# Research Papers — 2025-12 · bundle page 101 of 175 > Full-text markdown of papers #5001–5050 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/101 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/100.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/102.md) ### Zero-Knowledge Audit for Internet of Agents: Privacy-Preserving Communication Verification with Model Context Protocol Authors: Guanlin Jing, Huayi Qi Published: 2025-12-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.14737v1 Existing agent communication frameworks face critical limitations in providing verifiable audit trails without compromising the privacy and confidentiality of agent interactions. The protection of agent communication privacy while ensuring auditability emerges as a fundamental challenge for applications requiring accurate billing, compliance verification, and accountability in regulated environments. We introduce a framework for auditing agent communications that keeps messages private while still checking they follow expected rules. It pairs zero-knowledge proofs with the existing Model Context Protocol (MCP) so messages can be verified without revealing their contents. The approach runs in lightweight networks, stays compatible with standard MCP exchanges, and adds asynchronous audit verification to confirm format and general message types without exposing specifics. The framework enables mutual audits between agents: one side can check communication content and quality while the other verifies usage metrics, all without revealing sensitive information. We formalize security goals and show that zk-MCP provides data authenticity and communication privacy, achieving efficient verification with negligible latency overhead. We fully implement the framework, including Circom-based zero-knowledge proof generation and an audit protocol integrated with MCP's bidirectional channel, and, to our knowledge, this is the first privacy-preserving audit system for agent communications that offers verifiable mutual auditing without exposing message content or compromising agent privacy. --- ### PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents Authors: Yuqun Zhang, Yuxuan Zhao, Sijia Chen Published: 2025-12-11 Categories: q-fin.CP, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.14735v2 This paper proposes PyFi, a novel framework for pyramid-like financial image understanding that enables vision language models (VLMs) to reason through question chains in a progressive, simple-to-complex manner. At the core of PyFi is PyFi-600K, a dataset comprising 600K financial question-answer pairs organized into a reasoning pyramid: questions at the base require only basic perception, while those toward the apex demand increasing levels of capability in financial visual understanding and expertise. This data is scalable because it is synthesized without human annotations, using PyFi-adv, a multi-agent adversarial mechanism under the Monte Carlo Tree Search (MCTS) paradigm, in which, for each image, a challenger agent competes with a solver agent by generating question chains that progressively probe deeper capability levels in financial visual reasoning. Leveraging this dataset, we present fine-grained, hierarchical, and comprehensive evaluations of advanced VLMs in the financial domain. Moreover, fine-tuning Qwen2.5-VL-3B and Qwen2.5-VL-7B on the pyramid-structured question chains enables these models to answer complex financial questions by decomposing them into sub-questions with gradually increasing reasoning demands, yielding average accuracy improvements of 19.52% and 8.06%, respectively, on the dataset. All resources of code, dataset and models are available at: https://github.com/AgenticFinLab/PyFi . --- ### Inference Time Feature Injection: A Lightweight Approach for Real-Time Recommendation Freshness Authors: Qiang Chen, Venkatesh Ganapati Hegde, Hongfei Li Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14734v1 Many recommender systems in long-form video streaming reply on batch-trained models and batch-updated features, where user features are updated daily and served statically throughout the day. While efficient, this approach fails to incorporate a user's most recent actions, often resulting in stale recommendations. In this work, we present a lightweight, model-agnostic approach for intra-day personalization that selectively injects recent watch history at inference time without requiring model retraining. Our approach selectively overrides stale user features at inference time using the recent watch history, allowing the system to adapt instantly to evolving preferences. By reducing the personalization feedback loop from daily to intra-day, we observed a statistically significant 0.47% increase in key user engagement metrics which ranked among the most substantial engagement gains observed in recent experimentation cycles. To our knowledge, this is the first published evidence that intra-day personalization can drive meaningful impact in long-form video streaming service, providing a compelling alternative to full real-time architectures where model retraining is required. --- ### Where to Explore: A Reach and Cost-Aware Approach for Unbiased Data Collection in Recommender Systems Authors: Qiang Chen, Venkatesh Ganapati Hegde Published: 2025-12-11 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2512.14733v1 Exploration is essential to improve long-term recommendation quality, but it often degrades short-term business performance, especially in remote-first TV environments where users engage passively, expect instant relevance, and offer few chances for correction. This paper introduces an approach for delivering content-level exploration safely and efficiently by optimizing its placement based on reach and opportunity cost. Deployed on a large-scale streaming platform with over 100 million monthly active users, our approach identifies scroll-depth regions with lower engagement and strategically introduces a dedicated container, the "Something Completely Different" row containing randomized content. Rather than enforcing exploration uniformly across the user interface (UI), we condition its appearance on empirically low-cost, high-reach positions to ensure minimal tradeoff against platform-level watch time goals. Extensive A/B testing shows that this strategy preserves business metrics while collecting unbiased interaction data. Our method complements existing intra-row diversification and bandit-based exploration techniques by introducing a deployable, behaviorally informed mechanism for surfacing exploratory content at scale. Moreover, we demonstrate that the collected unbiased data, integrated into downstream candidate generation, significantly improves user engagement, validating its value for recommender systems. --- ### FloraForge: LLM-Assisted Procedural Generation of Editable and Analysis-Ready 3D Plant Geometric Models For Agricultural Applications Authors: Mozhgan Hadadi, Talukder Z. Jubery, Patrick S. Schnable, Arti Singh, Bedrich Benes, Adarsh Krishnamurthy, Baskar Ganapathysubramanian Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11925v1 Accurate 3D plant models are crucial for computational phenotyping and physics-based simulation; however, current approaches face significant limitations. Learning-based reconstruction methods require extensive species-specific training data and lack editability. Procedural modeling offers parametric control but demands specialized expertise in geometric modeling and an in-depth understanding of complex procedural rules, making it inaccessible to domain scientists. We present FloraForge, an LLM-assisted framework that enables domain experts to generate biologically accurate, fully parametric 3D plant models through iterative natural language Plant Refinements (PR), minimizing programming expertise. Our framework leverages LLM-enabled co-design to refine Python scripts that generate parameterized plant geometries as hierarchical B-spline surface representations with botanical constraints with explicit control points and parametric deformation functions. This representation can be easily tessellated into polygonal meshes with arbitrary precision, ensuring compatibility with functional structural plant analysis workflows such as light simulation, computational fluid dynamics, and finite element analysis. We demonstrate the framework on maize, soybean, and mung bean, fitting procedural models to empirical point cloud data through manual refinement of the Plant Descriptor (PD), human-readable files. The pipeline generates dual outputs: triangular meshes for visualization and triangular meshes with additional parametric metadata for quantitative analysis. This approach uniquely combines LLM-assisted template creation, mathematically continuous representations enabling both phenotyping and rendering, and direct parametric control through PD. The framework democratizes sophisticated geometric modeling for plant science while maintaining mathematical rigor. --- ### Vibe Coding in Practice: Flow, Technical Debt, and Guidelines for Sustainable Use Authors: Muhammad Waseem, Aakash Ahmad, Kai-Kristian Kemell, Jussi Rasku, Sami Lahti, Kalle Mäkelä, Pekka Abrahamsson Published: 2025-12-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.11922v1 Vibe Coding (VC) is a form of software development assisted by generative AI, in which developers describe the intended functionality or logic via natural language prompts, and the AI system generates the corresponding source code. VC can be leveraged for rapid prototyping or developing the Minimum Viable Products (MVPs); however, it may introduce several risks throughout the software development life cycle. Based on our experience from several internally developed MVPs and a review of recent industry reports, this article analyzes the flow-debt tradeoffs associated with VC. The flow-debt trade-off arises when the seamless code generation occurs, leading to the accumulation of technical debt through architectural inconsistencies, security vulnerabilities, and increased maintenance overhead. These issues originate from process-level weaknesses, biases in model training data, a lack of explicit design rationale, and a tendency to prioritize quick code generation over human-driven iterative development. Based on our experiences, we identify and explain how current model, platform, and hardware limitations contribute to these issues, and propose countermeasures to address them, informing research and practice towards more sustainable VC approaches. --- ### Towards Accessible Physical AI: LoRA-Based Fine-Tuning of VLA Models for Real-World Robot Control Authors: Abdullah Yahya Abdullah Omaisan, Ibrahim Sheikh Mohamed Published: 2025-12-11 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.11921v1 Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in robotic manipulation,enabling robots to execute natural language commands through end-to-end learning from visual observations.However, deploying large-scale VLA models on affordable robotic platforms remains challenging due to computational constraints and the need for efficient adaptation to new robot embodiments. This paper presents an efficient fine-tuning methodology and real-world deployment analysis for adapting VLA models to low-cost robotic manipulation systems.We propose a resource-efficient fine-tuning strategy using Low-Rank Adaptation (LoRA) and quantization techniques that enable multi-billion parameter VLA models ( 3.1B parameters) to run on consumer-grade GPUs with 8GB VRAM. Our methodology addresses the critical challenge of adapting pre-trained VLA models to new robot embodiments with limited demonstration data, focusing on the trade-offs between frozen and unfrozen vision encoders. Through real-world deployment on the SO101 robotic arm for a button-pressing manipulation task, we demonstrate that our approach achieves effective manipulation performance while maintaining computational efficiency. We provide detailed analysis of deployment challenges, failure modes, and the relationship between training data quantity and real-world performance,trained on 200 demonstration episodes. Our results show that with proper fine-tuning methodology, VLA models can be successfully deployed on affordable robotic platforms,making advanced manipulation capabilities accessible beyond expensive research robots. --- ### CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving Authors: Dong Liu, Yanxuan Yu Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11920v1 Large Language Models (LLMs) have revolutionized natural language processing tasks, but their deployment in datacenter environments faces significant challenges due to the massive memory requirements of key-value (KV) caches. During the autoregressive decoding process, KV caches consume substantial GPU memory, limiting batch sizes and overall system throughput. To address these challenges, we propose \textbf{CXL-SpecKV}, a novel disaggregated KV-cache architecture that leverages Compute Express Link (CXL) interconnects and FPGA accelerators to enable efficient speculative execution and memory disaggregation. Our approach introduces three key innovations: (i) a CXL-based memory disaggregation framework that offloads KV-caches to remote FPGA memory with low latency, (ii) a speculative KV-cache prefetching mechanism that predicts and preloads future tokens' cache entries, and (iii) an FPGA-accelerated KV-cache compression and decompression engine that reduces memory bandwidth requirements by up to 4$\times$. When evaluated on state-of-the-art LLM models, CXL-SpecKV achieves up to 3.2$\times$ higher throughput compared to GPU-only baselines, while reducing memory costs by 2.8$\times$ and maintaining accuracy. Our system demonstrates that intelligent memory disaggregation combined with speculative execution can effectively address the memory wall challenge in large-scale LLM serving. Our code implementation has been open-sourced at https://github.com/FastLM/CXL-SpecKV. --- ### A fine-grained look at causal effects in causal spaces Authors: Junhyung Park, Yuqing Zhou Published: 2025-12-11 Categories: stat.ME, cs.AI, math.ST arXiv: https://arxiv.org/abs/2512.11919v3 The notion of causal effect is fundamental across many scientific disciplines. Traditionally, quantitative researchers have studied causal effects at the level of variables; for example, how a certain drug dose (W) causally affects a patient's blood pressure (Y). However, in many modern data domains, the raw variables-such as pixels in an image or tokens in a language model-do not have the semantic structure needed to formulate meaningful causal questions. In this paper, we offer a more fine-grained perspective by studying causal effects at the level of events, drawing inspiration from probability theory, where core notions such as independence are first given for events and sigma-algebras, before random variables enter the picture. Within the measure-theoretic framework of causal spaces, a recently introduced axiomatisation of causality, we first introduce several binary definitions that determine whether a causal effect is present, as well as proving some properties of them linking causal effect to (in)dependence under an intervention measure. Further, we provide quantifying measures that capture the strength and nature of causal effects on events, and show that we can recover the common measures of treatment effect as special cases. --- ### Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis Authors: Liu Peng, Yaochu Jin Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11912v1 A systematic, comparative investigation into the effects of low-quality data reveals a stark spectrum of robustness across modern probabilistic models. We find that autoregressive language models, from token prediction to sequence-to-sequence tasks, are remarkably resilient (for GPT-2, test NLL increases modestly from 2.87 to 3.59 despite 50% token corruption). By contrast, under the same levels of data corruption, class-conditional diffusion models degrade catastrophically (image-label consistency plummets by 56.81% relative to baseline), while classifiers show a moderate impact that diminishes with dataset scale. To explain these discrepancies, we analyze the results through a multi-perspective lens, integrating information theory, PAC learning, and gradient dynamics. These analyses suggest that robustness is heavily influenced by two key principles: the richness of conditioning information, which constrains the learning problem, and the absolute information content of the training data, which allows the signal from correct information to dominate statistical noise. --- ### Motif-2-12.7B-Reasoning: A Practitioner's Guide to RL Training Recipes Authors: Junghwan Lim, Sungmin Lee, Dongseok Kim, Taehyun Kim, Eunhwan Park, Jeesoo Lee, Jeongdoo Lee, Junhyeok Lee, Wai Ting Cheung, Dahye Choi, Minsu Ha, Jaeheui Her et al. Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11463v1 We introduce Motif-2-12.7B-Reasoning, a 12.7B parameter language model designed to bridge the gap between open-weight systems and proprietary frontier models in complex reasoning and long-context understanding. Addressing the common challenges of model collapse and training instability in reasoning adaptation, we propose a comprehensive, reproducible training recipe spanning system, data, and algorithmic optimizations. Our approach combines memory-efficient infrastructure for 64K-token contexts using hybrid parallelism and kernel-level optimizations with a two-stage Supervised Fine-Tuning (SFT) curriculum that mitigates distribution mismatch through verified, aligned synthetic data. Furthermore, we detail a robust Reinforcement Learning Fine-Tuning (RLFT) pipeline that stabilizes training via difficulty-aware data filtering and mixed-policy trajectory reuse. Empirical results demonstrate that Motif-2-12.7B-Reasoning achieves performance comparable to models with significantly larger parameter counts across mathematics, coding, and agentic benchmarks, offering the community a competitive open model and a practical blueprint for scaling reasoning capabilities under realistic compute constraints. --- ### Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning Authors: Wei Duan, Jie Lu, En Yu, Junyu Xuan Published: 2025-12-11 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2512.11179v3 Graph-based multi-agent reinforcement learning (MARL) enables coordinated behavior under partial observability by modeling agents as nodes and communication links as edges. While recent methods excel at learning sparse coordination graphs-determining who communicates with whom-they do not address what information should be transmitted under hard bandwidth constraints. We study this bandwidth-limited regime and show that naive dimensionality reduction consistently degrades coordination performance. Hard bandwidth constraints force selective encoding, but deterministic projections lack mechanisms to control how compression occurs. We introduce Bandwidth-constrained Variational Message Encoding (BVME), a lightweight module that treats messages as samples from learned Gaussian posteriors regularized via KL divergence to an uninformative prior. BVME's variational framework provides principled, tunable control over compression strength through interpretable hyperparameters, directly constraining the representations used for decision-making. Across SMACv1, SMACv2, and MPE benchmarks, BVME achieves comparable or superior performance while using 67--83% fewer message dimensions, with gains most pronounced on sparse graphs where message quality critically impacts coordination. Ablations reveal U-shaped sensitivity to bandwidth, with BVME excelling at extreme ratios while adding minimal overhead. --- ### Harnessing Rich Multi-Modal Data for Spatial-Temporal Homophily-Embedded Graph Learning Across Domains and Localities Authors: Takuya Kurihana, Xiaojian Zhang, Wing Yee Au, Hon Yung Wong Published: 2025-12-11 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2512.11178v1 Modern cities are increasingly reliant on data-driven insights to support decision making in areas such as transportation, public safety and environmental impact. However, city-level data often exists in heterogeneous formats, collected independently by local agencies with diverse objectives and standards. Despite their numerous, wide-ranging, and uniformly consumable nature, national-level datasets exhibit significant heterogeneity and multi-modality. This research proposes a heterogeneous data pipeline that performs cross-domain data fusion over time-varying, spatial-varying and spatial-varying time-series datasets. We aim to address complex urban problems across multiple domains and localities by harnessing the rich information over 50 data sources. Specifically, our data-learning module integrates homophily from spatial-varying dataset into graph-learning, embedding information of various localities into models. We demonstrate the generalizability and flexibility of the framework through five real-world observations using a variety of publicly accessible datasets (e.g., ride-share, traffic crash, and crime reports) collected from multiple cities. The results show that our proposed framework demonstrates strong predictive performance while requiring minimal reconfiguration when transferred to new localities or domains. This research advances the goal of building data-informed urban systems in a scalable way, addressing one of the most pressing challenges in smart city analytics. --- ### CORL: Reinforcement Learning of MILP Policies Solved via Branch and Bound Authors: Akhil S Anand, Elias Aarekol, Martin Mziray Dalseg, Magnus Stalhane, Sebastien Gros Published: 2025-12-11 Categories: cs.AI, cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2512.11169v1 Combinatorial sequential decision making problems are typically modeled as mixed integer linear programs (MILPs) and solved via branch and bound (B&B) algorithms. The inherent difficulty of modeling MILPs that accurately represent stochastic real world problems leads to suboptimal performance in the real world. Recently, machine learning methods have been applied to build MILP models for decision quality rather than how accurately they model the real world problem. However, these approaches typically rely on supervised learning, assume access to true optimal decisions, and use surrogates for the MILP gradients. In this work, we introduce a proof of concept CORL framework that end to end fine tunes an MILP scheme using reinforcement learning (RL) on real world data to maximize its operational performance. We enable this by casting an MILP solved by B&B as a differentiable stochastic policy compatible with RL. We validate the CORL method in a simple illustrative combinatorial sequential decision making example. --- ### Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context Authors: Anatole Jacquin de Margerie, Alexis Roger, Irina Rish Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.11167v1 Reproducibility remains a cornerstone of scientific progress, yet complex multimodal models often lack transparent implementation details and accessible training infrastructure. In this work, we present a detailed reproduction and critical analysis of the Monkey Vision-Language Model (VLM) (Li et al. 2023b) published in CVPR24, a recent approach to high-resolution image understanding via image tiling. The original paper proposed splitting large images into tiles to recover fine-grained visual details while maintaining computational efficiency. Our study replicates this strategy using open checkpoints and reimplements the training pipeline. We confirm the key finding of the original Monkey VLM work, namely that tiling effectively recovers local details. We then extend this work further, by investigating the effect of the inclusion of the global context, which provide practical insights for future high-resolution multimodal modeling. However, we also report deviations in the results, with the magnitude of these effects depending heavily on task type and tile granularity. --- ### Classifying High-Energy Celestial Objects with Machine Learning Methods Authors: Alexis Mathis, Daniel Yu, Nolan Faught, Tyrian Hobbs. Published: 2025-12-11 Categories: astro-ph.IM, astro-ph.HE, stat.ML arXiv: https://arxiv.org/abs/2512.11162v1 Machine learning is a field that has been growing in importance since the early 2010s due to the increasing accuracy of classification models and hardware advances that have enabled faster training on large datasets. In the field of astronomy, tree-based models and simple neural networks have recently garnered attention as a means of classifying celestial objects based on photometric data. We apply common tree-based models to assess performance of these models for discriminating objects with similar photometric signals, pulsars and black holes. We also train a RNN on a downsampled and normalized version of the raw signal data to examine its potential as a model capable of object discrimination and classification in real-time. --- ### Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems Authors: Eddie Landesberg, Manjari Narayan Published: 2025-12-11 Categories: stat.ME, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2512.11150v3 Measuring long-run LLM outcomes (user satisfaction, expert judgment, downstream KPIs) is expensive. Teams default to cheap LLM judges, but uncalibrated proxies can invert rankings entirely. Causal Judge Evaluation (CJE) makes it affordable to aim at the right target: calibrate cheap scores against a small oracle slice, then evaluate at scale with valid uncertainty. We treat surrogate validity as auditable: for each policy or deployment context, a small oracle audit tests whether the learned calibration remains mean-unbiased, turning an uncheckable identification condition into a falsifiable diagnostic. On 4,961 Chatbot Arena prompts comparing five policies with a 16x oracle/judge cost ratio, at a 5% oracle fraction CJE achieves 99% pairwise ranking accuracy at 14x lower cost; across all configurations (5-50% oracle, varying n), accuracy averages 94%. An adversarial policy fails the transport audit and is correctly flagged; in such cases CJE refuses level claims rather than reporting biased estimates. Key findings: naive confidence intervals on raw judge scores achieve 0% coverage (CJE: ~95%); importance-weighted estimators fail despite >90% effective sample size; and the Coverage-Limited Efficiency (CLE) bound and its TTC diagnostic explain why. --- ### MiniScope: Authorizing Agents with Least-Privilege Permissions Authors: Jinhao Zhu, Xiao Huang, Kevin Tseng, Gil Vernik, Shishir G. Patil, Vivian Fang, Raluca Ada Popa Published: 2025-12-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.11147v2 AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a critical security challenge. Existing permission models, however, typically rely on flat permission structures that fail to balance security with usability: fine-grained confirmation induces user fatigue, while coarse-grained or persistent approval leads to overprivileged agents. To address this tradeoff, we propose a task-centric, hierarchical permission model that treats an agent as a delegate operating within a task-specific role instead of requiring a separate permission decision for every tool call. Building on this model, we present MiniScope, an end-to-end permission system for agents that automates permission-hierarchy discovery and enforces contextual least privilege at runtime. Our evaluation shows that MiniScope reduces simulated permission confirmations by 43.4%-89.4% for cautious and typical personas relative to per-tool prompting and mitigates all privilege-escalation attacks with negligible impact on utility and runtime. Applied to real-world deployments, MiniScope further uncovers six overprivileged connector configurations in ChatGPT and Claude. --- ### SENSE: Self-Supervised Neural Embeddings for Spatial Ensembles Authors: Hamid Gadirov, Lennard Manuel, Steffen Frey Published: 2025-12-11 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11145v2 Analyzing and visualizing scientific ensemble datasets with high dimensionality and complexity poses significant challenges. Dimensionality reduction techniques and autoencoders are powerful tools for extracting features, but they often struggle with such high-dimensional data. This paper presents an enhanced autoencoder framework that incorporates a clustering loss, based on the soft silhouette score, alongside a contrastive loss to improve the visualization and interpretability of ensemble datasets. First, EfficientNetV2 is used to generate pseudo-labels for the unlabeled portions of the scientific ensemble datasets. By jointly optimizing the reconstruction, clustering, and contrastive objectives, our method encourages similar data points to group together while separating distinct clusters in the latent space. UMAP is subsequently applied to this latent representation to produce 2D projections, which are evaluated using the silhouette score. Multiple types of autoencoders are evaluated and compared based on their ability to extract meaningful features. Experiments on two scientific ensemble datasets - channel structures in soil derived from Markov chain Monte Carlo, and droplet-on-film impact dynamics - show that models incorporating clustering or contrastive loss marginally outperform the baseline approaches. --- ### Learning complete and explainable visual representations from itemized text supervision Authors: Yiwei Lyu, Chenhui Zhao, Soumyanil Banerjee, Shixuan Liu, Akshay Rao, Akhil Kondepudi, Honglak Lee, Todd C. Hollon Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11141v2 Training vision models with language supervision enables general and transferable representations. However, many visual domains, especially non-object-centric domains such as medical imaging and remote sensing, contain itemized text annotations: multiple text items describing distinct and semantically independent findings within a single image. Such supervision differs from standard multi-caption supervision, where captions are redundant or highly overlapping. Here, we introduce ItemizedCLIP, a framework for learning complete and explainable visual representations from itemized text supervision. ItemizedCLIP employs a cross-attention module to produce text item-conditioned visual embeddings and a set of tailored objectives that jointly enforce item independence (distinct regions for distinct items) and representation completeness (coverage of all items). Across four domains with naturally itemized text supervision (brain MRI, head CT, chest CT, remote sensing) and one additional synthetically itemized dataset, ItemizedCLIP achieves substantial improvements in zero-shot performance and fine-grained interpretability over baselines. The resulting ItemizedCLIP representations are semantically grounded, item-differentiable, complete, and visually interpretable. Our code is available at https://github.com/MLNeurosurg/ItemizedCLIP. --- ### Autotune: fast, accurate, and automatic tuning parameter selection for Lasso Authors: Tathagata Sadhukhan, Ines Wilms, Stephan Smeekes, Sumanta Basu Published: 2025-12-11 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.11139v4 Least absolute shrinkage and selection operator (Lasso), the popular variable selection engine for high-dimensional regression, is commonly tuned using cross-validation (CV). This is known to be slow and loses accuracy in high-dimension, low signal-to-noise ratio (SNR) settings. These issues are exacerbated for high-dimensional time series models such as the vector autoregression (VAR), where time series cross-validaiton (TSCV) is used for tuning. We propose $\texttt{autotune}$, a strategy for the Lasso to tune itself automatically by exploiting information contained in partial residuals computed during a single Lasso fit. The strategy can also be viewed as alternately estimating noise standard deviation and column space of relevant predictors. Numerical experiments on regression and VAR models show that $\texttt{autotune}$ is faster than existing alternatives, and more accurate when the SNR is low. It also provides an accurate estimator of noise scale and diagnostic plots akin to screeplots for checking model sparsity. We demonstrate the benefit of $\texttt{autotune}$ on several real data sets and develop an R package available on CRAN. --- ### The Vekua Layer: Exact Physical Priors for Implicit Neural Representations via Generalized Analytic Functions Authors: Vladimer Khasia Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11138v1 Implicit Neural Representations (INRs) have emerged as a powerful paradigm for parameterizing physical fields, yet they often suffer from spectral bias and the computational expense of non-convex optimization. We introduce the Vekua Layer (VL), a differentiable spectral method grounded in the classical theory of Generalized Analytic Functions. By restricting the hypothesis space to the kernel of the governing differential operator -- specifically utilizing Harmonic and Fourier-Bessel bases -- the VL transforms the learning task from iterative gradient descent to a strictly convex least-squares problem solved via linear projection. We evaluate the VL against Sinusoidal Representation Networks (SIRENs) on homogeneous elliptic Partial Differential Equations (PDEs). Our results demonstrate that the VL achieves machine precision ($\text{MSE} \approx 10^{-33}$) on exact reconstruction tasks and exhibits superior stability in the presence of incoherent sensor noise ($\text{MSE} \approx 0.03$), effectively acting as a physics-informed spectral filter. Furthermore, we show that the VL enables "holographic" extrapolation of global fields from partial boundary data via analytic continuation, a capability absent in standard coordinate-based approximations. --- ### Fairness-Regularized Online Optimization with Switching Costs Authors: Pengfei Li, Yuelin Han, Adam Wierman, Shaolei Ren Published: 2025-12-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.11131v1 Fairness and action smoothness are two crucial considerations in many online optimization problems, but they have yet to be addressed simultaneously. In this paper, we study a new and challenging setting of fairness-regularized smoothed online convex optimization with switching costs. First, to highlight the fundamental challenges introduced by the long-term fairness regularizer evaluated based on the entire sequence of actions, we prove that even without switching costs, no online algorithms can possibly achieve a sublinear regret or finite competitive ratio compared to the offline optimal algorithm as the problem episode length $T$ increases. Then, we propose FairOBD (Fairness-regularized Online Balanced Descent), which reconciles the tension between minimizing the hitting cost, switching cost, and fairness cost. Concretely, FairOBD decomposes the long-term fairness cost into a sequence of online costs by introducing an auxiliary variable and then leverages the auxiliary variable to regularize the online actions for fair outcomes. Based on a new approach to account for switching costs, we prove that FairOBD offers a worst-case asymptotic competitive ratio against a novel benchmark -- the optimal offline algorithm with parameterized constraints -- by considering $T\to\infty$. Finally, we run trace-driven experiments of dynamic computing resource provisioning for socially responsible AI inference to empirically evaluate FairOBD, showing that FairOBD can effectively reduce the total fairness-regularized cost and better promote fair outcomes compared to existing baseline solutions. --- ### Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching Authors: Bowen Wen, Shaurya Dewan, Stan Birchfield Published: 2025-12-11 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.11130v2 Stereo foundation models achieve strong zero-shot generalization but remain computationally prohibitive for real-time applications. Efficient stereo architectures, on the other hand, sacrifice robustness for speed and require costly per-domain fine-tuning. To bridge this gap, we present Fast-FoundationStereo, a family of architectures that achieve, for the first time, strong zero-shot generalization at real-time frame rate. We employ a divide-and-conquer acceleration strategy with three components: (1) knowledge distillation to compress the hybrid backbone into a single efficient student; (2) blockwise neural architecture search for automatically discovering optimal cost filtering designs under latency budgets, reducing search complexity exponentially; and (3) structured pruning for eliminating redundancy in the iterative refinement module. Furthermore, we introduce an automatic pseudo-labeling pipeline used to curate 1.4M in-the-wild stereo pairs to supplement synthetic training data and facilitate knowledge distillation. The resulting model can run over 10x faster than FoundationStereo while closely matching its zero-shot accuracy, thus establishing a new state-of-the-art among real-time methods. Project page: https://nvlabs.github.io/Fast-FoundationStereo/ --- ### Refining Graphical Neural Network Predictions Using Flow Matching for Optimal Power Flow with Constraint-Satisfaction Guarantee Authors: Kshitiz Khanal Published: 2025-12-11 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.11127v1 The DC Optimal Power Flow (DC-OPF) problem is fundamental to power system operations, requiring rapid solutions for real-time grid management. While traditional optimization solvers provide optimal solutions, their computational cost becomes prohibitive for large-scale systems requiring frequent recalculations. Machine learning approaches offer promise for acceleration but often struggle with constraint satisfaction and cost optimality. We present a novel two-stage learning framework that combines physics-informed Graph Neural Networks (GNNs) with Continuous Flow Matching (CFM) for solving DC-OPF problems. Our approach embeds fundamental physical principles--including economic dispatch optimality conditions, Kirchhoff's laws, and Karush-Kuhn-Tucker (KKT) complementarity conditions--directly into the training objectives. The first stage trains a GNN to produce feasible initial solutions by learning from physics-informed losses that encode power system constraints. The second stage employs CFM, a simulation-free continuous normalizing flow technique, to refine these solutions toward optimality through learned vector field regression. Evaluated on the IEEE 30-bus system across five load scenarios ranging from 70\% to 130\% nominal load, our method achieves near-optimal solutions with cost gaps below 0.1\% for nominal loads and below 3\% for extreme conditions, while maintaining 100\% feasibility. Our framework bridges the gap between fast but approximate neural network predictions and optimal but slow numerical solvers, offering a practical solution for modern power systems with high renewable penetration requiring frequent dispatch updates. --- ### Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior Authors: Yuyang Hu, Mojtaba Sahraee-Ardakan, Arpit Bansal, Kangfu Mei, Chenyang Qi, Peyman Milanfar, Mauricio Delbracio Published: 2025-12-11 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.11121v2 Pre-trained image restoration models often fail on out-of-distribution (OOD) real-world degradations. Adapting to these domains is challenging as real-world data lacks paired ground truth, and unsupervised methods often require unstable architectural changes. We propose Generative Manifold Distillation (GMD), which reframes domain adaptation as geometric manifold alignment. GMD operates in a strictly unpaired setting, requiring only low-quality (LQ) target observations. By leveraging the flow-matching dynamics of a frozen text-to-image foundation model, GMD projects off-manifold restorations onto the natural image manifold to generate high-quality pseudo-targets. To ensure stability, a quality-gated manifold filter rejects off-manifold samples, while source-anchored trajectory regularization prevents error accumulation. Ultimately, GMD distills a powerful generative prior into an efficient restoration network. Experiments demonstrate that GMD seamlessly adapts to new distributions using only LQ inputs, drastically improving perceptual quality with zero architectural modifications or added inference latency. --- ### In-Context Multi-Objective Optimization Authors: Xinyu Zhang, Conor Hassan, Julien Martinelli, Daolang Huang, Samuel Kaski Published: 2025-12-11 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.11114v2 Balancing competing objectives is omnipresent across disciplines, from drug design to autonomous systems. Multi-objective Bayesian optimization is a promising solution for such expensive, black-box problems: it fits probabilistic surrogates and selects new designs via an acquisition function that balances exploration and exploitation. In practice, it requires tailored choices of surrogate and acquisition that rarely transfer to the next problem, is myopic when multi-step planning is often required, and adds refitting overhead, particularly in parallel or time-sensitive loops. We present TAMO, a fully amortized, universal policy for multi-objective black-box optimization. TAMO uses a transformer architecture that operates across varying input and objective dimensions, enabling pretraining on diverse corpora and transfer to new problems without retraining: at test time, the pretrained model proposes the next design with a single forward pass. We pretrain the policy with reinforcement learning to maximize cumulative hypervolume improvement over full trajectories, conditioning on the entire query history to approximate the Pareto frontier. Across synthetic benchmarks and real tasks, TAMO produces fast proposals, reducing proposal time by 50-1000x versus alternatives while matching or improving Pareto quality under tight evaluation budgets. These results show that transformers can perform multi-objective optimization entirely in-context, eliminating per-task surrogate fitting and acquisition engineering, and open a path to foundation-style, plug-and-play optimizers for scientific discovery workflows. --- ### FIBER: A Multilingual Evaluation Resource for Factual Inference Bias Authors: Evren Ayberk Munis, Deniz Yılmaz, Arianna Muti, Çağrı Toraman Published: 2025-12-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.11110v1 Large language models are widely used across domains, yet there are concerns about their factual reliability and biases. Factual knowledge probing offers a systematic means to evaluate these aspects. Most existing benchmarks focus on single-entity facts and monolingual data. We therefore present FIBER, a multilingual benchmark for evaluating factual knowledge in single- and multi-entity settings. The dataset includes sentence completion, question-answering, and object-count prediction tasks in English, Italian, and Turkish. Using FIBER, we examine whether the prompt language induces inference bias in entity selection and how large language models perform on multi-entity versus single-entity questions. The results indicate that the language of the prompt can influence the model's generated output, particularly for entities associated with the country corresponding to that language. However, this effect varies across different topics such that 31% of the topics exhibit factual inference bias score greater than 0.5. Moreover, the level of bias differs across languages such that Turkish prompts show higher bias compared to Italian in 83% of the topics, suggesting a language-dependent pattern. Our findings also show that models face greater difficulty when handling multi-entity questions than the single-entity questions. Model performance differs across both languages and model sizes. The highest mean average precision is achieved in English, while Turkish and Italian lead to noticeably lower scores. Larger models, including Llama-3.1-8B and Qwen-2.5-7B, show consistently better performance than smaller 3B-4B models. --- ### Limits and Gains of Test-Time Scaling in Vision-Language Reasoning Authors: Mohammadjavad Ahmadpour, Amirmahdi Meighani, Payam Taebi, Omid Ghahroodi, Amirmohammad Izadi, Mahdieh Soleymani Baghshah Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11109v1 Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference, yet its application to multimodal systems such as Vision-Language Models (VLMs) remains underexplored. In this work, we present a systematic empirical study of inference time reasoning methods applied across both open-source and closed-source VLMs on different benchmarks. Our results reveal that while closed-source models consistently benefit from structured reasoning and iterative Self-Refinement, open-source VLMs show inconsistent behavior: external verification provides the most reliable gains, whereas iterative refinement often degrades performance. We further find that the effectiveness of TTS is dataset-dependent, yielding clear improvements on multi-step reasoning tasks but offering only limited gains on perception-focused benchmarks. These findings demonstrate that TTS is not a universal solution and must be tailored to both model capabilities and task characteristics, motivating future work on adaptive TTS strategies and multimodal reward models. --- ### Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution Authors: Jonathan Kamp, Roos Bakker, Dominique Blok Published: 2025-12-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.11108v3 Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on the same input may vary greatly due to underlying biases of different methods. Users may be aware of this issue and mistrust their utility, while unaware users may trust them inadequately. In this work, we delve beyond the superficial inconsistencies between attribution methods, structuring their biases through a model- and method-agnostic framework of three evaluation metrics. We systematically assess both lexical and position bias (what and where in the input) for two transformers; first, in a controlled, pseudo-random classification task on artificial data; then, in a semi-controlled causal relation detection task on natural data. We find a trade-off between lexical and position biases in our model comparison, with models that score high on one type score low on the other. We also find signs that anomalous explanations are more likely to be biased. --- ### Information-driven Fusion of Pathology Foundation Models for Enhanced Disease Characterization Authors: Brennan Flannery, Thomas DeSilvio, Jane Nguyen, Satish E. Viswanath Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11104v1 Foundation models (FMs) have demonstrated strong performance across diverse pathology tasks. While there are similarities in the pre-training objectives of FMs, there is still limited understanding of their complementarity, redundancy in embedding spaces, or biological interpretation of features. In this study, we propose an information-driven, intelligent fusion strategy for integrating multiple pathology FMs into a unified representation and systematically evaluate its performance for cancer grading and staging across three distinct diseases. Diagnostic H&E whole-slide images from kidney (519 slides), prostate (490 slides), and rectal (200 slides) cancers were dichotomized into low versus high grade or stage. Both tile-level FMs (Conch v1.5, MUSK, Virchow2, H-Optimus1, Prov-Gigapath) and slide-level FMs (TITAN, CHIEF, MADELEINE) were considered to train downstream classifiers. We then evaluated three FM fusion schemes at both tile and slide levels: majority-vote ensembling, naive feature concatenation, and intelligent fusion based on correlation-guided pruning of redundant features. Under patient-stratified cross-validation with hold-out testing, intelligent fusion of tile-level embeddings yielded consistent gains in classification performance across all three cancers compared with the best single FMs and naive fusion. Global similarity metrics revealed substantial alignment of FM embedding spaces, contrasted by lower local neighborhood agreement, indicating complementary fine-grained information across FMs. Attention maps showed that intelligent fusion yielded concentrated attention on tumor regions while reducing spurious focus on benign regions. Our findings suggest that intelligent, correlation-guided fusion of pathology FMs can yield compact, task-tailored representations that enhance both predictive performance and interpretability in downstream computational pathology tasks. --- ### VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction Authors: Weitai Kang, Jason Kuen, Mengwei Ren, Zijun Wei, Yan Yan, Kangning Liu Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11099v1 Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special or object tokens for grounding, which may undermine the LLM's pretrained reasoning ability. In contrast, we propose VGent, a modular encoder-decoder architecture that explicitly disentangles high-level reasoning and low-level bounding box prediction. Specifically, a frozen MLLM serves as the encoder to provide untouched powerful reasoning capabilities, while a decoder takes high-quality boxes proposed by detectors as queries and selects target box(es) via cross-attending on encoder's hidden states. This design fully leverages advances in both object detection and MLLM, avoids the pitfalls of auto-regressive decoding, and enables fast inference. Moreover, it supports modular upgrades of both the encoder and decoder to benefit the whole system: we introduce (i) QuadThinker, an RL-based training paradigm for enhancing multi-target reasoning ability of the encoder; (ii) mask-aware label for resolving detection-segmentation ambiguity; and (iii) global target recognition to improve the recognition of all the targets which benefits the selection among augmented proposals. Experiments on multi-target visual grounding benchmarks show that VGent achieves a new state-of-the-art with +20.6% F1 improvement over prior methods, and further boosts gIoU by +8.2% and cIoU by +5.8% under visual reference challenges, while maintaining constant, fast inference latency. --- ### Vision-Language Models for Infrared Industrial Sensing in Additive Manufacturing Scene Description Authors: Nazanin Mahjourian, Vinh Nguyen Published: 2025-12-11 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.11098v2 Many manufacturing environments operate in low-light conditions or within enclosed machines where conventional vision systems struggle. Infrared cameras provide complementary advantages in such environments. Simultaneously, supervised AI systems require large labeled datasets, which makes zero-shot learning frameworks more practical for applications including infrared cameras. Recent advances in vision-language foundation models (VLMs) offer a new path in zero-shot predictions from paired image-text representations. However, current VLMs cannot understand infrared camera data since they are trained on RGB data. This work introduces VLM-IRIS (Vision-Language Models for InfraRed Industrial Sensing), a zero-shot framework that adapts VLMs to infrared data by preprocessing infrared images captured by a FLIR Boson sensor into RGB-compatible inputs suitable for CLIP-based encoders. We demonstrate zero-shot workpiece presence detection on a 3D printer bed where temperature differences between the build plate and workpieces make the task well-suited for thermal imaging. VLM-IRIS converts the infrared images to magma representation and applies centroid prompt ensembling with a CLIP ViT-B/32 encoder to achieve high accuracy on infrared images without any model retraining. These findings demonstrate that the proposed improvements to VLMs can be effectively extended to thermal applications for label-free monitoring. --- ### Investigating ECG Diagnosis with Ambiguous Labels using Partial Label Learning Authors: Sana Rahmani, Javad Hashemi, Ali Etemad Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11095v2 Label ambiguity is an inherent and largely unaddressed challenge in real-world electrocardiogram (ECG) diagnosis, arising from overlapping conditions and diagnostic disagreements. However, current ECG models are trained assuming clean and non-ambiguous annotations, limiting both the development and meaningful evaluation of models under real-world conditions. Although Partial Label Learning (PLL) frameworks are designed to learn from ambiguous labels, their effectiveness in medical time-series domains, ECG in particular, remains largely underexplored. We present the first systematic study of PLL methods for ECG diagnosis under both real and controlled ambiguity. First, we adapt nine PLL algorithms to multi-label ECG diagnosis under label ambiguity, and perform detailed evaluations on real clinical settings with multi-annotator diagnostic disagreements. Next, to study PLL effects on ECG in more depth under controlled settings, we introduce a diverse set of clinically motivated synthetic label ambiguities. Our experiments demonstrate that PLL methods vary substantially in robustness across ambiguity types and levels. Moreover, we observe that PLL generally outperforms standard supervised training under label ambiguity, highlighting the value of such frameworks. Through extensive analysis, we identify key limitations of current PLL approaches for clinical settings and outline future directions for developing robust and clinically aligned ambiguity-aware learning frameworks for ECG diagnosis. --- ### Data-Driven Model Reduction using WeldNet: Windowed Encoders for Learning Dynamics Authors: Biraj Dahal, Jiahui Cheng, Hao Liu, Rongjie Lai, Wenjing Liao Published: 2025-12-11 Categories: stat.ML, cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.11090v1 Many problems in science and engineering involve time-dependent, high dimensional datasets arising from complex physical processes, which are costly to simulate. In this work, we propose WeldNet: Windowed Encoders for Learning Dynamics, a data-driven nonlinear model reduction framework to build a low-dimensional surrogate model for complex evolution systems. Given time-dependent training data, we split the time domain into multiple overlapping windows, within which nonlinear dimension reduction is performed by auto-encoders to capture latent codes. Once a low-dimensional representation of the data is learned, a propagator network is trained to capture the evolution of the latent codes in each window, and a transcoder is trained to connect the latent codes between adjacent windows. The proposed windowed decomposition significantly simplifies propagator training by breaking long-horizon dynamics into multiple short, manageable segments, while the transcoders ensure consistency across windows. In addition to the algorithmic framework, we develop a mathematical theory establishing the representation power of WeldNet under the manifold hypothesis, justifying the success of nonlinear model reduction via deep autoencoder-based architectures. Our numerical experiments on various differential equations indicate that WeldNet can capture nonlinear latent structures and their underlying dynamics, outperforming both traditional projection-based approaches and recently developed nonlinear model reduction methods. --- ### TPV: Parameter Perturbations Through the Lens of Test Prediction Variance Authors: Devansh Arpit Published: 2025-12-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.11089v4 We introduce test prediction variance (TPV)--the first-order sensitivity of a trained model's outputs to parameter perturbations--as a unifying framework for analyzing post-training robustness. TPV is a fully label-free object whose trace form separates the geometry of the trained model from the specific perturbation mechanism, placing SGD noise, label noise, quantization, and pruning under a single lens. The resulting expressions recover the wide-minima hypothesis for SGD and quantization noise, and yield a distinct Jacobian-spectral characterization for label noise connecting label-noise TPV with benign overfitting in nonlinear networks. Theoretically, we prove that training-set TPV converges to its test-set counterpart in the overparameterized limit, irrespective of generalization performance, providing the first result that prediction variance under local parameter perturbations can be inferred from training inputs alone. Empirically, this stability holds far more broadly, including at very low widths. Further, TPV correlates well with test loss, enabling practical applications: JBR, a label-free pruning criterion derived from TPV geometry matching state-of-the-art baselines; and training-set based model selection signal for in-distribution and transfer learning scenarios. Code available at github.com/devansharpit/TPV. --- ### Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification Authors: Duo Zhou, Jorge Chavez, Hesun Chen, Grani A. Hanasusanto, Huan Zhang Published: 2025-12-11 Categories: cs.LG, cs.AI, cs.CR, math.OC arXiv: https://arxiv.org/abs/2512.11087v1 State-of-the-art neural network (NN) verifiers demonstrate that applying the branch-and-bound (BaB) procedure with fast bounding techniques plays a key role in tackling many challenging verification properties. In this work, we introduce the linear constraint-driven clipping framework, a class of scalable and efficient methods designed to enhance the efficacy of NN verifiers. Under this framework, we develop two novel algorithms that efficiently utilize linear constraints to 1) reduce portions of the input space that are either verified or irrelevant to a subproblem in the context of branch-and-bound, and 2) directly improve intermediate bounds throughout the network. The process novelly leverages linear constraints that often arise from bound propagation methods and is general enough to also incorporate constraints from other sources. It efficiently handles linear constraints using a specialized GPU procedure that can scale to large neural networks without the use of expensive external solvers. Our verification procedure, Clip-and-Verify, consistently tightens bounds across multiple benchmarks and can significantly reduce the number of subproblems handled during BaB. We show that our clipping algorithms can be integrated with BaB-based verifiers such as $α,β$-CROWN, utilizing either the split constraints in activation-space BaB or the output constraints that denote the unverified input space. We demonstrate the effectiveness of our procedure on a broad range of benchmarks where, in some instances, we witness a 96% reduction in the number of subproblems during branch-and-bound, and also achieve state-of-the-art verified accuracy across multiple benchmarks. Clip-and-Verify is part of the $α,β$-CROWN verifier (http://abcrown.org), the VNN-COMP 2025 winner. Code available at https://github.com/Verified-Intelligence/Clip_and_Verify. --- ### Memoryless Policy Iteration for Episodic POMDPs Authors: Roy van Zuijlen, Duarte Antunes Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11082v1 Memoryless and finite-memory policies offer a practical alternative for solving partially observable Markov decision processes (POMDPs), as they operate directly in the output space rather than in the high-dimensional belief space. However, extending classical methods such as policy iteration to this setting remains difficult; the output process is non-Markovian, making policy-improvement steps interdependent across stages. We introduce a new family of monotonically improving policy-iteration algorithms that alternate between single-stage output-based policy improvements and policy evaluations according to a prescribed periodic pattern. We show that this family admits optimal patterns that maximize a natural computational-efficiency index, and we identify the simplest pattern with minimal period. Building on this structure, we further develop a model-free variant that estimates values from data and learns memoryless policies directly. Across several POMDPs examples, our method achieves significant computational speedups over policy-gradient baselines and recent specialized algorithms in both model-based and model-free settings. --- ### Provable Recovery of Locally Important Signed Features and Interactions from Random Forest Authors: Kata Vuk, Nicolas Alexander Ihlo, Merle Behr Published: 2025-12-11 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2512.11081v2 Feature and Interaction Importance (FII) methods are essential in supervised learning for assessing the relevance of input variables and their interactions in complex prediction models. In many domains, such as personalized medicine, local interpretations for individual predictions are often required, rather than global scores summarizing overall feature importance. Random Forests (RFs) are widely used in these settings, and existing interpretability methods typically exploit tree structures and split statistics to provide model-specific insights. However, theoretical understanding of local FII methods for RF remains limited, making it unclear how to interpret high importance scores for individual predictions. We propose a novel, local, model-specific FII method that identifies frequent co-occurrences of features along decision paths, combining global patterns with those observed on paths specific to a given test point. We prove that our method consistently recovers the true local signal features and their interactions under a Locally Spike Sparse (LSS) model and also identifies whether large or small feature values drive a prediction. We illustrate the usefulness of our method and theoretical results through simulation studies and a real-world data example. --- ### Applying NLP to iMessages: Understanding Topic Avoidance, Responsiveness, and Sentiment Authors: Alan Gerber, Sam Cooperman Published: 2025-12-11 Categories: cs.CL, cs.CY, stat.AP, stat.OT arXiv: https://arxiv.org/abs/2512.11079v1 What is your messaging data used for? While many users do not often think about the information companies can gather based off of their messaging platform of choice, it is nonetheless important to consider as society increasingly relies on short-form electronic communication. While most companies keep their data closely guarded, inaccessible to users or potential hackers, Apple has opened a door to their walled-garden ecosystem, providing iMessage users on Mac with one file storing all their messages and attached metadata. With knowledge of this locally stored file, the question now becomes: What can our data do for us? In the creation of our iMessage text message analyzer, we set out to answer five main research questions focusing on topic modeling, response times, reluctance scoring, and sentiment analysis. This paper uses our exploratory data to show how these questions can be answered using our analyzer and its potential in future studies on iMessage data. --- ### A probabilistic framework for crystal structure denoising, phase classification, and order parameters Authors: Hyuna Kwon, Babak Sadigh, Sebastien Hamel, Vincenzo Lordi, John Klepeis, Fei Zhou Published: 2025-12-11 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2512.11077v3 Atomistic simulations generate large volumes of noisy structural data, yet extracting phase labels and continuous order parameters (OPs) in a robust and general manner remains challenging. Existing tools are often specialized to a limited set of prototypes and split thermal-noise removal, phase classification, and OP construction into separate steps. Here we present a unified probabilistic framework for analyzing noisy atomic configurations with respect to known crystal prototypes. The model predicts per-atom, per-prototype logits and aggregates them into a scalar log-probability (logP) landscape over atomic coordinates. Its gradient defines a conservative denoising field, while the logits provide local phase labels, prototype-resolved OPs, and ambiguity measures through logit margins. We train on AFLOW-mapped crystalline structures from the Materials Project with synthetic positional and elastic perturbations, then test extrapolation to stronger noise, finite-temperature disorder, point defects, water--ice coexistence, binary polymorphs, and shock-compressed Ti. A single differentiable scalar model recovers prototype identity after denoising, tracks smooth transformations such as Bain and Burgers paths, and exposes low-confidence regions near defects and phase boundaries. This provides an integrated and extensible tool for analyzing complex atomistic simulations. --- ### E-CHUM: Event-based Cameras for Human Detection and Urban Monitoring Authors: Jack Brady, Andrew Dailey, Kristen Schang, Zo Vic Shong Published: 2025-12-11 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.11076v1 Understanding human movement and city dynamics has always been challenging. From traditional methods of manually observing the city's inhabitant, to using cameras, to now using sensors and more complex technology, the field of urban monitoring has evolved greatly. Still, there are more that can be done to unlock better practices for understanding city dynamics. This paper surveys how the landscape of urban dynamics studying has evolved with a particular focus on event-based cameras. Event-based cameras capture changes in light intensity instead of the RGB values that traditional cameras do. They offer unique abilities, like the ability to work in low-light, that can make them advantageous compared to other sensors. Through an analysis of event-based cameras, their applications, their advantages and challenges, and machine learning applications, we propose event-based cameras as a medium for capturing information to study urban dynamics. They offer the ability to capture important information while maintaining privacy. We also suggest multi-sensor fusion of event-based cameras and other sensors in the study of urban dynamics. Combining event-based cameras and infrared, event-LiDAR, or vibration has to potential to enhance the ability of event-based cameras and overcome the challenges that event-based cameras have. --- ### Fast, accurate measurement of the worker populations of honey bee colonies using deep learning Authors: Junmin Zhong, Jon F. Harrison, Jennie Si, Jun Chen Published: 2025-12-11 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2512.11075v1 Honey bees play a crucial role in pollination, contributing significantly to global agriculture and ecosystems. Accurately estimating hive populations is essential for understanding the effects of environmental factors on bee colonies, yet traditional methods of counting bees are time-consuming, labor-intensive, and prone to human error, particularly in large-scale studies. In this paper, we present a deep learning-based solution for automating bee population counting using CSRNet and introduce ASUBEE, the FIRST high-resolution dataset specifically designed for this task. Our method employs density map estimation to predict bee populations, effectively addressing challenges such as occlusion and overlapping bees that are common in hive monitoring. We demonstrate that CSRNet achieves superior performance in terms of time efficiency, with a computation time of just 1 second per image, while delivering accurate counts even in complex and densely populated hive scenarios. Our findings show that deep learning approaches like CSRNet can dramatically enhance the efficiency of hive population assessments, providing a valuable tool for researchers and beekeepers alike. This work marks a significant advancement in applying AI technologies to ecological research, offering scalable and precise monitoring solutions for honey bee populations. --- ### MultiScript30k: Leveraging Multilingual Embeddings to Extend Cross Script Parallel Data Authors: Christopher Driggers-Ellis, Detravious Brinkley, Ray Chen, Aashish Dhawan, Daisy Zhe Wang, Christan Grant Published: 2025-12-11 Categories: cs.CL, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2512.11074v1 Multi30k is frequently cited in the multimodal machine translation (MMT) literature, offering parallel text data for training and fine-tuning deep learning models. However, it is limited to four languages: Czech, English, French, and German. This restriction has led many researchers to focus their investigations only on these languages. As a result, MMT research on diverse languages has been stalled because the official Multi30k dataset only represents European languages in Latin scripts. Previous efforts to extend Multi30k exist, but the list of supported languages, represented language families, and scripts is still very short. To address these issues, we propose MultiScript30k, a new Multi30k dataset extension for global languages in various scripts, created by translating the English version of Multi30k (Multi30k-En) using NLLB200-3.3B. The dataset consists of over \(30000\) sentences and provides translations of all sentences in Multi30k-En into Ar, Es, Uk, Zh\_Hans and Zh\_Hant. Similarity analysis shows that Multi30k extension consistently achieves greater than \(0.8\) cosine similarity and symmetric KL divergence less than \(0.000251\) for all languages supported except Zh\_Hant which is comparable to the previous Multi30k extensions ArEnMulti30k and Multi30k-Uk. COMETKiwi scores reveal mixed assessments of MultiScript30k as a translation of Multi30k-En in comparison to the related work. ArEnMulti30k scores nearly equal MultiScript30k-Ar, but Multi30k-Uk scores $6.4\%$ greater than MultiScript30k-Uk per split. --- ### KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration Authors: Guorui Xiao, Enhao Zhang, Nicole Sullivan, Will Hansen, Magdalena Balazinska Published: 2025-12-11 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2512.11067v1 Traditional DBMSs execute user- or application-provided SQL queries over relational data with strong semantic guarantees and advanced query optimization, but writing complex SQL is hard and focuses only on structured tables. Contemporary multimodal systems (which operate over relations but also text, images, and even videos) either expose low-level controls that force users to use (and possibly create) machine learning UDFs manually within SQL or offload execution entirely to black-box LLMs, sacrificing usability or explainability. We propose KathDB, a new system that combines relational semantics with the reasoning power of foundation models over multimodal data. Furthermore, KathDB includes human-AI interaction channels during query parsing, execution, and result explanation, such that users can iteratively obtain explainable answers across data modalities. --- ### VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation Authors: Felix O'Mahony, Roberto Cipolla, Ayush Tewari Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11061v2 Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack interactivity, and operate as opaque black boxes ill-suited for building structured, queryable worlds. To overcome these challenges, we propose a new paradigm focused on distilling an image caption pair into a tractable, abstract representation optimized for simulation. We introduce VDAWorld, a framework where a Vision-Language Model (VLM) acts as an intelligent agent to orchestrate this process. The VLM autonomously constructs a grounded (2D or 3D) scene representation by selecting from a suite of vision tools, and accordingly chooses a compatible physics simulator (e.g., rigid body, fluid) to act upon it. VDAWorld can then infer latent dynamics from the static scene to predict plausible future states. Our experiments show that this combination of intelligent abstraction and adaptive simulation results in a versatile world model capable of producing high quality simulations across a wide range of scenarios. We demonstrate several applications of VDAWorld across interactive control and counterfactual generation, and physical and logical reasoning, achieving state-of-the-art results on several benchmarks. --- ### Synthetic Vasculature and Pathology Enhance Vision-Language Model Reasoning Authors: Chenjun Li, Cheng Wan, Laurin Lux, Alexander Berger, Richard B. Rosen, Martin J. Menten, Johannes C. Paetzold Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11060v1 Vision-Language Models (VLMs) offer a promising path toward interpretable medical diagnosis by allowing users to ask about clinical explanations alongside predictions and across different modalities. However, training VLMs for detailed reasoning requires large-scale image-text datasets. In many specialized domains, for example in reading Optical Coherence Tomography Angiography (OCTA) images, such precise text with grounded description of pathologies is scarce or even non-existent. To overcome this bottleneck, we introduce Synthetic Vasculature Reasoning (SVR), a framework that controllably synthesizes images and corresponding text, specifically: realistic retinal vasculature with Diabetic Retinopathy (DR) features: capillary dropout, microaneurysms, neovascularization, and tortuosity, while automatically generating granular reasoning texts. Based on this we curate OCTA-100K-SVR, an OCTA image-reasoning dataset with 100,000 pairs. Our experiments show that a general-purpose VLM (Qwen3-VL-8b) trained on the dataset achieves a zero-shot balanced classification accuracy of 89.67% on real OCTA images, outperforming supervised baselines. Through human expert evaluation we also demonstrate that it significantly enhances explanation quality and pathology localization on clinical data. --- ### Weakly Supervised Tuberculosis Localization in Chest X-rays through Knowledge Distillation Authors: Marshal Ashif Shawkat, Moidul Hasan, Taufiq Hasan Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11057v1 Tuberculosis (TB) remains one of the leading causes of mortality worldwide, particularly in resource-limited countries. Chest X-ray (CXR) imaging serves as an accessible and cost-effective diagnostic tool but requires expert interpretation, which is often unavailable. Although machine learning models have shown high performance in TB classification, they often depend on spurious correlations and fail to generalize. Besides, building large datasets featuring high-quality annotations for medical images demands substantial resources and input from domain specialists, and typically involves several annotators reaching agreement, which results in enormous financial and logistical expenses. This study repurposes knowledge distillation technique to train CNN models reducing spurious correlations and localize TB-related abnormalities without requiring bounding-box annotations. By leveraging a teacher-student framework with ResNet50 architecture, the proposed method trained on TBX11k dataset achieve impressive 0.2428 mIOU score. Experimental results further reveal that the student model consistently outperforms the teacher, underscoring improved robustness and potential for broader clinical deployment in diverse settings. --- ### An Efficient Variant of One-Class SVM with Lifelong Online Learning Guarantees Authors: Joe Suk, Samory Kpotufe Published: 2025-12-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.11052v1 We study outlier (a.k.a., anomaly) detection for single-pass non-stationary streaming data. In the well-studied offline or batch outlier detection problem, traditional methods such as kernel One-Class SVM (OCSVM) are both computationally heavy and prone to large false-negative (Type II) errors under non-stationarity. To remedy this, we introduce SONAR, an efficient SGD-based OCSVM solver with strongly convex regularization. We show novel theoretical guarantees on the Type I/II errors of SONAR, superior to those known for OCSVM, and further prove that SONAR ensures favorable lifelong learning guarantees under benign distribution shifts. In the more challenging problem of adversarial non-stationary data, we show that SONAR can be used within an ensemble method and equipped with changepoint detection to achieve adaptive guarantees, ensuring small Type I/II errors on each phase of data. We validate our theoretical findings on synthetic and real-world datasets. --- ### WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control Authors: Haoran Jiang, Jin Chen, Qingwen Bu, Li Chen, Modi Shi, Yanjie Zhang, Delong Li, Chuanzhe Suo, Chuang Wang, Zhihui Peng, Hongyang Li Published: 2025-12-11 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11047v2 Humanoid robots require precise locomotion and dexterous manipulation to perform challenging loco-manipulation tasks. Yet existing approaches, modular or end-to-end, are deficient in manipulation-aware locomotion. This confines the robot to a limited workspace, preventing it from performing large-space loco-manipulation. We attribute this to: (1) the challenge of acquiring loco-manipulation knowledge due to the scarcity of humanoid teleoperation data, and (2) the difficulty of faithfully and reliably executing locomotion commands, stemming from the limited precision and stability of existing RL controllers. To acquire richer loco-manipulation knowledge, we propose a unified latent learning framework that enables Vision-Language-Action (VLA) system to learn from low-cost action-free egocentric videos. Moreover, an efficient human data collection pipeline is devised to augment the dataset and scale the benefits. To execute the desired locomotion commands more precisely, we present a loco-manipulation-oriented (LMO) RL policy specifically tailored for accurate and stable core loco-manipulation movements, such as advancing, turning, and squatting. Building on these components, we introduce WholeBodyVLA, a unified framework for humanoid loco-manipulation. To the best of our knowledge, WholeBodyVLA is one of its kind enabling large-space humanoid loco-manipulation. It is verified via comprehensive experiments on the AgiBot X2 humanoid, outperforming prior baseline by 21.3%. It also demonstrates strong generalization and high extensibility across a broad range of tasks. ---