# Research Papers — 2025-12 · bundle page 82 of 175 > Full-text markdown of papers #4051–4100 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/82 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/81.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/83.md) ### STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning Authors: Jie Qin, Jiancheng Huang, Limeng Qiao, Lin Ma Published: 2025-12-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.13752v1 Multimodal large language models (MLLMs) play a pivotal role in advancing the quest for general artificial intelligence. However, achieving unified target for multimodal understanding and generation remains challenging due to optimization conflicts and performance trade-offs. To effectively enhance generative performance while preserving existing comprehension capabilities, we introduce STAR: a STacked AutoRegressive scheme for task-progressive unified multimodal learning. This approach decomposes multimodal learning into multiple stages: understanding, generation, and editing. By freezing the parameters of the fundamental autoregressive (AR) model and progressively stacking isomorphic AR modules, it avoids cross-task interference while expanding the model's capabilities. Concurrently, we introduce a high-capacity VQ to enhance the granularity of image representations and employ an implicit reasoning mechanism to improve generation quality under complex conditions. Experiments demonstrate that STAR achieves state-of-the-art performance on GenEval (0.91), DPG-Bench (87.44), and ImgEdit (4.34), validating its efficacy for unified multimodal learning. --- ### MIDUS: Memory-Infused Depth Up-Scaling Authors: Taero Kim, Hoyoon Byun, Youngjun Choi, Sungrae Park, Kyungwoo Song Published: 2025-12-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.13751v2 Expanding pre-trained language models offers a practical way to increase capacity without training larger models from scratch. Depth Up-Scaling (DUS) does so by duplicating Transformer blocks and inserting them into a pre-trained backbone. This process also duplicates FFN-heavy blocks, increasing parameter and compute cost while adding capacity through a block-level dense residual branch. Yet prior work suggests that added capacity need not remain tied to dense FFN branches, while attention heads often play heterogeneous roles, motivating more efficient head-level residual corrections. We propose Memory-Infused Depth Up-Scaling (MIDUS), which replaces the duplicated FFN branches with memory layers and turns added depth into lightweight retrieval-based residual capacity. We introduce a Head-wise Memory Layer (HML), which combines multi-head product-key memory with Head-wise Implicit Value Expansion (HIVE). HML assigns each head a distinct key space, while HIVE realizes head-specific values from a shared latent bank through compact projections. Alongside empirical improvements in performance and efficiency, our head-importance and fixed-retrieval structural analyses characterize HML with HIVE as a structurally distinct, head-conditioned alternative to FFN-based residual expansion. --- ### The algorithmic muse and the public domain: Why copyrights legal philosophy precludes protection for generative AI outputs Authors: Ezieddin Elmahjub Published: 2025-12-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.13750v1 Generative AI (GenAI) outputs are not copyrightable. This article argues why. We bypass conventional doctrinal analysis that focuses on black letter law notions of originality and authorship to re-evaluate copyright's foundational philosophy. GenAI fundamentally severs the direct human creative link to expressive form. Traditional theories utilitarian incentive, labor desert and personality fail to provide coherent justification for protection. The public domain constitutes the default baseline for intellectual creations. Those seeking copyright coverage for GenAI outputs bear the burden of proof. Granting copyright to raw GenAI outputs would not only be philosophically unsound but would also trigger an unprecedented enclosure of the digital commons, creating a legal quagmire and stifling future innovation. The paper advocates for a clear distinction: human creative contributions to AI-generated works may warrant protection, but the raw algorithmic output should remain in the public domain. --- ### Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis Authors: Joyjit Roy, Samaresh Kumar Singh Published: 2025-12-15 Categories: cs.LG, cs.AI, cs.CE, cs.CY, cs.SE arXiv: https://arxiv.org/abs/2512.13749v2 Financial sentiment analysis enhances market understanding. However, standard Natural Language Processing (NLP) approaches encounter significant challenges when applied to small datasets. This study presents a comparative evaluation of embedding-based techniques for financial news sentiment classification in resource-constrained environments. Word2Vec, GloVe, and sentence transformer representations are evaluated in combination with gradient boosting on a manually labeled dataset of 349 financial news headlines. Experimental results identify a substantial gap between validation and test performance. Despite strong validation metrics, models underperform relative to trivial baselines. The analysis indicates that pretrained embeddings yield diminishing returns below a critical data sufficiency threshold. Small validation sets contribute to overfitting during model selection. Practical application is illustrated through weekly sentiment aggregation and narrative summarization for market monitoring. Overall, the findings indicate that embedding quality alone cannot address fundamental data scarcity in sentiment classification. Practitioners with limited labeled data should consider alternative strategies, including few-shot learning, data augmentation, or lexicon-enhanced hybrid methods. --- ### Why Text Prevails: Vision May Undermine Multimodal Medical Decision Making Authors: Siyuan Dai, Lunxiao Li, Kun Zhao, Eardi Lila, Paul K. Crane, Heng Huang, Dongkuan Xu, Haoteng Tang, Liang Zhan Published: 2025-12-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.13747v1 With the rapid progress of large language models (LLMs), advanced multimodal large language models (MLLMs) have demonstrated impressive zero-shot capabilities on vision-language tasks. In the biomedical domain, however, even state-of-the-art MLLMs struggle with basic Medical Decision Making (MDM) tasks. We investigate this limitation using two challenging datasets: (1) three-stage Alzheimer's disease (AD) classification (normal, mild cognitive impairment, dementia), where category differences are visually subtle, and (2) MIMIC-CXR chest radiograph classification with 14 non-mutually exclusive conditions. Our empirical study shows that text-only reasoning consistently outperforms vision-only or vision-text settings, with multimodal inputs often performing worse than text alone. To mitigate this, we explore three strategies: (1) in-context learning with reason-annotated exemplars, (2) vision captioning followed by text-only inference, and (3) few-shot fine-tuning of the vision tower with classification supervision. These findings reveal that current MLLMs lack grounded visual understanding and point to promising directions for improving multimodal decision making in healthcare. --- ### Probabilistic Predictions of Process-Induced Deformation in Carbon/Epoxy Composites Using a Deep Operator Network Authors: Elham Kiyani, Amit Makarand Deshpande, Madhura Limaye, Zhiwei Gao, Zongren Zou, Sai Aditya Pradeep, Srikanth Pilla, Gang Li, Zhen Li, George Em Karniadakis Published: 2025-12-15 Categories: cs.CE, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2512.13746v5 Fiber reinforcement and polymer matrix respond differently to manufacturing conditions due to mismatch in coefficient of thermal expansion and matrix shrinkage during curing of thermosets. These heterogeneities generate residual stresses over multiple length scales, whose partial release leads to process-induced deformation (PID), requiring accurate prediction and mitigation via optimized non-isothermal cure cycles. This study considers a unidirectional AS4 carbon fiber/amine bi-functional epoxy prepreg and models PID using a two-mechanism framework that accounts for thermal expansion/shrinkage and cure shrinkage. The model is validated against manufacturing trials to identify initial and boundary conditions, then used to generate PID responses for a diverse set of non-isothermal cure cycles (time-temperature profiles). Building on this physics-based foundation, we develop a data-driven surrogate based on Deep Operator Networks (DeepONets). A DeepONet is trained on a dataset combining high-fidelity simulations with targeted experimental measurements of PID. We extend this to a Feature-wise Linear Modulation (FiLM) DeepONet, where branch-network features are modulated by external parameters, including the initial degree of cure, enabling prediction of time histories of degree of cure, viscosity, and deformation. Because experimental data are available only at limited time instances (for example, final deformation), we use transfer learning: simulation-trained trunk and branch networks are fixed and only the final layer is updated using measured final deformation. Finally, we augment the framework with Ensemble Kalman Inversion (EKI) to quantify uncertainty under experimental conditions and to support optimization of cure schedules for reduced PID in composites. --- ### A Spatio-Temporal Hybrid Quantum-Classical Graph Convolutional Neural Network Approach for Urban Taxi Destination Prediction Authors: Xiuying Zhang, Qinsheng Zhu, Xiaodong Xing Published: 2025-12-15 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2512.13745v1 We propose a Hybrid Spatio-Temporal Quantum Graph Convolutional Network (H-STQGCN) algorithm by combining the strengths of quantum computing and classical deep learning to predict the taxi destination within urban road networks. Our algorithm consists of two branches: spatial processing and time evolution. Regarding the spatial processing, the classical module encodes the local topological features of the road network based on the GCN method, and the quantum module is designed to map graph features onto parameterized quantum circuits through a differentiable pooling layer. The time evolution is solved by integrating multi-source contextual information and capturing dynamic trip dependencies on the classical TCN theory. Finally, our experimental results demonstrate that the proposed algorithm outperforms the current methods in terms of prediction accuracy and stability, validating the unique advantages of the quantum-enhanced mechanism in capturing high-dimensional spatial dependencies. --- ### Toward Noise-Aware Audio Deepfake Detection: Survey, SNR-Benchmarks, and Practical Recipes Authors: Udayon Sen, Alka Luqman, Anupam Chattopadhyay Published: 2025-12-15 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2512.13744v1 Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and consumer channels - often lags clean-lab results. We survey and evaluate robustness for state-of-the-art audio deepfake detection models and present a reproducible framework that mixes MS-SNSD noises with ASVspoof 2021 DF utterances to evaluate under controlled signal-to-noise ratios (SNRs). SNR is a measured proxy for noise severity used widely in speech; it lets us sweep from near-clean (35 dB) to very noisy (-5 dB) to quantify graceful degradation. We study multi-condition training and fixed-SNR testing for pretrained encoders (WavLM, Wav2Vec2, MMS), reporting accuracy, ROC-AUC, and EER on binary and four-class (authenticity x corruption) tasks. In our experiments, finetuning reduces EER by 10-15 percentage points at 10-0 dB SNR across backbones. --- ### Quantum oracles give an advantage for identifying classical counterfactuals Authors: Ciarán M. Gilligan-Lee, Yìlè Yīng, Jonathan Richens, David Schmid Published: 2025-12-15 Categories: quant-ph, stat.ML arXiv: https://arxiv.org/abs/2512.13692v1 We show that quantum oracles provide an advantage over classical oracles for answering classical counterfactual questions in causal models, or equivalently, for identifying unknown causal parameters such as distributions over functional dependences. In structural causal models with discrete classical variables, observational data and even ideal interventions generally fail to answer all counterfactual questions, since different causal parameters can reproduce the same observational and interventional data while disagreeing on counterfactuals. Using a simple binary example, we demonstrate that if the classical variables of interest are encoded in quantum systems and the causal dependence among them is encoded in a quantum oracle, coherently querying the oracle enables the identification of all causal parameters -- hence all classical counterfactuals. We generalize this to arbitrary finite cardinalities and prove that coherent probing 1) allows the identification of all two-way joint counterfactuals p(Y_x=y, Y_{x'}=y'), which is not possible with any number of queries to a classical oracle, and 2) provides tighter bounds on higher-order multi-way counterfactuals than with a classical oracle. This work can also be viewed as an extension to traditional quantum oracle problems such as Deutsch--Jozsa to identifying more causal parameters beyond just, e.g., whether a function is constant or balanced. Finally, we raise the question of whether this quantum advantage relies on uniquely non-classical features like contextuality. We provide some evidence against this by showing that in the binary case, oracles in some classically-explainable theories like Spekkens' toy theory also give rise to a counterfactual identifiability advantage over strictly classical oracles. --- ### DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders Authors: Susung Hong, Chongjian Ge, Zhifei Zhang, Jui-Hsien Wang Published: 2025-12-15 Categories: cs.CV, cs.AI, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2512.13690v1 Video diffusion models have revolutionized generative video synthesis, but they are imprecise, slow, and can be opaque during generation -- keeping users in the dark for a prolonged period. In this work, we propose DiffusionBrowser, a model-agnostic, lightweight decoder framework that allows users to interactively generate previews at any point (timestep or transformer block) during the denoising process. Our model can generate multi-modal preview representations that include RGB and scene intrinsics at more than 4$\times$ real-time speed (less than 1 second for a 4-second video) that convey consistent appearance and motion to the final video. With the trained decoder, we show that it is possible to interactively guide the generation at intermediate noise steps via stochasticity reinjection and modal steering, unlocking a new control capability. Moreover, we systematically probe the model using the learned decoders, revealing how scene, object, and other details are composed and assembled during the otherwise black-box denoising process. --- ### LitePT: Lighter Yet Stronger Point Transformer Authors: Yuanwen Yue, Damien Robert, Jianyuan Wang, Sunghwan Hong, Jan Dirk Wegner, Christian Rupprecht, Konrad Schindler Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13689v2 Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud networks and find an intuitive behaviour: convolution is adequate to extract low-level geometry at high-resolution in early layers, where attention is expensive without bringing any benefits; attention captures high-level semantics and context in low-resolution, deep layers more efficiently, where convolution inflates the parameter count. Guided by this design principle, we propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers. To avoid the loss of spatial layout information when discarding redundant convolution layers, we introduce a novel, parameter-free 3D positional encoding, PointROPE. The resulting LitePT model has $3.6\times$ fewer parameters, runs $2\times$ faster, and uses $2\times$ less memory than the state-of-the-art Point Transformer V3, but nonetheless matches or outperforms it on a range of tasks and datasets. Code and models are available at: https://github.com/prs-eth/LitePT. --- ### Towards Scalable Pre-training of Visual Tokenizers for Generation Authors: Jingfeng Yao, Yuda Song, Yucong Zhou, Xinggang Wang Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13687v2 The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information, leading to a foundation flaw: better pixel-level accuracy does not lead to higher-quality generation. This implies that pouring extensive compute into visual tokenizer pre-training translates poorly to improved performance in generation. We identify this as the ``pre-training scaling problem`` and suggest a necessary shift: to be effective for generation, a latent space must concisely represent high-level semantics. We present VTP, a unified visual tokenizer pre-training framework, pioneering the joint optimization of image-text contrastive, self-supervised, and reconstruction losses. Our large-scale study reveals two principal findings: (1) understanding is a key driver of generation, and (2) much better scaling properties, where generative performance scales effectively with compute, parameters, and data allocated to the pretraining of the visual tokenizer. After large-scale pre-training, our tokenizer delivers a competitive profile (78.2 zero-shot accuracy and 0.36 rFID on ImageNet) and 4.1 times faster convergence on generation compared to advanced distillation methods. More importantly, it scales effectively: without modifying standard DiT training specs, solely investing more FLOPS in pretraining VTP achieves 65.8\% FID improvement in downstream generation, while conventional autoencoder stagnates very early at 1/10 FLOPS. Our pre-trained models are available at https://github.com/MiniMax-AI/VTP. --- ### Beyond surface form: A pipeline for semantic analysis in Alzheimer's Disease detection from spontaneous speech Authors: Dylan Phelps, Rodrigo Wilkens, Edward Gow-Smith, Lilian Hubner, Bárbara Malcorra, César Rennó-Costa, Marco Idiart, Maria-Cruz Villa-Uriol, Aline Villavicencio Published: 2025-12-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.13685v1 Alzheimer's Disease (AD) is a progressive neurodegenerative condition that adversely affects cognitive abilities. Language-related changes can be automatically identified through the analysis of outputs from linguistic assessment tasks, such as picture description. Language models show promise as a basis for screening tools for AD, but their limited interpretability poses a challenge in distinguishing true linguistic markers of cognitive decline from surface-level textual patterns. To address this issue, we examine how surface form variation affects classification performance, with the goal of assessing the ability of language models to represent underlying semantic indicators. We introduce a novel approach where texts surface forms are transformed by altering syntax and vocabulary while preserving semantic content. The transformations significantly modify the structure and lexical content, as indicated by low BLEU and chrF scores, yet retain the underlying semantics, as reflected in high semantic similarity scores, isolating the effect of semantic information, and finding models perform similarly to if they were using the original text, with only small deviations in macro-F1. We also investigate whether language from picture descriptions retains enough detail to reconstruct the original image using generative models. We found that image-based transformations add substantial noise reducing classification accuracy. Our methodology provides a novel way of looking at what features influence model predictions, and allows the removal of possible spurious correlations. We find that just using semantic information, language model based classifiers can still detect AD. This work shows that difficult to detect semantic impairment can be identified, addressing an overlooked feature of linguistic deterioration, and opening new pathways for early detection systems. --- ### Recurrent Video Masked Autoencoders Authors: Daniel Zoran, Nikhil Parthasarathy, Yi Yang, Drew A Hudson, Joao Carreira, Andrew Zisserman Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13684v2 We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a transformer-based recurrent neural network to aggregate information over time, training solely on a simple pixel reconstruction loss. This design yields a highly efficient "generalist" encoder: RVM achieves competitive performance with state-of-the-art video models (e.g. VideoMAE, V-JEPA) on video-level tasks like action classification, and point and object tracking, while matching or exceeding the performance of image models (e.g. DINOv2) on tasks that require strong geometric and dense spatial features. Notably, RVM achieves strong performance in the small-model regime without requiring knowledge distillation, exhibiting up to 30x greater parameter efficiency than competing video masked autoencoders. Finally, we demonstrate that RVM's recurrent nature allows for stable feature propagation over long temporal horizons with linear computational cost, overcoming some of the limitations of standard spatio-temporal attention-based video models. Ablation studies further highlight the factors driving the model's success, with qualitative results showing that RVM learns rich representations of scene semantics, structure, and motion. --- ### I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners Authors: Lu Ling, Yunhao Ge, Yichen Sheng, Aniket Bera Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13683v2 Generalization remains the central challenge for interactive 3D scene generation. Existing learning-based approaches ground spatial understanding in limited scene dataset, restricting generalization to new layouts. We instead reprogram a pre-trained 3D instance generator to act as a scene level learner, replacing dataset-bounded supervision with model-centric spatial supervision. This reprogramming unlocks the generator transferable spatial knowledge, enabling generalization to unseen layouts and novel object compositions. Remarkably, spatial reasoning still emerges even when the training scenes are randomly composed objects. This demonstrates that the generator's transferable scene prior provides a rich learning signal for inferring proximity, support, and symmetry from purely geometric cues. Replacing widely used canonical space, we instantiate this insight with a view-centric formulation of the scene space, yielding a fully feed-forward, generalizable scene generator that learns spatial relations directly from the instance model. Quantitative and qualitative results show that a 3D instance generator is an implicit spatial learner and reasoner, pointing toward foundation models for interactive 3D scene understanding and generation. Project page: https://luling06.github.io/I-Scene-project/ --- ### LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction Authors: Tianye Ding, Yiming Xie, Yiqing Liang, Moitreya Chatterjee, Pedro Miraldo, Huaizu Jiang Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13680v3 Recent feed-forward reconstruction models like VGGT and $π^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming methods address this through learned memory mechanisms or causal attention, they require extensive retraining and may not fully leverage the strong geometric priors of state-of-the-art offline models. We propose LASER, a training-free framework that converts an offline reconstruction model into a streaming system by aligning predictions across consecutive temporal windows. We observe that simple similarity transformation ($\mathrm{Sim}(3)$) alignment fails due to layer depth misalignment: monocular scale ambiguity causes relative depth scales of different scene layers to vary inconsistently between windows. To address this, we introduce layer-wise scale alignment, which segments depth predictions into discrete layers, computes per-layer scale factors, and propagates them across both adjacent windows and timestamps. Extensive experiments show that LASER achieves state-of-the-art performance on camera pose estimation and point map reconstruction %quality with offline models while operating at 14 FPS with 6 GB peak memory on a RTX A6000 GPU, enabling practical deployment for kilometer-scale streaming videos. Project website: https://neu-vi.github.io/LASER/ --- ### Feedforward 3D Editing via Text-Steerable Image-to-3D Authors: Ziqi Ma, Hongqiao Chen, Yisong Yue, Georgia Gkioxari Published: 2025-12-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.13678v1 Recent progress in image-to-3D has opened up immense possibilities for design, AR/VR, and robotics. However, to use AI-generated 3D assets in real applications, a critical requirement is the capability to edit them easily. We present a feedforward method, Steer3D, to add text steerability to image-to-3D models, which enables editing of generated 3D assets with language. Our approach is inspired by ControlNet, which we adapt to image-to-3D generation to enable text steering directly in a forward pass. We build a scalable data engine for automatic data generation, and develop a two-stage training recipe based on flow-matching training and Direct Preference Optimization (DPO). Compared to competing methods, Steer3D more faithfully follows the language instruction and maintains better consistency with the original 3D asset, while being 2.4x to 28.5x faster. Steer3D demonstrates that it is possible to add a new modality (text) to steer the generation of pretrained image-to-3D generative models with 100k data. Project website: https://glab-caltech.github.io/steer3d/ --- ### JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing Authors: Xiaohu Huang, Haoyang He, Hao Zhou, Qiangpeng Yang, Shilei Wen, Kai Han Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13677v2 In this paper, we present JoVA, a streamlined framework that unifies joint video-audio generation and editing. While existing methods often rely on fragmented, task-specific architectures or complex fusion mechanisms, JoVA employs native joint representation learning for direct video, audio, and text interaction in a dual-branch architecture. This design eliminates redundant alignment modules and effectively unifies diverse multimodal tasks within a single model. Furthermore, we utilize channel-wise conditioning for flexible image and video reference to avoid massive token expansion, alongside a mouth-area loss to enhance lip alignment. To fully empower and systematically evaluate this framework, we construct a comprehensive training corpus encompassing video-audio generation and editing datasets, and introduce unified benchmarks tailored for these multimodal tasks. Extensive experiments demonstrate that JoVA achieves state-of-the-art performance across benchmarks, establishing it as an extensible framework for versatile content creation. Project page: https://visual-ai.github.io/jova --- ### Towards Effective Model Editing for LLM Personalization Authors: Baixiang Huang, Limeng Cui, Jiapeng Liu, Haoran Wang, Jiawei Xu, Zhuiyue Tan, Yutong Chen, Chen Luo, Yi Liu, Kai Shu Published: 2025-12-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.13676v1 Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive, susceptible to catastrophic forgetting, and prone to performance degradation in multi-turn interactions or when handling implicit queries. To address these challenges, we conceptualize personalization as a model editing task and introduce Personalization Editing, a framework that applies localized edits guided by clustered preference representations. This design enables precise preference-aligned updates while preserving overall model capabilities. In addition, existing personalization benchmarks frequently rely on persona-based dialogs between LLMs rather than user-LLM interactions, or focus primarily on stylistic imitation while neglecting information-seeking tasks that require accurate recall of user-specific preferences. We introduce User Preference Question Answering (UPQA), a short-answer QA dataset constructed from in-situ user queries with varying levels of difficulty. Unlike prior benchmarks, UPQA directly evaluates a model's ability to recall and apply specific user preferences. Across experimental settings, Personalization Editing achieves higher editing accuracy and greater computational efficiency than fine-tuning, while outperforming prompting-based baselines in multi-turn conversations and implicit preference questions settings. --- ### Towards Interactive Intelligence for Digital Humans Authors: Yiyi Cai, Xuangeng Chu, Xiwei Gao, Sitong Gong, Yifei Huang, Caixin Kang, Kunhang Li, Haiyang Liu, Ruicong Liu, Yun Liu, Dianwen Ng, Zixiong Su et al. Published: 2025-12-15 Categories: cs.CV, cs.CL, cs.GR, cs.HC arXiv: https://arxiv.org/abs/2512.13674v2 We introduce Interactive Intelligence, a novel paradigm of digital human that is capable of personality-aligned expression, adaptive interaction, and self-evolution. To realize this, we present Mio (Multimodal Interactive Omni-Avatar), an end-to-end framework composed of five specialized modules: Thinker, Talker, Face Animator, Body Animator, and Renderer. This unified architecture integrates cognitive reasoning with real-time multimodal embodiment to enable fluid, consistent interaction. Furthermore, we establish a new benchmark to rigorously evaluate the capabilities of interactive intelligence. Extensive experiments demonstrate that our framework achieves superior performance compared to state-of-the-art methods across all evaluated dimensions. Together, these contributions move digital humans beyond superficial imitation toward intelligent interaction. --- ### Directional Textual Inversion for Personalized Text-to-Image Generation Authors: Kunhee Kim, NaHyeon Park, Kibeom Hong, Hyunjung Shim Published: 2025-12-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.13672v2 Textual Inversion (TI) is an efficient approach to text-to-image personalization but often fails on complex prompts. We trace these failures to embedding norm inflation: learned tokens drift to out-of-distribution magnitudes, degrading prompt conditioning in pre-norm Transformers. Empirically, we show semantics are primarily encoded by direction in CLIP token space, while inflated norms harm contextualization; theoretically, we analyze how large magnitudes attenuate positional information and hinder residual updates in pre-norm blocks. We propose Directional Textual Inversion (DTI), which fixes the embedding magnitude to an in-distribution scale and optimizes only direction on the unit hypersphere via Riemannian SGD. We cast direction learning as MAP with a von Mises-Fisher prior, yielding a constant-direction prior gradient that is simple and efficient to incorporate. Across personalization tasks, DTI improves text fidelity over TI and TI-variants while maintaining subject similarity. Crucially, DTI's hyperspherical parameterization enables smooth, semantically coherent interpolation between learned concepts (slerp), a capability that is absent in standard TI. Our findings suggest that direction-only optimization is a robust and scalable path for prompt-faithful personalization. Code is available at https://github.com/kunheek/dti. --- ### AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation Authors: Junwen Miao, Penghui Du, Yingying Fan, Yi Liu, Yu Wang, Runze He, Lida Huang, Yan Wang Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13671v2 Industrial anomaly detection (IAD) is challenging due to the subtle and highly localized nature of many defects, which single-pass vision--language models (VLMs) often fail to capture. Moreover, existing approaches lack mechanisms to actively acquire complementary evidence during inference. We propose AgentIAD, an agentic vision--language framework that enables iterative industrial inspection through a unified action space. The agent dynamically accesses two forms of memory during inspection: visual memory via the Perceptive Zoomer (PZ) for fine-grained local analysis, and retrieved memory via the Web Searcher (WS) and Comparative Retriever (CR) for external knowledge acquisition and cross-instance verification. This design allows the model to progressively gather evidence through multi-round perception--action reasoning. To effectively learn such policies under sparse supervision, AgentIAD adopts a two-stage training strategy: tool-aware supervised fine-tuning first initializes structured reasoning and memory-access behaviors, followed by agentic reinforcement learning to refine long-horizon decision policies. Extensive experiments show that, under the same backbone, AgentIAD improves classification accuracy by 5.92% over the previous state-of-the-art method on the MMAD benchmark while providing more reliable and interpretable anomaly analysis. --- ### A Scientific Reasoning Model for Organic Synthesis Procedure Generation Authors: Guoqing Liu, Junren Li, Zihan Zhao, Eray Inanc, Krzysztof Maziarz, Jose Garrido Torres, Victor Garcia Satorras, Shoko Ueda, Christopher M. Bishop, Marwin Segler Published: 2025-12-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13668v1 Solving computer-aided synthesis planning is essential for enabling fully automated, robot-assisted synthesis workflows and improving the efficiency of drug discovery. A key challenge, however, is bridging the gap between computational route design and practical laboratory execution, particularly the accurate prediction of viable experimental procedures for each synthesis step. In this work, we present QFANG, a scientific reasoning language model capable of generating precise, structured experimental procedures directly from reaction equations, with explicit chain-of-thought reasoning. To develop QFANG, we curated a high-quality dataset comprising 905,990 chemical reactions paired with structured action sequences, extracted and processed from patent literature using large language models. We introduce a Chemistry-Guided Reasoning (CGR) framework that produces chain-of-thought data grounded in chemical knowledge at scale. The model subsequently undergoes supervised fine-tuning to elicit complex chemistry reasoning. Finally, we apply Reinforcement Learning from Verifiable Rewards (RLVR) to further enhance procedural accuracy. Experimental results demonstrate that QFANG outperforms advanced general-purpose reasoning models and nearest-neighbor retrieval baselines, measured by traditional NLP similarity metrics and a chemically aware evaluator using an LLM-as-a-judge. Moreover, QFANG generalizes to certain out-of-domain reaction classes and adapts to variations in laboratory conditions and user-specific constraints. We believe that QFANG's ability to generate high-quality synthesis procedures represents an important step toward bridging the gap between computational synthesis planning and fully automated laboratory synthesis. --- ### A stylometric analysis of speaker attribution from speech transcripts Authors: Cristina Aggazzotti, Elizabeth Allyn Smith Published: 2025-12-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.13667v3 Forensic scientists often need to identify an unknown speaker or writer in cases such as ransom calls, covert recordings, alleged suicide notes, or anonymous online communications, among many others. Speaker recognition in the speech domain usually examines phonetic or acoustic properties of a voice, and these methods can be accurate and robust under certain conditions. However, if a speaker disguises their voice or employs text-to-speech software, vocal properties may no longer be reliable, leaving only their linguistic content available for analysis. Authorship attribution methods traditionally use syntactic, semantic, and related linguistic information to identify writers of written text (authorship attribution). In this paper, we apply a content-based authorship approach to speech that has been transcribed into text, using what a speaker says to attribute speech to individuals (speaker attribution). We introduce a stylometric method, StyloSpeaker, which incorporates character, word, token, sentence, and style features from the stylometric literature on authorship, to assess whether two transcripts were produced by the same speaker. We evaluate this method on two types of transcript formatting: one approximating prescriptive written text with capitalization and punctuation and another normalized style that removes these conventions. The transcripts' conversation topics are also controlled to varying degrees. We find generally higher attribution performance on normalized transcripts, except under the strongest topic control condition, in which overall performance is highest. Finally, we compare this more explainable stylometric model to black-box neural approaches on the same data and investigate which stylistic features most effectively distinguish speakers. --- ### SEDULity: A Proof-of-Learning Framework for Distributed and Secure Blockchains with Efficient Useful Work Authors: Weihang Cao, Mustafa Doger, Sennur Ulukus Published: 2025-12-15 Categories: cs.CR, cs.DC, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2512.13666v2 The security and decentralization of Proof-of-Work (PoW) have been well-tested in existing blockchain systems. However, its tremendous energy waste has raised concerns about sustainability. Proof-of-Useful-Work (PoUW) aims to redirect the meaningless computation to meaningful tasks such as solving machine learning (ML) problems, giving rise to the branch of Proof-of-Learning (PoL). While previous studies have proposed various PoLs, they all, to some degree, suffer from security, decentralization, or efficiency issues. In this paper, we propose a PoL framework that trains ML models efficiently while maintaining blockchain security in a fully distributed manner. We name the framework SEDULity, which stands for a Secure, Efficient, Distributed, and Useful Learning-based blockchain system. Specifically, we encode the template block into the training process and design a useful function that is difficult to solve but relatively easy to verify, as a substitute for the PoW puzzle. We show that our framework is distributed, secure, and efficiently trains ML models. We further demonstrate that the proposed PoL framework can be extended to other types of useful work and design an incentive mechanism to incentivize task verification. We show theoretically that a rational miner is incentivized to train fully honestly with well-designed system parameters. Finally, we present simulation results to demonstrate the performance of our framework and validate our analysis. --- ### Grab-3D: Detecting AI-Generated Videos from 3D Geometric Temporal Consistency Authors: Wenhan Chen, Sezer Karaoglu, Theo Gevers Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13665v1 Recent advances in diffusion-based generation techniques enable AI models to produce highly realistic videos, heightening the need for reliable detection mechanisms. However, existing detection methods provide only limited exploration of the 3D geometric patterns present in generated videos. In this paper, we use vanishing points as an explicit representation of 3D geometry patterns, revealing fundamental discrepancies in geometric consistency between real and AI-generated videos. We introduce Grab-3D, a geometry-aware transformer framework for detecting AI-generated videos based on 3D geometric temporal consistency. To enable reliable evaluation, we construct an AI-generated video dataset of static scenes, allowing stable 3D geometric feature extraction. We propose a geometry-aware transformer equipped with geometric positional encoding, temporal-geometric attention, and an EMA-based geometric classifier head to explicitly inject 3D geometric awareness into temporal modeling. Experiments demonstrate that Grab-3D significantly outperforms state-of-the-art detectors, achieving robust cross-domain generalization to unseen generators. --- ### Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics Authors: Enshen Zhou, Yibo Li, Jingkun An, Jiayuan Zhang, Shanyu Rong, Mengzhen Liu, Yi Han, Yuheng Ji, Huajie Tan, Jiawei He, Pengwei Wang, Zhongyuan Wang et al. Published: 2025-12-15 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.13660v4 Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However, existing methods struggle with this compositional task. To this end, we propose RoboTracer, a 3D-aware VLM that first achieves both 3D spatial referring and measuring via a universal spatial encoder and a regression-supervised decoder to enhance scale awareness during supervised fine-tuning (SFT). Moreover, RoboTracer advances multi-step metric-grounded reasoning via reinforcement fine-tuning (RFT) with metric-sensitive process rewards, supervising key intermediate perceptual cues to accurately generate spatial traces. To support SFT and RFT training, we introduce TraceSpatial, a large-scale dataset of 30M QA pairs, spanning outdoor/indoor/tabletop scenes and supporting complex reasoning processes (up to 9 steps). We further present TraceSpatial-Bench, a challenging benchmark filling the gap to evaluate spatial tracing. Experimental results show that RoboTracer surpasses baselines in spatial understanding, measuring, and referring, with an average success rate of 79.1%, and also achieves SOTA performance on TraceSpatial-Bench by a large margin, exceeding Gemini-2.5-Pro by 36% accuracy. Notably, RoboTracer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (UR5, G1 humanoid) in cluttered real-world scenes. Please see the project page at https://zhoues.github.io/RoboTracer. --- ### Embedding-Based Rankings of Educational Resources based on Learning Outcome Alignment: Benchmarking, Expert Validation, and Learner Performance Authors: Mohammadreza Molavi, Mohammad Moein, Mohammadreza Tavakoli, Abdolali Faraji, Stefan T. Mol, Gábor Kismihók Published: 2025-12-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.13658v1 As the online learning landscape evolves, the need for personalization is increasingly evident. Although educational resources are burgeoning, educators face challenges selecting materials that both align with intended learning outcomes and address diverse learner needs. Large Language Models (LLMs) are attracting growing interest for their potential to create learning resources that better support personalization, but verifying coverage of intended outcomes still requires human alignment review, which is costly and limits scalability. We propose a framework that supports the cost-effective automation of evaluating alignment between educational resources and intended learning outcomes. Using human-generated materials, we benchmarked LLM-based text-embedding models and found that the most accurate model (Voyage) achieved 79% accuracy in detecting alignment. We then applied the optimal model to LLM-generated resources and, via expert evaluation, confirmed that it reliably assessed correspondence to intended outcomes (83% accuracy). Finally, in a three-group experiment with 360 learners, higher alignment scores were positively related to greater learning performance, chi-squared(2, N = 360) = 15.39, p < 0.001. These findings show that embedding-based alignment scores can facilitate scalable personalization by confirming alignment with learning outcomes, which allows teachers to focus on tailoring content to diverse learner needs. --- ### Advancing Machine Learning Optimization of Chiral Photonic Metasurface: Comparative Study of Neural Network and Genetic Algorithm Approaches Authors: Davide Filippozzi, Alexandre Mayer, Nicolas Roy, Wei Fang, Arash Rahimi-Iman Published: 2025-12-15 Categories: physics.optics, physics.app-ph, stat.ML arXiv: https://arxiv.org/abs/2512.13656v1 Chiral photonic metasurfaces provide unique capabilities for tailoring light-matter interactions, which are essential for next-generation photonic devices. Here, we report an advanced optimization framework that combines deep learning and evolutionary algorithms to significantly improve both the design and performance of chiral photonic nanostructures. Building on previous work utilizing a three-layer perceptron reinforced learning and stochastic evolutionary algorithm with decaying changes and mass extinction for chiral photonic optimization, our study introduces a refined pipeline featuring a two-output neural network architecture to reduce the trade-off between high chiral dichroism (CD) and reflectivity. Additionally, we use an improved fitness function, and efficient data augmentation techniques. A comparative analysis between a neural network (NN)-based approach and a genetic algorithm (GA) is presented for structures of different interface pattern depth, material combinations, and geometric complexity. We demonstrate a twice higher CD and the impact of both the corner number and the refractive index contrast at the example of a GaP/air and PMMA/air metasurface as a result of superior optimization performance. Additionally, a substantial increase in the number of structures explored within limited computational resources is highlighted, with tailored spectral reflectivity suggested by our electromagnetic simulations, paving the way for chiral mirrors applicable to polarization-selective light-matter interaction studies. --- ### Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation Authors: Richard J. Young Published: 2025-12-15 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2512.13655v2 Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing, and security analysis. While abliteration techniques enable surgical removal of refusal representations through directional orthogonalization, the relative effectiveness of available implementations remains uncharacterized. This study evaluates four abliteration tools (Heretic, DECCP, ErisForge, FailSpy) across sixteen instruction-tuned models (7B-14B parameters), reporting tool compatibility on all 16 models and quantitative metrics on subsets dictated by tool support. Single-pass methods demonstrated superior capability preservation on the benchmarked subset (avg GSM8K change across three models: ErisForge -0.28 pp; DECCP -0.13 pp), while Bayesian-optimized abliteration produced variable distribution shift (KL divergence: 0.043-1.646) with model-dependent capability impact. These findings provide researchers with evidence-based selection criteria for abliteration tool deployment across diverse model architectures. The principal finding indicates that mathematical reasoning capabilities exhibit the highest sensitivity to abliteration interventions, with GSM8K change ranging from +1.51 pp to -18.81 pp (-26.5% relative) depending on tool selection and model architecture. --- ### Large-Language Memorization During the Classification of United States Supreme Court Cases Authors: John E. Ortega, Dhruv D. Joshi, Matt P. Borkowski Published: 2025-12-15 Categories: cs.CL, cs.AI, cs.ET, cs.IR arXiv: https://arxiv.org/abs/2512.13654v1 Large-language models (LLMs) have been shown to respond in a variety of ways for classification tasks outside of question-answering. LLM responses are sometimes called "hallucinations" since the output is not what is ex pected. Memorization strategies in LLMs are being studied in detail, with the goal of understanding how LLMs respond. We perform a deep dive into a classification task based on United States Supreme Court (SCOTUS) decisions. The SCOTUS corpus is an ideal classification task to study for LLM memory accuracy because it presents significant challenges due to extensive sentence length, complex legal terminology, non-standard structure, and domain-specific vocabulary. Experimentation is performed with the latest LLM fine tuning and retrieval-based approaches, such as parameter-efficient fine-tuning, auto-modeling, and others, on two traditional category-based SCOTUS classification tasks: one with 15 labeled topics and another with 279. We show that prompt-based models with memories, such as DeepSeek, can be more robust than previous BERT-based models on both tasks scoring about 2 points better than previous models not based on prompting. --- ### World Models for Learning Dexterous Hand-Object Interactions from Human Videos Authors: Raktim Gautam Goswami, Amir Bar, David Fan, Tsung-Yen Yang, Gaoyue Zhou, Prashanth Krishnamurthy, Michael Rabbat, Farshad Khorrami, Yann LeCun Published: 2025-12-15 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.13644v2 Modeling dexterous hand-object interactions is challenging as it requires understanding how subtle finger motions influence the environment through contact with objects. While recent world models address interaction modeling, they typically rely on coarse action spaces that fail to capture fine-grained dexterity. We, therefore, introduce DexWM, a Dexterous Interaction World Model that predicts future latent states of the environment conditioned on past states and dexterous actions. To overcome the scarcity of finely annotated dexterous datasets, DexWM represents actions using finger keypoints extracted from egocentric videos, enabling training on over 900 hours of human and non-dexterous robot data. Further, to accurately model dexterity, we find that predicting visual features alone is insufficient; therefore, we incorporate an auxiliary hand consistency loss that enforces accurate hand configurations. DexWM outperforms prior world models conditioned on text, navigation, or full-body actions in future-state prediction and demonstrates strong zero-shot transfer to unseen skills on a Franka Panda arm with an Allegro gripper, surpassing Diffusion Policy by over 50% on average across grasping, placing, and reaching tasks. --- ### From Many Models, One: Macroeconomic Forecasting with Reservoir Ensembles Authors: Giovanni Ballarin, Lyudmila Grigoryeva, Yui Ching Li Published: 2025-12-15 Categories: econ.EM, stat.ML arXiv: https://arxiv.org/abs/2512.13642v2 Model combination is a powerful approach for achieving superior performance compared to selecting a single model. We study both theoretically and empirically the effectiveness of ensembles of Multi-Frequency Echo State Networks (MFESNs), which have been shown to achieve state-of-the-art macroeconomic time series forecasting results (Ballarin et al., 2024a). The Hedge and Follow-the-Leader schemes are discussed, and their online learning guarantees are extended to settings with dependent data. In empirical applications, the proposed Ensemble Echo State Networks demonstrate significantly improved predictive performance relative to individual MFESN models. --- ### From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves Authors: Gabriel Vitorino de Andrade, Saulo Roberto dos Santos, Itallo Patrick Castro Alves da Silva, Emanuel Adler Medeiros Pereira, Erick de Andrade Barboza Published: 2025-12-15 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.13641v1 The validation and verification of artificial intelligence (AI) models through robustness assessment are essential to guarantee the reliable performance of intelligent systems facing real-world challenges, such as image corruptions including noise, blurring, and weather variations. Despite the global importance of mango (Mangifera indica L.), there is a lack of studies on the robustness of models for the diagnosis of disease in its leaves. This paper proposes a methodology to evaluate convolutional neural networks (CNNs) under adverse conditions. We adapted the MangoLeafDB dataset, generating MangoLeafDB-C with 19 types of artificial corruptions at five severity levels. We conducted a benchmark comparing five architectures: ResNet-50, ResNet-101, VGG-16, Xception, and LCNN (the latter being a lightweight architecture designed specifically for mango leaf diagnosis). The metrics include the F1 score, the corruption error (CE) and the relative mean corruption error (relative mCE). The results show that LCNN outperformed complex models in corruptions that can be present in real-world scenarios such as Defocus Blur, Motion Blur, while also achieving the lowest mCE. Modern architectures (e.g., ResNet-101) exhibited significant performance degradation in corrupted scenarios, despite their high accuracy under ideal conditions. These findings suggest that lightweight and specialized models may be more suitable for real-world applications in edge devices, where robustness and efficiency are critical. The study highlights the need to incorporate robustness assessments in the development of intelligent systems for agriculture, particularly in regions with technological limitations. --- ### Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All Authors: Michal Nazarczuk, Thomas Tanay, Arthur Moreau, Zhensong Zhang, Eduardo Pérez-Pellitero Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13639v1 This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety of dynamic scenes, complete with detailed textures, lighting, and motion, making it ideal for training and evaluating cutting-edge 4D scene reconstruction and novel view generation models. In addition to high-fidelity RGB images, we provide multiple complementary modalities, including depth, surface normals, object segmentation and optical flow, enabling a deeper understanding of scene geometry and motion. The dataset is organised into three distinct benchmarking scenarios: a dense multi-view camera setup, a sparse camera arrangement, and monocular video sequences, enabling a wide range of experimentation and comparison across varying levels of data sparsity. With its combination of visual richness, high-quality annotations, and diverse experimental setups, this dataset offers a unique resource for pushing the boundaries of view synthesis and 3D vision. --- ### MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning Authors: Haoyu Fu, Diankun Zhang, Zongchuang Zhao, Jianfeng Cui, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye, Dingkang Liang, Xiang Bai Published: 2025-12-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.13636v4 Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. To overcome this limitation, we propose MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. By feeding trajectory-level rewards back into the reasoning space, MindDrive enables trial-and-error learning over a finite set of discrete linguistic driving decisions, instead of operating directly in a continuous action space. This approach effectively balances optimal decision-making in complex scenarios, human-like driving behavior, and efficient exploration in online reinforcement learning. Using the lightweight Qwen-0.5B LLM, MindDrive achieves Driving Score (DS) of 78.04 and Success Rate (SR) of 55.09% on the challenging Bench2Drive benchmark. To the best of our knowledge, this is the first work to demonstrate the effectiveness of online reinforcement learning for the VLA model in autonomous driving. --- ### SCR2-ST: Combine Single Cell with Spatial Transcriptomics for Efficient Active Sampling via Reinforcement Learning Authors: Junchao Zhu, Ruining Deng, Junlin Guo, Tianyuan Yao, Chongyu Qu, Juming Xiong, Siqi Lu, Zhengyi Lu, Yanfan Zhu, Marilyn Lionts, Yuechen Yang, Yalin Zheng et al. Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13635v2 Spatial transcriptomics (ST) is an emerging technology that enables researchers to investigate the molecular relationships underlying tissue morphology. However, acquiring ST data remains prohibitively expensive, and traditional fixed-grid sampling strategies lead to redundant measurements of morphologically similar or biologically uninformative regions, thus resulting in scarce data that constrain current methods. The well-established single-cell sequencing field, however, could provide rich biological data as an effective auxiliary source to mitigate this limitation. To bridge these gaps, we introduce SCR2-ST, a unified framework that leverages single-cell prior knowledge to guide efficient data acquisition and accurate expression prediction. SCR2-ST integrates a single-cell guided reinforcement learning-based (SCRL) active sampling and a hybrid regression-retrieval prediction network SCR2Net. SCRL combines single-cell foundation model embeddings with spatial density information to construct biologically grounded reward signals, enabling selective acquisition of informative tissue regions under constrained sequencing budgets. SCR2Net then leverages the actively sampled data through a hybrid architecture combining regression-based modeling with retrieval-augmented inference, where a majority cell-type filtering mechanism suppresses noisy matches and retrieved expression profiles serve as soft labels for auxiliary supervision. We evaluated SCR2-ST on three public ST datasets, demonstrating SOTA performance in both sampling efficiency and prediction accuracy, particularly under low-budget scenarios. Code is publicly available at: https://github.com/hrlblab/SCR2ST --- ### Universality of high-dimensional scaling limits of stochastic gradient descent Authors: Reza Gheissari, Aukosh Jagannath Published: 2025-12-15 Categories: stat.ML, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2512.13634v2 We consider statistical tasks in high dimensions whose loss depends on the data only through its projection into a fixed-dimensional subspace spanned by the parameter vectors and certain ground truth vectors. This includes classifying mixture distributions with cross-entropy loss with one and two-layer networks, and learning single and multi-index models with one and two-layer networks. When the data is drawn from an isotropic Gaussian mixture distribution, it is known that the evolution of a finite family of summary statistics under stochastic gradient descent converges to an autonomous ordinary differential equation (ODE), as the dimension and sample size go to $\infty$ and the step size goes to $0$ commensurately. Our main result is that these ODE limits are universal in that this limit is the same whenever the data is drawn from mixtures of arbitrary product distributions whose first two moments match the corresponding Gaussian distribution, provided the initialization and ground truth vectors are coordinate-delocalized. We complement this by proving two corresponding non-universality results. We provide a simple example where the ODE limits are non-universal if the initialization is coordinate aligned. We also show that the stochastic differential equation limits arising as fluctuations of the summary statistics around their ODE's fixed points are not universal. --- ### StutterFuse: Mitigating Modality Collapse in Stuttering Detection with Jaccard-Weighted Metric Learning and Gated Fusion Authors: Guransh Singh, Md Shah Fahad Published: 2025-12-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13632v1 Stuttering detection breaks down when disfluencies overlap. Existing parametric models struggle to distinguish complex, simultaneous disfluencies (e.g., a 'block' with a 'prolongation') due to the scarcity of these specific combinations in training data. While Retrieval-Augmented Generation (RAG) has revolutionized NLP by grounding models in external knowledge, this paradigm remains unexplored in pathological speech processing. To bridge this gap, we introduce StutterFuse, the first Retrieval-Augmented Classifier (RAC) for multi-label stuttering detection. By conditioning a Conformer encoder on a non-parametric memory bank of clinical examples, we allow the model to classify by reference rather than memorization. We further identify and solve "Modality Collapse", an "Echo Chamber" effect where naive retrieval boosts recall but degrades precision. We mitigate this using: (1) SetCon, a Jaccard-Weighted Metric Learning objective that optimizes for multi-label set similarity, and (2) a Gated Mixture-of-Experts fusion strategy that dynamically arbitrates between acoustic evidence and retrieved context. On the SEP-28k dataset, StutterFuse achieves a weighted F1-score of 0.65, outperforming strong baselines and demonstrating remarkable zero-shot cross-lingual generalization. --- ### Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models Authors: Zefang Liu, Nam H. Nguyen, Yinzhu Quan, Shi-Xiong Zhang Published: 2025-12-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.13618v3 Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level representations or calendar tokens have been proposed. However, the optimal approach remains unclear, especially given the diverse statistical distributions of real-world event data, which range from smooth log-normal to discrete, spiky patterns. This paper presents a systematic empirical study of temporal tokenization for modeling event sequences with LLMs, comparing distinct encoding strategies: naive numeric strings, high-precision byte-level representations, human-semantic calendar tokens, classic uniform binning, and adaptive residual scalar quantization. We evaluate these strategies by fine-tuning LLMs on real-world datasets that exemplify these diverse distributions. Our analysis reveals that no single strategy is universally superior; instead, prediction performance depends heavily on aligning the tokenizer with the data's statistical properties, highlighting temporal tokenization as a critical yet often overlooked design dimension in LLM-based event modeling. --- ### LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification Authors: Ankit Sharma, Sayan Roy Gupta Published: 2025-12-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13617v1 Graph Neural Networks have demonstrated significant success in graph classification tasks, yet they often require substantial computational resources and struggle to capture global graph properties effectively. We introduce LightTopoGAT, a lightweight graph attention network that enhances node features through topological augmentation by incorporating node degree and local clustering coefficient to improve graph representation learning. The proposed approach maintains parameter efficiency through streamlined attention mechanisms while integrating structural information that is typically overlooked by local message passing schemes. Through comprehensive experiments on three benchmark datasets, MUTAG, ENZYMES, and PROTEINS, we show that LightTopoGAT achieves superior performance compared to established baselines including GCN, GraphSAGE, and standard GAT, with a 6.6 percent improvement in accuracy on MUTAG and a 2.2 percent improvement on PROTEINS. Ablation studies further confirm that these performance gains arise directly from the inclusion of topological features, demonstrating a simple yet effective strategy for enhancing graph neural network performance without increasing architectural complexity. --- ### Machine learning to optimize precision in the analysis of randomized trials: A journey in pre-specified, yet data-adaptive learning Authors: Laura B. Balzer, Mark J. van der Laan, Maya L. Petersen Published: 2025-12-15 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.13610v1 Covariate adjustment is an approach to improve the precision of trial analyses by adjusting for baseline variables that are prognostic of the primary endpoint. Motivated by the SEARCH Universal HIV Test-and-Treat Trial (2013-2017), we tell our story of developing, evaluating, and implementing a machine learning-based approach for covariate adjustment. We provide the rationale for as well as the practical concerns with such an approach for estimating marginal effects. Using schematics, we illustrate our procedure: targeted machine learning estimation (TMLE) with Adaptive Pre-specification. Briefly, sample-splitting is used to data-adaptively select the combination of estimators of the outcome regression (i.e., the conditional expectation of the outcome given the trial arm and covariates) and known propensity score (i.e., the conditional probability of being randomized to the intervention given the covariates) that minimizes the cross-validated variance estimate and, thereby, maximizes empirical efficiency. We discuss our approach for evaluating finite sample performance with parametric and plasmode simulations, pre-specifying the Statistical Analysis Plan, and unblinding in real-time on video conference with our colleagues from around the world. We present the results from applying our approach in the primary, pre-specified analysis of 8 recently published trials (2022-2024). We conclude with practical recommendations and an invitation to implement our approach in the primary analysis of your next trial. --- ### Do-Undo Bench: Reversibility for Action Understanding in Image Generation Authors: Shweta Mahajan, Shreya Kadambi, Hoang Le, Rajeev Yasarla, Apratim Bhattacharyya, Munawar Hayat, Fatih Porikli Published: 2025-12-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.13609v2 We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating plausible scene transformations driven by real-world actions. Unlike prior work that relies on prompt-based image generation and editing to perform action-conditioned image manipulation, our training hypothesis requires models to simulate the outcome of a real-world action and then reverse it to the original state. This forward-reverse requirement tests genuine cause-and-effect understanding rather than stylistic or semantic edits. We curate a high-quality benchmark of reversible actions from real-world scenarios to enable robust action grounding. Our experiments reveal that current models struggle with action reversibility, highlighting the need to evaluate action understanding. Do-Undo provides an intuitive testbed for evaluating and advancing action-aware generation in multimodal systems that must reason about real-world dynamics. --- ### DBT-DINO: Towards Foundation model based analysis of Digital Breast Tomosynthesis Authors: Felix J. Dorfner, Manon A. Dorster, Ryan Connolly, Oscar Gentilhomme, Edward Gibbs, Steven Graham, Seth Wander, Thomas Schultz, Manisha Bahl, Dania Daye, Albert E. Kim, Christopher P. Bridge Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13608v1 Foundation models have shown promise in medical imaging but remain underexplored for three-dimensional imaging modalities. No foundation model currently exists for Digital Breast Tomosynthesis (DBT), despite its use for breast cancer screening. To develop and evaluate a foundation model for DBT (DBT-DINO) across multiple clinical tasks and assess the impact of domain-specific pre-training. Self-supervised pre-training was performed using the DINOv2 methodology on over 25 million 2D slices from 487,975 DBT volumes from 27,990 patients. Three downstream tasks were evaluated: (1) breast density classification using 5,000 screening exams; (2) 5-year risk of developing breast cancer using 106,417 screening exams; and (3) lesion detection using 393 annotated volumes. For breast density classification, DBT-DINO achieved an accuracy of 0.79 (95\% CI: 0.76--0.81), outperforming both the MetaAI DINOv2 baseline (0.73, 95\% CI: 0.70--0.76, p<.001) and DenseNet-121 (0.74, 95\% CI: 0.71--0.76, p<.001). For 5-year breast cancer risk prediction, DBT-DINO achieved an AUROC of 0.78 (95\% CI: 0.76--0.80) compared to DINOv2's 0.76 (95\% CI: 0.74--0.78, p=.57). For lesion detection, DINOv2 achieved a higher average sensitivity of 0.67 (95\% CI: 0.60--0.74) compared to DBT-DINO with 0.62 (95\% CI: 0.53--0.71, p=.60). DBT-DINO demonstrated better performance on cancerous lesions specifically with a detection rate of 78.8\% compared to Dinov2's 77.3\%. Using a dataset of unprecedented size, we developed DBT-DINO, the first foundation model for DBT. DBT-DINO demonstrated strong performance on breast density classification and cancer risk prediction. However, domain-specific pre-training showed variable benefits on the detection task, with ImageNet baseline outperforming DBT-DINO on general lesion detection, indicating that localized detection tasks require further methodological development. --- ### Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models Authors: Boxin Wang, Chankyu Lee, Nayeon Lee, Sheng-Chieh Lin, Wenliang Dai, Yang Chen, Yangyi Chen, Zhuolin Yang, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping Published: 2025-12-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.13607v2 Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the RL infrastructure, slows training, and makes training curriculum (e.g., response length extension) and hyperparameter selection challenging. In this work, we propose cascaded domain-wise reinforcement learning (Cascade RL) to develop Nemotron-Cascade, capable of operating in both instruct and deep thinking modes, without any performance gap relative to a thinking-only counterpart. Departing from conventional approaches that blend heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL, reducing engineering complexity and delivering state-of-the-art performance across a wide range of benchmarks. Notably, RLHF for alignment, when used as a pre-step, boosts the model's reasoning ability far beyond mere preference optimization, and subsequent domain-wise RLVR stages rarely degrade the benchmark performance attained in earlier domains and may even improve it (see an illustration in Figure 1). Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6/Pro and achieves silver-medal performance in the 2025 International Olympiad in Informatics (IOI). We transparently share our training and data recipes. --- ### LongVie 2: Multimodal Controllable Ultra-Long Video World Model Authors: Jianxiong Gao, Zhaoxi Chen, Xian Liu, Junhao Zhuang, Chengming Xu, Jianfeng Feng, Yu Qiao, Yanwei Fu, Chenyang Si, Ziwei Liu Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13604v1 Building video world models upon pretrained video generation systems represents an important yet challenging step toward general spatiotemporal intelligence. A world model should possess three essential properties: controllability, long-term visual quality, and temporal consistency. To this end, we take a progressive approach-first enhancing controllability and then extending toward long-term, high-quality generation. We present LongVie 2, an end-to-end autoregressive framework trained in three stages: (1) Multi-modal guidance, which integrates dense and sparse control signals to provide implicit world-level supervision and improve controllability; (2) Degradation-aware training on the input frame, bridging the gap between training and long-term inference to maintain high visual quality; and (3) History-context guidance, which aligns contextual information across adjacent clips to ensure temporal consistency. We further introduce LongVGenBench, a comprehensive benchmark comprising 100 high-resolution one-minute videos covering diverse real-world and synthetic environments. Extensive experiments demonstrate that LongVie 2 achieves state-of-the-art performance in long-range controllability, temporal coherence, and visual fidelity, and supports continuous video generation lasting up to five minutes, marking a significant step toward unified video world modeling. --- ### DA-SSL: self-supervised domain adaptor to leverage foundational models in turbt histopathology slides Authors: Haoyue Zhang, Meera Chappidi, Erolcan Sayar, Helen Richards, Zhijun Chen, Lucas Liu, Roxanne Wadia, Peter A Humphrey, Fady Ghali, Alberto Contreras-Sanz, Peter Black, Jonathan Wright et al. Published: 2025-12-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.13600v1 Recent deep learning frameworks in histopathology, particularly multiple instance learning (MIL) combined with pathology foundational models (PFMs), have shown strong performance. However, PFMs exhibit limitations on certain cancer or specimen types due to domain shifts - these cancer types were rarely used for pretraining or specimens contain tissue-based artifacts rarely seen within the pretraining population. Such is the case for transurethral resection of bladder tumor (TURBT), which are essential for diagnosing muscle-invasive bladder cancer (MIBC), but contain fragmented tissue chips and electrocautery artifacts and were not widely used in publicly available PFMs. To address this, we propose a simple yet effective domain-adaptive self-supervised adaptor (DA-SSL) that realigns pretrained PFM features to the TURBT domain without fine-tuning the foundational model itself. We pilot this framework for predicting treatment response in TURBT, where histomorphological features are currently underutilized and identifying patients who will benefit from neoadjuvant chemotherapy (NAC) is challenging. In our multi-center study, DA-SSL achieved an AUC of 0.77+/-0.04 in five-fold cross-validation and an external test accuracy of 0.84, sensitivity of 0.71, and specificity of 0.91 using majority voting. Our results demonstrate that lightweight domain adaptation with self-supervision can effectively enhance PFM-based MIL pipelines for clinically challenging histopathology tasks. Code is Available at https://github.com/zhanghaoyue/DA_SSL_TURBT. --- ### Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization Authors: Daniel Melcer, Qi Chen, Wen-Hao Chiang, Shweta Garg, Pranav Garg, Christian Bock Published: 2025-12-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.13598v1 A well-engineered prompt can increase the performance of large language models; automatic prompt optimization techniques aim to increase performance without requiring human effort to tune the prompts. One leading class of prompt optimization techniques introduces the analogy of textual gradients. We investigate the behavior of these textual gradient methods through a series of experiments and case studies. While such methods often result in a performance improvement, our experiments suggest that the gradient analogy does not accurately explain their behavior. Our insights may inform the selection of prompt optimization strategies, and development of new approaches. --- ### Lighting in Motion: Spatiotemporal HDR Lighting Estimation Authors: Christophe Bolduc, Julien Philip, Li Ma, Mingming He, Paul Debevec, Jean-François Lalonde Published: 2025-12-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.13597v2 We present Lighting in Motion (LiMo), a diffusion-based approach to spatiotemporal lighting estimation. LiMo targets both realistic high-frequency detail prediction and accurate illuminance estimation. To account for both, we propose generating a set of mirrored and diffuse spheres at different exposures, based on their 3D positions in the input. Making use of diffusion priors, we fine-tune powerful existing diffusion models on a large-scale customized dataset of indoor and outdoor scenes, paired with spatiotemporal light probes. For accurate spatial conditioning, we demonstrate that depth alone is insufficient and we introduce a new geometric condition to provide the relative position of the scene to the target 3D position. Finally, we combine diffuse and mirror predictions at different exposures into a single HDRI map leveraging differentiable rendering. We thoroughly evaluate our method and design choices to establish LiMo as state-of-the-art for both spatial control and prediction accuracy. --- ### Verification of Unknown Dynamical Systems via Autoencoder Latent Space Authors: Robert Reed, Luca Laurenti, Morteza Lahijanian Published: 2025-12-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.13593v4 Formal verification provides a powerful framework for proving that dynamical systems satisfy their specifications. However, these techniques face scalability challenges in high-dimensional settings, as they often rely on state-space discretization which grows exponentially with dimension. Learning-based approaches to dimensionality reduction, utilizing neural networks and autoencoders, have shown great potential to alleviate this problem. However, ensuring correctness of latent space verification results remains an open question. In this work, we provide a formal approach to reduce the dimensionality of systems via convex autoencoders and learn the dynamics in the latent space through a kernel-based method. We then construct a finite abstraction from the learned model in the latent space and guarantee that the abstraction contains the true behaviors of the original system. We show that the verification results in the latent space can be mapped back to the original system. Finally, we demonstrate the approach on multiple systems, including a 26D system controlled by a neural network, showing significant scalability improvements. ---