are provided in open form for community adoption and adaptation. --- ### Reframing Music-Driven 2D Dance Pose Generation as Multi-Channel Image Generation Authors: Yan Zhang, Han Zou, Lincong Feng, Cong Xie, Ruiqi Yu, Zhenpeng Zhan Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11720v1 Recent pose-to-video models can translate 2D pose sequences into photorealistic, identity-preserving dance videos, so the key challenge is to generate temporally coherent, rhythm-aligned 2D poses from music, especially under complex, high-variance in-the-wild distributions. We address this by reframing music-to-dance generation as a music-token-conditioned multi-channel image synthesis problem: 2D pose sequences are encoded as one-hot images, compressed by a pretrained image VAE, and modeled with a DiT-style backbone, allowing us to inherit architectural and training advances from modern text-to-image models and better capture high-variance 2D pose distributions. On top of this formulation, we introduce (i) a time-shared temporal indexing scheme that explicitly synchronizes music tokens and pose latents over time and (ii) a reference-pose conditioning strategy that preserves subject-specific body proportions and on-screen scale while enabling long-horizon segment-and-stitch generation. Experiments on a large in-the-wild 2D dance corpus and the calibrated AIST++2D benchmark show consistent improvements over representative music-to-dance methods in pose- and video-space metrics and human preference, and ablations validate the contributions of the representation, temporal indexing, and reference conditioning. See supplementary videos at https://hot-dance.github.io --- ### Referring Change Detection in Remote Sensing Imagery Authors: Yilmaz Korkmaz, Jay N. Paranjape, Celso M. de Melo, Vishal M. Patel Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11719v1 Change detection in remote sensing imagery is essential for applications such as urban planning, environmental monitoring, and disaster management. Traditional change detection methods typically identify all changes between two temporal images without distinguishing the types of transitions, which can lead to results that may not align with specific user needs. Although semantic change detection methods have attempted to address this by categorizing changes into predefined classes, these methods rely on rigid class definitions and fixed model architectures, making it difficult to mix datasets with different label sets or reuse models across tasks, as the output channels are tightly coupled with the number and type of semantic classes. To overcome these limitations, we introduce Referring Change Detection (RCD), which leverages natural language prompts to detect specific classes of changes in remote sensing images. By integrating language understanding with visual analysis, our approach allows users to specify the exact type of change they are interested in. However, training models for RCD is challenging due to the limited availability of annotated data and severe class imbalance in existing datasets. To address this, we propose a two-stage framework consisting of (I) \textbf{RCDNet}, a cross-modal fusion network designed for referring change detection, and (II) \textbf{RCDGen}, a diffusion-based synthetic data generation pipeline that produces realistic post-change images and change maps for a specified category using only pre-change image, without relying on semantic segmentation masks and thereby significantly lowering the barrier to scalable data creation. Experiments across multiple datasets show that our framework enables scalable and targeted change detection. Project website is here: https://yilmazkorkmaz1.github.io/RCD. --- ### Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks Authors: Sergey Pankratov, Dan Alistarh Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11718v1 Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable speedup remain poorly understood. In this work, we establish the first ``tight'' lower bounds on the runtime of any deterministic speculative generation algorithm. This is achieved by drawing a parallel between the token generation process and branching random walks, which allows us to analyze the optimal draft tree selection problem. We prove, under basic assumptions, that the expected number of tokens successfully predicted per speculative iteration is bounded as $\mathbb{E}(X) \leq (μ+ μ_{(2)})\log(P )/μ^2 + O(1)$, where $P$ is the verifier's capacity, $μ$ is the expected entropy of the verifier's output distribution, and $μ_{(2)}$ is the expected second log-moment. This result provides new insights into the limits of parallel token generation, and could guide the design of future speculative decoding systems. Empirical evaluations on Llama models validate our theoretical predictions, confirming the tightness of our bounds in practical settings. --- ### EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing Authors: Wei Chow, Linfeng Li, Lingdong Kong, Zefeng Li, Qi Xu, Hang Song, Tian Ye, Xian Wang, Jinbin Bai, Shilin Xu, Xiangtai Li, Junting Pan et al. Published: 2025-12-12 Categories: cs.CV, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2512.11715v2 Recent advances in diffusion models (DMs) have achieved exceptional visual quality in image editing tasks. However, the global denoising dynamics of DMs inherently conflate local editing targets with the full-image context, leading to unintended modifications in non-target regions. In this paper, we shift our attention beyond DMs and turn to Masked Generative Transformers (MGTs) as an alternative approach to tackle this challenge. By predicting multiple masked tokens rather than holistic refinement, MGTs exhibit a localized decoding paradigm that endows them with the inherent capacity to explicitly preserve non-relevant regions during the editing process. Building upon this insight, we introduce the first MGT-based image editing framework, termed EditMGT. We first demonstrate that MGT's cross-attention maps provide informative localization signals for localizing edit-relevant regions and devise a multi-layer attention consolidation scheme that refines these maps to achieve fine-grained and precise localization. On top of these adaptive localization results, we introduce region-hold sampling, which restricts token flipping within low-attention areas to suppress spurious edits, thereby confining modifications to the intended target regions and preserving the integrity of surrounding non-target areas. To train EditMGT, we construct CrispEdit-2M, a high-resolution dataset spanning seven diverse editing categories. Without introducing additional parameters, we adapt a pre-trained text-to-image MGT into an image editing model through attention injection. Extensive experiments across four standard benchmarks demonstrate that, with fewer than 1B parameters, our model achieves similarity performance while enabling 6 times faster editing. Moreover, it delivers comparable or superior editing quality, with improvements of 3.6% and 17.6% on style change and style transfer tasks, respectively. --- ### EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing Authors: Wei Chow, Linfeng Li, Lingdong Kong, Zefeng Li, Qi Xu, Hang Song, Tian Ye, Xian Wang, Jinbin Bai, Shilin Xu, Xiangtai Li, Junting Pan et al. Published: 2025-12-12 Categories: cs.CV, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2512.11715v1 Recent advances in diffusion models (DMs) have achieved exceptional visual quality in image editing tasks. However, the global denoising dynamics of DMs inherently conflate local editing targets with the full-image context, leading to unintended modifications in non-target regions. In this paper, we shift our attention beyond DMs and turn to Masked Generative Transformers (MGTs) as an alternative approach to tackle this challenge. By predicting multiple masked tokens rather than holistic refinement, MGTs exhibit a localized decoding paradigm that endows them with the inherent capacity to explicitly preserve non-relevant regions during the editing process. Building upon this insight, we introduce the first MGT-based image editing framework, termed EditMGT. We first demonstrate that MGT's cross-attention maps provide informative localization signals for localizing edit-relevant regions and devise a multi-layer attention consolidation scheme that refines these maps to achieve fine-grained and precise localization. On top of these adaptive localization results, we introduce region-hold sampling, which restricts token flipping within low-attention areas to suppress spurious edits, thereby confining modifications to the intended target regions and preserving the integrity of surrounding non-target areas. To train EditMGT, we construct CrispEdit-2M, a high-resolution dataset spanning seven diverse editing categories. Without introducing additional parameters, we adapt a pre-trained text-to-image MGT into an image editing model through attention injection. Extensive experiments across four standard benchmarks demonstrate that, with fewer than 1B parameters, our model achieves similarity performance while enabling 6 times faster editing. Moreover, it delivers comparable or superior editing quality, with improvements of 3.6% and 17.6% on style change and style transfer tasks, respectively. --- ### High-Dimensional Surrogate Modeling for Closed-Loop Learning of Neural-Network-Parameterized Model Predictive Control Authors: Sebastian Hirt, Valentinus Suwanto, Hendrik Alsmeier, Maik Pfefferkorn, Rolf Findeisen Published: 2025-12-12 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2512.11705v1 Learning controller parameters from closed-loop data has been shown to improve closed-loop performance. Bayesian optimization, a widely used black-box and sample-efficient learning method, constructs a probabilistic surrogate of the closed-loop performance from few experiments and uses it to select informative controller parameters. However, it typically struggles with dense high-dimensional controller parameterizations, as they may appear, for example, in tuning model predictive controllers, because standard surrogate models fail to capture the structure of such spaces. This work suggests that the use of Bayesian neural networks as surrogate models may help to mitigate this limitation. Through a comparison between Gaussian processes with Matern kernels, finite-width Bayesian neural networks, and infinite-width Bayesian neural networks on a cart-pole task, we find that Bayesian neural network surrogate models achieve faster and more reliable convergence of the closed-loop cost and enable successful optimization of parameterizations with hundreds of dimensions. Infinite-width Bayesian neural networks also maintain performance in settings with more than one thousand parameters, whereas Matern-kernel Gaussian processes rapidly lose effectiveness. These results indicate that Bayesian neural network surrogate models may be suitable for learning dense high-dimensional controller parameterizations and offer practical guidance for selecting surrogate models in learning-based controller design. ---