# Research Papers — 2025-12 · bundle page 116 of 175 > Full-text markdown of papers #5751–5800 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/116 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/115.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/117.md) ### OmniPSD: Layered PSD Generation with Diffusion Transformer Authors: Cheng Liu, Yiren Song, Haofan Wang, Mike Zheng Shou Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09247v1 Recent advances in diffusion models have greatly improved image generation and editing, yet generating or reconstructing layered PSD files with transparent alpha channels remains highly challenging. We propose OmniPSD, a unified diffusion framework built upon the Flux ecosystem that enables both text-to-PSD generation and image-to-PSD decomposition through in-context learning. For text-to-PSD generation, OmniPSD arranges multiple target layers spatially into a single canvas and learns their compositional relationships through spatial attention, producing semantically coherent and hierarchically structured layers. For image-to-PSD decomposition, it performs iterative in-context editing, progressively extracting and erasing textual and foreground components to reconstruct editable PSD layers from a single flattened image. An RGBA-VAE is employed as an auxiliary representation module to preserve transparency without affecting structure learning. Extensive experiments on our new RGBA-layered dataset demonstrate that OmniPSD achieves high-fidelity generation, structural consistency, and transparency awareness, offering a new paradigm for layered design generation and decomposition with diffusion transformers. --- ### A Clinically Interpretable Deep CNN Framework for Early Chronic Kidney Disease Prediction Using Grad-CAM-Based Explainable AI Authors: Anas Bin Ayub, Nilima Sultana Niha, Md. Zahurul Haque Published: 2025-12-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.09244v1 Chronic Kidney Disease (CKD) constitutes a major global medical burden, marked by the gradual deterioration of renal function, which results in the impaired clearance of metabolic waste and disturbances in systemic fluid homeostasis. Owing to its substantial contribution to worldwide morbidity and mortality, the development of reliable and efficient diagnostic approaches is critically important to facilitate early detection and prompt clinical management. This study presents a deep convolutional neural network (CNN) for early CKD detection from CT kidney images, complemented by class balancing using Synthetic Minority Over-sampling Technique (SMOTE) and interpretability via Gradient-weighted Class Activation Mapping (Grad-CAM). The model was trained and evaluated on the CT KIDNEY DATASET, which contains 12,446 CT images, including 3,709 cyst, 5,077 normal, 1,377 stone, and 2,283 tumor cases. The proposed deep CNN achieved a remarkable classification performance, attaining 100% accuracy in the early detection of chronic kidney disease (CKD). This significant advancement demonstrates strong potential for addressing critical clinical diagnostic challenges and enhancing early medical intervention strategies. --- ### Training-free Context-adaptive Attention for Efficient Long Context Modeling Authors: Zeng You, Yaofo Chen, Shuhai Zhang, Zhijie Qiu, Tingyu Wu, Yingjian Li, Yaowei Wang, Mingkui Tan Published: 2025-12-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.09238v2 Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-attention mechanism, which enables modeling of long-range dependencies. However, the quadratic complexity of self-attention with respect to sequence length poses significant computational and memory challenges, especially as sequence length extends to extremes. While various sparse attention and KV cache compression methods have been proposed to improve efficiency, they often suffer from limitations such as reliance on fixed patterns, inability to handle both prefilling and decoding stages, or the requirement for additional training. In this paper, we propose Training-free Context-adaptive Attention (TCA-Attention), a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference. Our method consists of two lightweight phases: i) an offline calibration phase that determines head-specific sparsity budgets via a single forward pass, and ii) an online token selection phase that adaptively retains core context tokens using a lightweight redundancy metric. TCA-Attention provides a unified solution that accelerates both prefilling and decoding while reducing KV cache memory footprint, without requiring parameter updates or architectural changes. Theoretical analysis shows that our approach maintains bounded approximation error. Extensive experiments demonstrate that TCA-Attention achieves a 2.8$\times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention across various benchmarks, offering a practical plug-and-play solution for efficient long-context inference. --- ### Efficient Feature Compression for Machines with Global Statistics Preservation Authors: Md Eimran Hossain Eimon, Hyomin Choi, Fabien Racapé, Mateen Ulhaq, Velibor Adzic, Hari Kalva, Borko Furht Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09235v1 The split-inference paradigm divides an artificial intelligence (AI) model into two parts. This necessitates the transfer of intermediate feature data between the two halves. Here, effective compression of the feature data becomes vital. In this paper, we employ Z-score normalization to efficiently recover the compressed feature data at the decoder side. To examine the efficacy of our method, the proposed method is integrated into the latest Feature Coding for Machines (FCM) codec standard under development by the Moving Picture Experts Group (MPEG). Our method supersedes the existing scaling method used by the current standard under development. It both reduces the overhead bits and improves the end-task accuracy. To further reduce the overhead in certain circumstances, we also propose a simplified method. Experiments show that using our proposed method shows 17.09% reduction in bitrate on average across different tasks and up to 65.69% for object tracking without sacrificing the task accuracy. --- ### Enabling Next-Generation Consumer Experience with Feature Coding for Machines Authors: Md Eimran Hossain Eimon, Juan Merlos, Ashan Perera, Hari Kalva, Velibor Adzic, Borko Furht Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09232v1 As consumer devices become increasingly intelligent and interconnected, efficient data transfer solutions for machine tasks have become essential. This paper presents an overview of the latest Feature Coding for Machines (FCM) standard, part of MPEG-AI and developed by the Moving Picture Experts Group (MPEG). FCM supports AI-driven applications by enabling the efficient extraction, compression, and transmission of intermediate neural network features. By offloading computationally intensive operations to base servers with high computing resources, FCM allows low-powered devices to leverage large deep learning models. Experimental results indicate that the FCM standard maintains the same level of accuracy while reducing bitrate requirements by 75.90% compared to remote inference. --- ### Exploratory Mean-Variance with Jumps: An Equilibrium Approach Authors: Yuling Max Chen, Bin Li, David Saunders Published: 2025-12-10 Categories: q-fin.PM, stat.ML arXiv: https://arxiv.org/abs/2512.09224v1 Revisiting the continuous-time Mean-Variance (MV) Portfolio Optimization problem, we model the market dynamics with a jump-diffusion process and apply Reinforcement Learning (RL) techniques to facilitate informed exploration within the control space. We recognize the time-inconsistency of the MV problem and adopt the time-inconsistent control (TIC) approach to analytically solve for an exploratory equilibrium investment policy, which is a Gaussian distribution centered on the equilibrium control of the classical MV problem. Our approach accounts for time-inconsistent preferences and actions, and our equilibrium policy is the best option an investor can take at any given time during the investment period. Moreover, we leverage the martingale properties of the equilibrium policy, design a RL model, and propose an Actor-Critic RL algorithm. All of our RL model parameters converge to the corresponding true values in a simulation study. Our numerical study on 24 years of real market data shows that the proposed RL model is profitable in 13 out of 14 tests, demonstrating its practical applicability in real world investment. --- ### CORE: A Conceptual Reasoning Layer for Large Language Models Authors: Vishwas Hegde, Vindhya Shigehalli Published: 2025-12-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.09222v1 Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across turns. This token-first paradigm leads to drift, inconsistent reasoning modes, and growing prompts as conversations deepen. We propose CORE, a concept-first interaction layer that improves multi-turn stability without modifying model weights. CORE combines a small library of universal cognitive operators with a persistent Local Concept - a compact semantic state capturing the task, constraints, preferences, and intermediate results. Each model call receives only this concept state, the user's latest instruction, and the selected operator, eliminating the need to replay full history. A preliminary prototype simulating CORE's behavior shows about 42% reduction in cumulative prompt tokens, though this number reflects prototype conditions and should not be interpreted as a real-world performance estimate. CORE offers a model-agnostic mechanism that separates conceptual reasoning from language generation, suggesting a scalable direction for more stable multi-turn systems. --- ### View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs Authors: Yuanyuan Liu, Haiyang Mei, Dongyang Zhan, Jiayue Zhao, Dongsheng Zhou, Bo Dong, Xin Yang Published: 2025-12-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.09215v1 3D visual grounding (3DVG) identifies objects in 3D scenes from language descriptions. Existing zero-shot approaches leverage 2D vision-language models (VLMs) by converting 3D spatial information (SI) into forms amenable to VLM processing, typically as composite inputs such as specified view renderings or video sequences with overlaid object markers. However, this VLM + SI paradigm yields entangled visual representations that compel the VLM to process entire cluttered cues, making it hard to exploit spatial semantic relationships effectively. In this work, we propose a new VLM x SI paradigm that externalizes the 3D SI into a form enabling the VLM to incrementally retrieve only what it needs during reasoning. We instantiate this paradigm with a novel View-on-Graph (VoG) method, which organizes the scene into a multi-modal, multi-layer scene graph and allows the VLM to operate as an active agent that selectively accesses necessary cues as it traverses the scene. This design offers two intrinsic advantages: (i) by structuring 3D context into a spatially and semantically coherent scene graph rather than confounding the VLM with densely entangled visual inputs, it lowers the VLM's reasoning difficulty; and (ii) by actively exploring and reasoning over the scene graph, it naturally produces transparent, step-by-step traces for interpretable 3DVG. Extensive experiments show that VoG achieves state-of-the-art zero-shot performance, establishing structured scene exploration as a promising strategy for advancing zero-shot 3DVG. --- ### Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment Authors: Zixuan Liu, Siavash H. Khajavi, Guangkai Jiang, Xinru Liu Published: 2025-12-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.09212v2 Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a condition often violated due to annotation noise, bias, or limited coverage. This misalignment can lead to undesirable behaviors, where models optimize for flawed signals rather than true human values. In this paper, we investigate a novel framework to identify and mitigate such misalignment by treating the fine-tuning process as a form of knowledge integration. We focus on detecting instances of proxy-policy conflicts, cases where the base model strongly disagrees with the proxy. We argue that such conflicts often signify areas of shared ignorance, where neither the policy nor the reward model possesses sufficient knowledge, making them especially susceptible to misalignment. To this end, we propose two complementary metrics for identifying these conflicts: a localized Proxy-Policy Alignment Conflict Score (PACS) and a global Kendall-Tau Distance measure. Building on this insight, we design an algorithm named Selective Human-in-the-loop Feedback via Conflict-Aware Sampling (SHF-CAS) that targets high-conflict QA pairs for additional feedback, refining both the reward model and policy efficiently. Experiments on two alignment tasks demonstrate that our approach enhances general alignment performance, even when trained with a biased proxy reward. Our work provides a new lens for interpreting alignment failures and offers a principled pathway for targeted refinement in LLM training. --- ### Beyond Algorithm Evolution: An LLM-Driven Framework for the Co-Evolution of Swarm Intelligence Optimization Algorithms and Prompts Authors: Shipeng Cen, Ying Tan Published: 2025-12-10 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.09209v1 The field of automated algorithm design has been advanced by frameworks such as EoH, FunSearch, and Reevo. Yet, their focus on algorithm evolution alone, neglecting the prompts that guide them, limits their effectiveness with LLMs, especially in complex, uncertain environments where they nonetheless implicitly rely on strategies from swarm intelligence optimization algorithms. Recognizing this, we argue that swarm intelligence optimization provides a more generalized and principled foundation for automated design. Consequently, this paper proposes a novel framework for the collaborative evolution of both swarm intelligence algorithms and guiding prompts using a single LLM. To enhance interpretability, we also propose a simple yet efficient evaluation method for prompt templates. The framework was rigorously evaluated on a range of NP problems, where it demonstrated superior performance compared to several state-of-the-art automated design approaches. Experiments with various LLMs (e.g., GPT-4o-mini, Qwen3-32B, GPT-5) reveal significantly divergent evolutionary trajectories in the generated prompts, further underscoring the necessity of a structured co-evolution framework. Importantly, our approach maintains leading performance across different models, demonstrating reduced reliance on the most powerful LLMs and enabling more cost-effective deployments. Ablation studies and in-depth analysis of the evolved prompts confirm that collaborative evolution is essential for achieving optimal performance. Our work establishes a new paradigm for swarm intelligence optimization algorithms, underscoring the indispensable role of prompt evolution. --- ### Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers Authors: Jinming Lu, Jiayi Tian, Yequan Zhao, Hai Li, Zheng Zhang Published: 2025-12-10 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2512.09202v1 Physics-Informed Neural Networks (PINNs) have emerged as a promising paradigm for solving partial differential equations (PDEs) by embedding physical laws into neural network training objectives. However, their deployment on resource-constrained platforms is hindered by substantial computational and memory overhead, primarily stemming from higher-order automatic differentiation, intensive tensor operations, and reliance on full-precision arithmetic. To address these challenges, we present a framework that enables scalable and energy-efficient PINN training on edge devices. This framework integrates fully quantized training, Stein's estimator (SE)-based residual loss computation, and tensor-train (TT) decomposition for weight compression. It contributes three key innovations: (1) a mixed-precision training method that use a square-block MX (SMX) format to eliminate data duplication during backpropagation; (2) a difference-based quantization scheme for the Stein's estimator that mitigates underflow; and (3) a partial-reconstruction scheme (PRS) for TT-Layers that reduces quantization-error accumulation. We further design PINTA, a precision-scalable hardware accelerator, to fully exploit the performance of the framework. Experiments on the 2-D Poisson, 20-D Hamilton-Jacobi-Bellman (HJB), and 100-D Heat equations demonstrate that the proposed framework achieves accuracy comparable to or better than full-precision, uncompressed baselines while delivering 5.5x to 83.5x speedups and 159.6x to 2324.1x energy savings. This work enables real-time PDE solving on edge devices and paves the way for energy-efficient scientific computing at scale. --- ### RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal Retrieval-Augmented Generation on the Edge Authors: Ahmed Bin Khalid Published: 2025-12-09 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.22217v1 Retrieval-Augmented Generation (RAG) has established itself as the standard paradigm for grounding Large Language Models (LLMs) in domain-specific, up-to-date data. However, the prevailing architecture for RAG has evolved into a complex, distributed stack requiring cloud-hosted vector databases, heavy deep learning frameworks (e.g., PyTorch, CUDA), and high-latency embedding inference servers. This ``infrastructure bloat'' creates a significant barrier to entry for edge computing, air-gapped environments, and privacy-constrained applications where data sovereignty is paramount. This paper introduces RAGdb, a novel monolithic architecture that consolidates automated multimodal ingestion, ONNX-based extraction, and hybrid vector retrieval into a single, portable SQLite container. We propose a deterministic Hybrid Scoring Function (HSF) that combines sublinear TF-IDF vectorization with exact substring boosting, eliminating the need for GPU inference at query time. Experimental evaluation on an Intel i7-1165G7 consumer laptop demonstrates that RAGdb achieves 100\% Recall@1 for entity retrieval and an ingestion efficiency gain of 31.6x during incremental updates compared to cold starts. Furthermore, the system reduces disk footprint by approximately 99.5\% compared to standard Docker-based RAG stacks, establishing the ``Single-File Knowledge Container'' as a viable primitive for decentralized, local-first AI. Keywords: Edge AI, Retrieval-Augmented Generation, Vector Search, Green AI, Serverless Architecture, Knowledge Graphs, Efficient Computing. --- ### A Mobile Application Front-End for Presenting Explainable AI Results in Diabetes Risk Estimation Authors: Bernardus Willson, Henry Anand Septian Radityo, Raynard Tanadi, Latifa Dwiyanti, Saiful Akbar Published: 2025-12-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.15292v2 Diabetes is a significant and continuously rising health challenge in Indonesia. Although many artificial intelligence (AI)-based health applications have been developed for early detection, most function as "black boxes," lacking transparency in their predictions. Explainable AI (XAI) methods offer a solution, yet their technical outputs are often incomprehensible to non-expert users. This research aims to develop a mobile application front-end that presents XAI-driven diabetes risk analysis in an intuitive, understandable format. Development followed the waterfall methodology, comprising requirements analysis, interface design, implementation, and evaluation. Based on user preference surveys, the application adopts two primary visualization types - bar charts and pie charts - to convey the contribution of each risk factor. These are complemented by personalized textual narratives generated via integration with GPT-4o. The application was developed natively for Android using Kotlin and Jetpack Compose. The resulting prototype interprets SHAP (SHapley Additive exPlanations), a key XAI approach, into accessible graphical visualizations and narratives. Evaluation through user comprehension testing (Likert scale and interviews) and technical functionality testing confirmed the research objectives were met. The combination of visualization and textual narrative effectively enhanced user understanding (average score 4.31/5) and empowered preventive action, supported by a 100% technical testing success rate. --- ### Implementation of high-efficiency, lightweight residual spiking neural network processor based on field-programmable gate arrays Authors: Hou Yue, Xiang Shuiying, Zou Tao, Huang Zhiquan, Shi Shangxuan, Guo Xingxing, Zhang Yahui, Zheng Ling, Hao Yue Published: 2025-12-09 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.00802v1 With the development of hardware-optimized deployment of spiking neural networks (SNNs), SNN processors based on field-programmable gate arrays (FPGAs) have become a research hotspot due to their efficiency and flexibility. However, existing methods rely on multi-timestep training and reconfigurable computing architectures, which increases computational and memory overhead, thus reducing deployment efficiency. This work presents an efficient and lightweight residual SNN accelerator that combines algorithm and hardware co-design to optimize inference energy efficiency. In terms of the algorithm, we employ single-timesteps training, integrate grouped convolutions, and fuse batch normalization (BN) layers, thus compressing the network to only 0.69M parameters. Quantization-aware training (QAT) further constrains all parameters to 8-bit precision. In terms of hardware, the reuse of intra-layer resources maximizes FPGA utilization, a full pipeline cross-layer architecture improves throughput, and on-chip block RAM (BRAM) stores network parameters and intermediate results to improve memory efficiency. The experimental results show that the proposed processor achieves a classification accuracy of 87.11% on the CIFAR-10 dataset, with an inference time of 3.98 ms per image and an energy efficiency of 183.5 FPS/W. Compared with mainstream graphics processing unit (GPU) platforms, it achieves more than double the energy efficiency. Furthermore, compared with other SNN processors, it achieves at least a 4x faster inference speed and a 5x higher energy efficiency. --- ### HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate Authors: Shenzhe Zhu Published: 2025-12-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.23717v1 Large language models (LLMs) are equipped with safety mechanisms to detect and block harmful queries, yet current alignment approaches primarily focus on overtly dangerous content and overlook more subtle threats. However, users can often disguise harmful intent through covert rephrasing that preserves malicious objectives while appearing benign, which creates a significant gap in existing safety training data. To address this limitation, we introduce HarmTransform, a multi-agent debate framework for systematically transforming harmful queries into stealthier forms while preserving their underlying harmful intent. Our framework leverages iterative critique and refinement among multiple agents to generate high-quality, covert harmful query transformations that can be used to improve future LLM safety alignment. Experiments demonstrate that HarmTransform significantly outperforms standard baselines in producing effective query transformations. At the same time, our analysis reveals that debate acts as a double-edged sword: while it can sharpen transformations and improve stealth, it may also introduce topic shifts and unnecessary complexity. These insights highlight both the promise and the limitations of multi-agent debate for generating comprehensive safety training data. --- ### CytoDINO: Risk-Aware and Biologically-Informed Adaptation of DINOv3 for Bone Marrow Cytomorphology Authors: Aziz Muminov, Anne Pham Published: 2025-12-09 Categories: q-bio.OT, cs.CV, eess.IV, q-bio.QM arXiv: https://arxiv.org/abs/2512.17930v1 Bone marrow cell cytomorphology analysis is critical for the diagnosis of hematological malignancies but remains a labor-intensive process subject to significant inter-observer variability. While recent foundation models have shown promise in computational pathology, they often require extensive computational resources and fail to account for the asymmetric risks associated with clinical misdiagnosis. We introduce CytoDINO, a framework that achieves state-of-the-art performance on the Munich Leukemia Laboratory (MLL) dataset by fine-tuning DINOv3 using Low-Rank Adaptation (LoRA). Our primary contribution is a novel Hierarchical Focal Loss with Critical Penalties, which encodes biological relationships between cell lineages and explicitly penalizes clinically dangerous misclassifications (e.g., classifying blasts as normal cells). CytoDINO achieves an 88.2% weighted F1 score and 76.5% macro F1 on a held-out test set of 21 cell classes. By utilizing parameter-efficient fine-tuning with only 8% trainable parameters on a single NVIDIA RTX 5080, we demonstrate that consumer-grade hardware can match specialized infrastructure. Furthermore, confidence-based selective prediction yields 99.5% accuracy on 67% of samples, suggesting a viable pathway for clinical deployment where high-uncertainty cases are flagged for expert review --- ### Reinforcement Learning for Monetary Policy Under Macroeconomic Uncertainty: Analyzing Tabular and Function Approximation Methods Authors: Tony Wang, Kyle Feinstein, Sheryl Chen Published: 2025-12-09 Categories: q-fin.ST, cs.AI, cs.LG, econ.EM arXiv: https://arxiv.org/abs/2512.17929v2 We study how a central bank should dynamically set short-term nominal interest rates to stabilize inflation and unemployment when macroeconomic relationships are uncertain and time-varying. We model monetary policy as a sequential decision-making problem where the central bank observes macroeconomic conditions quarterly and chooses interest rate adjustments. Using publicly accessible historical Federal Reserve Economic Data (FRED), we construct a linear-Gaussian transition model and implement a discrete-action Markov Decision Process with a quadratic loss reward function. We chose to compare nine different reinforcement learning style approaches against Taylor Rule and naive baselines, including tabular Q-learning variants, SARSA, Actor-Critic, Deep Q-Networks, Bayesian Q-learning with uncertainty quantification, and POMDP formulations with partial observability. Notably, despite its simplicity, standard tabular Q-learning achieved the best performance (-615.13 +- 309.58 mean return), outperforming both enhanced RL methods and traditional policy rules. Our results suggest that while sophisticated RL techniques show promise for monetary policy applications, simpler approaches may be more robust in this domain, highlighting important challenges in applying modern RL to macroeconomic policy. --- ### Efficient Beamforming Optimization for STAR-RIS-Assisted Communications: A Gradient-Based Meta Learning Approach Authors: Dongdong Yang, Bin Li, Jiguang He, Yicheng Yan, Xiaoyu Zhang, Chongwen Huang Published: 2025-12-09 Categories: eess.SP, cs.AI, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2512.17928v1 Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) has emerged as a promising technology to realize full-space coverage and boost spectral efficiency in next-generation wireless networks. Yet, the joint design of the base station precoding matrix as well as the STAR-RIS transmission and reflection coefficient matrices leads to a high-dimensional, strongly nonconvex, and NP-hard optimization problem. Conventional alternating optimization (AO) schemes typically involve repeated large-scale matrix inversion operations, resulting in high computational complexity and poor scalability, while existing deep learning approaches often rely on expensive pre-training and large network models. In this paper, we develop a gradient-based meta learning (GML) framework that directly feeds optimization gradients into lightweight neural networks, thereby removing the need for pre-training and enabling fast adaptation. Specifically, we design dedicated GML-based schemes for both independent-phase and coupled-phase STAR-RIS models, effectively handling their respective amplitude and phase constraints while achieving weighted sum-rate performance very close to that of AO-based benchmarks. Extensive simulations demonstrate that, for both phase models, the proposed methods substantially reduce computational overhead, with complexity growing nearly linearly when the number of BS antennas and STAR-RIS elements grows, and yielding up to 10 times runtime speedup over AO, which confirms the scalability and practicality of the proposed GML method for large-scale STAR-RIS-assisted communications. --- ### A Critical Perspective on Finite Sample Conformal Prediction Theory in Medical Applications Authors: Klaus-Rudolf Kladny, Bernhard Schölkopf, Lisa Koch, Christian F. Baumgartner, Michael Muehlebach Published: 2025-12-09 Categories: cs.LG, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2512.14727v1 Machine learning (ML) is transforming healthcare, but safe clinical decisions demand reliable uncertainty estimates that standard ML models fail to provide. Conformal prediction (CP) is a popular tool that allows users to turn heuristic uncertainty estimates into uncertainty estimates with statistical guarantees. CP works by converting predictions of a ML model, together with a calibration sample, into prediction sets that are guaranteed to contain the true label with any desired probability. An often cited advantage is that CP theory holds for calibration samples of arbitrary size, suggesting that uncertainty estimates with practically meaningful statistical guarantees can be achieved even if only small calibration sets are available. We question this promise by showing that, although the statistical guarantees hold for calibration sets of arbitrary size, the practical utility of these guarantees does highly depend on the size of the calibration set. This observation is relevant in medical domains because data is often scarce and obtaining large calibration sets is therefore infeasible. We corroborate our critique in an empirical demonstration on a medical image classification task. --- ### Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning Authors: Abraham Itzhak Weinberg Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14726v1 Offline reinforcement learning enables policy learning from pre-collected datasets without environment interaction, but existing Decision Transformer (DT) architectures struggle with long-horizon credit assignment and complex state-action dependencies. We introduce the Quantum Decision Transformer (QDT), a novel architecture incorporating quantum-inspired computational mechanisms to address these challenges. Our approach integrates two core components: Quantum-Inspired Attention with entanglement operations that capture non-local feature correlations, and Quantum Feedforward Networks with multi-path processing and learnable interference for adaptive computation. Through comprehensive experiments on continuous control tasks, we demonstrate over 2,000\% performance improvement compared to standard DTs, with superior generalization across varying data qualities. Critically, our ablation studies reveal strong synergistic effects between quantum-inspired components: neither alone achieves competitive performance, yet their combination produces dramatic improvements far exceeding individual contributions. This synergy demonstrates that effective quantum-inspired architecture design requires holistic co-design of interdependent mechanisms rather than modular component adoption. Our analysis identifies three key computational advantages: enhanced credit assignment through non-local correlations, implicit ensemble behavior via parallel processing, and adaptive resource allocation through learnable interference. These findings establish quantum-inspired design principles as a promising direction for advancing transformer architectures in sequential decision-making, with implications extending beyond reinforcement learning to neural architecture design more broadly. --- ### Generative Urban Flow Modeling: From Geometry to Airflow with Graph Diffusion Authors: Francisco Giral, Álvaro Manzano, Ignacio Gómez, Petros Koumoutsakos, Soledad Le Clainche Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14725v1 Urban wind flow modeling and simulation play an important role in air quality assessment and sustainable city planning. A key challenge for modeling and simulation is handling the complex geometries of the urban landscape. Low order models are limited in capturing the effects of geometry, while high-fidelity Computational Fluid Dynamics (CFD) simulations are prohibitively expensive, especially across multiple geometries or wind conditions. Here, we propose a generative diffusion framework for synthesizing steady-state urban wind fields over unstructured meshes that requires only geometry information. The framework combines a hierarchical graph neural network with score-based diffusion modeling to generate accurate and diverse velocity fields without requiring temporal rollouts or dense measurements. Trained across multiple mesh slices and wind angles, the model generalizes to unseen geometries, recovers key flow structures such as wakes and recirculation zones, and offers uncertainty-aware predictions. Ablation studies confirm robustness to mesh variation and performance under different inference regimes. This work develops is the first step towards foundation models for the built environment that can help urban planners rapidly evaluate design decisions under densification and climate uncertainty. --- ### HATSolver: Learning Groebner Bases with Hierarchical Attention Transformers Authors: Mohamed Malhou, Ludovic Perret, Kristin Lauter Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14722v1 At NeurIPS 2024, Kera et al. introduced the use of transformers for computing Groebner bases, a central object in computer algebra with numerous practical applications. In this paper, we improve this approach by applying Hierarchical Attention Transformers (HATs) to solve systems of multivariate polynomial equations via Groebner bases computation. The HAT architecture incorporates a tree-structured inductive bias that enables the modeling of hierarchical relationships present in the data and thus achieves significant computational savings compared to conventional flat attention models. We generalize to arbitrary depths and include a detailed computational cost analysis. Combined with curriculum learning, our method solves instances that are much larger than those in Kera et al. (2024 Learning to compute Groebner bases) --- ### Automatic Extraction of Rules for Generating Synthetic Patient Data From Real-World Population Data Using Glioblastoma as an Example Authors: Arno Appenzeller, Nick Terzer, André Homeyer, Jan-Philipp Redlich, Sabine Luttmann, Friedrich Feuerhake, Nadine S. Schaadt, Timm Intemann, Sarah Teuber-Hanselmann, Stefan Nikolin, Joachim Weis, Klaus Kraywinkel et al. Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14721v2 The generation of synthetic data is a promising technology to make medical data available for secondary use in a privacy-compliant manner. A popular method for creating realistic patient data is the rule-based Synthea data generator. Synthea generates data based on rules describing the lifetime of a synthetic patient. These rules typically express the probability of a condition occurring, such as a disease, depending on factors like age. Since they only contain statistical information, rules usually have no specific data protection requirements. However, creating meaningful rules can be a very complex process that requires expert knowledge and realistic sample data. In this paper, we introduce and evaluate an approach to automatically generate Synthea rules based on statistics from tabular data, which we extracted from cancer reports. As an example use case, we created a Synthea module for glioblastoma from a real-world dataset and used it to generate a synthetic dataset. Compared to the original dataset, the synthetic data reproduced known disease courses and mostly retained the statistical properties. Overall, synthetic patient data holds great potential for privacy-preserving research. The data can be used to formulate hypotheses and to develop prototypes, but medical interpretation should consider the specific limitations as with any currently available approach. --- ### SoMe: A Realistic Benchmark for LLM-based Social Media Agents Authors: Dizhan Xue, Jing Cui, Shengsheng Qian, Chuanrui Hu, Changsheng Xu Published: 2025-12-09 Categories: cs.SI, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.14720v1 Intelligent agents powered by large language models (LLMs) have recently demonstrated impressive capabilities and gained increasing popularity on social media platforms. While LLM agents are reshaping the ecology of social media, there exists a current gap in conducting a comprehensive evaluation of their ability to comprehend media content, understand user behaviors, and make intricate decisions. To address this challenge, we introduce SoMe, a pioneering benchmark designed to evaluate social media agents equipped with various agent tools for accessing and analyzing social media data. SoMe comprises a diverse collection of 8 social media agent tasks, 9,164,284 posts, 6,591 user profiles, and 25,686 reports from various social media platforms and external websites, with 17,869 meticulously annotated task queries. Compared with the existing datasets and benchmarks for social media tasks, SoMe is the first to provide a versatile and realistic platform for LLM-based social media agents to handle diverse social media tasks. By extensive quantitative and qualitative analysis, we provide the first overview insight into the performance of mainstream agentic LLMs in realistic social media environments and identify several limitations. Our evaluation reveals that both the current closed-source and open-source LLMs cannot handle social media agent tasks satisfactorily. SoMe provides a challenging yet meaningful testbed for future social media agents. Our code and data are available at https://github.com/LivXue/SoMe --- ### Hybrid Attribution Priors for Explainable and Robust Model Training Authors: Zhuoran Zhang, Feng Zhang, Shangyuan Li, Yang Shi, Yuanxing Zhang, Wei Chen, Tengjiao Wang, Kam-Fai Wong Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14719v1 Small language models (SLMs) are widely used in tasks that require low latency and lightweight deployment, particularly classification. As interpretability and robustness gain increasing importance, explanation-guided learning has emerged as an effective framework by introducing attribution-based supervision during training; however, deriving general and reliable attribution priors remains a significant challenge. Through an analysis of representative attribution methods in classification settings, we find that although these methods can reliably highlight class-relevant tokens, they often focus on common keywords shared by semantically similar classes. Because such classes are already difficult to distinguish under standard training, these attributions provide insufficient discriminative cues, limiting their ability to improve model differentiation. To overcome this limitation, we propose Class-Aware Attribution Prior (CAP), a novel attribution prior extraction framework that guides language models toward capturing fine-grained class distinctions and producing more salient, discriminative attribution priors. Building on this idea, we further introduce CAP Hybrid, which combines priors from CAP with those from existing attribution techniques to form a more comprehensive and balanced supervisory signal. By aligning a model's self-attribution with these enriched priors, our approach encourages the learning of diverse, decision-relevant features. Extensive experiments in full-data, few-shot, and adversarial scenarios demonstrate that our method consistently enhances both interpretability and robustness. --- ### SEED: Spectral Entropy-Guided Evaluation of SpatialTemporal Dependencies for Multivariate Time Series Forecasting Authors: Feng Xiong, Zongxia Xie, Yanru Sun, Haoyu Wang, Jianhong Lin Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14718v2 Effective multivariate time series forecasting often benefits from accurately modeling complex inter-variable dependencies. However, existing attention- or graph-based methods face three key issues: (a) strong temporal self-dependencies are often disrupted by irrelevant variables; (b) softmax normalization ignores and reverses negative correlations; (c) variables struggle to perceive their temporal positions. To address these, we propose \textbf{SEED}, a Spectral Entropy-guided Evaluation framework for spatial-temporal Dependency modeling. SEED introduces a Dependency Evaluator, a key innovation that leverages spectral entropy to dynamically provide a preliminary evaluation of the spatial and temporal dependencies of each variable, enabling the model to adaptively balance Channel Independence (CI) and Channel Dependence (CD) strategies. To account for temporal regularities originating from the influence of other variables rather than intrinsic dynamics, we propose Spectral Entropy-based Fuser to further refine the evaluated dependency weights, effectively separating this part. Moreover, to preserve negative correlations, we introduce a Signed Graph Constructor that enables signed edge weights, overcoming the limitations of softmax. Finally, to help variables perceive their temporal positions and thereby construct more comprehensive spatial features, we introduce the Context Spatial Extractor, which leverages local contextual windows to extract spatial features. Extensive experiments on 12 real-world datasets from various application domains demonstrate that SEED achieves state-of-the-art performance, validating its effectiveness and generality. --- ### Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox Authors: Ziqian Bi, Danyang Zhang, Junhao Song, Chiung-Yi Tseng Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14717v1 The rapid adoption of large language models in financial services necessitates rigorous evaluation frameworks to assess their performance, efficiency, and practical applicability. This paper conducts a comprehensive evaluation of the GPT-OSS model family alongside contemporary LLMs across ten diverse financial NLP tasks. Through extensive experimentation on 120B and 20B parameter variants of GPT-OSS, we reveal a counterintuitive finding: the smaller GPT-OSS-20B model achieves comparable accuracy (65.1% vs 66.5%) while demonstrating superior computational efficiency with 198.4 Token Efficiency Score and 159.80 tokens per second processing speed (1). Our evaluation encompasses sentiment analysis, question answering, and entity recognition tasks using real-world financial datasets including Financial PhraseBank, FiQA-SA, and FLARE FINERORD. We introduce novel efficiency metrics that capture the trade-off between model performance and resource utilization, providing critical insights for deployment decisions in production environments. The benchmark reveals that GPT-OSS models consistently outperform larger competitors including Qwen3-235B, challenging the prevailing assumption that model scale directly correlates with task performance (2). Our findings demonstrate that architectural innovations and training strategies in GPT-OSS enable smaller models to achieve competitive performance with significantly reduced computational overhead, offering a pathway toward sustainable and cost-effective deployment of LLMs in financial applications. --- ### How a Bit Becomes a Story: Semantic Steering via Differentiable Fault Injection Authors: Zafaryab Haider, Md Hafizur Rahman, Shane Moeykens, Vijay Devabhaktuni, Prabuddha Chakraborty Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14715v1 Hard-to-detect hardware bit flips, from either malicious circuitry or bugs, have already been shown to make transformers vulnerable in non-generative tasks. This work, for the first time, investigates how low-level, bitwise perturbations (fault injection) to the weights of a large language model (LLM) used for image captioning can influence the semantic meaning of its generated descriptions while preserving grammatical structure. While prior fault analysis methods have shown that flipping a few bits can crash classifiers or degrade accuracy, these approaches overlook the semantic and linguistic dimensions of generative systems. In image captioning models, a single flipped bit might subtly alter how visual features map to words, shifting the entire narrative an AI tells about the world. We hypothesize that such semantic drifts are not random but differentiably estimable. That is, the model's own gradients can predict which bits, if perturbed, will most strongly influence meaning while leaving syntax and fluency intact. We design a differentiable fault analysis framework, BLADE (Bit-level Fault Analysis via Differentiable Estimation), that uses gradient-based sensitivity estimation to locate semantically critical bits and then refines their selection through a caption-level semantic-fluency objective. Our goal is not merely to corrupt captions, but to understand how meaning itself is encoded, distributed, and alterable at the bit level, revealing that even imperceptible low-level changes can steer the high-level semantics of generative vision-language models. It also opens pathways for robustness testing, adversarial defense, and explainable AI, by exposing how structured bit-level faults can reshape a model's semantic output. --- ### Improving Underwater Acoustic Classification Through Learnable Gabor Filter Convolution and Attention Mechanisms Authors: Lucas Cesar Ferreira Domingos, Russell Brinkworth, Paulo Eduardo Santos, Karl Sammut Published: 2025-12-09 Categories: cs.LG, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2512.14714v2 Remotely detecting and classifying underwater acoustic targets is critical for environmental monitoring and defence. However, the complexity of ship-radiated and environmental noise poses significant challenges for accurate signal processing. While recent advancements in machine learning have improved classification accuracy, limited dataset availability and a lack of standardised experimentation hinder generalisation and robustness. This paper introduces GSE ResNeXt, a deep learning architecture integrating learnable Gabor convolutional layers with a ResNeXt backbone enhanced by squeeze-and-excitation attention. The Gabor filters serve as two-dimensional adaptive band-pass filters, extending the feature channel representation. Its combination with channel attention improves training stability and convergence while enhancing the model's ability to extract discriminative features. The model is evaluated using three training-test split strategies that reflect increasingly complex classification tasks, demonstrating how systematic evaluation design addresses issues such as data leakage, temporal separation, and taxonomy. Results show that GSE ResNeXt consistently outperforms baseline models like Xception, ResNet, and MobileNetV2, in terms of classification performance. Regarding stability and convergence, adding Gabor convolutions to the initial layers of the model reduced training time by up to 62%. During the evaluation of training-testing splits, temporal separation between subsets significantly affected performance, proving more influential than training data volume. These findings suggest that signal processing can enhance model reliability and generalisation under varying environmental conditions, particularly in data-limited underwater acoustic classification. Future developments should focus on mitigating environmental effects on input signals. --- ### Federated Few-Shot Learning for Epileptic Seizure Detection Under Privacy Constraints Authors: Ekaterina Sysoykova, Bernhard Anzengruber-Tanase, Michael Haslgrubler, Philipp Seidl, Alois Ferscha Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.13717v1 Many deep learning approaches have been developed for EEG-based seizure detection; however, most rely on access to large centralized annotated datasets. In clinical practice, EEG data are often scarce, patient-specific distributed across institutions, and governed by strict privacy regulations that prohibit data pooling. As a result, creating usable AI-based seizure detection models remains challenging in real-world medical settings. To address these constraints, we propose a two-stage federated few-shot learning (FFSL) framework for personalized EEG-based seizure detection. The method is trained and evaluated on the TUH Event Corpus, which includes six EEG event classes. In Stage 1, a pretrained biosignal transformer (BIOT) is fine-tuned across non-IID simulated hospital sites using federated learning, enabling shared representation learning without centralizing EEG recordings. In Stage 2, federated few-shot personalization adapts the classifier to each patient using only five labeled EEG segments, retaining seizure-specific information while still benefiting from cross-site knowledge. Federated fine-tuning achieved a balanced accuracy of 0.43 (centralized: 0.52), Cohen's kappa of 0.42 (0.49), and weighted F1 of 0.69 (0.74). In the FFSL stage, client-specific models reached an average balanced accuracy of 0.77, Cohen's kappa of 0.62, and weighted F1 of 0.73 across four sites with heterogeneous event distributions. These results suggest that FFSL can support effective patient-adaptive seizure detection under realistic data-availability and privacy constraints. --- ### ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making Authors: Yitong Luo, Ziang Chen, Hou Hei Lam, Jiayu zhan, Junqi Wang, Zhenliang Zhang, Xue Feng Published: 2025-12-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.13716v1 Personalized decision-making is essential for human-AI interaction, enabling AI agents to act in alignment with individual users' value preferences. As AI systems expand into real-world applications, adapting to personalized values beyond task completion or collective alignment has become a critical challenge. We address this by proposing a value-driven approach to personalized decision-making. Human values serve as stable, transferable signals that support consistent and generalizable behavior across contexts. Compared to task-oriented paradigms driven by external rewards and incentives, value-driven decision-making enhances interpretability and enables agents to act appropriately even in novel scenarios. We introduce ValuePilot, a two-phase framework consisting of a dataset generation toolkit (DGT) and a decision-making module (DMM). DGT constructs diverse, value-annotated scenarios from a human-LLM collaborative pipeline. DMM learns to evaluate actions based on personal value preferences, enabling context-sensitive, individualized decisions. When evaluated on previously unseen scenarios, DMM outperforms strong LLM baselines, including GPT-5, Claude-Sonnet-4, Gemini-2-flash, and Llama-3.1-70b, in aligning with human action choices. Our results demonstrate that value-driven decision-making is an effective and extensible engineering pathway toward building interpretable, personalized AI agents. --- ### Beyond Automation: Rethinking Work, Creativity, and Governance in the Age of Generative AI Authors: Haocheng Lin Published: 2025-12-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.11893v2 The rapid expansion of generative artificial intelligence (AI) is transforming work, creativity, and economic security in ways that extend beyond automation and productivity. This paper examines four interconnected dimensions of contemporary AI deployment: (1) transformations in employment and task composition (2) unequal diffusion of AI across sectors and socio-demographic groups (3) the role of universal basic income (UBI) as a stabilising response to AI-induced volatility (4) the effects of model alignment and content governance on human creativity, autonomy, and decision-making Using a hybrid approach that integrates labour market task exposure modelling, sectoral diffusion analysis, policy review, and qualitative discourse critique, the study develops an Inclusive AI Governance Framework. It introduces Level 1.5 autonomy as a human centred design principle that preserves evaluative authority while enabling partial automation, and highlights evidence of creative regression and emergent sycophancy in newer model generations. The paper argues that UBI should be embedded within a broader socio-technical governance ecosystem encompassing skills development, proportional regulation, and creativity preservation. --- ### Should AI Become an Intergenerational Civil Right? Authors: Jon Crowcroft, Rute C. Sofia, Dirk Trossen, Vassilis Tsaoussidis Published: 2025-12-09 Categories: cs.CY, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2512.11892v1 Artificial Intelligence (AI) is rapidly becoming a foundational layer of social, economic, and cognitive infrastructure. At the same time, the training and large-scale deployment of AI systems rely on finite and unevenly distributed energy, networking, and computational resources. This tension exposes a largely unexamined problem in current AI governance: while expanding access to AI is essential for social inclusion and equal opportunity, unconstrained growth in AI use risks unsustainable resource consumption, whereas restricting access threatens to entrench inequality and undermine basic rights. This paper argues that access to AI outputs largely derived from publicly produced knowledge should not be treated solely as a commercial service, but as a fundamental civil interest requiring explicit protection. We show that existing regulatory frameworks largely ignore the coupling between equitable access and resource constraints, leaving critical questions of fairness, sustainability, and long-term societal impact unresolved. To address this gap, we propose recognizing access to AI as an \emph{Intergenerational Civil Right}, establishing a legal and ethical framework that simultaneously safeguards present-day inclusion and the rights of future generations. Beyond normative analysis, we explore how this principle can be technically realized. Drawing on emerging paradigms in IoT--Edge--Cloud computing, decentralized inference, and energy-aware networking, we outline technological trajectories and a strawman architecture for AI Delivery Networks that support equitable access under strict resource constraints. By framing AI as a shared social infrastructure rather than a discretionary market commodity, this work connects governance principles with concrete system design choices, offering a pathway toward AI deployment that is both socially just and environmentally sustainable. --- ### Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directions Authors: Yihan Liao, Jingyu Zhang, Jacky Keung, Yan Xiao, Yurou Dai Published: 2025-12-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.11887v1 Autonomous driving systems (ADSs) promise improved transportation efficiency and safety, yet ensuring their reliability in complex real-world environments remains a critical challenge. Effective testing is essential to validate ADS performance and reduce deployment risks. This study investigates current ADS testing practices for both modular and end-to-end systems, identifies key demands from industry practitioners and academic researchers, and analyzes the gaps between existing research and real-world requirements. We review major testing techniques and further consider emerging factors such as Vehicle-to-Everything (V2X) communication and foundation models, including large language models and vision foundation models, to understand their roles in enhancing ADS testing. We conducted a large-scale survey with 100 participants from both industry and academia. Survey questions were refined through expert discussions, followed by quantitative and qualitative analyses to reveal key trends, challenges, and unmet needs. Our results show that existing ADS testing techniques struggle to comprehensively evaluate real-world performance, particularly regarding corner case diversity, the simulation to reality gap, the lack of systematic testing criteria, exposure to potential attacks, practical challenges in V2X deployment, and the high computational cost of foundation model-based testing. By further analyzing participant responses together with 105 representative studies, we summarize the current research landscape and highlight major limitations. This study consolidates critical research gaps in ADS testing and outlines key future research directions, including comprehensive testing criteria, cross-model collaboration in V2X systems, cross-modality adaptation for foundation model-based testing, and scalable validation frameworks for large-scale ADS evaluation. --- ### Generalization vs. Specialization: Evaluating Segment Anything Model (SAM3) Zero-Shot Segmentation Against Fine-Tuned YOLO Detectors Authors: Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee, Nikolaos D. Tselikas Published: 2025-12-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11884v1 Deep learning has advanced two fundamentally different paradigms for instance segmentation: specialized models optimized through task-specific fine-tuning and generalist foundation models capable of zero-shot segmentation. This work presents a comprehensive comparison between SAM3 (Segment Anything Model, also called SAMv3) operating in zero-shot mode and three variants of Ultralytics YOLO11 (nano, medium, and large) fine-tuned for instance segmentation. The evaluation is conducted on the MinneApple dataset, a dense benchmark comprising 670 orchard images with 28,179 annotated apple instances, enabling rigorous validation of model behavior under high object density and occlusion. Our analysis shows IoU choices can inflate performance gaps by up to 30%. At the appropriate IoU = 0.15 threshold, YOLO models achieve 68.9%, 72.2%, and 71.9% F1, while SAM3 reaches 59.8% in pure zero-shot mode. However, YOLO exhibits steep degradation 48-50 points across IoU ranges whereas SAM3 drops only 4 points, revealing 12 times superior boundary stability of SAM3. This highlights the strength of SAMv3 in mask precision versus specialization in detection completeness of YOLO11. We provide open-source code, evaluation pipelines, and methodological recommendations, contributing to a deeper understanding of when specialized fine-tuned models or generalist foundation models are preferable for dense instance segmentation tasks. This project repository is available on GitHub as https://github.com/Applied-AI-Research-Lab/Segment-Anything-Model-SAM3-Zero-Shot-Segmentation-Against-Fine-Tuned-YOLO-Detectors --- ### Position: Universal Aesthetic Alignment Narrows Artistic Expression Authors: Wenqi Marshall Guo, Qingyun Qian, Khalad Hasan, Shan Du Published: 2025-12-09 Categories: cs.CY, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.11883v3 Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when "anti-aesthetic" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias by constructing a wide-spectrum aesthetics dataset and evaluating state-of-the-art generation and reward models. This position paper finds that aesthetic-aligned generation models frequently default to conventionally beautiful outputs, failing to respect instructions for low-quality or negative imagery. Crucially, reward models penalize anti-aesthetic images even when they perfectly match the explicit user prompt. We confirm this systemic bias through image-to-image editing and evaluation against real abstract artworks. Our code, fine-tuned models, and datasets are available on our meta-expression intentionally anti-aesthetics webpage: https://weathon.github.io/icml2026_position/. --- ### MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax Authors: Zhanpeng Chen, Weihao Gao, Shunyu Wang, Yanan Zhu, Hong Meng, Yuexian Zou Published: 2025-12-09 Categories: cs.LG, cs.AI, physics.chem-ph, q-bio.QM arXiv: https://arxiv.org/abs/2512.10991v1 Generating precise 3D molecular geometries is crucial for drug discovery and material science. While prior efforts leverage 1D representations like SELFIES to ensure molecular validity, they fail to fully exploit the rich chemical knowledge entangled within 1D models, leading to a disconnect between 1D syntactic generation and 3D geometric realization. To bridge this gap, we propose MolSculpt, a novel framework that "sculpts" 3D molecular geometries from chemical syntax. MolSculpt is built upon a frozen 1D molecular foundation model and a 3D molecular diffusion model. We introduce a set of learnable queries to extract inherent chemical knowledge from the foundation model, and a trainable projector then injects this cross-modal information into the conditioning space of the diffusion model to guide the 3D geometry generation. In this way, our model deeply integrates 1D latent chemical knowledge into the 3D generation process through end-to-end optimization. Experiments demonstrate that MolSculpt achieves state-of-the-art (SOTA) performance in \textit{de novo} 3D molecule generation and conditional 3D molecule generation, showing superior 3D fidelity and stability on both the GEOM-DRUGS and QM9 datasets. Code is available at https://github.com/SakuraTroyChen/MolSculpt. --- ### Dora: QoE-Aware Hybrid Parallelism for Distributed Edge AI Authors: Jianli Jin, Ziyang Lin, Qianli Dong, Yi Chen, Jayanth Srinivasa, Myungjin Lee, Zhaowei Tan, Fan Lai Published: 2025-12-09 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2512.10990v1 With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first class objective, as these models operate in resource constrained settings and directly interact with users. Yet, modern AI models routinely exceed the resource capacity of individual devices, necessitating distributed execution across heterogeneous devices over variable and contention prone networks. Existing planners for hybrid (e.g., data and pipeline) parallelism largely optimize for throughput or device utilization, overlooking QoE, leading to severe resource inefficiency (e.g., unnecessary energy drain) or QoE violations under runtime dynamics. We present Dora, a framework for QoE aware hybrid parallelism in distributed edge AI training and inference. Dora jointly optimizes heterogeneous computation, contention prone networks, and multi dimensional QoE objectives via three key mechanisms: (i) a heterogeneity aware model partitioner that determines and assigns model partitions across devices, forming a compact set of QoE compliant plans; (ii) a contention aware network scheduler that further refines these candidate plans by maximizing compute communication overlap; and (iii) a runtime adapter that adaptively composes multiple plans to maximize global efficiency while respecting overall QoEs. Across representative edge deployments, including smart homes, traffic analytics, and small edge clusters, Dora achieves 1.1--6.3 times faster execution and, alternatively, reduces energy consumption by 21--82 percent, all while maintaining QoE under runtime dynamics. --- ### ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs Authors: Mohammad M Maheri, Sunil Cotterill, Alex Davidson, Hamed Haddadi Published: 2025-12-09 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.09953v2 Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety requirements. In real deployments, providers distribute a global model to many edge devices, where each client personalizes the model using private data. When a deletion request is issued, clients may ignore it or falsely claim compliance, and providers cannot check their parameters or data. This makes verification difficult, especially because personalized models must forget the targeted samples while preserving local utility, and verification must remain lightweight on edge devices. We introduce ZK APEX, a zero-shot personalized unlearning method that operates directly on the personalized model without retraining. ZK APEX combines sparse masking on the provider side with a small Group OBS compensation step on the client side, using a blockwise empirical Fisher matrix to create a curvature-aware update designed for low overhead. Paired with Halo2 zero-knowledge proofs, it enables the provider to verify that the correct unlearning transformation was applied without revealing any private data or personalized parameters. On Vision Transformer classification tasks, ZK APEX recovers nearly all personalization accuracy while effectively removing the targeted information. Applied to the OPT125M generative model trained on code data, it recovers around seventy percent of the original accuracy. Proof generation for the ViT case completes in about two hours, more than ten million times faster than retraining-based checks, with less than one gigabyte of memory use and proof sizes around four hundred megabytes. These results show the first practical framework for verifiable personalized unlearning on edge devices. --- ### Residual Primitive Fitting of 3D Shapes with SuperFrusta Authors: Aditya Ganeshan, Matheus Gadelha, Thibault Groueix, Zhiqin Chen, Siddhartha Chaudhuri, Vladimir G. Kim, Wang Yifan, Daniel Ritchie Published: 2025-12-09 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2512.09201v2 We introduce a framework for converting 3D shapes into compact and editable assemblies of analytic primitives, directly addressing the persistent trade-off between reconstruction fidelity and parsimony. Our approach combines two key contributions: a novel primitive, termed SuperFrustum, and an iterative fiting algorithm, Residual Primitive Fitting (ResFit). SuperFrustum is an analytical primitive that is simultaneously (1) expressive, being able to model various common solids such as cylinders, spheres, cones & their tapered and bent forms, (2) editable, being compactly parameterized with 8 parameters, and (3) optimizable, with a sign distance field differentiable w.r.t. its parameters almost everywhere. ResFit is an unsupervised procedure that interleaves global shape analysis with local optimization, iteratively fitting primitives to the unexplained residual of a shape to discover a parsimonious yet accurate decompositions for each input shape. On diverse 3D benchmarks, our method achieves state-of-the-art results, improving IoU by over 9 points while using nearly half as many primitives as prior work. The resulting assemblies bridge the gap between dense 3D data and human-controllable design, producing high-fidelity and editable shape programs. --- ### LLMs for Analog Circuit Design Continuum (ACDC) Authors: Yasaman Esfandiari, Jocelyn Rego, Austin Meyer, Jonathan Gallagher, Mia Levy Published: 2025-12-09 Categories: cs.LG, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2512.09199v1 Large Language Models (LLMs) and transformer architectures have shown impressive reasoning and generation capabilities across diverse natural language tasks. However, their reliability and robustness in real-world engineering domains remain largely unexplored, limiting their practical utility in human-centric workflows. In this work, we investigate the applicability and consistency of LLMs for analog circuit design -- a task requiring domain-specific reasoning, adherence to physical constraints, and structured representations -- focusing on AI-assisted design where humans remain in the loop. We study how different data representations influence model behavior and compare smaller models (e.g., T5, GPT-2) with larger foundation models (e.g., Mistral-7B, GPT-oss-20B) under varying training conditions. Our results highlight key reliability challenges, including sensitivity to data format, instability in generated designs, and limited generalization to unseen circuit configurations. These findings provide early evidence on the limits and potential of LLMs as tools to enhance human capabilities in complex engineering tasks, offering insights into designing reliable, deployable foundation models for structured, real-world applications. --- ### Towards Optimal Valve Prescription for Transcatheter Aortic Valve Replacement (TAVR) Surgery: A Machine Learning Approach Authors: Phevos Paschalidis, Vasiliki Stoumpou, Lisa Everest, Yu Ma, Talhat Azemi, Jawad Haider, Steven Zweibel, Eleftherios M. Protopapas, Jeff Mather, Maciej Tysarowski, George E. Sarris, Robert C. Hagberg et al. Published: 2025-12-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.09198v2 Transcatheter Aortic Valve Replacement (TAVR) has emerged as a prominent, minimally invasive treatment for patients with severe aortic stenosis, a life-threatening cardiovascular condition. Multiple transcatheter heart valves (THV) have been approved for use in TAVR, but current guidelines regarding valve type prescription remain a topic of ongoing debate within the medical community. We propose a data-driven clinical support tool to identify the optimal valve type with the objective of minimizing the risk of permanent pacemaker implantation (PPI), a predominant postoperative complication. We synthesize a novel dataset, combining U.S. and Greek patient populations, that integrates data from three distinct sources (patient demographics, computed tomography scans, echocardiograms) while harmonizing the different encoding processes specific to each country's record system. We propose leaf-level analysis to leverage the heterogeneity of the patient populations and avoid benchmarking against uncertain counterfactual risk estimates. The final prescriptive model shows a reduction in PPI rates of 26% and 16% compared to the current standard of care in our internal U.S. population and external, Greek validation set, respectively. To the best of our knowledge, this work represents the first unified, personalized prescription strategy for THV selection in TAVR. --- ### Understanding Mental States in Active and Autonomous Driving with EEG Authors: Prithila Angkan, Paul Hungler, Ali Etemad Published: 2025-12-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.09190v1 Understanding how driver mental states differ between active and autonomous driving is critical for designing safe human-vehicle interfaces. This paper presents the first EEG-based comparison of cognitive load, fatigue, valence, and arousal across the two driving modes. Using data from 31 participants performing identical tasks in both scenarios of three different complexity levels, we analyze temporal patterns, task-complexity effects, and channel-wise activation differences. Our findings show that although both modes evoke similar trends across complexity levels, the intensity of mental states and the underlying neural activation differ substantially, indicating a clear distribution shift between active and autonomous driving. Transfer-learning experiments confirm that models trained on active driving data generalize poorly to autonomous driving and vice versa. We attribute this distribution shift primarily to differences in motor engagement and attentional demands between the two driving modes, which lead to distinct spatial and temporal EEG activation patterns. Although autonomous driving results in lower overall cortical activation, participants continue to exhibit measurable fluctuations in cognitive load, fatigue, valence, and arousal associated with readiness to intervene, task-evoked emotional responses, and monotony-related passive fatigue. These results emphasize the need for scenario-specific data and models when developing next-generation driver monitoring systems for autonomous vehicles. --- ### WOLF: Werewolf-based Observations for LLM Deception and Falsehoods Authors: Mrinal Agarwal, Saad Rana, Theo Sundoro, Hermela Berhe, Spencer Kim, Vasu Sharma, Sean O'Brien, Kevin Zhu Published: 2025-12-09 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2512.09187v1 Deception is a fundamental challenge for multi-agent reasoning: effective systems must strategically conceal information while detecting misleading behavior in others. Yet most evaluations reduce deception to static classification, ignoring the interactive, adversarial, and longitudinal nature of real deceptive dynamics. Large language models (LLMs) can deceive convincingly but remain weak at detecting deception in peers. We present WOLF, a multi-agent social deduction benchmark based on Werewolf that enables separable measurement of deception production and detection. WOLF embeds role-grounded agents (Villager, Werewolf, Seer, Doctor) in a programmable LangGraph state machine with strict night-day cycles, debate turns, and majority voting. Every statement is a distinct analysis unit, with self-assessed honesty from speakers and peer-rated deceptiveness from others. Deception is categorized via a standardized taxonomy (omission, distortion, fabrication, misdirection), while suspicion scores are longitudinally smoothed to capture both immediate judgments and evolving trust dynamics. Structured logs preserve prompts, outputs, and state transitions for full reproducibility. Across 7,320 statements and 100 runs, Werewolves produce deceptive statements in 31% of turns, while peer detection achieves 71-73% precision with ~52% overall accuracy. Precision is higher for identifying Werewolves, though false positives occur against Villagers. Suspicion toward Werewolves rises from ~52% to over 60% across rounds, while suspicion toward Villagers and the Doctor stabilizes near 44-46%. This divergence shows that extended interaction improves recall against liars without compounding errors against truthful roles. WOLF moves deception evaluation beyond static datasets, offering a dynamic, controlled testbed for measuring deceptive and detective capacity in adversarial multi-agent interaction. --- ### Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation Authors: Hao Chen, Rui Yin, Yifan Chen, Qi Chen, Chao Li Published: 2025-12-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.09185v4 Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment. While recent generative approaches have attempted to model progression, key mismatches remain: disease dynamics are inherently continuous and monotonic, yet latent representations are often scattered, lacking semantic structure, and diffusion-based models disrupt continuity with random denoising process. In this work, we propose to treat the disease dynamic as a velocity field and leverage Flow Matching (FM) to align the temporal evolution of patient data. Unlike prior methods, it captures the intrinsic dynamic of disease, making the progression more interpretable. However, a key challenge remains: in latent space, Auto-Encoders (AEs) do not guarantee alignment across patients or correlation with clinical-severity indicators (e.g., age and disease conditions). To address this, we propose to learn patient-specific latent alignment, which enforces patient trajectories to lie along a specific axis, with magnitude increasing monotonically with disease severity. This leads to a consistent and semantically meaningful latent space. Together, we present $Δ$-LFM, a framework for modeling patient-specific latent progression with flow matching. Across three longitudinal MRI benchmarks, $Δ$-LFM demonstrates strong empirical performance and, more importantly, offers a new framework for interpreting and visualizing disease dynamics. --- ### Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks Authors: Hunjae Lee Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09182v1 Transformers and more specifically decoder-only transformers dominate modern LLM architectures. While they have shown to work exceptionally well, they are not without issues, resulting in surprising failure modes and predictably asymmetric performance degradation. This article is a study of many of these observed failure modes of transformers through the lens of graph neural network (GNN) theory. We first make the case that much of deep learning, including transformers, is about learnable information mixing and propagation. This makes the study of model failure modes a study of bottlenecks in information propagation. This naturally leads to GNN theory, where there is already a rich literature on information propagation bottlenecks and theoretical failure modes of models. We then make the case that many issues faced by GNNs are also experienced by transformers. In addition, we analyze how the causal nature of decoder-only transformers create interesting geometric properties in information propagation, resulting in predictable and potentially devastating failure modes. Finally, we observe that existing solutions in transformer research tend to be ad-hoc and driven by intuition rather than grounded theoretical motivation. As such, we unify many such solutions under a more theoretical perspective, providing insight into why they work, what problem they are actually solving, and how they can be further improved to target specific failure modes of transformers. Overall, this article is an attempt to bridge the gap between observed failure modes in transformers and a general lack of theoretical understanding of them in this space. --- ### Prompt-Based Continual Compositional Zero-Shot Learning Authors: Sauda Maryam, Sara Nadeem, Faisal Qureshi, Mohsen Ali Published: 2025-12-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.09172v3 We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while preventing forgetting of prior knowledge. Unlike classical continual learning where classes are disjoint, CCZSL is more complex as attributes and objects may reoccur across sessions while compositions remain unique. Built on a frozen VLM backbone, we propose the first Prompt-based Continual Compositional Zero-Shot Learning (PromptCCZSL) framework that retains prior knowledge through recency-weighted multi-teacher distillation. It employs session-aware compositional prompts to fuse multimodal features for new compositions, while attribute and object prompts are learned through session-agnostic fusion to maintain global semantic consistency, which is further stabilized by a Cosine Anchor Loss (CAL) to preserve prior knowledge. To enhance adaptation in the current session, an Orthogonal Projection Loss (OPL) ensures that new attribute and object embeddings remain distinct from previous ones, preventing overlap, while an Intra-Session Diversity Loss (IDL) promotes variation among current-session embeddings for richer, more discriminative representations. We also introduce a comprehensive protocol that jointly measures catastrophic forgetting and compositional generalization. Extensive experiments on UT-Zappos and C-GQA benchmarks demonstrate that PromptCCZSL achieves substantial improvements over prior VLM-based and non-VLM baselines, setting a new benchmark for CCZSL in closed-world settings. --- ### AI-Driven Expansion and Application of the Alexandria Database Authors: Théo Cavignac, Jonathan Schmidt, Pierre-Paul De Breuck, Antoine Loew, Tiago F. T. Cerqueira, Hai-Chen Wang, Anton Bochkarev, Yury Lysogorskiy, Aldo H. Romero, Ralf Drautz, Silvana Botti, Miguel A. L. Marques Published: 2025-12-09 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2512.09169v2 We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches. By combining the Matra-Genoa generative model, Orb-v2 universal machine learning interatomic potential, and ALIGNN graph neural network for energy prediction, we generated 119 million candidate structures and added 1.3 million DFT-validated compounds to the ALEXANDRIA database, including 74 thousand new stable materials. The expanded ALEXANDRIA database now contains 5.8 million structures with 175 thousand compounds on the convex hull. Predicted structural disorder rates (37-43%) match experimental databases, unlike other recent AI-generated datasets. Analysis reveals fundamental patterns in space group distributions, coordination environments, and phase stability networks, including sub-linear scaling of convex hull connectivity. We release the complete dataset, including sAlex25 with 14 million out-of-equilibrium structures containing forces and stresses for training universal force fields. We demonstrate that fine-tuning a GRACE model on this data improves benchmark accuracy. All data, models, and workflows are freely available under Creative Commons licenses. --- ### Spectral Embedding via Chebyshev Bases for Robust DeepONet Approximation Authors: Muhammad Abid, Omer San Published: 2025-12-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.09165v3 Deep Operator Networks (DeepONets) have emerged as a powerful framework for data-driven operator learning, providing flexible surrogates for nonlinear mappings arising in partial differential equations (PDEs). However, the standard trunk network, which operates directly on raw spatial or spatiotemporal coordinates through fully connected layers, often struggles to represent sharp gradients, boundary layers, and other non-periodic solution structures on bounded domains. To address these limitations, we introduce the Spectral-Embedded Deep Operator Network (SEDONet), a novel DeepONet architecture in which the trunk is driven by a fixed Chebyshev spectral dictionary instead of coordinate inputs. This non-periodic spectral embedding provides a principled inductive bias for bounded domains, enabling the learned operator to capture fine-scale features that are difficult for Fourier-based or MLP-only trunks to represent. SEDONet is evaluated on the 2-D Poisson equation, 1-D Burgers' equation, 1-D advection-diffusion equation, Allen-Cahn equation, Lorenz-96 chaotic system, and Darcy flow, covering elliptic, hyperbolic, parabolic, chaotic, and multiscale problems. Across all benchmarks, SEDONet consistently achieves the lowest or statistically comparable relative $L^2$ errors among DeepONet, FEDONet, and SEDONet, with improvements of up to 54% over the baseline DeepONet and consistent gains over Fourier-embedded variants on bounded, non-periodic problems. Energy spectrum analyses further demonstrate that SEDONet more accurately preserves intermediate- and high-frequency solution structures. The proposed framework provides a simple, parameter-neutral modification to DeepONets, offering a robust and computationally efficient spectral approach for surrogate modeling of nonlinear operators in scientific computing. --- ### WonderZoom: Multi-Scale 3D World Generation Authors: Jin Cao, Hong-Xing Yu, Jiajun Wu Published: 2025-12-09 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2512.09164v1 We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene contents at varying granularities. The fundamental challenge is the lack of a scale-aware 3D representation capable of generating and rendering content with largely different spatial sizes. WonderZoom addresses this through two key innovations: (1) scale-adaptive Gaussian surfels for generating and real-time rendering of multi-scale 3D scenes, and (2) a progressive detail synthesizer that iteratively generates finer-scale 3D contents. Our approach enables users to "zoom into" a 3D region and auto-regressively synthesize previously non-existent fine details from landscapes to microscopic features. Experiments demonstrate that WonderZoom significantly outperforms state-of-the-art video and 3D models in both quality and alignment, enabling multi-scale 3D world creation from a single image. We show video results and an interactive viewer of generated multi-scale 3D worlds in https://wonderzoom.github.io/ ---