# Research Papers — 2025-12 · bundle page 148 of 175

> Full-text markdown of papers #7351–7400 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/148
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/147.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/149.md)

### DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution

Authors: L. D. M. S. Sai Teja, N. Siva Gopala Krishna, Ufaq Khan, Muhammad Haris Khan, Atul Mishra
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04838v2

In the age of advanced large language models (LLMs), the boundaries between human and AI-generated text are becoming increasingly blurred. We address the challenge of segmenting mixed-authorship text, that is identifying transition points in text where authorship shifts from human to AI or vice-versa, a problem with critical implications for authenticity, trust, and human oversight. We introduce a novel framework, called Info-Mask for mixed authorship detection that integrates stylometric cues, perplexity-driven signals, and structured boundary modeling to accurately segment collaborative human-AI content. To evaluate the robustness of our system against adversarial perturbations, we construct and release an adversarial benchmark dataset Mixed-text Adversarial setting for Segmentation (MAS), designed to probe the limits of existing detectors. Beyond segmentation accuracy, we introduce Human-Interpretable Attribution (HIA overlays that highlight how stylometric features inform boundary predictions, and we conduct a small-scale human study assessing their usefulness. Across multiple architectures, Info-Mask significantly improves span-level robustness under adversarial conditions, establishing new baselines while revealing remaining challenges. Our findings highlight both the promise and limitations of adversarially robust, interpretable mixed-authorship detection, with implications for trust and oversight in human-AI co-authorship.

---

### DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution

Authors: L. D. M. S. Sai Teja, N. Siva Gopala Krishna, Ufaq Khan, Muhammad Haris Khan, Partha Pakray, Atul Mishra
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04838v1

In the age of advanced large language models (LLMs), the boundaries between human and AI-generated text are becoming increasingly blurred. We address the challenge of segmenting mixed-authorship text, that is identifying transition points in text where authorship shifts from human to AI or vice-versa, a problem with critical implications for authenticity, trust, and human oversight. We introduce a novel framework, called Info-Mask for mixed authorship detection that integrates stylometric cues, perplexity-driven signals, and structured boundary modeling to accurately segment collaborative human-AI content. To evaluate the robustness of our system against adversarial perturbations, we construct and release an adversarial benchmark dataset Mixed-text Adversarial setting for Segmentation (MAS), designed to probe the limits of existing detectors. Beyond segmentation accuracy, we introduce Human-Interpretable Attribution (HIA overlays that highlight how stylometric features inform boundary predictions, and we conduct a small-scale human study assessing their usefulness. Across multiple architectures, Info-Mask significantly improves span-level robustness under adversarial conditions, establishing new baselines while revealing remaining challenges. Our findings highlight both the promise and limitations of adversarially robust, interpretable mixed-authorship detection, with implications for trust and oversight in human-AI co-authorship.

---

### A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World

Authors: Jikang Cheng, Renye Yan, Zhiyuan Yan, Yaozhong Gan, Xueyi Zhang, Zhongyuan Wang, Wei Peng, Ling Liang
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04837v1

Existing methods for deepfake detection aim to develop generalizable detectors. Although "generalizable" is the ultimate target once and for all, with limited training forgeries and domains, it appears idealistic to expect generalization that covers entirely unseen variations, especially given the diversity of real-world deepfakes. Therefore, introducing large-scale multi-domain data for training can be feasible and important for real-world applications. However, within such a multi-domain scenario, the differences between multiple domains, rather than the subtle real/fake distinctions, dominate the feature space. As a result, despite detectors being able to relatively separate real and fake within each domain (i.e., high AUC), they struggle with single-image real/fake judgments in domain-unspecified conditions (i.e., low ACC). In this paper, we first define a new research paradigm named Multi-In-Domain Face Forgery Detection (MID-FFD), which includes sufficient volumes of real-fake domains for training. Then, the detector should provide definitive real-fake judgments to the domain-unspecified inputs, which simulate the frame-by-frame independent detection scenario in the real world. Meanwhile, to address the domain-dominant issue, we propose a model-agnostic framework termed DevDet (Developer for Detector) to amplify real/fake differences and make them dominant in the feature space. DevDet consists of a Face Forgery Developer (FFDev) and a Dose-Adaptive detector Fine-Tuning strategy (DAFT). Experiments demonstrate our superiority in predicting real-fake under the MID-FFD scenario while maintaining original generalization ability to unseen data.

---

### Are LLMs Truly Multilingual? Exploring Zero-Shot Multilingual Capability of LLMs for Information Retrieval: An Italian Healthcare Use Case

Authors: Vignesh Kumar Kembu, Pierandrea Morandini, Marta Bianca Maria Ranzini, Antonino Nocera
Published: 2025-12-04
Categories: cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2512.04834v1

Large Language Models (LLMs) have become a key topic in AI and NLP, transforming sectors like healthcare, finance, education, and marketing by improving customer service, automating tasks, providing insights, improving diagnostics, and personalizing learning experiences. Information extraction from clinical records is a crucial task in digital healthcare. Although traditional NLP techniques have been used for this in the past, they often fall short due to the complexity, variability of clinical language, and high inner semantics in the free clinical text. Recently, Large Language Models (LLMs) have become a powerful tool for better understanding and generating human-like text, making them highly effective in this area. In this paper, we explore the ability of open-source multilingual LLMs to understand EHRs (Electronic Health Records) in Italian and help extract information from them in real-time. Our detailed experimental campaign on comorbidity extraction from EHR reveals that some LLMs struggle in zero-shot, on-premises settings, and others show significant variation in performance, struggling to generalize across various diseases when compared to native pattern matching and manual annotations.

---

### BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis

Authors: Manuel Ladron de Guevara, Jinmo Rhee, Ardavan Bidgoli, Vaidas Razgaitis, Michael Bergin
Published: 2025-12-04
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2512.04832v3

We present a BIM-native tokenization for room-level layout synthesis in Building Information Modeling (BIM) scenes. The core contribution is representational: we encode each room as a sequence of BIM-Token Bundles, realized as columns of a sparse attribute-feature matrix that unifies categorical and continuous attributes of walls, openings, and entities under wall-referenced (translation/scale-invariant) coordinates. A mixed-type embedding module produces a unified token vector from this matrix; a single Transformer backbone is then trained in two modes: encoder-only for room embeddings and retrieval, and encoder-decoder for autoregressive entity placement, which we call Data-Driven Entity Prediction (DDEP). On a controlled same-data benchmark with shared ontology and evaluation harness, DDEP outperforms ATISS and BLT baselines bridged into our representation, with ablations identifying joint continuous-feature embedding and entity ordering as primary drivers. Encoder embeddings cluster rooms by type more tightly than large general-purpose text encoders, which in turn retain an edge on within-type ranking. We frame this work as evidence that modestly sized, domain-specific sequence models over well-designed BIM tokenizations are a useful primitive for constraint-aware spatial generation, complementary to general-purpose LLMs/VLMs which we also benchmark.

---

### Tokenizing Buildings: A Transformer for Layout Synthesis

Authors: Manuel Ladron de Guevara, Jinmo Rhee, Ardavan Bidgoli, Vaidas Razgaitis, Michael Bergin
Published: 2025-12-04
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2512.04832v1

We introduce Small Building Model (SBM), a Transformer-based architecture for layout synthesis in Building Information Modeling (BIM) scenes. We address the question of how to tokenize buildings by unifying heterogeneous feature sets of architectural elements into sequences while preserving compositional structure. Such feature sets are represented as a sparse attribute-feature matrix that captures room properties. We then design a unified embedding module that learns joint representations of categorical and possibly correlated continuous feature groups. Lastly, we train a single Transformer backbone in two modes: an encoder-only pathway that yields high-fidelity room embeddings, and an encoder-decoder pipeline for autoregressive prediction of room entities, referred to as Data-Driven Entity Prediction (DDEP). Experiments across retrieval and generative layout synthesis show that SBM learns compact room embeddings that reliably cluster by type and topology, enabling strong semantic retrieval. In DDEP mode, SBM produces functionally sound layouts, with fewer collisions and boundary violations and improved navigability.

---

### FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis

Authors: Shijie Chen, Peixi Peng
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04830v1

Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting large-scale evaluation and training. While recent generative models demonstrate strong visual realism, they struggle to jointly achieve interpolation consistency and extrapolation realism without per-scene optimization. To address this, we propose FreeGen, a feed-forward reconstruction-generation co-training framework for free-viewpoint driving scene synthesis. The reconstruction model provides stable geometric representations to ensure interpolation consistency, while the generation model performs geometry-aware enhancement to improve realism at unseen viewpoints. Through co-training, generative priors are distilled into the reconstruction model to improve off-trajectory rendering, and the refined geometry in turn offers stronger structural guidance for generation. Experiments demonstrate that FreeGen achieves state-of-the-art performance for free-viewpoint driving scene synthesis.

---

### Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing

Authors: Rasul Tutunov, Alexandre Maraval, Antoine Grosnit, Xihan Li, Jun Wang, Haitham Bou-Ammar
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04829v2

Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptography, crystallography, and medical imaging, the problem remains unresolved: beyond a few special dimensions, neither optimal packings nor tight upper bounds are known. Even a major breakthrough in dimension $n=8$, later recognised with a Fields Medal, underscores its difficulty. A leading technique for upper bounds, the three-point method, reduces the problem to solving large, high-precision semidefinite programs (SDPs). Because each candidate SDP may take days to evaluate, standard data-intensive AI approaches are infeasible. We address this challenge by formulating SDP construction as a sequential decision process, the SDP game, in which a policy assembles SDP formulations from a set of admissible components. Using a sample-efficient model-based framework that combines Bayesian optimisation with Monte Carlo Tree Search, we obtain new state-of-the-art upper bounds in dimensions $4-16$, showing that model-based search can advance computational progress in longstanding geometric problems. Together, these results demonstrate that sample-efficient, model-based search can make tangible progress on mathematically rigid, evaluation limited problems, pointing towards a complementary direction for AI-assisted discovery beyond large-scale LLM-driven exploration.

---

### Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing

Authors: Rasul Tutunov, Alexandre Maraval, Antoine Grosnit, Xihan Li, Jun Wang, Haitham Bou-Ammar
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04829v1

Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptography, crystallography, and medical imaging, the problem remains unresolved: beyond a few special dimensions, neither optimal packings nor tight upper bounds are known. Even a major breakthrough in dimension $n=8$, later recognised with a Fields Medal, underscores its difficulty. A leading technique for upper bounds, the three-point method, reduces the problem to solving large, high-precision semidefinite programs (SDPs). Because each candidate SDP may take days to evaluate, standard data-intensive AI approaches are infeasible. We address this challenge by formulating SDP construction as a sequential decision process, the SDP game, in which a policy assembles SDP formulations from a set of admissible components. Using a sample-efficient model-based framework that combines Bayesian optimisation with Monte Carlo Tree Search, we obtain new state-of-the-art upper bounds in dimensions $4-16$, showing that model-based search can advance computational progress in longstanding geometric problems. Together, these results demonstrate that sample-efficient, model-based search can make tangible progress on mathematically rigid, evaluation limited problems, pointing towards a complementary direction for AI-assisted discovery beyond large-scale LLM-driven exploration.

---

### Contract-Driven QoE Auditing for Speech and Singing Services: From MOS Regression to Service Graphs

Authors: Wenzhang Du
Published: 2025-12-04
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2512.04827v1

Subjective mean opinion scores (MOS) remain the de-facto target for non-intrusive speech and singing quality assessment. However, MOS is a scalar that collapses heterogeneous user expectations, ignores service-level objectives, and is difficult to compare across deployment graphs. We propose a contract-driven QoE auditing framework: each service graph G is evaluated under a set of human-interpretable experience contracts C, yielding a contract-level satisfaction vector Q(G, C). We show that (i) classical MOS regression is a special case with a degenerate contract set, (ii) contract-driven quality is more stable than MOS under graph view transformations (e.g., pooling by system vs. by system type), and (iii) the effective sample complexity of learning contracts is governed by contract semantics rather than merely the dimensionality of C. We instantiate the framework on URGENT2024 MOS (6.9k speech utterances with raw rating vectors) and SingMOS v1 (7,981 singing clips; 80 systems). On URGENT, we train a contract-aware neural auditor on self-supervised WavLM embeddings; on SingMOS, we perform contract-driven graph auditing using released rating vectors and metadata without decoding audio. Empirically, our auditor matches strong MOS predictors in MOS accuracy while providing calibrated contract probabilities; on SingMOS, Q(G, C) exhibits substantially smaller cross-view drift than raw MOS and graph-only baselines; on URGENT, difficulty curves reveal that mis-specified "simple" contracts can be harder to learn than richer but better aligned contract sets.

---

### Enabling Ethical AI: A case study in using Ontological Context for Justified Agentic AI Decisions

Authors: Liam McGee, James Harvey, Lucy Cull, Andreas Vermeulen, Bart-Floris Visscher, Malvika Sharan
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04822v1

In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate, correct, and extend these structures, with their feedback used to improve subsequent models. Authors show how this process captures tacit institutional knowledge, improves response quality and efficiency, and mitigates institutional amnesia. We argue for a shift from post-hoc explanation to justifiable Agentic AI, where decisions are grounded in explicit, inspectable evidence and reasoning accessible to both experts and non-specialists.

---

### LatentFM: A Latent Flow Matching Approach for Generative Medical Image Segmentation

Authors: Ngoc Huynh Trinh, Hoang Anh Nguyen Kim, Hai Toan Nguyen, Quoc Long Tran
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04821v4

Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and attracted significant attention as a simulation-free flow-based framework capable of learning exact data densities. Motivated by these advances, we propose LatentFM, a flow-based model operating in the latent space for medical image segmentation. To model the data distribution, we first design two variational autoencoders (VAEs) to encode both medical images and their corresponding masks into a lower-dimensional latent space. We then estimate a conditional velocity field that guides the flow based on the input image. By sampling multiple latent representations, our method synthesizes diverse segmentation outputs whose pixel-wise variance reliably captures the underlying data distribution, enabling both highly accurate and uncertainty-aware predictions. Furthermore, we generate confidence maps that quantify the model certainty, providing clinicians with richer information for deeper analysis. We conduct experiments on two datasets, ISIC-2018 and CVC-Clinic, and compare our method with several prior baselines, including both deterministic and generative approach models. Through comprehensive evaluations, both qualitative and quantitative results show that our approach achieves superior segmentation accuracy while remaining highly efficient in the latent space.

---

### RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS

Authors: Chuanyu Fu, Guanying Chen, Yuqi Zhang, Kunbin Yao, Yuan Xiong, Chuan Huang, Shuguang Cui, Yasuyuki Matsushita, Xiaochun Cao
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04815v1

3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling in-the-wild scenes affected by transient objects and illuminations, leading to artifacts in the rendered images. We identify that the Gaussian densification process, while enhancing scene detail capture, unintentionally contributes to these artifacts by growing additional Gaussians that model transient disturbances and illumination variations. To address this, we propose RobustSplat++, a robust solution based on several critical designs. First, we introduce a delayed Gaussian growth strategy that prioritizes optimizing static scene structure before allowing Gaussian splitting/cloning, mitigating overfitting to transient objects in early optimization. Second, we design a scale-cascaded mask bootstrapping approach that first leverages lower-resolution feature similarity supervision for reliable initial transient mask estimation, taking advantage of its stronger semantic consistency and robustness to noise, and then progresses to high-resolution supervision to achieve more precise mask prediction. Third, we incorporate the delayed Gaussian growth strategy and mask bootstrapping with appearance modeling to handling in-the-wild scenes including transients and illuminations. Extensive experiments on multiple challenging datasets show that our method outperforms existing methods, clearly demonstrating the robustness and effectiveness of our method.

---

### Shared Multi-modal Embedding Space for Face-Voice Association

Authors: Christopher Simic, Korbinian Riedhammer, Tobias Bocklet
Published: 2025-12-04
Categories: cs.SD, cs.CV
arXiv: https://arxiv.org/abs/2512.04814v1

The FAME 2026 challenge comprises two demanding tasks: training face-voice associations combined with a multilingual setting that includes testing on languages on which the model was not trained. Our approach consists of separate uni-modal processing pipelines with general face and voice feature extraction, complemented by additional age-gender feature extraction to support prediction. The resulting single-modal features are projected into a shared embedding space and trained with an Adaptive Angular Margin (AAM) loss. Our approach achieved first place in the FAME 2026 challenge, with an average Equal-Error Rate (EER) of 23.99%.

---

### EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture

Authors: Xin He, Longhui Wei, Jianbo Ouyang, Minghui Liao, Lingxi Xie, Qi Tian
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04810v5

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the number of tokens required for generation. This also ensures the training balance between understanding and generation tasks by applying the same compression ratio to images. 2) Channel-wise concatenation instead of token-wise concatenation among visual understanding and generation tokens, which further reduces the visual tokens in unified architectures. 3) A shared-and-decoupled network that enables mutual improvements across tasks while meeting the task-specific modeling requirements. 4) A mixture-of-experts mechanism adopted for visual understanding encoder, which substantially improves perceptual capabilities with a few parameters increase. Extensive experiments have shown that EMMA-4B can significantly outperform state-of-the-art unified multimodal approaches (e.g., BAGEL-7B) in both efficiency and performance, while also achieving competitive results compared to recent multimodal understanding and generation experts (e.g., Qwen3-VL and Qwen-Image). We believe that EMMA lays a solid foundation for the future development of unified multimodal architectures.

---

### Setting up for failure: automatic discovery of the neural mechanisms of cognitive errors

Authors: Puria Radmard, Paul M. Bays, Máté Lengyel
Published: 2025-12-04
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2512.04808v2

Discovering the neural mechanisms underpinning cognition is one of the grand challenges of neuroscience. However, previous approaches for building models of RNN dynamics that explain behaviour required iterative refinement of architectures and/or optimisation objectives, resulting in a piecemeal, and mostly heuristic, human-in-the-loop process. Here, we offer an alternative approach that automates the discovery of viable RNN mechanisms by explicitly training RNNs to reproduce behaviour, including the same characteristic errors and suboptimalities, that humans and animals produce in a cognitive task. Achieving this required two main innovations. First, as the amount of behavioural data that can be collected in experiments is often too limited to train RNNs, we use a non-parametric generative model of behavioural responses to produce surrogate data for training RNNs. Second, to capture all relevant statistical aspects of the data, we developed a novel diffusion model-based approach for training RNNs. To showcase the potential of our approach, we chose a visual working memory task as our test-bed, as behaviour in this task is well known to produce response distributions that are patently multimodal (due to swap errors). The resulting network dynamics correctly qualitative features of macaque neural data. Importantly, these results were not possible to obtain with more traditional approaches, i.e., when only a limited set of behavioural signatures (rather than the full richness of behavioural response distributions) were fitted, or when RNNs were trained for task optimality (instead of reproducing behaviour). Our approach also yields novel predictions about the mechanism of swap errors, which can be readily tested in experiments. These results suggest that fitting RNNs to rich patterns of behaviour provides a powerful way to automatically discover mechanisms of important cognitive functions.

---

### 287,872 Supermassive Black Holes Masses: Deep Learning Approaching Reverberation Mapping Accuracy

Authors: Yuhao Lu, HengJian SiTu, Jie Li, Yixuan Li, Yang Liu, Wenbin Lin, Yu Wang
Published: 2025-12-04
Categories: astro-ph.GA, astro-ph.HE, astro-ph.IM, cs.AI
arXiv: https://arxiv.org/abs/2512.04803v1

We present a population-scale catalogue of 287,872 supermassive black hole masses with high accuracy. Using a deep encoder-decoder network trained on optical spectra with reverberation-mapping (RM) based labels of 849 quasars and applied to all SDSS quasars up to $z=4$, our method achieves a root-mean-square error of $0.058$\,dex, a relative uncertainty of $\approx 14\%$, and coefficient of determination $R^{2}\approx0.91$ with respect to RM-based masses, far surpassing traditional single-line virial estimators. Notably, the high accuracy is maintained for both low ($<10^{7.5}\,M_\odot$) and high ($>10^{9}\,M_\odot$) mass quasars, where empirical relations are unreliable.

---

### DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors

Authors: Gianluca Barmina, Nathalie Carmen Hau Norman, Peter Schneider-Kamp, Lukas Galke Poech
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04799v2

We present an enhanced benchmark for evaluating linguistic acceptability in Danish. We first analyze the most common errors found in written Danish. Based on this analysis, we introduce a set of fourteen corruption functions that generate incorrect sentences by systematically introducing errors into existing correct Danish sentences. To ensure the accuracy of these corruptions, we assess their validity using both manual and automatic methods. The results are then used as a benchmark for evaluating Large Language Models on a linguistic acceptability judgement task. Our findings demonstrate that this extension is both broader and more comprehensive than the current state of the art. By incorporating a greater variety of corruption types, our benchmark provides a more rigorous assessment of linguistic acceptability, increasing task difficulty, as evidenced by the lower performance of LLMs on our benchmark compared to existing ones. Our results also suggest that our benchmark has a higher discriminatory power which allows to better distinguish well-performing models from low-performing ones.

---

### SIMA 2: A Generalist Embodied Agent for Virtual Worlds

Authors: SIMA team, Adrian Bolton, Alexander Lerchner, Alexandra Cordell, Alexandre Moufarek, Andrew Bolt, Andrew Lampinen, Anna Mitenkova, Arne Olav Hallingstad, Bojan Vujatovic, Bonnie Li, Cong Lu et al.
Published: 2025-12-04
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.04797v1

We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.

---

### YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biases

Authors: Gongyu Chen, Xiaoyu Zhang, Zhenqiang Weng, Junjie Zheng, Da Shen, Chaofan Ding, Wei-Qiang Zhang, Zihao Chen
Published: 2025-12-04
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.04793v1

Singing voice conversion (SVC) aims to render the target singer's timbre while preserving melody and lyrics. However, existing zero-shot SVC systems remain fragile in real songs due to harmony interference, F0 errors, and the lack of inductive biases for singing. We propose YingMusic-SVC, a robust zero-shot framework that unifies continuous pre-training, robust supervised fine-tuning, and Flow-GRPO reinforcement learning. Our model introduces a singing-trained RVC timbre shifter for timbre-content disentanglement, an F0-aware timbre adaptor for dynamic vocal expression, and an energy-balanced rectified flow matching loss to enhance high-frequency fidelity. Experiments on a graded multi-track benchmark show that YingMusic-SVC achieves consistent improvements over strong open-source baselines in timbre similarity, intelligibility, and perceptual naturalness, especially under accompanied and harmony-contaminated conditions, demonstrating its effectiveness for real-world SVC deployment.

---

### LaFiTe: A Generative Latent Field for 3D Native Texturing

Authors: Chia-Hao Chen, Zi-Xin Zou, Yan-Pei Cao, Ze Yuan, Guan Luo, Xiaojuan Qi, Ding Liang, Song-Hai Zhang, Yuan-Chen Guo
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04786v1

Generating high-fidelity, seamless textures directly on 3D surfaces, what we term 3D-native texturing, remains a fundamental open challenge, with the potential to overcome long-standing limitations of UV-based and multi-view projection methods. However, existing native approaches are constrained by the absence of a powerful and versatile latent representation, which severely limits the fidelity and generality of their generated textures. We identify this representation gap as the principal barrier to further progress. We introduce LaFiTe, a framework that addresses this challenge by learning to generate textures as a 3D generative sparse latent color field. At its core, LaFiTe employs a variational autoencoder (VAE) to encode complex surface appearance into a sparse, structured latent space, which is subsequently decoded into a continuous color field. This representation achieves unprecedented fidelity, exceeding state-of-the-art methods by >10 dB PSNR in reconstruction, by effectively disentangling texture appearance from mesh topology and UV parameterization. Building upon this strong representation, a conditional rectified-flow model synthesizes high-quality, coherent textures across diverse styles and geometries. Extensive experiments demonstrate that LaFiTe not only sets a new benchmark for 3D-native texturing but also enables flexible downstream applications such as material synthesis and texture super-resolution, paving the way for the next generation of 3D content creation workflows.

---

### ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications

Authors: Eranga Bandara, Amin Hass, Ross Gore, Sachin Shetty, Ravi Mukkamala, Safdar H. Bouk, Xueping Liang, Ng Wee Keong, Kasun De Zoysa, Aruna Withanage, Nilaan Loganathan
Published: 2025-12-04
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2512.04785v1

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these systems introduce novel and evolving security challenges, including prompt injection attacks, context poisoning, model manipulation, and opaque agent-to-agent communication, that are not effectively captured by traditional threat modeling frameworks. In this paper, we introduce ASTRIDE, an automated threat modeling platform purpose-built for AI agent-based systems. ASTRIDE extends the classical STRIDE framework by introducing a new threat category, A for AI Agent-Specific Attacks, which encompasses emerging vulnerabilities such as prompt injection, unsafe tool invocation, and reasoning subversion, unique to agent-based applications. To automate threat modeling, ASTRIDE combines a consortium of fine-tuned vision-language models (VLMs) with the OpenAI-gpt-oss reasoning LLM to perform end-to-end analysis directly from visual agent architecture diagrams, such as data flow diagrams(DFDs). LLM agents orchestrate the end-to-end threat modeling automation process by coordinating interactions between the VLM consortium and the reasoning LLM. Our evaluations demonstrate that ASTRIDE provides accurate, scalable, and explainable threat modeling for next-generation intelligent systems. To the best of our knowledge, ASTRIDE is the first framework to both extend STRIDE with AI-specific threats and integrate fine-tuned VLMs with a reasoning LLM to fully automate diagram-driven threat modeling in AI agent-based applications.

---

### Pick-to-Learn for Systems and Control: Data-driven Synthesis with State-of-the-art Safety Guarantees

Authors: Dario Paccagnan, Daniel Marks, Marco C. Campi, Simone Garatti
Published: 2025-12-04
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2512.04781v1

Data-driven methods have become paramount in modern systems and control problems characterized by growing levels of complexity. In safety-critical environments, deploying these methods requires rigorous guarantees, a need that has motivated much recent work at the interface of statistical learning and control. However, many existing approaches achieve this goal at the cost of sacrificing valuable data for testing and calibration, or by constraining the choice of learning algorithm, thus leading to suboptimal performances. In this paper, we describe Pick-to-Learn (P2L) for Systems and Control, a framework that allows any data-driven control method to be equipped with state-of-the-art safety and performance guarantees. P2L enables the use of all available data to jointly synthesize and certify the design, eliminating the need to set aside data for calibration or validation purposes. In presenting a comprehensive version of P2L for systems and control, this paper demonstrates its effectiveness across a range of core problems, including optimal control, reachability analysis, safe synthesis, and robust control. In many of these applications, P2L delivers designs and certificates that outperform commonly employed methods, and shows strong potential for broad applicability in diverse practical settings.

---

### YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance

Authors: Junjie Zheng, Chunbo Hao, Guobin Ma, Xiaoyu Zhang, Gongyu Chen, Chaofan Ding, Zihao Chen, Lei Xie
Published: 2025-12-04
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.04779v1

Singing Voice Synthesis (SVS) remains constrained in practical deployment due to its strong dependence on accurate phoneme-level alignment and manually annotated melody contours, requirements that are resource-intensive and hinder scalability. To overcome these limitations, we propose a melody-driven SVS framework capable of synthesizing arbitrary lyrics following any reference melody, without relying on phoneme-level alignment. Our method builds on a Diffusion Transformer (DiT) architecture, enhanced with a dedicated melody extraction module that derives melody representations directly from reference audio. To ensure robust melody encoding, we employ a teacher model to guide the optimization of the melody extractor, alongside an implicit alignment mechanism that enforces similarity distribution constraints for improved melodic stability and coherence. Additionally, we refine duration modeling using weakly annotated song data and introduce a Flow-GRPO reinforcement learning strategy with a multi-objective reward function to jointly enhance pronunciation clarity and melodic fidelity. Experiments show that our model achieves superior performance over existing approaches in both objective measures and subjective listening tests, especially in zero-shot and lyric adaptation settings, while maintaining high audio quality without manual annotation. This work offers a practical and scalable solution for advancing data-efficient singing voice synthesis. To support reproducibility, we release our inference code and model checkpoints.

---

### Using Machine Learning to Take Stay-or-Go Decisions in Data-driven Drone Missions

Authors: Giorgos Polychronis, Foivos Pournaropoulos, Christos D. Antonopoulos, Spyros Lalis
Published: 2025-12-04
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.04773v1

Drones are becoming indispensable in many application domains. In data-driven missions, besides sensing, the drone must process the collected data at runtime to decide whether additional action must be taken on the spot, before moving to the next point of interest. If processing does not reveal an event or situation that requires such an action, the drone has waited in vain instead of moving to the next point. If, however, the drone starts moving to the next point and it turns out that a follow-up action is needed at the previous point, it must spend time to fly-back. To take this decision, we propose different machine-learning methods based on branch prediction and reinforcement learning. We evaluate these methods for a wide range of scenarios where the probability of event occurrence changes with time. Our results show that the proposed methods consistently outperform the regression-based method proposed in the literature and can significantly improve the worst-case mission time by up to 4.1x. Also, the achieved median mission time is very close, merely up to 2.7% higher, to that of a method with perfect knowledge of the current underlying event probability at each point of interest.

---

### Complementary Characterization of Agent-Based Models via Computational Mechanics and Diffusion Models

Authors: Roberto Garrone
Published: 2025-12-04
Categories: cs.MA, cs.LG
arXiv: https://arxiv.org/abs/2512.04771v1

This article extends the preprint "Characterizing Agent-Based Model Dynamics via $ε$-Machines and Kolmogorov-Style Complexity" by introducing diffusion models as orthogonal and complementary tools for characterizing the output of agent-based models (ABMs). Where $ε$-machines capture the predictive temporal structure and intrinsic computation of ABM-generated time series, diffusion models characterize high-dimensional cross-sectional distributions, learn underlying data manifolds, and enable synthetic generation of plausible population-level outcomes. We provide a formal analysis demonstrating that the two approaches operate on distinct mathematical domains -- processes vs. distributions -- and show that their combination yields a two-axis representation of ABM behavior based on temporal organization and distributional geometry. To our knowledge, this is the first framework to integrate computational mechanics with score-based generative modeling for the structural analysis of ABM outputs, thereby situating ABM characterization within the broader landscape of modern machine-learning methods for density estimation and intrinsic computation. The framework is validated using the same elder-caregiver ABM dataset introduced in the companion paper, and we provide precise definitions and propositions formalizing the mathematical complementarity between $ε$-machines and diffusion models. This establishes a principled methodology for jointly analyzing temporal predictability and high-dimensional distributional structure in complex simulation models.

---

### Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges

Authors: Yuxing Wang, Zhiyu Chen, Tiantian Zhang, Qiyue Yin, Yongzhe Chang, Zhiheng Li, Liang Wang, Xueqian Wang
Published: 2025-12-04
Categories: cs.RO, cs.AI, cs.ET, eess.SY
arXiv: https://arxiv.org/abs/2512.04770v2

Brain-body co-evolution enables animals to develop complex behaviors in their environments. Inspired by this biological synergy, embodied co-design (ECD) has emerged as a transformative paradigm for creating intelligent agents-from virtual creatures to physical robots-by jointly optimizing their morphologies and controllers rather than treating control in isolation. This integrated approach facilitates richer environmental interactions and robust task performance. In this survey, we provide a systematic overview of recent advances in ECD. We first formalize the concept of ECD and position it within related fields. We then introduce a hierarchical taxonomy: a lower layer that breaks down agent design into three fundamental components-controlling brain, body morphology, and task environment-and an upper layer that integrates these components into four major ECD frameworks: bi-level, single-level, generative, and open-ended. This taxonomy allows us to synthesize insights from more than one hundred recent studies. We further review notable benchmarks, datasets, and applications in both simulated and real-world scenarios. Finally, we identify significant challenges and offer insights into promising future research directions. A project associated with this survey has been created at https://github.com/Yuxing-Wang-THU/SurveyBrainBody.

---

### AdiBhashaa: A Community-Curated Benchmark for Machine Translation into Indian Tribal Languages

Authors: Pooja Singh, Sandeep Kumar
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04765v1

Large language models and multilingual machine translation (MT) systems increasingly drive access to information, yet many languages of the tribal communities remain effectively invisible in these technologies. This invisibility exacerbates existing structural inequities in education, governance, and digital participation. We present AdiBhashaa, a community-driven initiative that constructs the first open parallel corpora and baseline MT systems for four major Indian tribal languages-Bhili, Mundari, Gondi, and Santali. This work combines participatory data creation with native speakers, human-in-the-loop validation, and systematic evaluation of both encoder-decoder MT models and large language models. In addition to reporting technical findings, we articulate how AdiBhashaa illustrates a possible model for more equitable AI research: it centers local expertise, builds capacity among early-career researchers from marginalized communities, and foregrounds human validation in the development of language technologies.

---

### Human Cognitive Biases in Explanation-Based Interaction: The Case of Within and Between Session Order Effect

Authors: Dario Pesenti, Alessandro Bogani, Katya Tentori, Stefano Teso
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04764v1

Explanatory Interactive Learning (XIL) is a powerful interactive learning framework designed to enable users to customize and correct AI models by interacting with their explanations. In a nutshell, XIL algorithms select a number of items on which an AI model made a decision (e.g. images and their tags) and present them to users, together with corresponding explanations (e.g. image regions that drive the model's decision). Then, users supply corrective feedback for the explanations, which the algorithm uses to improve the model. Despite showing promise in debugging tasks, recent studies have raised concerns that explanatory interaction may trigger order effects, a well-known cognitive bias in which the sequence of presented items influences users' trust and, critically, the quality of their feedback. We argue that these studies are not entirely conclusive, as the experimental designs and tasks employed differ substantially from common XIL use cases, complicating interpretation. To clarify the interplay between order effects and explanatory interaction, we ran two larger-scale user studies (n = 713 total) designed to mimic common XIL tasks. Specifically, we assessed order effects both within and between debugging sessions by manipulating the order in which correct and wrong explanations are presented to participants. Order effects had a limited, through significant impact on users' agreement with the model (i.e., a behavioral measure of their trust), and only when examined withing debugging sessions, not between them. The quality of users' feedback was generally satisfactory, with order effects exerting only a small and inconsistent influence in both experiments. Overall, our findings suggest that order effects do not pose a significant issue for the successful employment of XIL approaches. More broadly, our work contributes to the ongoing efforts for understanding human factors in AI.

---

### MemLoRA: Distilling Expert Adapters for On-Device Memory Systems

Authors: Massimo Bini, Ondrej Bohdal, Umberto Michieli, Zeynep Akata, Mete Ozay, Taha Ceritli
Published: 2025-12-04
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2512.04763v1

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during prolonged dialogues by storing relevant memories and incorporating them as context. Such memory-based personalization is also key in on-device settings that allow users to keep their conversations and data private. However, memory-augmented systems typically rely on LLMs that are too costly for local on-device deployment. Even though Small Language Models (SLMs) are more suitable for on-device inference than LLMs, they cannot achieve sufficient performance. Additionally, these LLM-based systems lack native visual capabilities, limiting their applicability in multimodal contexts. In this paper, we introduce (i) MemLoRA, a novel memory system that enables local deployment by equipping SLMs with specialized memory adapters, and (ii) its vision extension MemLoRA-V, which integrates small Vision-Language Models (SVLMs) to memory systems, enabling native visual understanding. Following knowledge distillation principles, each adapter is trained separately for specific memory operations$\unicode{x2013}$knowledge extraction, memory update, and memory-augmented generation. Equipped with memory adapters, small models enable accurate on-device memory operations without cloud dependency. On text-only operations, MemLoRA outperforms 10$\times$ larger baseline models (e.g., Gemma2-27B) and achieves performance comparable to 60$\times$ larger models (e.g., GPT-OSS-120B) on the LoCoMo benchmark. To evaluate visual understanding operations instead, we extend LoCoMo with challenging Visual Question Answering tasks that require direct visual reasoning. On this, our VLM-integrated MemLoRA-V shows massive improvements over caption-based approaches (81.3 vs. 23.7 accuracy) while keeping strong performance in text-based tasks, demonstrating the efficacy of our method in multimodal contexts.

---

### Order Matters: 3D Shape Generation from Sequential VR Sketches

Authors: Yizi Chen, Sidi Wu, Tianyi Xiao, Nina Wiedemann, Loic Landrieu
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04761v3

VR sketching lets users explore and iterate on ideas directly in 3D, offering a faster and more intuitive alternative to conventional CAD tools. However, existing sketch-to-shape models ignore the temporal ordering of strokes, discarding crucial cues about structure and design intent. We introduce VRSketch2Shape, the first framework and multi-category dataset for generating 3D shapes from sequential VR sketches. Our contributions are threefold: (i) an automated pipeline that generates sequential VR sketches from arbitrary shapes, (ii) a dataset of over 20k synthetic and 900 hand-drawn sketch-shape pairs across four categories, and (iii) an order-aware sketch encoder coupled with a diffusion-based 3D generator. Our approach yields higher geometric fidelity than prior work, generalizes effectively from synthetic to real sketches with minimal supervision, and performs well even on partial sketches. All data and models will be released open-source at https://chenyizi086.github.io/VRSketch2Shape_website.

---

### Challenging the Abilities of Large Language Models in Italian: a Community Initiative

Authors: Malvina Nissim, Danilo Croce, Viviana Patti, Pierpaolo Basile, Giuseppe Attanasio, Elio Musacchio, Matteo Rinaldi, Federico Borazio, Maria Francis, Jacopo Gili, Daniel Scalena, Begoña Altuna et al.
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04759v1

The rapid progress of Large Language Models (LLMs) has transformed natural language processing and broadened its impact across research and society. Yet, systematic evaluation of these models, especially for languages beyond English, remains limited. "Challenging the Abilities of LAnguage Models in ITAlian" (CALAMITA) is a large-scale collaborative benchmarking initiative for Italian, coordinated under the Italian Association for Computational Linguistics. Unlike existing efforts that focus on leaderboards, CALAMITA foregrounds methodology: it federates more than 80 contributors from academia, industry, and the public sector to design, document, and evaluate a diverse collection of tasks, covering linguistic competence, commonsense reasoning, factual consistency, fairness, summarization, translation, and code generation. Through this process, we not only assembled a benchmark of over 20 tasks and almost 100 subtasks, but also established a centralized evaluation pipeline that supports heterogeneous datasets and metrics. We report results for four open-weight LLMs, highlighting systematic strengths and weaknesses across abilities, as well as challenges in task-specific evaluation. Beyond quantitative results, CALAMITA exposes methodological lessons: the necessity of fine-grained, task-representative metrics, the importance of harmonized pipelines, and the benefits and limitations of broad community engagement. CALAMITA is conceived as a rolling benchmark, enabling continuous integration of new tasks and models. This makes it both a resource -- the most comprehensive and diverse benchmark for Italian to date -- and a framework for sustainable, community-driven evaluation. We argue that this combination offers a blueprint for other languages and communities seeking inclusive and rigorous LLM evaluation practices.

---

### EtCon: Edit-then-Consolidate for Reliable Knowledge Editing

Authors: Ruilin Li, Yibin Wang, Wenhong Zhu, Chenglin Li, Jinghao Zhang, Chenliang Li, Junchi Yan, Jiaqi Wang
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04753v2

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations. However, they still encounter challenges in real-world autoregressive generation scenarios, which greatly limit their practical applicability. Our empirical analysis reveals two issues: (1) Most methods degrade pre-trained capabilities after injecting new knowledge; (2) They may exhibit a discrepancy between stored parametric knowledge and inference-time autoregressive generation behavior. To this end, we propose EtCon, an edit-then-consolidate paradigm that couples targeted edits with post-edit consolidation. Specifically, our framework comprises two stages: (1) Targeted Proximal Supervised Fine-Tuning (TPSFT) performs a constrained targeted edit to update parametric knowledge while controlling policy drift. (2) Group Relative Policy Optimization (GRPO) consolidates the edit by aligning autoregressive trajectories with the intended fact. Extensive experiments demonstrate that our EtCon improves editing reliability and real-world generalization, while better preserving pre-trained capabilities.

---

### RLHFSpec: Breaking the Efficiency Bottleneck in RLHF Training via Adaptive Drafting

Authors: Siqi Wang, Hailong Yang, Junjie Zhu, Xuezhu Wang, Yufan Xu, Depei Qian
Published: 2025-12-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.04752v2

Reinforcement Learning from Human Feedback (RLHF) is an important fine-tuning technique for large language models (LLMs) and comprises three stages: generation, inference, and training. The generation stage generates samples that are then used to infer learnable experiences for training. We observe that the generation stage is the bottleneck of the entire execution process and consider it a key point for optimization. Specifically, we realize the first attempt to integrate speculative decoding into the RLHF generation stage and propose RLHFSpec, an RLHF system that accelerates generation execution with efficient speculative decoding and sample reallocation. To fully exploit the performance potential provided by speculative decoding, especially dealing with the dynamic workload of the generation stage, RLHFSpec proposes a workload-aware drafting strategy selection mechanism, which selects the near-optimal strategy by jointly considering the verification cost and the number of accepted tokens. Moreover, RLHFSpec also proposes sample reallocation to fully utilize the GPU resources, and optimizes it with an efficient sample migration mechanism. The experimental results show that the RLHFSpec can achieve higher throughput in the generation stage compared to state-of-the-art works. Moreover, due to the effective alleviation of the generation bottleneck, RLHFSpec also shows significant performance speedup in the entire RLHF execution.

---

### UnwrapDiff: A Conditional Diffusion Model for InSAR Phase Unwrapping

Authors: Yijia Song, Juliet Biggs, Alin Achim, Robert Popescu, Simon Orrego, Nantheera Anantrasirichai
Published: 2025-12-04
Categories: physics.geo-ph, cs.AI
arXiv: https://arxiv.org/abs/2512.04749v1

Phase unwrapping is a fundamental problem in InSAR data processing, supporting geophysical applications such as deformation monitoring and hazard assessment. Its reliability is limited by noise and decorrelation in radar acquisitions, which makes accurate reconstruction of the deformation signal challenging. We propose a denoising diffusion probabilistic model (DDPM)-based framework for InSAR phase unwrapping, UnwrapDiff, in which the output of the traditional minimum cost flow algorithm (SNAPHU) is incorporated as conditional guidance. To evaluate robustness, we construct a synthetic dataset that incorporates atmospheric effects and diverse noise patterns, representative of realistic InSAR observations. Experiments show that the proposed model leverages the conditional prior while reducing the effect of diverse noise patterns, achieving on average a 10.11\% reduction in NRMSE compared to SNAPHU. It also achieves better reconstruction quality in difficult cases such as dyke intrusions.

---

### Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time

Authors: Xinyue Kang, Diwei Shi, Li Chen
Published: 2025-12-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.04748v1

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is not only computationally expensive but also risks degrading the model's pre-existing abilities.To address this, we introduce a lightweight component, Test-Time Steering Vectors (TTSV), which is prepended to the input while keeping the LLM's parameters entirely frozen. By optimizing the TTSV on test data to minimize the model's output entropy, we steer the model towards an internal state of higher confidence, activating its inherent abilities most relevant to the current task. TTSV is both lightweight and highly efficient to optimize, making it a true plug-and-play enhancement. Extensive experiments validate our approach's effectiveness on both base models and reasoning-enhanced models. For instance, on the MATH500 task, TTSV achieves a 45.88% relative performance gain on the Qwen2.5-Math-7B model and a 16.22% relative gain on the Qwen3-4B model. Furthermore, our approach exhibits robust generalization, with its steering vectors proving highly transferable across diverse tasks.

---

### A Tutorial on Regression Analysis: From Linear Models to Deep Learning -- Lecture Notes on Artificial Intelligence

Authors: Jingyuan Wang, Jiahao Ji
Published: 2025-12-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.04747v1

This article serves as the regression analysis lecture notes in the Intelligent Computing course cluster (including the courses of Artificial Intelligence, Data Mining, Machine Learning, and Pattern Recognition). It aims to provide students -- who are assumed to possess only basic university-level mathematics (i.e., with prerequisite courses in calculus, linear algebra, and probability theory) -- with a comprehensive and self-contained understanding of regression analysis without requiring any additional references. The lecture notes systematically introduce the fundamental concepts, modeling components, and theoretical foundations of regression analysis, covering linear regression, logistic regression, multinomial logistic regression, polynomial regression, basis-function models, kernel-based methods, and neural-network-based nonlinear regression. Core methodological topics include loss-function design, parameter-estimation principles, ordinary least squares, gradient-based optimization algorithms and their variants, as well as regularization techniques such as Ridge and LASSO regression. Through detailed mathematical derivations, illustrative examples, and intuitive visual explanations, the materials help students understand not only how regression models are constructed and optimized, but also how they reveal the underlying relationships between features and response variables. By bridging classical statistical modeling and modern machine-learning practice, these lecture notes aim to equip students with a solid conceptual and technical foundation for further study in advanced artificial intelligence models.

---

### SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Authors: Wenhua Cheng, Weiwei Zhang, Heng Guo, Haihao Shen, Zaner Ma
Published: 2025-12-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.04746v2

Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, a post-training quantization framework designed to maintain high performance even under aggressive compression. SignRoundV2 introduces (1) a simple yet efficient adaptive mixed-precision strategy that leverages gradient information and quantization-induced reconstruction errors to guide layer-wise bit allocation, and (2) a set of lightweight stabilization techniques, including loss filtering and a pre-tuning scale search, to improve tuning effectiveness in extremely low-bit regimes. Our approach takes a significant step toward closing the performance gap between quantized and full-precision models. Experimental results across diverse LLMs demonstrate that SignRoundV2 achieves near-lossless performance in mixed MXFP settings, narrowing the gap to $\sim$1\% at an average of 4.5 bits, while substantially improving accuracy in challenging 2-bit weight-only quantization. The source code is available at \url{https://github.com/intel/auto-round}.

---

### An Energy-Based Mechanism for Compositional Behavior

Authors: Francesca Rossi, Veronica Centorrino, Francesco Bullo, Giovanni Russo
Published: 2025-12-04
Categories: math.OC, cs.AI, eess.SY, nlin.AO
arXiv: https://arxiv.org/abs/2512.04745v4

Flexible intelligence relies on the ability to reuse previously acquired behaviors and combine them differently as circumstances change. In biological and artificial systems, this ability is often attributed to gating mechanisms that determine how much each available behavior should contribute at a given time. Yet these gating rules, the dynamics that compute them, and the neural circuits that may implement them are usually introduced separately, leaving unclear whether they reflect a common underlying principle. Here, we show that they can all be derived from a single variational principle for behavioral composition. The resulting mechanism naturally gives rise to softmax gating, evolves as an energy-based dynamical system with guaranteed convergence, and admits a recurrent neural network instantiation featuring context-dependent and local interactions. Across collective behavior, human decision-making, and layered control, the same mechanism reproduces characteristic behavioral patterns, provides interpretable accounts of how different behaviors are combined, and matches or outperforms established approaches. These results provide a unified account of how behavioral composition can emerge from a common principle, with implications for understanding flexible behavior in natural systems and for designing artificial agents that can adapt by recombining existing capabilities.

---

### OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models

Authors: Zhuoyue Wan, Wentao Hu, Chen Jason Zhang, Yuanfeng Song, Shuaimin Li, Ruiqiang Xiao, Xiao-Yong Wei, Raymond Chi-Wing Wong
Published: 2025-12-04
Categories: cs.CL, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2512.04738v1

Bridging natural language and structured query languages is a long-standing challenge in the database community. While recent advances in language models have shown promise in this direction, existing solutions often rely on large-scale closed-source models that suffer from high inference costs, limited transparency, and lack of adaptability for lightweight deployment. In this paper, we present OsmT, an open-source tag-aware language model specifically designed to bridge natural language and Overpass Query Language (OverpassQL), a structured query language for accessing large-scale OpenStreetMap (OSM) data. To enhance the accuracy and structural validity of generated queries, we introduce a Tag Retrieval Augmentation (TRA) mechanism that incorporates contextually relevant tag knowledge into the generation process. This mechanism is designed to capture the hierarchical and relational dependencies present in the OSM database, addressing the topological complexity inherent in geospatial query formulation. In addition, we define a reverse task, OverpassQL-to-Text, which translates structured queries into natural language explanations to support query interpretation and improve user accessibility. We evaluate OsmT on a public benchmark against strong baselines and observe consistent improvements in both query generation and interpretation. Despite using significantly fewer parameters, our model achieves competitive accuracy, demonstrating the effectiveness of open-source pre-trained language models in bridging natural language and structured query languages within schema-rich geospatial environments.

---

### MT-Depth: Multi-task Instance feature analysis for the Depth Completion

Authors: Abdul Haseeb Nizamani, Dandi Zhou, Xinhai Sun
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04734v2

Depth completion plays a vital role in 3D perception systems, especially in scenarios where sparse depth data must be densified for tasks such as autonomous driving, robotics, and augmented reality. While many existing approaches rely on semantic segmentation to guide depth completion, they often overlook the benefits of object-level understanding. In this work, we introduce an instance-aware depth completion framework that explicitly integrates binary instance masks as spatial priors to refine depth predictions. Our model combines four main components: a frozen YOLO V11 instance segmentation branch, a U-Net-based depth completion backbone, a cross-attention fusion module, and an attention-guided prediction head. The instance segmentation branch generates per-image foreground masks that guide the depth branch via cross-attention, allowing the network to focus on object-centric regions during refinement. We validate our method on the Virtual KITTI 2 dataset, showing that it achieves lower Root Mean Squared Error (RMSE) compared to both a U-Net-only baseline and previous semantic-guided methods, while maintaining competitive Mean Absolute Error (MAE). Qualitative and quantitative results demonstrate that the proposed model effectively enhances depth accuracy near object boundaries, occlusions, and thin structures. Our findings suggest that incorporating instance-aware cues offers a promising direction for improving depth completion without relying on dense semantic labels.

---

### E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving

Authors: Yihong Tang, Haicheng Liao, Tong Nie, Junlin He, Ao Qu, Kehua Chen, Wei Ma, Zhenning Li, Lijun Sun, Chengzhong Xu
Published: 2025-12-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.04733v3

End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valenc-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These evaluation results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and feedback.

---

### Measuring the Unspoken: A Disentanglement Model and Benchmark for Psychological Analysis in the Wild

Authors: Yigui Feng, Qinglin Wang, Haotian Mo, Yang Liu, Ke Liu, Gencheng Liu, Xinhai Chen, Siqi Shen, Songzhu Mei, Jie Liu
Published: 2025-12-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.04728v1

Generative psychological analysis of in-the-wild conversations faces two fundamental challenges: (1) existing Vision-Language Models (VLMs) fail to resolve Articulatory-Affective Ambiguity, where visual patterns of speech mimic emotional expressions; and (2) progress is stifled by a lack of verifiable evaluation metrics capable of assessing visual grounding and reasoning depth. We propose a complete ecosystem to address these twin challenges. First, we introduce Multilevel Insight Network for Disentanglement(MIND), a novel hierarchical visual encoder that introduces a Status Judgment module to algorithmically suppress ambiguous lip features based on their temporal feature variance, achieving explicit visual disentanglement. Second, we construct ConvoInsight-DB, a new large-scale dataset with expert annotations for micro-expressions and deep psychological inference. Third, Third, we designed the Mental Reasoning Insight Rating Metric (PRISM), an automated dimensional framework that uses expert-guided LLM to measure the multidimensional performance of large mental vision models. On our PRISM benchmark, MIND significantly outperforms all baselines, achieving a +86.95% gain in micro-expression detection over prior SOTA. Ablation studies confirm that our Status Judgment disentanglement module is the most critical component for this performance leap. Our code has been opened.

---

### Sequential Enumeration in Large Language Models

Authors: Kuinan Hou, Marco Zorzi, Alberto Testolin
Published: 2025-12-04
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.04727v2

Reliably counting and generating sequences of items remain a significant challenge for neural networks, including Large Language Models (LLMs). Indeed, although this capability is readily handled by rule-based symbolic systems based on serial computation, learning to systematically deploy counting procedures is difficult for neural models, which should acquire these skills through learning. Previous research has demonstrated that recurrent architectures can only approximately track and enumerate sequences of events, and it remains unclear whether modern deep learning systems, including LLMs, can deploy systematic counting procedures over sequences of discrete symbols. This paper aims to fill this gap by investigating the sequential enumeration abilities of five state-of-the-art LLMs, including proprietary, open-source, and reasoning models. We probe LLMs in sequential naming and production tasks involving lists of letters and words, adopting a variety of prompting instructions to explore the role of chain-of-thought in the spontaneous emerging of counting strategies. We also evaluate open-source models with the same architecture but increasing size to see whether the mastering of counting principles follows scaling laws, and we analyze the embedding dynamics during sequential enumeration to investigate the emergent encoding of numerosity. We find that some LLMs are indeed capable of deploying counting procedures when explicitly prompted to do so, but none of them spontaneously engage in counting when simply asked to enumerate the number of items in a sequence. Our results suggest that, despite their impressive emergent abilities, LLMs cannot yet robustly and systematically deploy counting procedures, highlighting a persistent gap between neural and symbolic approaches to compositional generalization.

---

### CIG-MAE: Cross-Modal Information-Guided Masked Autoencoder for Self-Supervised WiFi Sensing

Authors: Gang Liu, Yanling Hao, Yixuan Zou
Published: 2025-12-04
Categories: eess.SP, cs.CV
arXiv: https://arxiv.org/abs/2512.04723v2

Human Action Recognition using WiFi Channel State Information (CSI) has emerged as an attractive alternative to vision-based methods due to its ubiquity, device-agnostic nature, and inherent privacy-preserving capabilities. However, the high cost of manual annotation and the limited scale of publicly available CSI datasets restrict the performance of supervised approaches. Self-supervised learning (SSL) offers a promising avenue, but existing contrastive paradigms rely on data augmentations that conflict with the physical semantics of radio signals and require large-batch training, making them poorly suited for CSI. To overcome these challenges, we introduce CIG-MAE -- a Cross-modal Information-Guided Masked Autoencoder -- that reconstructs both the amplitude and phase of CSI using a symmetric dual-stream architecture with a high masking ratio. Specifically, we propose an Adaptive Information-Guided Masking strategy that dynamically allocates attention to time-frequency regions with high information density to improve learning efficiency, and incorporate a Barlow Twins regularizer to align cross-modal representations without negative samples. Experiments on three public datasets show that CIG-MAE consistently outperforms SOTA SSL methods and even surpasses a fully supervised baseline, demonstrating superior data efficiency, robustness, and representation generalization.

---

### Towards an AI Fluid Scientist: LLM-Powered Scientific Discovery in Experimental Fluid Mechanics

Authors: Haodong Feng, Lugang Ye, Dixia Fan
Published: 2025-12-04
Categories: physics.flu-dyn, cs.AI
arXiv: https://arxiv.org/abs/2512.04716v1

The integration of artificial intelligence into experimental fluid mechanics promises to accelerate discovery, yet most AI applications remain narrowly focused on numerical studies. This work proposes an AI Fluid Scientist framework that autonomously executes the complete experimental workflow: hypothesis generation, experimental design, robotic execution, data analysis, and manuscript preparation. We validate this through investigation of vortex-induced vibration (VIV) and wake-induced vibration (WIV) in tandem cylinders. Our work has four key contributions: (1) A computer-controlled circulating water tunnel (CWT) with programmatic control of flow velocity, cylinder position, and forcing parameters (vibration frequency and amplitude) with data acquisition (displacement, force, and torque). (2) Automated experiments reproduce literature benchmarks (Khalak and Williamson (1999) and Assi et al. (2013, 2010)) with frequency lock-in within 4% and matching critical spacing trends. (3) The framework with Human-in-the-Loop (HIL) discovers more WIV amplitude response phenomena, and uses a neural network to fit physical laws from data, which is 31% higher than that of polynomial fitting. (4) The framework with multi-agent with virtual-real interaction system executes hundreds of experiments end-to-end, which automatically completes the entire process of scientific research from hypothesis generation, experimental design, experimental execution, data analysis, and manuscript preparation. It greatly liberates human researchers and improves study efficiency, providing new paradigm for the development and research of experimental fluid mechanics.

---

### Playing the Player: A Heuristic Framework for Adaptive Poker AI

Authors: Andrew Paterson, Carl Sanders
Published: 2025-12-04
Categories: cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2512.04714v1

For years, the discourse around poker AI has been dominated by the concept of solvers and the pursuit of unexploitable, machine-perfect play. This paper challenges that orthodoxy. It presents Patrick, an AI built on the contrary philosophy: that the path to victory lies not in being unexploitable, but in being maximally exploitative. Patrick's architecture is a purpose-built engine for understanding and attacking the flawed, psychological, and often irrational nature of human opponents. Through detailed analysis of its design, its novel prediction-anchored learning method, and its profitable performance in a 64,267-hand trial, this paper makes the case that the solved myth is a distraction from the real, far more interesting challenge: creating AI that can master the art of human imperfection.

---

### Large Speech Model Enabled Semantic Communication

Authors: Yun Tian, Zhijin Qin, Guocheng Lv, Ye Jin, Kaibin Huang, Zhu Han
Published: 2025-12-04
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.04711v1

Existing speech semantic communication systems mainly based on Joint Source-Channel Coding (JSCC) architectures have demonstrated impressive performance, but their effectiveness remains limited by model structures specifically designed for particular tasks and datasets. Recent advances indicate that generative large models pre-trained on massive datasets, can achieve outstanding performance arexhibit exceptional performance across diverse downstream tasks with minimal fine-tuning. To exploit the rich semantic knowledge embedded in large models and enable adaptive transmission over lossy channels, we propose a Large Speech Model enabled Semantic Communication (LargeSC) system. Simultaneously achieving adaptive compression and robust transmission over lossy channels remains challenging, requiring trade-offs among compression efficiency, speech quality, and latency. In this work, we employ the Mimi as a speech codec, converting speech into discrete tokens compatible with existing network architectures. We propose an adaptive controller module that enables adaptive transmission and in-band Unequal Error Protection (UEP), dynamically adjusting to both speech content and packet loss probability under bandwidth constraints. Additionally, we employ Low-Rank Adaptation (LoRA) to finetune the Moshi foundation model for generative recovery of lost speech tokens. Simulation results show that the proposed system supports bandwidths ranging from 550 bps to 2.06 kbps, outperforms conventional baselines in speech quality under high packet loss rates and achieves an end-to-end latency of approximately 460 ms, thereby demonstrating its potential for real-time deployment.

---

### Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators

Authors: Alaa Zniber, Arne Symons, Ouassim Karrakchou, Marian Verhelst, Mounir Ghogho
Published: 2025-12-04
Categories: cs.CC, cs.AR, cs.CV
arXiv: https://arxiv.org/abs/2512.04705v3

The deployment of Early-Exiting Neural Networks (EENNs) on edge accelerators requires optimizing not only the network architecture but also its hardware deployment. Exit configuration, quantization, and hardware workload mapping interact in non-trivial ways, influencing memory traffic, accelerator utilization, and ultimately the energy-latency trade-off. This work presents a hardware-aware co-design framework for EENNs that jointly optimizes exit configuration, quantization-aware training, and multi-core hardware mapping within a unified NAS process. Leveraging analytical design space exploration, the framework identifies efficient workload mappings for each candidate architecture while providing accurate latency and energy estimates during the search. We further formulate EENN deployment as a constrained multi-objective optimization problem balancing predictive accuracy, energy-latency product, exit overhead, and dynamic inference efficiency. Experimental results on CIFAR-10 demonstrate that the proposed framework achieves over a 50\% reduction in energy-latency product compared with static baselines under 8-bit quantization. These results demonstrate that jointly optimizing architecture and deployment is essential for realizing the full efficiency potential of dynamic inference on heterogeneous edge accelerators.

---

### Towards Continuous-Time Approximations for Stochastic Gradient Descent without Replacement

Authors: Stefan Perko
Published: 2025-12-04
Categories: cs.LG, math.PR
arXiv: https://arxiv.org/abs/2512.04703v1

Gradient optimization algorithms using epochs, that is those based on stochastic gradient descent without replacement (SGDo), are predominantly used to train machine learning models in practice. However, the mathematical theory of SGDo and related algorithms remain underexplored compared to their "with replacement" and "one-pass" counterparts. In this article, we propose a stochastic, continuous-time approximation to SGDo with additive noise based on a Young differential equation driven by a stochastic process we call an "epoched Brownian motion". We show its usefulness by proving the almost sure convergence of the continuous-time approximation for strongly convex objectives and learning rate schedules of the form $u_t = \frac{1}{(1+t)^β}, β\in (0,1)$. Moreover, we compute an upper bound on the asymptotic rate of almost sure convergence, which is as good or better than previous results for SGDo.

---