# Research Papers — 2025-12 · bundle page 164 of 175

> Full-text markdown of papers #8151–8200 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/164
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/163.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/165.md)

### ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data

Authors: Yuxing Liu, Zheng Li, Huanhuan Liang, Ji Zhang, Zeyu Sun, Yong Liu
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02686v2

Anomaly segmentation seeks to detect and localize unknown or out-of-distribution (OoD) objects that fall outside predefined semantic classes a capability essential for safe autonomous driving. However, the scarcity and limited diversity of anomaly data severely constrain model generalization in open-world environments. Existing approaches mitigate this issue through synthetic data generation, either by copy-pasting external objects into driving scenes or by leveraging text-to-image diffusion models to inpaint anomalous regions. While these methods improve anomaly diversity, they often lack contextual coherence and physical realism, resulting in domain gaps between synthetic and real data. In this paper, we present ClimaDrive, a semantics-guided image-to-image framework for synthesizing semantically coherent, weather-diverse, and physically plausible OoD driving data. ClimaDrive unifies structure-guided multi-weather generation with prompt-driven anomaly inpainting, enabling the creation of visually realistic training data. Based on this framework, we construct ClimaOoD, a large-scale benchmark spanning six representative driving scenarios under both clear and adverse weather conditions. Extensive experiments on four state-of-the-art methods show that training with ClimaOoD leads to robust improvements in anomaly segmentation. Across all methods, AUROC, AP, and FPR95 show notable gains, with FPR95 dropping from 3.97 to 3.52 for RbA on Fishyscapes LAF. These results demonstrate that ClimaOoD enhances model robustness, offering valuable training data for better generalization in open-world anomaly detection.

---

### Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance

Authors: Huankun Sheng, Ming Li, Yixiang Wei, Yeying Fan, Yu-Hui Wen, Tieliang Gong, Yong-Jin Liu
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02685v2

Recent advances in object-centric representation learning have shown that slot attention-based methods can effectively decompose visual scenes into object slot representations without supervision. However, existing approaches typically process foreground and background regions indiscriminately, often resulting in background interference and suboptimal instance discovery performance on real-world data. To address this limitation, we propose Foreground-Aware Slot Attention (FASA), a two-stage framework that explicitly separates foreground from background to enable precise object discovery. In the first stage, FASA performs a coarse scene decomposition to distinguish foreground from background regions through a dual-slot competition mechanism. These slots are initialized via a clustering-based strategy, yielding well-structured representations of salient regions. In the second stage, we introduce a masked slot attention mechanism where the first slot captures the background while the remaining slots compete to represent individual foreground objects. To further address over-segmentation of foreground objects, we incorporate pseudo-mask guidance derived from a patch affinity graph constructed with self-supervised image features to guide the learning of foreground slots. Extensive experiments on both synthetic and real-world datasets demonstrate that FASA consistently outperforms state-of-the-art methods, validating the effectiveness of explicit foreground modeling and pseudo-mask guidance for robust scene decomposition and object-coherent representation. Code will be made publicly available.

---

### Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions

Authors: Piercosma Bisconti, Marcello Galisai, Federico Pierucci, Marcantonio Bracale, Matteo Prandi
Published: 2025-12-02
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2512.02682v1

This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models (LLMs) interact with each other. Most current governance practices still rely on single-agent safety containment, prompts, fine-tuning, and moderation layers that constrain individual model behavior but leave the dynamics of multi-model interaction ungoverned. These mechanisms assume a dyadic setting: one model responding to one user under stable oversight. Yet research and industrial development are rapidly shifting toward LLM-to-LLM ecosystems, where outputs are recursively reused as inputs across chains of agents. In such systems, local compliance can aggregate into collective failure even when every model is individually aligned. We propose a conceptual transition from model-level safety to system-level safety, introducing the framework of the Emergent Systemic Risk Horizon (ESRH) to formalize how instability arises from interaction structure rather than from isolated misbehavior. The paper contributes (i) a theoretical account of collective risk in interacting LLMs, (ii) a taxonomy connecting micro, meso, and macro-level failure modes, and (iii) a design proposal for InstitutionalAI, an architecture for embedding adaptive oversight within multi-agent systems.

---

### PGP-DiffSR: Phase-Guided Progressive Pruning for Efficient Diffusion-based Image Super-Resolution

Authors: Zhongbao Yang, Jiangxin Dong, Yazhou Yao, Jinhui Tang, Jinshan Pan
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02681v1

Although diffusion-based models have achieved impressive results in image super-resolution, they often rely on large-scale backbones such as Stable Diffusion XL (SDXL) and Diffusion Transformers (DiT), which lead to excessive computational and memory costs during training and inference. To address this issue, we develop a lightweight diffusion method, PGP-DiffSR, by removing redundant information from diffusion models under the guidance of the phase information of inputs for efficient image super-resolution. We first identify the intra-block redundancy within the diffusion backbone and propose a progressive pruning approach that removes redundant blocks while reserving restoration capability. We note that the phase information of the restored images produced by the pruned diffusion model is not well estimated. To solve this problem, we propose a phase-exchange adapter module that explores the phase information of the inputs to guide the pruned diffusion model for better restoration performance. We formulate the progressive pruning approach and the phase-exchange adapter module into a unified model. Extensive experiments demonstrate that our method achieves competitive restoration quality while significantly reducing computational load and memory consumption. The code is available at https://github.com/yzb1997/PGP-DiffSR.

---

### Exploring Depth Generalization in Large Language Models for Solving Recursive Logic Tasks

Authors: Zhiyuan He
Published: 2025-12-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.02677v1

Large language models have demonstrated remarkable capabilities across many tasks, yet face significant challenges when dealing with recursive reasoning problems, those requiring the resolution of nested hierarchical structures. While prior research has extensively studied length generalization (a model's ability to handle longer sequences than seen during training), we investigate a distinct and underexplored limitation: depth generalization. Here, depth refers to the number of nested levels in a hierarchical problem, such as the layers of parentheses in a mathematical expression or the nesting of logical clauses in a Boolean formula. Our work reveals that standard transformer architectures struggle with problems involving deeper recursion than encountered during training, even when they perform well on longer but non-nested sequences. This limitation stems from their inability to maintain stack-like behavior, the capacity to track and resolve multiple levels of nested dependencies. Through systematic analysis, we demonstrate how this architectural constraint leads to rapid performance decay as the depth of the recursion increases. To address this challenge, we develop a novel looped locate-and-replace pipeline that decomposes recursive problems into manageable subcomponents. The approach employs two specialized models: a locator that identifies solvable subexpressions and a replacer that evaluates these components while preserving the overall structure. We evaluated this method in three carefully designed domains: Boolean algebra, recursive arithmetic, and propositional logic, each with a controllable depth of recursion. We show that our method effectively alleviates the performance decay when tested on out-of-distribution recursion depth.

---

### SAND Challenge: Four Approaches for Dysartria Severity Classification

Authors: Gauri Deshpande, Harish Battula, Ashish Panda, Sunil Kumar Kopparapu
Published: 2025-12-02
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.02669v1

This paper presents a unified study of four distinct modeling approaches for classifying dysarthria severity in the Speech Analysis for Neurodegenerative Diseases (SAND) challenge. All models tackle the same five class classification task using a common dataset of speech recordings. We investigate: (1) a ViT-OF method leveraging a Vision Transformer on spectrogram images, (2) a 1D-CNN approach using eight 1-D CNN's with majority-vote fusion, (3) a BiLSTM-OF approach using nine BiLSTM models with majority vote fusion, and (4) a Hierarchical XGBoost ensemble that combines glottal and formant features through a two stage learning framework. Each method is described, and their performances on a validation set of 53 speakers are compared. Results show that while the feature-engineered XGBoost ensemble achieves the highest macro-F1 (0.86), the deep learning models (ViT, CNN, BiLSTM) attain competitive F1-scores (0.70) and offer complementary insights into the problem.

---

### UAUTrack: Towards Unified Multimodal Anti-UAV Visual Tracking

Authors: Qionglin Ren, Dawei Zhang, Chunxu Tian, Dan Zhang
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02668v1

Research in Anti-UAV (Unmanned Aerial Vehicle) tracking has explored various modalities, including RGB, TIR, and RGB-T fusion. However, a unified framework for cross-modal collaboration is still lacking. Existing approaches have primarily focused on independent models for individual tasks, often overlooking the potential for cross-modal information sharing. Furthermore, Anti-UAV tracking techniques are still in their infancy, with current solutions struggling to achieve effective multimodal data fusion. To address these challenges, we propose UAUTrack, a unified single-target tracking framework built upon a single-stream, single-stage, end-to-end architecture that effectively integrates multiple modalities. UAUTrack introduces a key component: a text prior prompt strategy that directs the model to focus on UAVs across various scenarios. Experimental results show that UAUTrack achieves state-of-the-art performance on the Anti-UAV and DUT Anti-UAV datasets, and maintains a favourable trade-off between accuracy and speed on the Anti-UAV410 dataset, demonstrating both high accuracy and practical efficiency across diverse Anti-UAV scenarios.

---

### Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents

Authors: Haozhuo Zheng, Cheng Wang, Yang Liu
Published: 2025-12-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.02667v1

The de novo generation of molecules with desirable properties is a critical challenge, where diffusion models are computationally intensive and autoregressive models struggle with error propagation. In this work, we introduce the Graph VQ-Transformer (GVT), a two-stage generative framework that achieves both high accuracy and efficiency. The core of our approach is a novel Graph Vector Quantized Variational Autoencoder (VQ-VAE) that compresses molecular graphs into high-fidelity discrete latent sequences. By synergistically combining a Graph Transformer with canonical Reverse Cuthill-McKee (RCM) node ordering and Rotary Positional Embeddings (RoPE), our VQ-VAE achieves near-perfect reconstruction rates. An autoregressive Transformer is then trained on these discrete latents, effectively converting graph generation into a well-structured sequence modeling problem. Crucially, this mapping of complex graphs to high-fidelity discrete sequences bridges molecular design with the powerful paradigm of large-scale sequence modeling, unlocking potential synergies with Large Language Models (LLMs). Extensive experiments show that GVT achieves state-of-the-art or highly competitive performance across major benchmarks like ZINC250k, MOSES, and GuacaMol, and notably outperforms leading diffusion models on key distribution similarity metrics such as FCD and KL Divergence. With its superior performance, efficiency, and architectural novelty, GVT not only presents a compelling alternative to diffusion models but also establishes a strong new baseline for the field, paving the way for future research in discrete latent-space molecular generation.

---

### Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization

Authors: Jing Ma
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02665v1

Large language models (LLMs) are now used in settings such as Google's AI Overviews, where it summarizes multiple long documents. However, it remains unclear whether they weight all inputs equally. Focusing on abortion-related news, we construct 40 pro-neutral-con article triplets, permute each triplet into six input orders, and prompt Gemini 2.5 Flash to generate a neutral overview. We evaluate each summary against its source articles using ROUGE-L (lexical overlap), BERTScore (semantic similarity), and SummaC (factual consistency). One-way ANOVA reveals a significant primacy effect for BERTScore across all stances, indicating that summaries are more semantically aligned with the first-seen article. Pairwise comparisons further show that Position 1 differs significantly from Positions 2 and 3, while the latter two do not differ from each other, confirming a selective preference for the first document. The findings present risks for applications that rely on LLM-generated overviews and for agentic AI systems, where the steps involving LLMs can disproportionately influence downstream actions.

---

### PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes

Authors: Derui Shan, Qian Qiao, Hao Lu, Tao Du, Peng Lu
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02664v1

Polarization-aware Neural Radiance Fields (NeRF) enable novel view synthesis of specular-reflection scenes but face challenges in slow training, inefficient rendering, and strong dependencies on material/viewpoint assumptions. However, 3D Gaussian Splatting (3DGS) enables real-time rendering yet struggles with accurate reflection reconstruction from reflection-geometry entanglement, adding a deferred reflection module introduces environment map dependence. We address these limitations by proposing PolarGuide-GSDR, a polarization-forward-guided paradigm establishing a bidirectional coupling mechanism between polarization and 3DGS: first 3DGS's geometric priors are leveraged to resolve polarization ambiguity, and then the refined polarization information cues are used to guide 3DGS's normal and spherical harmonic representation. This process achieves high-fidelity reflection separation and full-scene reconstruction without requiring environment maps or restrictive material assumptions. We demonstrate on public and self-collected datasets that PolarGuide-GSDR achieves state-of-the-art performance in specular reconstruction, normal estimation, and novel view synthesis, all while maintaining real-time rendering capabilities. To our knowledge, this is the first framework embedding polarization priors directly into 3DGS optimization, yielding superior interpretability and real-time performance for modeling complex reflective scenes.

---

### Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation

Authors: Athos Georgiou
Published: 2025-12-02
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2512.02660v3

Late-interaction multimodal retrieval models like ColPali achieve state-of-the-art document retrieval by embedding pages as images and computing fine-grained similarity between query tokens and visual patches. However, they operate at page-level granularity, limiting utility for retrieval-augmented generation (RAG) where precise context is paramount. Conversely, OCR-based systems extract structured text with bounding box coordinates but lack semantic grounding for relevance assessment. We propose a hybrid architecture that unifies these paradigms: using ColPali's patch-level similarity scores as spatial relevance filters over OCR-extracted regions. We formalize the coordinate mapping between vision transformer patch grids and OCR bounding boxes, introduce intersection metrics for relevance propagation, and establish theoretical bounds on area efficiency. We evaluate on BBox-DocVQA with ground-truth bounding boxes. For within-page localization (given correct page retrieval), ColQwen3-4B with percentile-50 thresholding achieves 59.7% hit rate at IoU@0.5 (84.4% at IoU@0.25, 35.8% at IoU@0.7), with mean IoU of 0.569, compared to ~6.7% for random region selection. Our approach reduces context tokens by 28.8% compared to returning all OCR regions and by 52.3% compared to full-page image tokens. Our approach operates at inference time without additional training. We release Snappy, an open-source implementation at https://github.com/athrael-soju/Snappy.

---

### Locality-Aware Continual Unlearning for Diffusion Models

Authors: Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji
Published: 2025-12-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.02657v2

Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time. Existing unlearning methods, however, are designed for single-step deletion and collapse after only 3-5 sequential applications. We trace this instability to two compounding factors: (i) coarse mapping targets that cause degradation to accumulate unnecessarily across steps, and (ii) the absence of local protection for semantically neighboring concepts, whose shared internal representations make them the first to suffer collateral damage. Because this damage is strongest in the local semantic neighborhood of the forget concept, global replay alone cannot prevent it. Building on this analysis, we propose Locality-Aware Continual Unlearning (LACU), a framework with two complementary mechanisms. Locality-Aware Target Selection chooses, for each forget prompt, the context-preserving mapping prompt that the diffusion model itself treats as most similar to the original prompt, measured by score-prediction distance (how differently the model denoises the same noisy image under two text conditions), ensuring each update is as small and targeted as possible. Locality-Aware Replay uses the same metric to identify the retain concepts closest to the forget concept in the model's own representation and replays them as a local functional regularizer, directly shielding the most vulnerable neighborhood. Combined with teacher-student distillation and lightweight $\ell_2$ parameter regularization, LACU maintains stable unlearning over 10 sequential steps, preserving significantly higher related retention ($RR_{\text{acc}}$) and general retention ($GR_{\text{acc}}$) than recent baselines.

---

### Adaptive Weighted LSSVM for Multi-View Classification

Authors: Farnaz Faramarzi Lighvan, Mehrdad Asadi, Lynn Houthuys
Published: 2025-12-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.02653v2

Multi-view learning integrates diverse representations of the same instances and can improve performance when interactions across views are effectively exploited. Most existing kernel-based multi-view learning methods either rely on fusion techniques without explicitly enforcing a consensus or complementary collaboration across views, or use co-regularization-based loss functions that impose only pairwise interactions, thereby limiting global collaboration. We propose AW-LSSVM, an adaptive weighted LS-SVM that explicitly enforces complementary learning across all views through an iterative global coupling mechanism. At each iteration, each view not only learns from its own data but is also guided to compensate for samples misclassified by other views in previous iterations by assigning adaptive sample weights. We introduce two strategies for computing these weights: (1) based on averaging misclassification errors across other views and, (2) based on a dissimilarity-aware error aggregation that puts more emphasis on errors from more dissimilar views. Experiments demonstrate that AW-LSSVM outperforms existing multi-view methods on most benchmark datasets.

---

### Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

Authors: Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li
Published: 2025-12-02
Categories: cs.SD, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2512.02652v2

Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and language. To address this gap, we introduce Pianist Transformer, with three key contributions: 1) introducing large-scale self-supervised learning into expressive piano performance rendering through a unified Musical Instrument Digital Interface (MIDI) representation, enabling pre-training on 10B tokens of unlabeled MIDI data; 2) an efficient asymmetric Transformer with note-level compression, substantially improving training efficiency, memory usage, and inference speed for long-context music modeling; 3) a state-of-the-art rendering model with an editable workflow, achieving strong objective and subjective results and enabling integration into real-world music production workflows. Overall, Pianist Transformer outlines a scalable path toward human-like performance synthesis in the music domain. Code, audio samples, and model checkpoints are available on our project page: https://yhj137.github.io/pianist-transformer-demo/.

---

### Real-Time Multimodal Data Collection Using Smartwatches and Its Visualization in Education

Authors: Alvaro Becerra, Pablo Villegas, Ruth Cobos
Published: 2025-12-02
Categories: cs.HC, cs.CV, cs.SE
arXiv: https://arxiv.org/abs/2512.02651v1

Wearable sensors, such as smartwatches, have become increasingly prevalent across domains like healthcare, sports, and education, enabling continuous monitoring of physiological and behavioral data. In the context of education, these technologies offer new opportunities to study cognitive and affective processes such as engagement, attention, and performance. However, the lack of scalable, synchronized, and high-resolution tools for multimodal data acquisition continues to be a significant barrier to the widespread adoption of Multimodal Learning Analytics in real-world educational settings. This paper presents two complementary tools developed to address these challenges: Watch-DMLT, a data acquisition application for Fitbit Sense 2 smartwatches that enables real-time, multi-user monitoring of physiological and motion signals; and ViSeDOPS, a dashboard-based visualization system for analyzing synchronized multimodal data collected during oral presentations. We report on a classroom deployment involving 65 students and up to 16 smartwatches, where data streams including heart rate, motion, gaze, video, and contextual annotations were captured and analyzed. Results demonstrate the feasibility and utility of the proposed system for supporting fine-grained, scalable, and interpretable Multimodal Learning Analytics in real learning environments.

---

### Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

Authors: Junwon Lee, Juhan Nam, Jiyoung Lee
Published: 2025-12-02
Categories: cs.CV, cs.LG, cs.MM, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2512.02650v2

This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. We propose SELVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector to distinctly extract prompt-relevant sound-source visual features from the video encoder. To suppress text-irrelevant activations with efficient video encoder finetuning, the proposed supplementary tokens promote cross-attention to yield robust semantic and temporal grounding. SELVA further employs an autonomous video-mixing scheme in a self-supervised manner to overcome the lack of mono audio track supervision. We evaluate SELVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization.

---

### PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking

Authors: Dong Li, Jiahao Xiong, Yingda Huang, Le Chang
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02648v2

We introduce PoreTrack3D, the first benchmark for dynamic 3D Gaussian splatting in pore-scale, non-rigid 3D facial trajectory tracking. It contains over 440,000 facial trajectories in total, among which more than 52,000 are longer than 10 frames, including 68 manually reviewed trajectories that span the entire 150 frames. To the best of our knowledge, PoreTrack3D is the first benchmark dataset to capture both traditional facial landmarks and pore-scale keypoints trajectory, advancing the study of fine-grained facial expressions through the analysis of subtle skin-surface motion. We systematically evaluate state-of-the-art dynamic 3D Gaussian splatting methods on PoreTrack3D, establishing the first performance baseline in this domain. Overall, the pipeline developed for this benchmark dataset's creation establishes a new framework for high-fidelity facial motion capture and dynamic 3D reconstruction. Our dataset are publicly available at: https://github.com/JHXion9/PoreTrack3D

---

### Leveraging Large-Scale Pretrained Spatial-Spectral Priors for General Zero-Shot Pansharpening

Authors: Yongchuan Cui, Peng Liu, Yi Zeng
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02643v1

Existing deep learning methods for remote sensing image fusion often suffer from poor generalization when applied to unseen datasets due to the limited availability of real training data and the domain gap between different satellite sensors. To address this challenge, we explore the potential of foundation models by proposing a novel pretraining strategy that leverages large-scale simulated datasets to learn robust spatial-spectral priors. Specifically, our approach first constructs diverse simulated datasets by applying various degradation operations (blur, noise, downsampling) and augmentations (bands generation, channel shuffling, high-pass filtering, color jittering, etc.) to natural images from ImageNet and remote sensing images from SkyScript. We then pretrain fusion models on these simulated data to learn generalizable spatial-spectral representations. The pretrained models are subsequently evaluated on six datasets (WorldView-2/3/4, IKONOS, QuickBird, GaoFen-2) using zero-shot and one-shot paradigms, with both full- and freeze-tuning approaches for fine-tuning. Extensive experiments on different network architectures including convolutional neural networks, Transformer, and Mamba demonstrate that our pretraining strategy significantly improves generalization performance across different satellite sensors and imaging conditions for various fusion models. The pretrained models achieve superior results in zero-shot scenarios and show remarkable adaptation capability with minimal real data in one-shot settings. Our work provides a practical solution for cross-domain pansharpening, establishes a new benchmark for generalization in remote sensing image fusion tasks, and paves the way for leveraging foundation models through advanced training strategies.

---

### Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models

Authors: Xinyue Ai, Yutong He, Albert Gu, Ruslan Salakhutdinov, J Zico Kolter, Nicholas Matthew Boffi, Max Simchowitz
Published: 2025-12-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.02636v3

Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet paradoxically, some of today's best generative models -- diffusion and flow-based models -- still require hundreds to thousands of neural function evaluations (NFEs) to compute a single likelihood. While recent distillation methods have successfully accelerated sampling to just a few steps, they achieve this at the cost of likelihood tractability: existing approaches either abandon likelihood computation entirely or still require expensive integration over full trajectories. We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude. Our key insight is that in continuous normalizing flows, the coupled ODEs for sampling and likelihood are computed from a shared underlying velocity field, allowing us to jointly distill both the sampling trajectory and cumulative divergence using a single flow map. F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head. Experiments demonstrate F2D2's capability of achieving accurate log-likelihood with few-step evaluations while maintaining high sample quality, solving a long-standing computational bottleneck in flow-based generative models. As an application of our approach, we propose a lightweight self-guidance method that enables a 2-step MeanFlow to outperform a 1024 step flow matching model with only a single additional backward NFE.

---

### Zero-Shot Instruction Following in RL via Structured LTL Representations

Authors: Mattia Giuri, Mathias Jackermeier, Alessandro Abate
Published: 2025-12-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.02633v1

Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents. Recent work has shown that interpreting LTL instructions as finite automata, which can be seen as high-level programs monitoring task progress, enables learning a single generalist policy capable of executing arbitrary instructions at test time. However, existing approaches fall short in environments where multiple high-level events (i.e., atomic propositions) can be true at the same time and potentially interact in complicated ways. In this work, we propose a novel approach to learning a multi-task policy for following arbitrary LTL instructions that addresses this shortcoming. Our method conditions the policy on sequences of simple Boolean formulae, which directly align with transitions in the automaton, and are encoded via a graph neural network (GNN) to yield structured task representations. Experiments in a complex chess-based environment demonstrate the advantages of our approach.

---

### SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization

Authors: Zhengcheng Wang, Zichuan Lin, Yijun Yang, Haobo Fu, Deheng Ye
Published: 2025-12-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.02631v1

Existing Vision-Language Navigation (VLN) agents based on Large Vision-Language Models (LVLMs) often suffer from perception errors, reasoning errors, and planning errors, which significantly hinder their navigation performance. To address these limitations, a novel VLN agent framework, named SeeNav-Agent, is proposed in this work. First, to reduce perception hallucinations of the visual module of the VLN agent, a dual-view Visual Prompt (VP) technique is introduced in the input space, which can also improve the agent's understanding of current spatial states. Subsequently, a novel step-level Reinforcement Fine-Tuning (RFT) method, Step Reward Group Policy Optimization (SRGPO), is designed for the post-training of VLN agents. In SRGPO, we first define verifiable process rewards for the navigation task, and then perform efficient step-level advantage estimation by randomly grouping different navigation steps. SRGPO provides dense reward signals for the reinforcement learning process of the VLN agent and enhances its planning capability. Experimental results on the EmbodiedBench Navigation benchmark indicate that by introducing the zero-shot VP module, the GPT-4.1 achieves a navigation success rate of 86.7%, surpassing the current best LVLM by approximately 20 percentage points (pp). Through post-training based on SRGPO, the Qwen2.5-VL-3B model reaches a navigation success rate of 72.3%, outperforming the best existing LVLM model by 5.6 pp. Moreover, compared to RFT algorithms such as GRPO and GiGPO, the proposed SRGPO demonstrates significant improvements in training stability, convergence efficiency, and generalization capability.

---

### Adapting Tensor Kernel Machines to Enable Efficient Transfer Learning for Seizure Detection

Authors: Seline J. S. de Rooij, Borbála Hunyadi
Published: 2025-12-02
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.02626v1

Transfer learning aims to optimize performance in a target task by learning from a related source problem. In this work, we propose an efficient transfer learning method using a tensor kernel machine. Our method takes inspiration from the adaptive SVM and hence transfers 'knowledge' from the source to the 'adapted' model via regularization. The main advantage of using tensor kernel machines is that they leverage low-rank tensor networks to learn a compact non-linear model in the primal domain. This allows for a more efficient adaptation without adding more parameters to the model. To demonstrate the effectiveness of our approach, we apply the adaptive tensor kernel machine (Adapt-TKM) to seizure detection on behind-the-ear EEG. By personalizing patient-independent models with a small amount of patient-specific data, the patient-adapted model (which utilizes the Adapt-TKM), achieves better performance compared to the patient-independent and fully patient-specific models. Notably, it is able to do so while requiring around 100 times fewer parameters than the adaptive SVM model, leading to a correspondingly faster inference speed. This makes the Adapt-TKM especially useful for resource-constrained wearable devices.

---

### CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography

Authors: Mayar Elfares, Pascal Reisert, Tilman Dietz, Manpa Barman, Ahmed Zaki, Ralf Küsters, Andreas Bulling
Published: 2025-12-02
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.02625v1

Large language models (LLMs) excel at many general-purpose natural language processing tasks. However, their ability to perform deep reasoning and mathematical analysis, particularly for complex tasks as required in cryptography, remains poorly understood, largely due to the lack of suitable data for evaluation and training. To address this gap, we present CryptoQA, the first large-scale question-answering (QA) dataset specifically designed for cryptography. CryptoQA contains over two million QA pairs drawn from curated academic sources, along with contextual metadata that can be used to test the cryptographic capabilities of LLMs and to train new LLMs on cryptographic tasks. We benchmark 15 state-of-the-art LLMs on CryptoQA, evaluating their factual accuracy, mathematical reasoning, consistency, referencing, backward reasoning, and robustness to adversarial samples. In addition to quantitative metrics, we provide expert reviews that qualitatively assess model outputs and establish a gold-standard baseline. Our results reveal significant performance deficits of LLMs, particularly on tasks that require formal reasoning and precise mathematical knowledge. This shows the urgent need for LLM assistants tailored to cryptography research and development. We demonstrate that, by using CryptoQA, LLMs can be fine-tuned to exhibit better performance on cryptographic tasks.

---

### PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding

Authors: Zheng Huang, Xukai Liu, Tianyu Hu, Kai Zhang, Ye Liu
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02624v1

PowerPoint presentations combine rich textual content with structured visual layouts, making them a natural testbed for evaluating the multimodal reasoning and layout understanding abilities of modern MLLMs. However, existing benchmarks focus solely on narrow subtasks while overlooking layout-centric challenges, which are central to real-world slide creation and editing. To bridge this gap, we introduce PPTBench, a comprehensive multimodal benchmark for evaluating LLMs on PowerPoint-related tasks. Leveraging a diverse source of 958 PPTX files, PPTBench evaluates models across four categories with 4,439 samples, including Detection, Understanding, Modification, and Generation. Our experiments reveal a substantial gap between semantic understanding and visual-layout reasoning in current MLLMs: models can interpret slide content but fail to produce coherent spatial arrangements. Ablation and further analysis show that current MLLMs struggle to combine visual cues with JSON-based layout structures and fail to integrate visual information into their API planning ability. And case studies visually expose systematic layout errors such as misalignment and element overlap. These findings provides a new perspective on evaluating VLLMs in PPT scenarios, highlighting challenges and directions for future research on visual-structural reasoning and coherent slide generation. All datasets and code are fully released to support reproducibility and future research.

---

### RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence

Authors: Xuming He, Zehao Fan, Hengjia Li, Fan Zhuo, Hankun Xu, Senlin Cheng, Di Weng, Haifeng Liu, Can Ye, Boxi Wu
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02622v1

Recent advances in video generation have enabled the synthesis of videos with strong temporal consistency and impressive visual quality, marking a crucial step toward vision foundation models. To evaluate these video generation models, existing benchmarks primarily focus on factors related to visual perception and understanding, like visual aesthetics, instruction adherence, and temporal coherence. However, the rule-based reasoning capabilities of video generation models remain largely unexplored. Although recent studies have carried out preliminary explorations into whether video models can serve as zero-shot learners, they still lack a fine-grained decomposition of reasoning capabilities and a comprehensive evaluation protocol. To address this gap, we introduce RULER-Bench, a benchmark designed to evaluate the reasoning ability of video generation models from the perspective of cognitive rules. Built upon two fundamental paradigms: text-to-video and image-to-video, RULER-Bench covers 40 representative tasks spanning six rule categories with 622 high-quality annotated instances. For the evaluation of each generated video, we construct a checklist covering four metrics and leverage GPT-o3 to assign scores to each question, achieving 85% alignment with human judgements. Extensive experiments show that the state-of-the-art model achieves only 48.87% on the rule coherence metric, highlighting significant room for improvement in the reasoning capability of next-level video models. We expect that the insight obtained from RULER-Bench will facilitate further development of reasoning-aware video generation, advancing video generation models toward vision foundation intelligence.

---

### Content-Aware Texturing for Gaussian Splatting

Authors: Panagiotis Papantonakis, Georgios Kopanas, Fredo Durand, George Drettakis
Published: 2025-12-02
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.02621v1

Gaussian Splatting has become the method of choice for 3D reconstruction and real-time rendering of captured real scenes. However, fine appearance details need to be represented as a large number of small Gaussian primitives, which can be wasteful when geometry and appearance exhibit different frequency characteristics. Inspired by the long tradition of texture mapping, we propose to use texture to represent detailed appearance where possible. Our main focus is to incorporate per-primitive texture maps that adapt to the scene in a principled manner during Gaussian Splatting optimization. We do this by proposing a new appearance representation for 2D Gaussian primitives with textures where the size of a texel is bounded by the image sampling frequency and adapted to the content of the input images. We achieve this by adaptively upscaling or downscaling the texture resolution during optimization. In addition, our approach enables control of the number of primitives during optimization based on texture resolution. We show that our approach performs favorably in image quality and total number of parameters used compared to alternative solutions for textured Gaussian primitives. Project page: https://repo-sam.inria.fr/nerphys/gs-texturing/

---

### Modeling and Inverse Identification of Interfacial Heat Conduction in Finite Layer and Semi-Infinite Substrate Systems via a Physics-Guided Neural Framework

Authors: Wenhao Sha, Tienchong Chang
Published: 2025-12-02
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2512.02618v1

Heat transfer in semiconductor devices is dominated by chip and substrate assemblies, where heat generated within a finite chip layer dissipates into a semi-infinite substrate with much higher thermophysical properties. This mismatch produces steep interfacial temperature gradients, making the transient thermal response highly sensitive to the interface. Conventional numerical solvers require excessive discretization to resolve these dynamics, while physics-informed neural networks (PINNs) often exhibit unstable convergence and loss of physical consistency near the material interface. To address these challenges, we introduce HeatTransFormer, a physics-guided Transformer architecture for interface-dominated diffusion problems. The framework integrates physically informed spatiotemporal sampling, a Laplace-based activation emulating analytical diffusion solutions, and a mask-free attention mechanism supporting bidirectional spatiotemporal coupling. These components enable the model to resolve steep gradients, maintain physical consistency, and remain stable where PINNs typically fail. HeatTransFormer produces coherent temperature fields across the interface when applied to a finite layer and semi-infinite substrate configuration. Coupled with a physics-constrained inverse strategy, it further enables reliable identification of three unknown thermal properties simultaneously using only external measurements. Overall, this work demonstrates that physics-guided Transformer architectures provide a unified framework for forward and inverse modeling in interface-dominated thermal systems.

---

### Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction

Authors: Yubo Hou, Mohamed Ragab, Min Wu, Chee-Keong Kwoh, Xiaoli Li, Zhenghua Chen
Published: 2025-12-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.02610v1

Accurate prediction of the Remaining Useful Life (RUL) in machinery can significantly diminish maintenance costs, enhance equipment up-time, and mitigate adverse outcomes. Data-driven RUL prediction techniques have demonstrated commendable performance. However, their efficacy often relies on the assumption that training and testing data are drawn from the same distribution or domain, which does not hold in real industrial settings. To mitigate this domain discrepancy issue, prior adversarial domain adaptation methods focused on deriving domain-invariant features. Nevertheless, they overlook target-specific information and inconsistency characteristics pertinent to the degradation stages, resulting in suboptimal performance. To tackle these issues, we propose a novel domain adaptation approach for cross-domain RUL prediction named TACDA. Specifically, we propose a target domain reconstruction strategy within the adversarial adaptation process, thereby retaining target-specific information while learning domain-invariant features. Furthermore, we develop a novel clustering and pairing strategy for consistent alignment between similar degradation stages. Through extensive experiments, our results demonstrate the remarkable performance of our proposed TACDA method, surpassing state-of-the-art approaches with regard to two different evaluation metrics. Our code is available at https://github.com/keyplay/TACDA.

---

### SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction

Authors: Shengkai Wu, Jinrong Yang, Wenqiu Luo, Linfeng Gao, Chaohui Shang, Meiyu Zhi, Mingshan Sun, Fangping Yang, Liangliang Ren, Yong Zhao
Published: 2025-12-02
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2512.02609v1

Imitation learning for robotic grasping is often plagued by the multimodal problem: when a scene contains multiple valid targets, demonstrations of grasping different objects create conflicting training signals. Standard imitation learning policies fail by averaging these distinct actions into a single, invalid action. In this paper, we introduce SAM2Grasp, a novel framework that resolves this issue by reformulating the task as a uni-modal, prompt-conditioned prediction problem. Our method leverages the frozen SAM2 model to use its powerful visual temporal tracking capability and introduces a lightweight, trainable action head that operates in parallel with its native segmentation head. This design allows for training only the small action head on pre-computed temporal-visual features from SAM2. During inference, an initial prompt, such as a bounding box provided by an upstream object detection model, designates the specific object to be grasped. This prompt conditions the action head to predict a unique, unambiguous grasp trajectory for that object alone. In all subsequent video frames, SAM2's built-in temporal tracking capability automatically maintains stable tracking of the selected object, enabling our model to continuously predict the grasp trajectory from the video stream without further external guidance. This temporal-prompted approach effectively eliminates ambiguity from the visuomotor policy. We demonstrate through extensive experiments that SAM2Grasp achieves state-of-the-art performance in cluttered, multi-object grasping tasks.

---

### IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai

Authors: Pengju Lu
Published: 2025-12-02
Categories: cs.AI, cs.MA, cs.SE
arXiv: https://arxiv.org/abs/2512.02605v1

This technical white paper introduces the Interactive Agents Call Tree (IACT), a computational model designed to address the limitations of static, hard-coded agent workflows. Unlike traditional systems that require pre-defined graphs or specialized programming, IACT operates as a general-purpose autonomous system driven purely by user dialogue. Given a high-level objective, the system autonomously grows a dynamic, recursive agent topology incrementally tailored to the problem's structure. This allows it to scale its organizational complexity to match open-ended tasks. To mitigate the error propagation inherent in unidirectional function calls, IACT introduces interactional redundancy by replacing rigid invocations with bidirectional, stateful dialogues. This mechanism enables runtime error correction and ambiguity resolution. We describe the architecture, design principles, and practical lessons behind the production deployment of this model in the kragent.ai system, presenting qualitative evidence from real-world workflows rather than exhaustive benchmark results.

---

### Spoken Conversational Agents with Large Language Models

Authors: Chao-Han Huck Yang, Andreas Stolcke, Larry Heck
Published: 2025-12-02
Categories: cs.CL, cs.MA, cs.NE, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2512.02593v1

Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-grounded systems. We frame adaptation of text LLMs to audio, cross-modal alignment, and joint speech-text training; review datasets, metrics, and robustness across accents and compare design choices (cascaded vs. E2E, post-ASR correction, streaming). We link industrial assistants to current open-domain and task-oriented agents, highlight reproducible baselines, and outline open problems in privacy, safety, and evaluation. Attendees leave with practical recipes and a clear systems-level roadmap.

---

### PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Authors: Junyi Hou, Andre Lin Huikai, Nuo Chen, Yiwei Gong, Bingsheng He
Published: 2025-12-02
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2512.02589v2

Large language models are increasingly embedded into academic writing workflows, yet existing assistants remain external to the editor, preventing deep interaction with document state, structure, and revision history. This separation makes it impossible to support agentic, context-aware operations directly within LaTeX editors such as Overleaf. We present PaperDebugger, an in-editor, multi-agent, and plugin-based academic writing assistant that brings LLM-driven reasoning directly into the writing environment. Enabling such in-editor interaction is technically non-trivial: it requires reliable bidirectional synchronization with the editor, fine-grained version control and patching, secure state management, multi-agent scheduling, and extensible communication with external tools. PaperDebugger addresses these challenges through a Chrome-approved extension, a Kubernetes-native orchestration layer, and a Model Context Protocol (MCP) toolchain that integrates literature search, reference lookup, document scoring, and revision pipelines. Our demo showcases a fully integrated workflow, including localized edits, structured reviews, parallel agent execution, and diff-based updates, encapsulated within a minimal-intrusion user interface (UI). Early aggregated analytics demonstrate active user engagement and validate the practicality of an editor-native, agentic writing assistant. More details about this demo and video could be found at https://github.com/PaperDebugger/PaperDebugger.

---

### Training Diffusion Policies via Prior-Mapping Co-Evolution

Authors: Chubin Zhang, Zhenglin Wan, Feng Chen, Fuchao Yang, Lang Feng, Yaxin Zhou, Xingrui Yu, Yang You, Ivor Tsang, Bo An
Published: 2025-12-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.02581v3

Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions required for complex control. Conversely, expressive generative policies -- such as diffusion and flow matching -- can be difficult to optimize in online RL due to intractable likelihoods and gradients propagating through long sampling chains. We address this tension with a key structural principle: decoupling optimization from generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm-agnostic framework that trains expressive policies from scratch by confining policy optimization to a tractable latent space while delegating action synthesis to a conditional generative decoder. Viewed as prior-mapping co-evolution, each stage first improves a tractable latent prior through RL and then consolidates the resulting behavior into a more expressive prior-to-action mapping. This two-timescale schedule, anchored by fixed-prior decoder refinement, enables stable optimization while continuously expanding expressiveness. Empirically, \textsc{GoRL} consistently outperforms unimodal and generative baselines across diverse continuous-control tasks. Notably, GoRL achieves returns exceeding 870 on HopperStand, more than 3* the strongest baseline; on high-dimensional humanoid tasks, it further outperforms the strongest non-GoRL baseline by over an order of magnitude.

---

### From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Authors: Changpeng Yang, Jinyang Wu, Yuchen Liu, Shuai Zhang, Yang Li, Qiliang Liang, Hongzhen Wang, Shuai Nie, Jiaming Xu, Runyu Shi, Ying Huang, Guoquan Zhang
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02580v2

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than expected, thereby yielding both positive and negative signals for training. However, the indiscriminate mixing of the two signals in existing methods, especially from the early stages, may lead to ambiguous guidance and limited gains. To address this issue, we propose **CAPO** (**C**urriculum **A**dvantage **P**olicy **O**ptimization), an adaptive curriculum mechanism based on advantage signals. The proposed mechanism bootstraps imitation learning with positive-only advantage samples to establish robust foundations, and subsequently introduces negative signals to cultivate discriminative capabilities, thereby improving generalization across complex scenarios. Compatible with diverse optimization methods including GRPO, PPO, RLOO, and Reinforce++, our method consistently achieves stable and significant improvements in mathematical reasoning tasks, and further generalizes effectively to multimodal Graphical User Interface (GUI) reasoning scenarios, establishing itself as a versatile and robust optimization framework.

---

### Co-speech Gesture Video Generation via Motion-Based Graph Retrieval

Authors: Yafei Song, Peng Zhang, Bang Zhang
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02576v1

Synthesizing synchronized and natural co-speech gesture videos remains a formidable challenge. Recent approaches have leveraged motion graphs to harness the potential of existing video data. To retrieve an appropriate trajectory from the graph, previous methods either utilize the distance between features extracted from the input audio and those associated with the motions in the graph or embed both the input audio and motion into a shared feature space. However, these techniques may not be optimal due to the many-to-many mapping nature between audio and gestures, which cannot be adequately addressed by one-to-one mapping. To alleviate this limitation, we propose a novel framework that initially employs a diffusion model to generate gesture motions. The diffusion model implicitly learns the joint distribution of audio and motion, enabling the generation of contextually appropriate gestures from input audio sequences. Furthermore, our method extracts both low-level and high-level features from the input audio to enrich the training process of the diffusion model. Subsequently, a meticulously designed motion-based retrieval algorithm is applied to identify the most suitable path within the graph by assessing both global and local similarities in motion. Given that not all nodes in the retrieved path are sequentially continuous, the final step involves seamlessly stitching together these segments to produce a coherent video output. Experimental results substantiate the efficacy of our proposed method, demonstrating a significant improvement over prior approaches in terms of synchronization accuracy and naturalness of generated gestures.

---

### Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System

Authors: Martin Weiss, Jesko Hecking-Harbusch, Jochen Quante, Matthias Woehrle
Published: 2025-12-02
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.02567v2

The advent of strong generative AI has a considerable impact on various software engineering tasks such as code repair, test generation, or language translation. While tools like GitHub Copilot are already in widespread use in interactive settings, automated approaches require a higher level of reliability before being usable in industrial practice. In this paper, we focus on three aspects that directly influence the quality of the results: a) the effect of automated feedback loops, b) the choice of Large Language Model (LLM), and c) the influence of behavior-preserving code changes. We study the effect of these three variables on an automated C-to-Rust translation system. Code translation from C to Rust is an attractive use case in industry due to Rust's safety guarantees. The translation system is based on a generate-and-check pattern, in which Rust code generated by the LLM is automatically checked for compilability and behavioral equivalence with the original C code. For negative checking results, the LLM is re-prompted in a feedback loop to repair its output. These checks also allow us to evaluate and compare the respective success rates of the translation system when varying the three variables. Our results show that without feedback loops LLM selection has a large effect on translation success. However, when the translation system uses feedback loops the differences across models diminish. We observe this for the average performance of the system as well as its robustness under code perturbations. Finally, we also identify that diversity provided by code perturbations can even result in improved system performance.

---

### From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature

Authors: Kun Yuan, Min Woo Sun, Zhen Chen, Alejandro Lozano, Xiangteng He, Shi Li, Nassir Navab, Xiaoxiao Sun, Nicolas Padoy, Serena Yeung-Levy
Published: 2025-12-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.02566v2

There is a growing interest in developing strong biomedical vision-language models. A popular approach to achieve robust representations is to use web-scale scientific data. However, current biomedical vision-language pretraining typically compresses rich scientific figures and text into coarse figure-level pairs, discarding the fine-grained correspondences that clinicians actually rely on when zooming into local structures. To tackle this issue, we introduce Panel2Patch, a novel data pipeline that mines hierarchical structure from existing biomedical scientific literature, i.e., multi-panel, marker-heavy figures and their surrounding text, and converts them into multi-granular supervision. Given scientific figures and captions, Panel2Patch parses layouts, panels, and visual markers, then constructs hierarchical aligned vision-language pairs at the figure, panel, and patch levels, preserving local semantics instead of treating each figure as a single data sample. Built on this hierarchical corpus, we develop a granularity-aware pretraining strategy that unifies heterogeneous objectives from coarse didactic descriptions to fine region-focused phrases. By applying Panel2Patch to only a small set of the literature figures, we extract far more effective supervision than prior pipelines, enabling substantially better performance with less pretraining data.

---

### EZYer: A simulacrum of high school with generative agent

Authors: Jinming Yang, Zimu Ji, Weiqi Luo, Gaoxi Wang, Bin Ma, Yueling Deng
Published: 2025-12-02
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2512.02561v1

With the rapid development of the online education and large language model, the existing educational tools still suffer from incomplete service, insufficient performance and weak interactivity in terms of courseware generation, interactive notes and quality assurance of content. In particular, the proposed generative agent EZYer : 1) Teacher Module: Integrating the Text Corpus retrieval and in-depth generation technologies, it automatically generates structured teaching materials and LaTeX Beamer courseware in line with the high school mathematics syllabus and supports user-defined image insertion. 2) Student Module: Throughout the collaborative interaction of the four roles of Teacher, Assistant, Top Student and Struggling Student, Note Taker summarizes and generates academic notes to enhance the depth and interest of learning. 3) Controller: set up keyword filtering system, content scoring system, role co-validation system, and dynamic content correction system. This ensure academic strictness and pedagogical propriety of EZYer inputs and outputs. In order to evaluate EZYer, this paper designs five-dimensional evaluation indexes of content accuracy, knowledge coverage, usability, formatting correctness and visual design and appeal, and scores 100 Beamer and Notes generated by EZYer by five large language models, separately, and the results show that the quality of EZYer-generated content is excellent and has a good application prospect.

---

### Empathy Level Prediction in Multi-Modal Scenario with Supervisory Documentation Assistance

Authors: Yufei Xiao, Shangfei Wang
Published: 2025-12-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.02558v1

Prevalent empathy prediction techniques primarily concentrate on a singular modality, typically textual, thus neglecting multi-modal processing capabilities. They also overlook the utilization of certain privileged information, which may encompass additional empathetic content. In response, we introduce an advanced multi-modal empathy prediction method integrating video, audio, and text information. The method comprises the Multi-Modal Empathy Prediction and Supervisory Documentation Assisted Training. We use pre-trained networks in the empathy prediction network to extract features from various modalities, followed by a cross-modal fusion. This process yields a multi-modal feature representation, which is employed to predict empathy labels. To enhance the extraction of text features, we incorporate supervisory documents as privileged information during the assisted training phase. Specifically, we apply the Latent Dirichlet Allocation model to identify potential topic distributions to constrain text features. These supervisory documents, created by supervisors, focus on the counseling topics and the counselor's display of empathy. Notably, this privileged information is only available during training and is not accessible during the prediction phase. Experimental results on the multi-modal and dialogue empathy datasets demonstrate that our approach is superior to the existing methods.

---

### DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Authors: DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu et al.
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02556v1

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance in long-context scenarios. (2) Scalable Reinforcement Learning Framework: By implementing a robust reinforcement learning protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par with Gemini-3.0-Pro, achieving gold-medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). (3) Large-Scale Agentic Task Synthesis Pipeline: To integrate reasoning into tool-use scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This methodology facilitates scalable agentic post-training, yielding substantial improvements in generalization and instruction-following robustness within complex, interactive environments.

---

### ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce

Authors: Zheng Fang, Donghao Xie, Ming Pang, Chunyuan Yuan, Xue Jiang, Changping Peng, Zhangang Lin, Zheng Luo
Published: 2025-12-02
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2512.02555v1

Relevance modeling in e-commerce search remains challenged by semantic gaps in term-matching methods (e.g., BM25) and neural models' reliance on the scarcity of domain-specific hard samples. We propose ADORE, a self-sustaining framework that synergizes three innovations: (1) A Rule-aware Relevance Discrimination module, where a Chain-of-Thought LLM generates intent-aligned training data, refined via Kahneman-Tversky Optimization (KTO) to align with user behavior; (2) An Error-type-aware Data Synthesis module that auto-generates adversarial examples to harden robustness; and (3) A Key-attribute-enhanced Knowledge Distillation module that injects domain-specific attribute hierarchies into a deployable student model. ADORE automates annotation, adversarial generation, and distillation, overcoming data scarcity while enhancing reasoning. Large-scale experiments and online A/B testing verify the effectiveness of ADORE. The framework establishes a new paradigm for resource-efficient, cognitively aligned relevance modeling in industrial applications.

---

### OmniPerson: Unified Identity-Preserving Pedestrian Generation

Authors: Changxiao Ma, Chao Yuan, Xincheng Shi, Yuzhuo Ma, Yongfei Zhang, Longkun Zhou, Yujia Zhang, Shangze Li, Yifan Xu
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02554v1

Person re-identification (ReID) suffers from a lack of large-scale high-quality training data due to challenges in data privacy and annotation costs. While previous approaches have explored pedestrian generation for data augmentation, they often fail to ensure identity consistency and suffer from insufficient controllability, thereby limiting their effectiveness in dataset augmentation. To address this, We introduce OmniPerson, the first unified identity-preserving pedestrian generation pipeline for visible/infrared image/video ReID tasks. Our contributions are threefold: 1) We proposed OmniPerson, a unified generation model, offering holistic and fine-grained control over all key pedestrian attributes. Supporting RGB/IR modality image/video generation with any number of reference images, two kinds of person poses, and text. Also including RGB-to-IR transfer and image super-resolution abilities.2) We designed Multi-Refer Fuser for robust identity preservation with any number of reference images as input, making OmniPerson could distill a unified identity from a set of multi-view reference images, ensuring our generated pedestrians achieve high-fidelity pedestrian generation.3) We introduce PersonSyn, the first large-scale dataset for multi-reference, controllable pedestrian generation, and present its automated curation pipeline which transforms public, ID-only ReID benchmarks into a richly annotated resource with the dense, multi-modal supervision required for this task. Experimental results demonstrate that OmniPerson achieves SoTA in pedestrian generation, excelling in both visual fidelity and identity consistency. Furthermore, augmenting existing datasets with our generated data consistently improves the performance of ReID models. We will open-source the full codebase, pretrained model, and the PersonSyn dataset.

---

### From Veracity to Diffusion: Adressing Operational Challenges in Moving From Fake-News Detection to Information Disorders

Authors: Francesco Paolo Savatteri, Chahan Vidal-Gorène, Florian Cafiero
Published: 2025-12-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.02552v2

A wide part of research on misinformation has relied lies on fake-news detection, a task framed as the prediction of veracity labels attached to articles or claims. Yet social-science research has repeatedly emphasized that information manipulation goes beyond fabricated content and often relies on amplification dynamics. This theoretical turn has consequences for operationalization in applied social science research. What changes empirically when prediction targets move from veracity to diffusion? And which performance level can be attained in limited resources setups ? In this paper we compare fake-news detection and virality prediction across two datasets, EVONS and FakeNewsNet. We adopt an evaluation-first perspective and examine how benchmark behavior changes when the prediction target shifts from veracity to diffusion. Our experiments show that fake-news detection is comparatively stable once strong textual embeddings are available, whereas virality prediction is much more sensitive to operational choices such as threshold definition and early observation windows. The paper proposes practical ways to operationalize lightweight, transparent pipelines for misinformation-related prediction tasks that can rival with state-of-the-art.

---

### CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Authors: Songqiao Su, Xiaoya Li, Albert Wang, Guoyin Wang, Jiwei Li, Chris Shum
Published: 2025-12-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.02551v4

In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. Using CUDA execution speed as the RL reward, CUDA-L2 automatically optimizes HGEMM kernels across 1,000 configurations. CUDA-L2 systematically outperforms major matmul baselines to date, from the widely-used torch.matmul to state-of-the-art Nvidia's closed-source libraries, i.e., cuBLAS, cuBLASLt. In offline mode, where kernels are executed consecutively without time intervals, CUDA-L2 yields +22.0% over torch.matmul on average; +19.2% over cuBLAS using the optimal layout configuration (normal-normal NN and transposed-normal TN); +16.8% over cuBLASLt-heuristic, which queries cuBLASLt library and selects the algorithm based on the heuristic's suggestion; and +11.4% over the most competitive cuBLASLt-AutoTuning model, which selects the fastest algorithm from up to 100 candidates from cuBLASLt's suggestions. In server mode, where kernels are executed at random intervals simulating real-time inference, the speedups further increase to +28.7%, +26.0%, +22.4%, and +15.9% for torch.matmul, cuBLAS, cuBLASLt-heuristic, and cuBLASLt-AutoTuning respectively. CUDA-L2 shows that even the most performance-critical, heavily-optimized kernels like HGEMM can be improved through LLM-guided RL automation by systematically exploring configuration spaces at scales impractical for humans. Project and code can be found at github.com/ornith-ai/CUDA-L2

---

### Sparse Computations in Deep Learning Inference

Authors: Ioanna Tasou, Panagiotis Mpakos, Angelos Vlachos, Dionysios Adamopoulos, Georgios Giannakopoulos, Konstantinos Katsikopoulos, Ioannis Karaparisis, Maria Lazou, Spyridon Loukovitis, Areti Mei, Anastasia Poulopoulou, Angeliki Dimitriou et al.
Published: 2025-12-02
Categories: cs.CE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.02550v1

The computational demands of modern Deep Neural Networks (DNNs) are immense and constantly growing. While training costs usually capture public attention, inference demands are also contributing in significant computational, energy and environmental footprints. Sparsity stands out as a critical mechanism for drastically reducing these resource demands. However, its potential remains largely untapped and is not yet fully incorporated in production AI systems. To bridge this gap, this work provides the necessary knowledge and insights for performance engineers keen to get involved in deep learning inference optimization. In particular, in this work we: a) discuss the various forms of sparsity that can be utilized in DNN inference, b) explain how the original dense computations translate to sparse kernels, c) provide an extensive bibliographic review of the state-of-the-art in the implementation of these kernels for CPUs and GPUs, d) discuss the availability of sparse datasets in support of sparsity-related research and development, e) explore the current software tools and frameworks that provide robust sparsity support, and f) present evaluation results of different implementations of the key SpMM and SDDMM kernels on CPU and GPU platforms. Ultimately, this paper aims to serve as a resource for performance engineers seeking to develop and deploy highly efficient sparse deep learning models in productions.

---

### Tensor Network Based Feature Learning Model

Authors: Albert Saiapin, Kim Batselier
Published: 2025-12-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.02547v1

Many approximations were suggested to circumvent the cubic complexity of kernel-based algorithms, allowing their application to large-scale datasets. One strategy is to consider the primal formulation of the learning problem by mapping the data to a higher-dimensional space using tensor-product structured polynomial and Fourier features. The curse of dimensionality due to these tensor-product features was effectively solved by a tensor network reparameterization of the model parameters. However, another important aspect of model training - identifying optimal feature hyperparameters - has not been addressed and is typically handled using the standard cross-validation approach. In this paper, we introduce the Feature Learning (FL) model, which addresses this issue by representing tensor-product features as a learnable Canonical Polyadic Decomposition (CPD). By leveraging this CPD structure, we efficiently learn the hyperparameters associated with different features alongside the model parameters using an Alternating Least Squares (ALS) optimization method. We prove the effectiveness of the FL model through experiments on real data of various dimensionality and scale. The results show that the FL model can be consistently trained 3-5 times faster than and have the prediction quality on par with a standard cross-validated model.

---

### Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt Engineering

Authors: Vishnu Sarukkai, Asanshay Gupta, James Hong, Michaël Gharbi, Kayvon Fatahalian
Published: 2025-12-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.02543v3

Deploying LLM agents at scale typically requires choosing between quality and cost. Existing cost-reduction approaches fail to preserve agility: the ability to iterate rapidly without human time bottlenecks. Prompt engineering is brittle and slows iteration, while fine-tuning requires multi-day training and commitment to fixed designs; both are impractical for iterative workflows and time-sensitive batch jobs. We demonstrate that established inference-time techniques--dynamic in-context learning and self-consistency cascades--can be leveraged to shift the cost-accuracy Pareto frontier while preserving agility. Practitioners run the teacher on a small task subset to collect demonstrations, then immediately deploy a cheaper student on the remainder. At each step, the system retrieves relevant teacher demonstrations as in-context examples. When multiple student samples agree, we proceed; when they diverge, we fall back to the teacher. This requires no prompt engineering or training. On ALFWorld, we match teacher accuracy at 2.5x lower cost (0.059 to 0.024 per episode). On AppWorld, we achieve 3.5x cost reduction while recovering 79% of teacher accuracy. Our empirical analyses provide guidance on key design choices: teacher database size, demonstration set size, retrieval strategy, and cascade thresholds. These analyses highlight inference-time levers for navigating cost-performance tradeoffs without sacrificing human development speed.

---

### AVGGT: Rethinking Global Attention for Accelerating VGGT

Authors: Xianbing Sun, Zhikai Zhu, Zhengyu Lou, Bo Yang, Jinyang Tang, Liqing Zhang, He Wang, Jianfu Zhang
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02541v2

Models such as VGGT and $π^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a systematic analysis of how global attention contributes to multi-view reasoning. In this paper, we first conduct an in-depth investigation of the global attention modules in VGGT and $π^3$ to better understand their roles. Our analysis reveals a clear division of roles in the alternating global-frame architecture: early global layers do not form meaningful correspondences, middle layers perform cross-view alignment, and last layers provide only minor refinements. Guided by these findings, we propose a training-free two-step acceleration scheme: (1) converting early global layers into frame attention, and (2) subsampling global attention by subsampling K/V over patch tokens with diagonal preservation and a mean-fill component. We instantiate this strategy on VGGT and $π^3$ and evaluate across standard pose and point-map benchmarks. Our method achieves substantial inference acceleration across different context lengths, yielding about $2\times$ speedup at 100 frames, $4$--$5\times$ at 300 frames, and $8$--$10\times$ at 800 frames, while matching or slightly improving the accuracy of the original models and remaining robust in extremely dense multi-view settings where prior sparse-attention baselines fail.

---

### WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens

Authors: Jian Yang, Dacheng Yin, Xiaoxuan He, Yong Li, Fengyun Rao, Jing Lyu, Wei Zhai, Yang Cao, Zheng-Jun Zha
Published: 2025-12-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.02536v1

Recent progress in multimodal large language models (MLLMs) has highlighted the challenge of efficiently bridging pre-trained Vision-Language Models (VLMs) with Diffusion Models. While methods using a fixed number of learnable query tokens offer computational efficiency, they suffer from task generalization collapse, failing to adapt to new tasks that are distant from their pre-training tasks. To overcome this, we propose Noisy Query Tokens, which learn a distributed representation space between the VLM and Diffusion Model via end-to-end optimization, enhancing continual learning. Additionally, we introduce a VAE branch with linear projection to recover fine-grained image details. Experimental results confirm our approach mitigates generalization collapse and enables stable continual learning across diverse tasks.

---

### Laplace Approximation For Tensor Train Kernel Machines In System Identification

Authors: Albert Saiapin, Kim Batselier
Published: 2025-12-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.02532v1

To address the scalability limitations of Gaussian process (GP) regression, several approximation techniques have been proposed. One such method is based on tensor networks, which utilizes an exponential number of basis functions without incurring exponential computational cost. However, extending this model to a fully probabilistic formulation introduces several design challenges. In particular, for tensor train (TT) models, it is unclear which TT-core should be treated in a Bayesian manner. We introduce a Bayesian tensor train kernel machine that applies Laplace approximation to estimate the posterior distribution over a selected TT-core and employs variational inference (VI) for precision hyperparameters. Experiments show that core selection is largely independent of TT-ranks and feature structure, and that VI replaces cross-validation while offering up to 65x faster training. The method's effectiveness is demonstrated on an inverse dynamics problem.

---