# Research Papers — 2025-12 · bundle page 162 of 175

> Full-text markdown of papers #8051–8100 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/162
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/161.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/163.md)

### Rethinking Generalized BCIs: Benchmarking 340,000+ Unique Algorithmic Configurations for EEG Mental Command Decoding

Authors: Paul Barbaste, Olivier Oullier, Xavier Vasques
Published: 2025-12-02
Categories: q-bio.NC, cs.AI, cs.HC, cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2512.02978v1

Robust decoding and classification of brain patterns measured with electroencephalography (EEG) remains a major challenge for real-world (i.e. outside scientific lab and medical facilities) brain-computer interface (BCI) applications due to well documented inter- and intra-participant variability. Here, we present a large-scale benchmark evaluating over 340,000+ unique combinations of spatial and nonlinear EEG classification. Our methodological pipeline consists in combinations of Common Spatial Patterns (CSP), Riemannian geometry, functional connectivity, and fractal- or entropy-based features across three open-access EEG datasets. Unlike prior studies, our analysis operates at the per-participant level and across multiple frequency bands (8-15 Hz and 8-30 Hz), enabling direct assessment of both group-level performance and individual variability. Covariance tangent space projection (cov-tgsp) and CSP consistently achieved the highest average classification accuracies. However, their effectiveness was strongly dataset-dependent, and marked participant-level differences persisted, particularly in the most heterogeneous of the datasets. Importantly, nonlinear methods outperformed spatial approaches for specific individuals, underscoring the need for personalized pipeline selection. Our findings highlight that no universal 'one-size-fits-all' method can optimally decode EEG motor imagery patterns across all users or datasets. Future work will require adaptive, multimodal, and possibly novel approaches to fully address neurophysiological variability in practical BCI applications where the system can automatically adapt to what makes each user unique.

---

### Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities

Authors: Yuan Xiong, Ziqi Miao, Lijun Li, Chen Qian, Jie Li, Jing Shao
Published: 2025-12-02
Categories: cs.CV, cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2512.02973v1

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a secondary prompt. This approach underutilizes the unique potential of images to carry complex, contextual information. To address this gap, we propose a new image-centric attack method, Contextual Image Attack (CIA), which employs a multi-agent system to subtly embeds harmful queries into seemingly benign visual contexts using four distinct visualization strategies. To further enhance the attack's efficacy, the system incorporate contextual element enhancement and automatic toxicity obfuscation techniques. Experimental results on the MMSafetyBench-tiny dataset show that CIA achieves high toxicity scores of 4.73 and 4.83 against the GPT-4o and Qwen2.5-VL-72B models, respectively, with Attack Success Rates (ASR) reaching 86.31\% and 91.07\%. Our method significantly outperforms prior work, demonstrating that the visual modality itself is a potent vector for jailbreaking advanced MLLMs.

---

### BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection

Authors: Guowen Zhang, Chenhang He, Liyi Chen, Lei Zhang
Published: 2025-12-02
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.02972v1

Integrating LiDAR and camera information in the bird's eye view (BEV) representation has demonstrated its effectiveness in 3D object detection. However, because of the fundamental disparity in geometric accuracy between these sensors, indiscriminate fusion in previous methods often leads to degraded performance. In this paper, we propose BEVDilation, a novel LiDAR-centric framework that prioritizes LiDAR information in the fusion. By formulating image BEV features as implicit guidance rather than naive concatenation, our strategy effectively alleviates the spatial misalignment caused by image depth estimation errors. Furthermore, the image guidance can effectively help the LiDAR-centric paradigm to address the sparsity and semantic limitations of point clouds. Specifically, we propose a Sparse Voxel Dilation Block that mitigates the inherent point sparsity by densifying foreground voxels through image priors. Moreover, we introduce a Semantic-Guided BEV Dilation Block to enhance the LiDAR feature diffusion processing with image semantic guidance and long-range context capture. On the challenging nuScenes benchmark, BEVDilation achieves better performance than state-of-the-art methods while maintaining competitive computational efficiency. Importantly, our LiDAR-centric strategy demonstrates greater robustness to depth noise compared to naive fusion. The source code is available at https://github.com/gwenzhang/BEVDilation.

---

### Identification of Multivariate Measurement Error Models

Authors: Yingyao Hu
Published: 2025-12-02
Categories: econ.EM, stat.ML
arXiv: https://arxiv.org/abs/2512.02970v2

This paper develops new identification results for multidimensional continuous measurement-error models where all observed measurements are contaminated by potentially correlated errors and none provides an injective mapping of the latent distribution. Using third order cross moments, the paper constructs a three way tensor whose unique decomposition, guaranteed by Kruskal theorem, identifies the factor loading matrices. Starting with a linear structure, the paper recovers the full distribution of latent factors by constructing suitable measurements and applying scalar or multivariate versions of Kotlarski identity. As a result, the joint distribution of the latent vector and measurement errors is fully identified without requiring injective measurements, showing that multivariate latent structure can be recovered in broader settings than previously believed. Under injectivity, the paper also provides user-friendly testable conditions for identification. Finally, this paper provides general identification results for nonlinear models using a newly-defined generalized Kruskal rank - signal rank - of intergral operators. These results have wide applicability in empirical work involving noisy or indirect measurements, including factor models, survey data with reporting errors, mismeasured regressors in econometrics, and multidimensional latent-trait models in psychology and marketing, potentially enabling more robust estimation and interpretation when clean measurements are unavailable.

---

### Flexible Gravitational-Wave Parameter Estimation with Transformers

Authors: Annalena Kofler, Maximilian Dax, Stephen R. Green, Jonas Wildberger, Nihar Gupte, Jakob H. Macke, Jonathan Gair, Alessandra Buonanno, Bernhard Schölkopf
Published: 2025-12-02
Categories: gr-qc, astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2512.02968v2

Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of observations represent a growing challenge. Deep learning provides a powerful alternative to traditional inference, but existing neural models typically lack the flexibility to handle variations in data analysis settings. Such variations accommodate imperfect observations or are required for specialized tests, and could include changes in detector configurations, overall frequency ranges, or localized cuts. We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time. Applied to parameter estimation, we demonstrate that a single flexible model, called Dingo-T1, can (i) analyze 48 gravitational-wave events from the third LIGO-Virgo-KAGRA Observing Run under a wide range of analysis configurations, (ii) enable systematic studies of how detector and frequency configurations impact inferred posteriors, and (iii) perform inspiral-merger-ringdown consistency tests probing general relativity. Dingo-T1 also improves median sample efficiency on real events from a baseline of 1.4% to 4.2%. Our approach thus demonstrates flexible and scalable inference with a principled framework for handling missing or incomplete data, key capabilities for current and next-generation observatories.

---

### Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis

Authors: Jennifer Zvonek, Andrew Gillette
Published: 2025-12-02
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2512.02967v1

An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are prized for being more memory-efficient than traditional data stored on a lattice, many visualization tasks still require discretization to a regular grid. We present PruningAMR, an algorithm that builds a mesh with resolution adapted to geometric features encoded by the INR. To identify these geometric features, we use an interpolative decomposition pruning method on the weight matrices of the INR. The resulting pruned network is used to guide adaptive mesh refinement, enabling automatic mesh generation tailored to the underlying resolution of the function. Starting from a pre-trained INR--without access to its training data--we produce a variable resolution visualization with substantial memory savings.

---

### Lumos: Let there be Language Model System Certification

Authors: Isha Chaudhary, Vedaant Jain, Prineet Parhar, Kavya Sachdeva, Avaljot Singh, Sayan Ranu, Gagandeep Singh
Published: 2025-12-02
Categories: cs.PL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2512.02966v2

We introduce the first principled framework, Lumos, for specifying and formally certifying Language Model System (LMS) behaviors. Lumos is an imperative probabilistic programming DSL over graphs, with constructs to generate independent and identically distributed prompts for LMS. It offers a structured view of prompt distributions via graphs, forming random prompts from sampled subgraphs. Lumos supports certifying LMS for arbitrary prompt distributions via integration with statistical certifiers. We provide hybrid (operational and denotational) semantics for Lumos, providing a rigorous way to interpret the specifications. Using only a small set of composable constructs, Lumos can encode existing LMS specifications, including complex relational and temporal specifications. It also facilitates specifying new properties - we present the first safety specifications for vision-language models (VLMs) in autonomous driving scenarios developed with Lumos. Using these, we show that the state-of-the-art VLM Qwen-VL exhibits critical safety failures, producing incorrect and unsafe responses with at least 90% probability in right-turn scenarios under rainy driving conditions, revealing substantial safety risks. Lumos's modular structure allows easy modification of the specifications, enabling LMS certification to stay abreast with the rapidly evolving threat landscape. We further integrate a prompt-level deterministic verifier to obtain guarantees over the privacy of the LLM generation distribution over a prompt distribution. Lumos is simple to program in, requiring only a few constructs, as evidenced by state-of-the-art large language models generating correct Lumos specifications in zero-shot settings. Lumos is the first systematic and extensible language-based framework for specifying and certifying LMS behaviors, paving the way for a wider adoption of LMS certification.

---

### UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement

Authors: Yuhan Chen, Yicui Shi, Guofa Li, Guangrui Bai, Wenxuan Yu, Ying Fang, Wenbo Chu, Keqiang Li
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02965v2

Addressing the urgent need for high-performance real-time low-light image enhancement on resource-constrained edge devices in low-illumination scenarios such as nighttime and tunnels, this paper presents UltraFast-LiNET, an ultra-lightweight network designed for extreme efficiency. The proposed network introduces Dynamic Shift Convolution, DSConv, a highly compact operation with only 12 learnable parameters. By using DSConv to construct a Multi-Scale Shift Residual Block, MSRB, UltraFast-LiNET effectively enlarges the receptive field while maintaining an exceptionally small parameter count. To alleviate gradient instability during the training of lightweight models, we further propose a multi-level gradient-aware loss function that strengthens supervision signals across different feature levels. UltraFast-LiNET supports flexible parameter configurations, enabling the model size to be reduced to as few as 36 learnable parameters. Remarkably, with only 180 learnable parameters, UltraFast-LiNET achieves a PSNR of 19.81 dB on the LOL dataset, surpassing the current state-of-the-art by 0.08 dB. Experimental results demonstrate that the proposed method achieves an effective balance between millisecond-level real-time processing and superior enhancement quality under extreme computational constraints. These results highlight its chip-level computational efficiency and broad prospects for edge-side deployment.

---

### Layout Anything: One Transformer for Universal Room Layout Estimation

Authors: Md Sohag Mia, Muhammad Abdullah Adnan
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02952v1

We present Layout Anything, a transformer-based framework for indoor layout estimation that adapts the OneFormer's universal segmentation architecture to geometric structure prediction. Our approach integrates OneFormer's task-conditioned queries and contrastive learning with two key modules: (1) a layout degeneration strategy that augments training data while preserving Manhattan-world constraints through topology-aware transformations, and (2) differentiable geometric losses that directly enforce planar consistency and sharp boundary predictions during training. By unifying these components in an end-to-end framework, the model eliminates complex post-processing pipelines while achieving high-speed inference at 114ms. Extensive experiments demonstrate state-of-the-art performance across standard benchmarks, with pixel error (PE) of 5.43% and corner error (CE) of 4.02% on the LSUN, PE of 7.04% (CE 5.17%) on the Hedau and PE of 4.03% (CE 3.15%) on the Matterport3D-Layout datasets. The framework's combination of geometric awareness and computational efficiency makes it particularly suitable for augmented reality applications and large-scale 3D scene reconstruction tasks.

---

### Representation of Inorganic Synthesis Reactions and Prediction: Graphical Framework and Datasets

Authors: Samuel Andrello, Daniel Alabi, Simon J. L. Billinge
Published: 2025-12-02
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2512.02947v1

While machine learning has enabled the rapid prediction of inorganic materials with novel properties, the challenge of determining how to synthesize these materials remains largely unsolved. Previous work has largely focused on predicting precursors or reaction conditions, but only rarely on full synthesis pathways. We introduce the ActionGraph, a directed acyclic graph framework that encodes both the chemical and procedural structure, in terms of synthesis operations, of inorganic synthesis reactions. Using 13,017 text-mined solid-state synthesis reactions from the Materials Project, we show that incorporating PCA-reduced ActionGraph adjacency matrices into a $k$-nearest neighbors retrieval model significantly improves synthesis pathway prediction. While the ActionGraph framework only results in a 1.34% and 2.76% increase in precursor and operation F1 scores (average over varying numbers of PCA components) respectively, the operation length matching accuracy rises 3.4 times (from 15.8% to 53.3%). We observe an interesting trade-off where precursor prediction performance peaks at 10-11 PCA components while operation prediction continues improving up to 30 components. This suggests composition information dominates precursor selection while structural information is critical for operation sequencing. Overall, the ActionGraph framework demonstrates strong potential, and with further adoption, its full range of benefits can be effectively realized.

---

### Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

Authors: Lanxiang Hu, Abhilash Shankarampeta, Yixin Huang, Zilin Dai, Haoyang Yu, Yujie Zhao, Haoqiang Kang, Daniel Zhao, Tajana Rosing, Hao Zhang
Published: 2025-12-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.02942v1

The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical outcome modeling under diverse conditions. However, existing video benchmarks are physical commonsense-based, offering limited insight into video models' scientific reasoning capability. We introduce VideoScience-Bench, a benchmark designed to evaluate undergraduate-level scientific understanding in video models. Each prompt encodes a composite scientific scenario that requires understanding and reasoning across multiple scientific concepts to generate the correct phenomenon. The benchmark comprises 200 carefully curated prompts spanning 14 topics and 103 concepts in physics and chemistry. We conduct expert-annotated evaluations across seven state-of-the-art video models in T2V and I2V settings along five dimensions: Prompt Consistency, Phenomenon Congruency, Correct Dynamism, Immutability, and Spatio-Temporal Continuity. Using a VLM-as-a-Judge to assess video generations, we observe strong correlation with human assessments. To the best of our knowledge, VideoScience-Bench is the first benchmark to evaluate video models not only as generators but also as reasoners, requiring their generations to demonstrate scientific understanding consistent with expected physical and chemical phenomena. Our data and evaluation code are available at: \href{https://github.com/hao-ai-lab/VideoScience}{github.com/hao-ai-lab/VideoScience}.

---

### LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization

Authors: Zhihan Xiao, Lin Liu, Yixin Gao, Xiaopeng Zhang, Haoxuan Che, Songping Mai, Qi Tian
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02933v2

Text-guided video editing, particularly for object removal and addition, remains a challenging task due to the need for precise spatial and temporal consistency. Existing methods often rely on auxiliary masks or reference images for editing guidance, which limits their scalability and generalization. To address these issues, we propose LoVoRA, a novel framework for mask-free video object removal and addition using object-aware localization mechanism. Our approach utilizes a unique dataset construction pipeline that integrates image-to-video translation, optical flow-based mask propagation, and video inpainting, enabling temporally consistent edits. The core innovation of LoVoRA is its learnable object-aware localization mechanism, which provides dense spatio-temporal supervision for both object insertion and removal tasks. By leveraging a Diffusion Mask Predictor, LoVoRA achieves end-to-end video editing without requiring external control signals during inference. Extensive experiments and human evaluation demonstrate the effectiveness and high-quality performance of LoVoRA. https://cz-5f.github.io/LoVoRA.github.io

---

### EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis

Authors: Yancheng Zhang, Guangyu Sun, Chen Chen
Published: 2025-12-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.02932v1

Novel view synthesis (NVS) is crucial in computer vision and graphics, with wide applications in AR, VR, and autonomous driving. While 3D Gaussian Splatting (3DGS) enables real-time rendering with high appearance fidelity, it suffers from multi-view inconsistencies, limiting geometric accuracy. In contrast, 2D Gaussian Splatting (2DGS) enforces multi-view consistency but compromises texture details. To address these limitations, we propose Exchangeable Gaussian Splatting (EGGS), a hybrid representation that integrates 2D and 3D Gaussians to balance appearance and geometry. To achieve this, we introduce Hybrid Gaussian Rasterization for unified rendering, Adaptive Type Exchange for dynamic adaptation between 2D and 3D Gaussians, and Frequency-Decoupled Optimization that effectively exploits the strengths of each type of Gaussian representation. Our CUDA-accelerated implementation ensures efficient training and inference. Extensive experiments demonstrate that EGGS outperforms existing methods in rendering quality, geometric accuracy, and efficiency, providing a practical solution for high-quality NVS.

---

### DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation

Authors: Ying Yang, Zhengyao Lv, Tianlin Pan, Haofan Wang, Binxin Yang, Hubery Yin, Chen Li, Chenyang Si
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02931v1

In this paper, we investigate the underexplored challenge of sample diversity in autoregressive (AR) generative models with bitwise visual tokenizers. We first analyze the factors that limit diversity in bitwise AR models and identify two key issues: (1) the binary classification nature of bitwise modeling, which restricts the prediction space, and (2) the overly sharp logits distribution, which causes sampling collapse and reduces diversity. Building on these insights, we propose DiverseAR, a principled and effective method that enhances image diversity without sacrificing visual quality. Specifically, we introduce an adaptive logits distribution scaling mechanism that dynamically adjusts the sharpness of the binary output distribution during sampling, resulting in smoother predictions and greater diversity. To mitigate potential fidelity loss caused by distribution smoothing, we further develop an energy-based generation path search algorithm that avoids sampling low-confidence tokens, thereby preserving high visual quality. Extensive experiments demonstrate that DiverseAR substantially improves sample diversity in bitwise autoregressive image generation.

---

### Fast Gaussian Process Approximations for Autocorrelated Data

Authors: Ahmadreza Chokhachian, Matthias Katzfuss, Yu Ding
Published: 2025-12-02
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.02925v1

This paper is concerned with the problem of how to speed up computation for Gaussian process models trained on autocorrelated data. The Gaussian process model is a powerful tool commonly used in nonlinear regression applications. Standard regression modeling assumes random samples and an independently, identically distributed noise. Various fast approximations that speed up Gaussian process regression work under this standard setting. But for autocorrelated data, failing to account for autocorrelation leads to a phenomenon known as temporal overfitting that deteriorates model performance on new test instances. To handle autocorrelated data, existing fast Gaussian process approximations have to be modified; one such approach is to segment the originally correlated data points into blocks in which the blocked data are de-correlated. This work explains how to make some of the existing Gaussian process approximations work with blocked data. Numerical experiments across diverse application datasets demonstrate that the proposed approaches can remarkably accelerate computation for Gaussian process regression on autocorrelated data without compromising model prediction performance.

---

### AutoNeural: Co-Designing Vision-Language Models for NPU Inference

Authors: Wei Chen, Liangmin Wu, Yunhai Hu, Zhiyuan Li, Zhiyuan Cheng, Yicheng Qian, Lingyue Zhu, Zhipeng Hu, Luoyi Liang, Qiang Tang, Zhen Liu, Han Yang
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02924v3

While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary factors: the quantization brittleness of Vision Transformers (ViTs) and the I/O-bound nature of autoregressive attention mechanisms, which fail to utilize the high arithmetic throughput of NPUs. To bridge this gap, we propose AutoNeural, an NPU-native VLM architecture co-designed for integer-only inference. We replace the standard ViT encoder with a MobileNetV5-style backbone utilizing depthwise separable convolutions, which ensures bounded activation distributions for stable INT4/8/16 quantization. Complementing this, our language backbone integrates State-Space Model (SSM) principles with Transformer layers, employing efficient gated convolutions to achieve linear-time complexity. This hybrid design eliminates the heavy memory I/O overhead of Key-Value caching during generation. Our approach delivers substantial efficiency gains, reducing quantization error of vision encoder by up to 7x and end-to-end latency by 14x compared to conventional baselines. The AutoNeural also delivers 3x decoding speed and 4x longer context window than the baseline. We validate these improvements via a real-world automotive case study on the Qualcomm SA8295P SoC, demonstrating real-time performance for cockpit applications. Our results highlight that rethinking model topology specifically for NPU constraints is a prerequisite for robust multi-modal edge intelligence.

---

### Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation

Authors: Ziniu Zhang, Minxuan Duan, Haris N. Koutsopoulos, Hongyang R. Zhang
Published: 2025-12-02
Categories: cs.LG, cs.CV, cs.SI
arXiv: https://arxiv.org/abs/2512.02920v3

We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes. Previous work for predicting accident occurrences relies primarily on road network structural features while overlooking physical and environmental information from the road surface and its surroundings. In this work, we construct a large multimodal dataset spanning six U.S. states, containing nine million traffic accident records from official sources, and one million high-resolution satellite images for each node of the road network. Additionally, every node is annotated with features such as the region's weather statistics and road type (e.g., residential vs. motorway), and each edge is annotated with traffic volume information (i.e., Average Annual Daily Traffic). Utilizing this dataset, we conduct a comprehensive evaluation of multimodal learning methods that integrate both visual and network embeddings. Our findings show that integrating both data modalities improves prediction accuracy, achieving an average AUROC of $90.1\%$, a $3.7\%$ gain over graph neural network models that use only graph structures. With the improved embeddings, we conduct a causal analysis using a matching estimator to identify the key factors influencing traffic accidents. We find that accident rates rise by $24\%$ under higher precipitation, by $22\%$ on higher-speed roads such as motorways, and by $29\%$ due to seasonal patterns, after adjusting for other confounding factors. Ablation studies confirm that satellite imagery features are essential for achieving accurate prediction.

---

### Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning

Authors: Zhonghao He, Tianyi Qiu, Hirokazu Shirado, Maarten Sap
Published: 2025-12-02
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.02914v1

Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to provide accurate, truthful, and reliable information. However, emerging evidence suggests that iterative reasoning may foster belief entrenchment and confirmation bias, rather than enhancing truth-seeking behavior. In this study, we propose a systematic evaluation framework for belief entrenchment in LLM reasoning by leveraging the Martingale property from Bayesian statistics. This property implies that, under rational belief updating, the expected value of future beliefs should remain equal to the current belief, i.e., belief updates are unpredictable from the current belief. We propose the unsupervised, regression-based Martingale Score to measure violations of this property, which signal deviation from the Bayesian ability of updating on new evidence. In open-ended problem domains including event forecasting, value-laden questions, and academic paper review, we find such violations to be widespread across models and setups, where the current belief positively predicts future belief updates, a phenomenon which we term belief entrenchment. We identify the models, reasoning techniques, and domains more prone to belief entrenchment. Finally, we validate the Martingale Score by showing that it predicts ground-truth accuracy on problem domains where ground truth labels are available. This indicates that, while designed as an unsupervised metric that operates even in domains without access to ground truth, the Martingale Score is a useful proxy of the truth-seeking ability of a reasoning process.

---

### Hypothesis Testing for Generalized Thurstone Models

Authors: Anuran Makur, Japneet Singh
Published: 2025-12-02
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2512.02912v1

In this work, we develop a hypothesis testing framework to determine whether pairwise comparison data is generated by an underlying \emph{generalized Thurstone model} $\mathcal{T}_F$ for a given choice function $F$. While prior work has predominantly focused on parameter estimation and uncertainty quantification for such models, we address the fundamental problem of minimax hypothesis testing for $\mathcal{T}_F$ models. We formulate this testing problem by introducing a notion of separation distance between general pairwise comparison models and the class of $\mathcal{T}_F$ models. We then derive upper and lower bounds on the critical threshold for testing that depend on the topology of the observation graph. For the special case of complete observation graphs, this threshold scales as $Θ((nk)^{-1/2})$, where $n$ is the number of agents and $k$ is the number of comparisons per pair. Furthermore, we propose a hypothesis test based on our separation distance, construct confidence intervals, establish time-uniform bounds on the probabilities of type I and II errors using reverse martingale techniques, and derive minimax lower bounds using information-theoretic methods. Finally, we validate our results through experiments on synthetic and real-world datasets.

---

### In Silico Development of Psychometric Scales: Feasibility of Representative Population Data Simulation with LLMs

Authors: Enrico Cipriani, Pavel Okopnyi, Danilo Menicucci, Simone Grassini
Published: 2025-12-02
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.02910v2

Developing and validating psychometric scales requires large samples, multiple testing phases, and substantial resources. Recent advances in Large Language Models (LLMs) enable the generation of synthetic participant data by prompting models to answer items while impersonating individuals of specific demographic profiles, potentially allowing in silico piloting before real data collection. Across four preregistered studies (N = circa 300 each), we tested whether LLM-simulated datasets can reproduce the latent structures and measurement properties of human responses. In Studies 1-2, we compared LLM-generated data with real datasets for two validated scales; in Studies 3-4, we created new scales using EFA on simulated data and then examined whether these structures generalized to newly collected human samples. Simulated datasets replicated the intended factor structures in three of four studies and showed consistent configural and metric invariance, with scalar invariance achieved for the two newly developed scales. However, correlation-based tests revealed substantial differences between real and synthetic datasets, and notable discrepancies appeared in score distributions and variances. Thus, while LLMs capture group-level latent structures, they do not approximate individual-level data properties. Simulated datasets also showed full internal invariance across gender. Overall, LLM-generated data appear useful for early-stage, group-level psychometric prototyping, but not as substitutes for individual-level validation. We discuss methodological limitations, risks of bias and data pollution, and ethical considerations related to in silico psychometric simulations.

---

### MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding

Authors: Fan Yang, Xingping Dong, Xin Yu, Wenhan Luo, Wei Liu, Kaihao Zhang
Published: 2025-12-02
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2512.02906v3

Understanding high-resolution (HR) images remains a critical challenge for multimodal large language models (MLLMs). Recent approaches leverage vision-based retrieval-augmented generation (RAG) to retrieve query-relevant crops from HR images, improving understanding capacity of MLLMs. However, this paradigm often leads to object fragmentation, resulting in semantic bias and incomplete retrieval, while also introducing false positives from irrelevant background patches. To address these issues, we propose Multi-resolution Retrieval-Detection (MRD), a training-free framework that enhances HR image understanding from both local and global perspectives. Locally, MRD enforces cross-scale semantic consistency via multi-resolution semantic fusion to mitigate single-resolution bias and alleviate object fragmentation. Globally, it integrates open-vocabulary object detection (OVD) as localization priors within a unified framework. Extensive experiments across multiple MLLMs on HR image benchmarks demonstrate that MRD achieves state-of-the-art (SOTA) performance on both single-object and multi-object understanding tasks. Code will be available at: https://github.com/yf0412/MRD.

---

### Towards a fully differentiable digital twin for solar cells

Authors: Marie Louise Schubert, Houssam Metni, Jan David Fischbach, Benedikt Zerulla, Marjan Krstić, Ulrich W. Paetzold, Seyedamir Orooji, Olivier J. J. Ronsin, Yasin Ameslon, Jens Harting, Thomas Kirchartz, Sandheep Ravishankar et al.
Published: 2025-12-02
Categories: physics.comp-ph, cs.AI
arXiv: https://arxiv.org/abs/2512.02904v1

Maximizing energy yield (EY) - the total electric energy generated by a solar cell within a year at a specific location - is crucial in photovoltaics (PV), especially for emerging technologies. Computational methods provide the necessary insights and guidance for future research. However, existing simulations typically focus on only isolated aspects of solar cells. This lack of consistency highlights the need for a framework unifying all computational levels, from material to cell properties, for accurate prediction and optimization of EY prediction. To address this challenge, a differentiable digital twin, Sol(Di)$^2$T, is introduced to enable comprehensive end-to-end optimization of solar cells. The workflow starts with material properties and morphological processing parameters, followed by optical and electrical simulations. Finally, climatic conditions and geographic location are incorporated to predict the EY. Each step is either intrinsically differentiable or replaced with a machine-learned surrogate model, enabling not only accurate EY prediction but also gradient-based optimization with respect to input parameters. Consequently, Sol(Di)$^2$T extends EY predictions to previously unexplored conditions. Demonstrated for an organic solar cell, the proposed framework marks a significant step towards tailoring solar cells for specific applications while ensuring maximal performance.

---

### VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling

Authors: Weiqi Li, Quande Zhang, Ruifeng Zhai, Liang Lin, Guangrun Wang
Published: 2025-12-02
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.02902v2

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling, rather than Physical Modeling. To address this, we propose a one-shot adaptation framework that recalibrates visual representations through lightweight, learnable updates. Our first method, Feature Token Modulation (FTM), applies a global affine transformation to visual tokens and improves Libero viewpoint accuracy from 48.5% to 87.1% with only 4K parameters. Building on this, Feature Linear Adaptation (FLA) introduces low-rank updates to the ViT encoder, achieving 90.8% success with 4.7M parameters -- matching LoRA-scale finetuning at far lower cost. Together, these results reveal substantial untapped robustness in pretrained VLA models and demonstrate that targeted, minimal visual adaptation is sufficient to restore viewpoint generalization.

---

### Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\{\pm 1, \pm i\}$

Authors: Feiyu Wang, Xinyu Tan, Bokai Huang, Yihao Zhang, Guoan Wang, Peizhuang Cong, Tong Yang
Published: 2025-12-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.02901v3

Large language models (LLMs) have revolutionized artificial intelligence, yet their massive memory and computational demands necessitate aggressive quantization, increasingly pushing representations toward the theoretical limit of a single bit. While complex-valued LLMs, such as iFairy, offer a superior chance for low-bit representation compared to real-valued counterparts, they require training from scratch, preventing the utilization of the vast ecosystem of pre-trained real-valued foundation models. Here we present Fairy2i, a universal framework that transforms pre-trained real-valued layers into an equivalent widely-linear complex form, enabling extremely low-bit quantization while reusing existing checkpoints. By proving a lossless mathematical equivalence between real and widely-linear maps, we convert standard Transformers into the complex domain and employ a phase-aware quantization scheme with a highly efficient codebook of fourth roots of unity. Furthermore, we introduce a recursive residual quantization mechanism that iteratively minimizes quantization error, allowing inference to proceed via efficient multiplication-free accumulation. We demonstrate that Fairy2i restores the performance of LLaMA-2 7B at an effective 2-bit precision to levels nearly comparable with full-precision baselines, significantly outperforming state-of-the-art real-valued binary and ternary quantization methods. This work bridges the gap between the representational efficiency of complex-valued arithmetic and the practical utility of pre-trained models, paving a new way for efficient inference on commodity hardware. We open-source the Fairy2i model and code at https://huggingface.co/PKU-DS-LAB/Fairy2i-W2 and https://github.com/PKULab1806/Fairy2i-W2.

---

### Glance: Accelerating Diffusion Models with 1 Sample

Authors: Zhuobai Dong, Rui Zhao, Songjie Wu, Junchao Yi, Linjie Li, Zhengyuan Yang, Lijuan Wang, Alex Jinpeng Wang
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02899v2

Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference steps. Previous efforts on fewer-step distillation attempt to skip redundant steps by training compact student models, yet they often suffer from heavy retraining costs and degraded generalization. In this work, we take a different perspective: we accelerate smartly, not evenly, applying smaller speedups to early semantic stages and larger ones to later redundant phases. We instantiate this phase-aware strategy with two experts that specialize in slow and fast denoising phases. Surprisingly, instead of investing massive effort in retraining student models, we find that simply equipping the base model with lightweight LoRA adapters achieves both efficient acceleration and strong generalization. We refer to these two adapters as Slow-LoRA and Fast-LoRA. Through extensive experiments, our method achieves up to 5 acceleration over the base model while maintaining comparable visual quality across diverse benchmarks. Remarkably, the LoRA experts are trained with only 1 samples on a single V100 within one hour, yet the resulting models generalize strongly on unseen prompts.

---

### Model-Based Diagnosis with Multiple Observations: A Unified Approach for C Software and Boolean Circuits

Authors: Pedro Orvalho, Marta Kwiatkowska, Mikoláš Janota, Vasco Manquinho
Published: 2025-12-02
Categories: cs.SE, cs.AI, cs.LO, cs.SC
arXiv: https://arxiv.org/abs/2512.02898v1

Debugging is one of the most time-consuming and expensive tasks in software development and circuit design. Several formula-based fault localisation (FBFL) methods have been proposed, but they fail to guarantee a set of diagnoses across all failing tests or may produce redundant diagnoses that are not subset-minimal, particularly for programs/circuits with multiple faults. This paper introduces CFaults, a novel fault localisation tool for C software and Boolean circuits with multiple faults. CFaults leverages Model-Based Diagnosis (MBD) with multiple observations and aggregates all failing test cases into a unified Maximum Satisfiability (MaxSAT) formula. Consequently, our method guarantees consistency across observations and simplifies the fault localisation procedure. Experimental results on three benchmark sets, two of C programs, TCAS and C-Pack-IPAs, and one of Boolean circuits, ISCAS85, show that CFaults is faster at localising faults in C software than other FBFL approaches such as BugAssist, SNIPER, and HSD. On the ISCAS85 benchmark, CFaults is generally slower than HSD; however, it localises faults in only 6% fewer circuits, demonstrating that it remains competitive in this domain. Furthermore, CFaults produces only subset-minimal diagnoses of faulty statements, whereas the other approaches tend to enumerate redundant diagnoses (e.g., BugAssist and SNIPER).

---

### Polar Perspectives: Evaluating 2-D LiDAR Projections for Robust Place Recognition with Visual Foundation Models

Authors: Pierpaolo Serio, Giulio Pisaneschi, Andrea Dan Ryals, Vincenzo Infantino, Lorenzo Gentilini, Valentina Donzella, Lorenzo Pollini
Published: 2025-12-02
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.02897v1

This work presents a systematic investigation into how alternative LiDAR-to-image projections affect metric place recognition when coupled with a state-of-the-art vision foundation model. We introduce a modular retrieval pipeline that controls for backbone, aggregation, and evaluation protocol, thereby isolating the influence of the 2-D projection itself. Using consistent geometric and structural channels across multiple datasets and deployment scenarios, we identify the projection characteristics that most strongly determine discriminative power, robustness to environmental variation, and suitability for real-time autonomy. Experiments with different datasets, including integration into an operational place recognition policy, validate the practical relevance of these findings and demonstrate that carefully designed projections can serve as an effective surrogate for end-to-end 3-D learning in LiDAR place recognition.

---

### MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm

Authors: Wei Chen, Chaoqun Du, Feng Gu, Wei He, Qizhen Li, Zide Liu, Xuhao Pan, Chang Ren, Xudong Rao, Chenfeng Wang, Tao Wei, Chengjun Yu et al.
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02895v2

We present MindGPT-4ov, a multimodal large language model (MLLM) that introduces a general post-training paradigm spanning data production, model training, and efficient deployment. It achieves state-of-the-art performance across multiple benchmarks at low cost, effectively enhancing the foundational capabilities of MLLMs and the generalization ability. Focusing on data construction, supervised fine-tuning strategies, and multimodal reinforcement learning methods, this work proposes three key innovations: (1) An information density-based data generation scheme, integrated with a dual-dimensional tree-structured label system, enabling automated generation of high-quality cross-domain data. (2) A collaborative curriculum supervised fine-tuning approach that balances the injection of domain-specific knowledge with the preservation of general capabilities. (3) A hybrid reinforcement learning paradigm that enhances reasoning ability while simultaneously addressing multi-objective optimization such as diversity exploration, maintenance of multimodal perception, and response conciseness. Moreover, we implement a series of infrastructure optimizations, such as 5D parallel training, operator optimization, and inference quantization to enhance training and inference efficiency while reducing the cost of domain adaptation. Experimental results demonstrate that the MindGPT-4ov model outperforms state-of-the-art models on benchmarks such as MMBench, MMStar, MathVision, and MathVista. In addition, MindGPT-4ov also demonstrates superior user experience in vertical domain tasks, enabling a seamless transition from academic research to industrial deployment. MindGPT-4ov provides a general post-training paradigm applicable to a wide range of MLLMs. The model weights, datasets, and code for the Qwen3-VL-based variants will be recently open-sourced to support the community's development of MLLMs.

---

### Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules

Authors: Amr Mohamed, Yang Zhang, Michalis Vazirgiannis, Guokan Shang
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02892v1

Diffusion large language models (dLLMs) offer a promising alternative to autoregressive models, but their practical utility is severely hampered by slow, iterative sampling. We present SchED, a training-free, model-agnostic early-exit algorithm that aggregates full-span logit margins and halts decoding once a smooth, progress-dependent confidence threshold is met. We evaluated SchED on two dLLM families (Dream and LLaDA), in base and instruction-tuned variants across ten benchmarks spanning downstream tasks including multiple-choice question answering (MCQ), math, long-form QA/summarization, and translation. SchED delivers large, stable accelerations: on instruction-tuned models, it achieves $3.8$-$4.0\times$ speedups while retaining $99.8$-$100\%$ of the baseline score on average. On base models, SchED yields consistent speedup gains with $99.1$-$100\%$ performance retention, with up to $2.34\times$ under more aggressive settings. Using a conservative speed metric that heavily penalizes quality loss (QPS, $γ{=}4$), we show that SchED is robust and clearly outperforms prior confidence-based early-exit methods, which break down on long-form generation. An entropy analysis of the model's token predictions reveals that instruction tuning speeds up the decay of predictive entropy. By turning genuine confidence stabilization into computational savings, SchED makes dLLM decoding substantially more efficient.

---

### OptPO: Optimal Rollout Allocation for Test-time Policy Optimization

Authors: Youkang Wang, Jian Wang, Rubing Chen, Tianyi Zeng, Xiao-Yong Wei, Qing Li
Published: 2025-12-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.02882v1

Test-time policy optimization enables large language models (LLMs) to adapt to distribution shifts by leveraging feedback from self-generated rollouts. However, existing methods rely on fixed-budget majority voting to estimate rewards, incurring substantial computational redundancy. We propose Optimal Rollout Allocation for Test-time Policy Optimization (OptPO), a principled framework that adaptively allocates inference budgets. By formulating the voting process as a Bayesian sequential probability ratio test, OptPO dynamically halts sampling once the posterior confidence in a consensus answer exceeds a specified threshold. Crucially, it utilizes the retained rollouts for on-policy updates, seamlessly integrating with algorithms like PPO or GRPO without requiring ground-truth labels. Across diverse reasoning benchmarks, OptPO significantly reduces rollout overhead compared to fixed-sample baselines while preserving or improving accuracy. By unifying statistically optimal stopping with test-time learning, OptPO offers a computationally efficient paradigm for test-time adaptation. The source code will be open upon acceptance at https://open-upon-acceptance.

---

### The future of AI in critical mineral exploration

Authors: Jef Caers
Published: 2025-12-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.02879v1

The energy transition through increased electrification has put the worlds attention on critical mineral exploration Even with increased investments a decrease in new discoveries has taken place over the last two decades Here I propose a solution to this problem where AI is implemented as the enabler of a rigorous scientific method for mineral exploration that aims to reduce cognitive bias and false positives drive down the cost of exploration I propose a new scientific method that is based on a philosophical approach founded on the principles of Bayesianism and falsification In this approach data acquisition is in the first place seen as a means to falsify human generated hypothesis Decision of what data to acquire next is quantified with verifiable metrics and based on rational decision making A practical protocol is provided that can be used as a template in any exploration campaign However in order to make this protocol practical various form of artificial intelligence are needed I will argue that the most important form are one novel unsupervised learning methods that collaborate with domain experts to better understand data and generate multiple competing geological hypotheses and two humanintheloop AI algorithms that can optimally plan various geological geophysical geochemical and drilling data acquisition where uncertainty reduction of geological hypothesis precedes the uncertainty reduction on grade and tonnage

---

### Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning

Authors: Haonan Wang, Chao Du, Kenji Kawaguchi, Tianyu Pang
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02874v1

Majority voting has proven effective for close-ended question answering by aggregating parallel reasoning traces. However, it is not directly applicable to open-ended reasoning, such as code generation and web-based deep research, where a "majority" over complete solutions is ill-defined. We introduce ThinkMerge, a training-free, plug-and-play decoding strategy that runs K parallel reasoning traces and averages their next-token logits at synchronization points to produce a single coherent output. ThinkMerge integrates seamlessly with vLLM/SGLang and remains compatible with standard decoding techniques such as Top-p/Top-k. Empirically, it matches or surpasses majority voting on AIME and GPQA, while delivering consistent gains on open-ended coding tasks: on LiveCodeBench (hard), pass@1 improves by +8.28% for DeepCoder-14B-Preview and +7.58% for Qwen3-8B. Beyond code, we further show that ThinkMerge improves web-based deep-research agents (e.g., WebSailor-7B/32B) across GAIA, BrowseComp-en/zh, and XbenchDeepSearch. These results demonstrate that parallel test-time scaling can benefit open-ended reasoning without relying on voting over complete outputs.

---

### Taming Camera-Controlled Video Generation with Verifiable Geometry Reward

Authors: Zhaoqing Wang, Xiaobo Xia, Zhuolin Bie, Jinlin Liu, Dongdong Yu, Jia-Wang Bian, Changhu Wang
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02870v1

Recent advances in video diffusion models have remarkably improved camera-controlled video generation, but most methods rely solely on supervised fine-tuning (SFT), leaving online reinforcement learning (RL) post-training largely underexplored. In this work, we introduce an online RL post-training framework that optimizes a pretrained video generator for precise camera control. To make RL effective in this setting, we design a verifiable geometry reward that delivers dense segment-level feedback to guide model optimization. Specifically, we estimate the 3D camera trajectories for both generated and reference videos, divide each trajectory into short segments, and compute segment-wise relative poses. The reward function then compares each generated-reference segment pair and assigns an alignment score as the reward signal, which helps alleviate reward sparsity and improve optimization efficiency. Moreover, we construct a comprehensive dataset featuring diverse large-amplitude camera motions and scenes with varied subject dynamics. Extensive experiments show that our online RL post-training clearly outperforms SFT baselines across multiple aspects, including camera-control accuracy, geometric consistency, and visual quality, demonstrating its superiority in advancing camera-controlled video generation.

---

### Assessing the performance of correlation-based multi-fidelity neural emulators

Authors: Cristian J. Villatoro, Gianluca Geraci, Daniele E. Schiavazzi
Published: 2025-12-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.02868v1

Outer loop tasks such as optimization, uncertainty quantification or inference can easily become intractable when the underlying high-fidelity model is computationally expensive. Similarly, data-driven architectures typically require large datasets to perform predictive tasks with sufficient accuracy. A possible approach to mitigate these challenges is the development of multi-fidelity emulators, leveraging potentially biased, inexpensive low-fidelity information while correcting and refining predictions using scarce, accurate high-fidelity data. This study investigates the performance of multi-fidelity neural emulators, neural networks designed to learn the input-to-output mapping by integrating limited high-fidelity data with abundant low-fidelity model solutions. We investigate the performance of such emulators for low and high-dimensional functions, with oscillatory character, in the presence of discontinuities, for collections of models with equal and dissimilar parametrization, and for a possibly large number of potentially corrupted low-fidelity sources. In doing so, we consider a large number of architectural, hyperparameter, and dataset configurations including networks with a different amount of spectral bias (Multi-Layered Perceptron, Siren and Kolmogorov Arnold Network), various mechanisms for coordinate encoding, exact or learnable low-fidelity information, and for varying training dataset size. We further analyze the added value of the multi-fidelity approach by conducting equivalent single-fidelity tests for each case, quantifying the performance gains achieved through fusing multiple sources of information.

---

### MICCAI STSR 2025 Challenge: Semi-Supervised Teeth and Pulp Segmentation and CBCT-IOS Registration

Authors: Yaqi Wang, Zhi Li, Chengyu Wu, Jun Liu, Yifan Zhang, Jialuo Chen, Jiaxue Ni, Qian Luo, Jin Liu, Can Han, Changkai Ji, Zhi Qin Tan et al.
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02867v1

Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but annotated data scarcity limits automated solutions for pulp canal segmentation and cross-modal registration. To benchmark semi-supervised learning (SSL) in this domain, we organized the STSR 2025 Challenge at MICCAI 2025, featuring two tasks: (1) semi-supervised segmentation of teeth and pulp canals in CBCT, and (2) semi-supervised rigid registration of CBCT and IOS. We provided 60 labeled and 640 unlabeled IOS samples, plus 30 labeled and 250 unlabeled CBCT scans with varying resolutions and fields of view. The challenge attracted strong community participation, with top teams submitting open-source deep learning-based SSL solutions. For segmentation, leading methods used nnU-Net and Mamba-like State Space Models with pseudo-labeling and consistency regularization, achieving a Dice score of 0.967 and Instance Affinity of 0.738 on the hidden test set. For registration, effective approaches combined PointNetLK with differentiable SVD and geometric augmentation to handle modality gaps; hybrid neural-classical refinement enabled accurate alignment despite limited labels. All data and code are publicly available at https://github.com/ricoleehduu/STS-Challenge-2025 to ensure reproducibility.

---

### Spectral Joint Subspace Estimation for Heterogeneous Multi-View Data: Geometry and Reweighting

Authors: Jingyang Li, Zhongyuan Lyu
Published: 2025-12-02
Categories: math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2512.02866v2

Many modern datasets consist of multiple related matrices measured on a common set of units, with the goal of recovering a shared low-dimensional subspace. The Angle-based Joint and Individual Variation Explained (AJIVE) framework addresses this problem through equal-weight aggregation, which can be suboptimal when views exhibit statistical heterogeneity in signal-to-noise ratios and dimensions, as well as structural heterogeneity from individual components. For equal-weight AJIVE, we show that the previously identified ``non-diminishing'' error barrier is geometry dependent: under near-orthogonal deterministic loading orientations, the second-order term is reduced, whereas under sign-symmetric random loadings, it is centered and averages out, yielding a $K^{-1/2}$-type rate without iterative refinement. Under a majority sign-alignment condition in rank-one setting, a bias at the squared single-view perturbation scale can persist. For general weights, we establish error bounds that disentangle the two layers of heterogeneity, and propose HeteroJIVE, the weighted AJIVE estimator using an explicit weight that is optimal whenever its identifiability gap is constant. We also provide a data-driven plug-in implementation of HeteroJIVE, together with an optional geometry-adaptive extension of this data-driven procedure. Simulations and analyses of multi-omics and image data illustrate the practical benefits of HeteroJIVE.

---

### Leveraging generative adversarial networks with spatially adaptive denormalization for multivariate stochastic seismic data inversion

Authors: Roberto Miele, Leonardo Azevedo
Published: 2025-12-02
Categories: physics.geo-ph, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2512.02863v1

Probabilistic seismic inverse modeling often requires the prediction of both spatially correlated geological heterogeneities (e.g., facies) and continuous parameters (e.g., rock and elastic properties). Generative adversarial networks (GANs) provide an efficient training-image-based simulation framework capable of reproducing complex geological models with high accuracy and comparably low generative cost. However, their application in stochastic geophysical inversion for multivariate property prediction is limited, as representing multiple coupled properties requires large and unstable networks with high memory and training demands. A more recent variant of GANs with spatially adaptive denormalization (SPADE-GAN) enables the direct conditioning of facies spatial distributions on local probability maps. Leveraging on such features, an iterative geostatistical inversion algorithm is proposed, SPADE-GANInv, integrating a pre-trained SPADE-GAN with geostatistical simulation, for the prediction of facies and multiple correlated continuous properties from seismic data. The SPADE-GAN is trained to reproduce realistic facies geometries, while sequential stochastic co-simulation predicts the spatial variability of the facies-dependent continuous properties. At each iteration, a set of subsurface realizations is generated and used to compute synthetic seismic data. The realizations providing the highest similarity coefficient to the observed data are used to update the subsurface probability models in the next iteration. The method is demonstrated on both 2-D synthetic scenarios and field data, targeting the prediction of facies, porosity, and acoustic impedance from full-stack seismic data. Results show that the algorithm enables accurate multivariate prediction, mitigates the impact of biased prior data, and accommodates additional local conditioning such as well logs.

---

### RFOP: Rethinking Fusion and Orthogonal Projection for Face-Voice Association

Authors: Abdul Hannan, Furqan Malik, Hina Jabbar, Syed Suleman Sadiq, Mubashir Noman
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02860v1

Face-voice association in multilingual environment challenge 2026 aims to investigate the face-voice association task in multilingual scenario. The challenge introduces English-German face-voice pairs to be utilized in the evaluation phase. To this end, we revisit the fusion and orthogonal projection for face-voice association by effectively focusing on the relevant semantic information within the two modalities. Our method performs favorably on the English-German data split and ranked 3rd in the FAME 2026 challenge by achieving the EER of 33.1.

---

### Adaptive Decentralized Federated Learning for Robust Optimization

Authors: Shuyuan Wu, Feifei Wang, Yuan Gao, Rui Wang, Hansheng Wang
Published: 2025-12-02
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2512.02852v2

In decentralized federated learning (DFL), the presence of abnormal clients, often caused by noisy or poisoned data, can significantly disrupt the learning process and degrade the overall robustness of the model. Previous methods on this issue often require a sufficiently large number of normal neighboring clients or prior knowledge of reliable clients, which reduces the practical applicability of DFL. To address these limitations, we develop here a novel adaptive DFL (aDFL) approach for robust estimation. The key idea is to adaptively adjust the learning rates of clients. By assigning smaller rates to suspicious clients and larger rates to normal clients, aDFL mitigates the negative impact of abnormal clients on the global model in a fully adaptive way. Our theory does not put any stringent conditions on neighboring nodes and requires no prior knowledge. A rigorous convergence analysis is provided to guarantee the oracle property of aDFL. Extensive numerical experiments demonstrate the superior performance of the aDFL method.

---

### Are Detectors Fair to Indian IP-AIGC? A Cross-Generator Study

Authors: Vishal Dubey, Pallavi Tyagi
Published: 2025-12-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.02850v1

Modern image editors can produce identity-preserving AIGC (IP-AIGC), where the same person appears with new attire, background, or lighting. The robustness and fairness of current detectors in this regime remain unclear, especially for under-represented populations. We present what we believe is the first systematic study of IP-AIGC detection for Indian and South-Asian faces, quantifying cross-generator generalization and intra-population performance. We assemble Indian-focused training splits from FairFD and HAV-DF, and construct two held-out IP-AIGC test sets (HIDF-img-ip-genai and HIDF-vid-ip-genai) using commercial web-UI generators (Gemini and ChatGPT) with identity-preserving prompts. We evaluate two state-of-the-art detectors (AIDE and Effort) under pretrained (PT) and fine-tuned (FT) regimes and report AUC, AP, EER, and accuracy. Fine-tuning yields strong in-domain gains (for example, Effort AUC 0.739 to 0.944 on HAV-DF-test; AIDE EER 0.484 to 0.259), but consistently degrades performance on held-out IP-AIGC for Indian cohorts (for example, AIDE AUC 0.923 to 0.563 on HIDF-img-ip-genai; Effort 0.740 to 0.533), which indicates overfitting to training-generator cues. On non-IP HIDF images, PT performance remains high, which suggests a specific brittleness to identity-preserving edits rather than a generic distribution shift. Our study establishes IP-AIGC-Indian as a challenging and practically relevant scenario and motivates representation-preserving adaptation and India-aware benchmark curation to close generalization gaps in AIGC detection.

---

### GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace

Authors: Mikołaj Sacha, Hammad Jafri, Mattie Terzolo, Ayan Sinha, Andrew Rabinovich
Published: 2025-12-02
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2512.02849v1

Recommending matches in a text-rich, dynamic two-sided marketplace presents unique challenges due to evolving content and interaction graphs. We introduce GraphMatch, a new large-scale recommendation framework that fuses pre-trained language models with graph neural networks to overcome these challenges. Unlike prior approaches centered on standalone models, GraphMatch is a comprehensive recipe built on powerful text encoders and GNNs working in tandem. It employs adversarial negative sampling alongside point-in-time subgraph training to learn representations that capture both the fine-grained semantics of evolving text and the time-sensitive structure of the graph. We evaluated extensively on interaction data from Upwork, a leading labor marketplace, at large scale, and discuss our approach towards low-latency inference suitable for real-time use. In our experiments, GraphMatch outperforms language-only and graph-only baselines on matching tasks while being efficient at runtime. These results demonstrate that unifying language and graph representations yields a highly effective solution to text-rich, dynamic two-sided recommendations, bridging the gap between powerful pretrained LMs and large-scale graphs in practice.

---

### Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?

Authors: Manuel Benavent-Lledo, Konstantinos Bacharidis, Victoria Manousaki, Konstantinos Papoutsakis, Antonis Argyros, Jose Garcia-Rodriguez
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02846v1

Anticipating actions before they occur is a core challenge in action understanding research. While conventional methods rely on extracting and aggregating temporal information from videos, as humans we can often predict upcoming actions by observing a single moment from a scene, when given sufficient context. Can a model achieve this competence? The short answer is yes, although its effectiveness depends on the complexity of the task. In this work, we investigate to what extent video aggregation can be replaced with alternative modalities. To this end, based on recent advances in visual feature extraction and language-based reasoning, we introduce AAG, a method for Action Anticipation at a Glimpse. AAG combines RGB features with depth cues from a single frame for enhanced spatial reasoning, and incorporates prior action information to provide long-term context. This context is obtained either through textual summaries from Vision-Language Models, or from predictions generated by a single-frame action recognizer. Our results demonstrate that multimodal single-frame action anticipation using AAG can perform competitively compared to both temporally aggregated video baselines and state-of-the-art methods across three instructional activity datasets: IKEA-ASM, Meccano, and Assembly101.

---

### Bangla Hate Speech Classification with Fine-tuned Transformer Models

Authors: Yalda Keivan Jafari, Krishno Dey
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02845v1

Hate speech recognition in low-resource languages remains a difficult problem due to insufficient datasets, orthographic heterogeneity, and linguistic variety. Bangla is spoken by more than 230 million people of Bangladesh and India (West Bengal). Despite the growing need for automated moderation on social media platforms, Bangla is significantly under-represented in computational resources. In this work, we study Subtask 1A and Subtask 1B of the BLP 2025 Shared Task on hate speech detection. We reproduce the official baselines (e.g., Majority, Random, Support Vector Machine) and also produce and consider Logistic Regression, Random Forest, and Decision Tree as baseline methods. We also utilized transformer-based models such as DistilBERT, BanglaBERT, m-BERT, and XLM-RoBERTa for hate speech classification. All the transformer-based models outperformed baseline methods for the subtasks, except for DistilBERT. Among the transformer-based models, BanglaBERT produces the best performance for both subtasks. Despite being smaller in size, BanglaBERT outperforms both m-BERT and XLM-RoBERTa, which suggests language-specific pre-training is very important. Our results highlight the potential and need for pre-trained language models for the low-resource Bangla language.

---

### VLM as Strategist: Adaptive Generation of Safety-critical Testing Scenarios via Guided Diffusion

Authors: Xinzheng Wu, Junyi Chen, Naiting Zhong, Yong Shen
Published: 2025-12-02
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.02844v1

The safe deployment of autonomous driving systems (ADSs) relies on comprehensive testing and evaluation. However, safety-critical scenarios that can effectively expose system vulnerabilities are extremely sparse in the real world. Existing scenario generation methods face challenges in efficiently constructing long-tail scenarios that ensure fidelity, criticality, and interactivity, while particularly lacking real-time dynamic response capabilities to the vehicle under test (VUT). To address these challenges, this paper proposes a safety-critical testing scenario generation framework that integrates the high-level semantic understanding capabilities of Vision Language Models (VLMs) with the fine-grained generation capabilities of adaptive guided diffusion models. The framework establishes a three-layer hierarchical architecture comprising a strategic layer for VLM-directed scenario generation objective determination, a tactical layer for guidance function formulation, and an operational layer for guided diffusion execution. We first establish a high-quality fundamental diffusion model that learns the data distribution of real driving scenarios. Next, we design an adaptive guided diffusion method that enables real-time, precise control of background vehicles (BVs) in closed-loop simulation. The VLM is then incorporated to autonomously generate scenario generation objectives and guidance functions through deep scenario understanding and risk reasoning, ultimately guiding the diffusion model to achieve VLM-directed scenario generation. Experimental results demonstrate that the proposed method can efficiently generate realistic, diverse, and highly interactive safety-critical testing scenarios. Furthermore, case studies validate the adaptability and VLM-directed generation performance of the proposed method.

---

### Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages

Authors: Lechen Zhang, Yusheng Zhou, Tolga Ergen, Lajanugen Logeswaran, Moontae Lee, David Jurgens
Published: 2025-12-02
Categories: cs.CL, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2512.02841v1

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt to operate reliably across languages. This paper presents a comprehensive study of how different system prompts steer models toward accurate and robust cross-lingual behavior. We propose a unified four-dimensional evaluation framework to assess system prompts in multilingual environments. Through large-scale experiments on five languages, three LLMs, and three benchmarks, we uncover that certain prompt components, such as CoT, emotion, and scenario, correlate with robust multilingual behavior. We develop a prompt optimization framework for multilingual settings and show it can automatically discover prompts that improve all metrics by 5-10%. Finally, we analyze over 10 million reasoning units and find that more performant system prompts induce more structured and consistent reasoning patterns, while reducing unnecessary language-switching. Together, we highlight system prompt optimization as a scalable path to accurate and robust multilingual LLM behavior.

---

### promptolution: A Unified, Modular Framework for Prompt Optimization

Authors: Tom Zehle, Timo Heiß, Moritz Schlager, Matthias Aßenmacher, Matthias Feurer
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02840v2

Prompt optimization has become crucial for enhancing the performance of large language models (LLMs) across a broad range of tasks. Although many research papers demonstrate its effectiveness, practical adoption is hindered because existing implementations are often tied to unmaintained, isolated research codebases or require invasive integration into application frameworks. To address this, we introduce promptolution, a unified, modular open-source framework that provides all components required for prompt optimization within a single extensible system for both practitioners and researchers. It integrates multiple contemporary discrete prompt optimizers, supports systematic and reproducible benchmarking, and returns framework-agnostic prompt strings, enabling seamless integration into existing LLM pipelines while remaining agnostic to the underlying model implementation.

---

### ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning

Authors: Yifan Li, Yingda Yin, Lingting Zhu, Weikai Chen, Shengju Qian, Xin Wang, Yanwei Fu
Published: 2025-12-02
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.02835v1

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .

---

### Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach

Authors: Siyuan Yang, Yang Zhang, Haoran He, Ling Pan, Xiu Li, Chenjia Bai, Xuelong Li
Published: 2025-12-02
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.02834v1

Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs incorporate diverse data modes in the pre-training stage, and the finetuning dataset often contains demonstration data collected in a kinematically suboptimal or undesirable way, it exists redundant action modes that are irrelevant to the success action modes of the downstream task. Specifically, we observe a critical inference-time fragility among various sampled noises after supervised finetuning of pre-trained VLAs. In this paper, we attribute this instability to the distribution shift between the VLA policy and the policy induced by stable success modes of the downstream task dataset. Thus, we propose \textbf{TACO}, a test-time-scaling (TTS) framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks. The VLA models integrated with TACO can execute the actions with maximum pseudo-count from all sampled action chunks, thereby preventing distribution shifts while preserving the generalization ability of VLAs since the constraint is applied only during inference. Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits compared to RL update, especially for flow or diffusion-based VLAs which are difficult to perform RL update due to denoising process. Extensive experiments across four simulation benchmarks (RoboTwin2.0, Robotwin, LIBERO, SimplerEnv) and a dual-arm platform demonstrate that our method significantly improves the inference stability and success rates in downstream-task adaptations.

---

### A Comparative Study on How Data Normalization Affects Zero-Shot Generalization in Time Series Foundation Models

Authors: Ihab Ahmed, Denis Krompaß, Cheng Feng, Volker Tresp
Published: 2025-12-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.02833v2

We investigate input normalization methods for Time-Series Foundation Models (TSFMs). While normalization is well-studied in dataset-specific time-series models, it remains overlooked in TSFMs where generalization is critical. Time-series data, unlike text or images, exhibits significant scale variation across domains and channels, coupled with non-stationarity, can undermine TSFM performance regardless of architectural complexity. Through systematic evaluation across four architecturally diverse TSFMs, we empirically establish REVIN as the most efficient approach, reducing zero-shot MASE by 89\% relative to an un-normalized baseline and by 44\% versus other normalization methods, while matching the best in-domain accuracy (0.84 MASE) without any dataset-level preprocessing -- yielding the highest accuracy-efficiency trade-off. Yet its effect utilization depends on architectural design choices and optimization objective, particularly with respect to training loss scale sensitivity and model type (probabilistic, point-forecast, or LLM-based models).

---

### Revisiting Theory of Contrastive Learning for Domain Generalization

Authors: Ali Alvandi, Mina Rezaei
Published: 2025-12-02
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2512.02831v1

Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in the latent space. Existing theoretical methods assume that downstream task classes are drawn from the same latent class distribution used during the pretraining phase. However, in real-world settings, downstream tasks may not only exhibit distributional shifts within the same label space but also introduce new or broader label spaces, leading to domain generalization challenges. In this work, we introduce novel generalization bounds that explicitly account for both types of mismatch: domain shift and domain generalization. Specifically, we analyze scenarios where downstream tasks either (i) draw classes from the same latent class space but with shifted distributions, or (ii) involve new label spaces beyond those seen during pretraining. Our analysis reveals how the performance of contrastively learned representations depends on the statistical discrepancy between pretraining and downstream distributions. This extended perspective allows us to derive provable guarantees on the performance of learned representations on average classification tasks involving class distributions outside the pretraining latent class set.

---