# Research Papers — 2026-01 · bundle page 173 of 189 > Full-text markdown of papers #8601–8650 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/173 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/172.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/174.md) ### Remote Sensing Change Detection via Weak Temporal Supervision Authors: Xavier Bou, Elliot Vincent, Gabriele Facciolo, Rafael Grompone von Gioi, Jean-Michel Morel, Thibaud Ehret Published: 2026-01-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.02126v1 Semantic change detection in remote sensing aims to identify land cover changes between bi-temporal image pairs. Progress in this area has been limited by the scarcity of annotated datasets, as pixel-level annotation is costly and time-consuming. To address this, recent methods leverage synthetic data or generate artificial change pairs, but out-of-domain generalization remains limited. In this work, we introduce a weak temporal supervision strategy that leverages additional temporal observations of existing single-temporal datasets, without requiring any new annotations. Specifically, we extend single-date remote sensing datasets with new observations acquired at different times and train a change detection model by assuming that real bi-temporal pairs mostly contain no change, while pairing images from different locations to generate change examples. To handle the inherent noise in these weak labels, we employ an object-aware change map generation and an iterative refinement process. We validate our approach on extended versions of the FLAIR and IAILD aerial datasets, achieving strong zero-shot and low-data regime performance across different benchmarks. Lastly, we showcase results over large areas in France, highlighting the scalability potential of our method. --- ### SingingBot: An Avatar-Driven System for Robotic Face Singing Performance Authors: Zhuoxiong Xu, Xuanchen Li, Yuhao Cheng, Fei Xu, Yichao Yan, Xiaokang Yang Published: 2026-01-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.02125v1 Equipping robotic faces with singing capabilities is crucial for empathetic Human-Robot Interaction. However, existing robotic face driving research primarily focuses on conversations or mimicking static expressions, struggling to meet the high demands for continuous emotional expression and coherence in singing. To address this, we propose a novel avatar-driven framework for appealing robotic singing. We first leverage portrait video generation models embedded with extensive human priors to synthesize vivid singing avatars, providing reliable expression and emotion guidance. Subsequently, these facial features are transferred to the robot via semantic-oriented mapping functions that span a wide expression space. Furthermore, to quantitatively evaluate the emotional richness of robotic singing, we propose the Emotion Dynamic Range metric to measure the emotional breadth within the Valence-Arousal space, revealing that a broad emotional spectrum is crucial for appealing performances. Comprehensive experiments prove that our method achieves rich emotional expressions while maintaining lip-audio synchronization, significantly outperforming existing approaches. --- ### DeCode: Decoupling Content and Delivery for Medical QA Authors: Po-Jen Ko, Chen-Han Tsai, Yu-Shao Peng Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.02123v3 Large language models (LLMs) exhibit strong medical knowledge and can generate factually accurate responses. However, existing models often fail to account for individual patient contexts, producing answers that are clinically correct yet poorly aligned with patients' needs. In this work, we introduce DeCode (Decoupling Content and Delivery), a training-free, model-agnostic framework that adapts existing LLMs to produce contextualized answers in clinical settings. We evaluate DeCode on OpenAI HealthBench, a comprehensive and challenging benchmark designed to assess clinical relevance and validity of LLM responses. DeCode boosts zero-shot performance from 28.4% to 49.8% and achieves new state-of-the-art compared to existing methods. Experimental results suggest the effectiveness of DeCode in improving clinical question answering of LLMs. --- ### Inferring Network Evolutionary History via Structure-State Coupled Learning Authors: En Xu, Shihe Zhou, Huandong Wang, Jingtao Ding, Yong Li Published: 2026-01-05 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2601.02121v1 Inferring a network's evolutionary history from a single final snapshot with limited temporal annotations is fundamental yet challenging. Existing approaches predominantly rely on topology alone, which often provides insufficient and noisy cues. This paper leverages network steady-state dynamics -- converged node states under a given dynamical process -- as an additional and widely accessible observation for network evolution history inference. We propose CS$^2$, which explicitly models structure-state coupling to capture how topology modulates steady states and how the two signals jointly improve edge discrimination for formation-order recovery. Experiments on six real temporal networks, evaluated under multiple dynamical processes, show that CS$^2$ consistently outperforms strong baselines, improving pairwise edge precedence accuracy by 4.0% on average and global ordering consistency (Spearman-$ρ$) by 7.7% on average. CS$^2$ also more faithfully recovers macroscopic evolution trajectories such as clustering formation, degree heterogeneity, and hub growth. Moreover, a steady-state-only variant remains competitive when reliable topology is limited, highlighting steady states as an independent signal for evolution inference. --- ### Car Drag Coefficient Prediction from 3D Point Clouds Using a Slice-Based Surrogate Model Authors: Utkarsh Singh, Absaar Ali, Adarsh Roy Published: 2026-01-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.02112v1 The automotive industry's pursuit of enhanced fuel economy and performance necessitates efficient aerodynamic design. However, traditional evaluation methods such as computational fluid dynamics (CFD) and wind tunnel testing are resource intensive, hindering rapid iteration in the early design stages. Machine learning-based surrogate models offer a promising alternative, yet many existing approaches suffer from high computational complexity, limited interpretability, or insufficient accuracy for detailed geometric inputs. This paper introduces a novel lightweight surrogate model for the prediction of the aerodynamic drag coefficient (Cd) based on a sequential slice-wise processing of the geometry of the 3D vehicle. Inspired by medical imaging, 3D point clouds of vehicles are decomposed into an ordered sequence of 2D cross-sectional slices along the stream-wise axis. Each slice is encoded by a lightweight PointNet2D module, and the sequence of slice embeddings is processed by a bidirectional LSTM to capture longitudinal geometric evolution. The model, trained and evaluated on the DrivAerNet++ dataset, achieves a high coefficient of determination (R^2 > 0.9528) and a low mean absolute error (MAE approx 6.046 x 10^{-3}) in Cd prediction. With an inference time of approximately 0.025 seconds per sample on a consumer-grade GPU, our approach provides fast, accurate, and interpretable aerodynamic feedback, facilitating more agile and informed automotive design exploration. --- ### MagicFight: Personalized Martial Arts Combat Video Generation Authors: Jiancheng Huang, Mingfu Yan, Songyan Chen, Yi Huang, Shifeng Chen Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02107v1 Amid the surge in generic text-to-video generation, the field of personalized human video generation has witnessed notable advancements, primarily concentrated on single-person scenarios. However, to our knowledge, the domain of two-person interactions, particularly in the context of martial arts combat, remains uncharted. We identify a significant gap: existing models for single-person dancing generation prove insufficient for capturing the subtleties and complexities of two engaged fighters, resulting in challenges such as identity confusion, anomalous limbs, and action mismatches. To address this, we introduce a pioneering new task, Personalized Martial Arts Combat Video Generation. Our approach, MagicFight, is specifically crafted to overcome these hurdles. Given this pioneering task, we face a lack of appropriate datasets. Thus, we generate a bespoke dataset using the game physics engine Unity, meticulously crafting a multitude of 3D characters, martial arts moves, and scenes designed to represent the diversity of combat. MagicFight refines and adapts existing models and strategies to generate high-fidelity two-person combat videos that maintain individual identities and ensure seamless, coherent action sequences, thereby laying the groundwork for future innovations in the realm of interactive video content creation. Website: https://MingfuYAN.github.io/MagicFight/ Dataset: https://huggingface.co/datasets/MingfuYAN/KungFu-Fiesta --- ### Prototype-Based Learning for Healthcare: A Demonstration of Interpretable AI Authors: Ashish Rana, Ammar Shaker, Sascha Saralajew, Takashi Suzuki, Kosuke Yasuda, Shintaro Kato, Toshikazu Wada, Toshiyuki Fujikawa, Toru Kikutsuji Published: 2026-01-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.02106v1 Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the healthcare sector. We present a demonstration of how prototype-based learning can address these needs. Our proposed framework, ProtoPal, features both front- and back-end modes; it achieves superior quantitative performance while also providing an intuitive presentation of interventions and their simulated outcomes. --- ### LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training Authors: Hyunjun Kim Published: 2026-01-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.02105v1 Weight initialization remains decisive for neural network optimization, yet existing methods are largely layer-agnostic. We study initialization for deeply-supervised architectures with auxiliary classifiers, where untrained auxiliary heads can destabilize early training through gradient interference. We propose LION-DG, a layer-informed initialization that zero-initializes auxiliary classifier heads while applying standard He-initialization to the backbone. We prove that this implements Gradient Awakening: auxiliary gradients are exactly zero at initialization, then phase in naturally as weights grow -- providing an implicit warmup without hyperparameters. Experiments on CIFAR-10 and CIFAR-100 with DenseNet-DS and ResNet-DS architectures demonstrate: (1) DenseNet-DS: +8.3% faster convergence on CIFAR-10 with comparable accuracy, (2) Hybrid approach: Combining LSUV with LION-DG achieves best accuracy (81.92% on CIFAR-10), (3) ResNet-DS: Positive speedup on CIFAR-100 (+11.3%) with side-tap auxiliary design. We identify architecture-specific trade-offs and provide clear guidelines for practitioners. LION-DG is simple, requires zero hyperparameters, and adds no computational overhead. --- ### HeadLighter: Disentangling Illumination in Generative 3D Gaussian Heads via Lightstage Captures Authors: Yating Wang, Yuan Sun, Xuan Wang, Ran Yi, Boyao Zhou, Yipengjing Sun, Hongyu Liu, Yinuo Wang, Lizhuang Ma Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02103v2 Recent 3D-aware head generative models based on 3D Gaussian Splatting achieve real-time, photorealistic and view-consistent head synthesis. However, a fundamental limitation persists: the deep entanglement of illumination and intrinsic appearance prevents controllable relighting. Existing disentanglement methods rely on strong assumptions to enable weakly supervised learning, which restricts their capacity for complex illumination. To address this challenge, we introduce HeadLighter, a novel supervised framework that learns a physically plausible decomposition of appearance and illumination in head generative models. Specifically, we design a dual-branch architecture that separately models lighting-invariant head attributes and physically grounded rendering components. A progressive disentanglement training is employed to gradually inject head appearance priors into the generative architecture, supervised by multi-view images captured under controlled light conditions with a light stage setup. We further introduce a distillation strategy to generate high-quality normals for realistic rendering. Experiments demonstrate that our method preserves high-quality generation and real-time rendering, while simultaneously supporting explicit lighting and viewpoint editing. We will publicly release our code and dataset. --- ### 360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images Authors: Jiaqi Yao, Zhongmiao Yan, Jingyi Xu, Songpengcheng Xia, Yan Xiang, Ling Pei Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02102v1 3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches, though capable of producing high-quality results, require per-scene optimization and lack real-time efficiency. Explicit 3D Gaussian Splatting (3DGS) enables efficient rendering, but most feed-forward variants focus on visual quality rather than geometric consistency, limiting accurate surface reconstruction and overall reliability in spatial perception tasks. This paper presents a novel feed-forward 3DGS framework for 360 images, capable of generating geometrically consistent Gaussian primitives while maintaining high rendering quality. A Depth-Normal geometric regularization is introduced to couple rendered depth gradients with normal information, supervising Gaussian rotation, scale, and position to improve point cloud and surface accuracy. Experimental results show that the proposed method maintains high rendering quality while significantly improving geometric consistency, providing an effective solution for 3D reconstruction in spatial perception tasks. --- ### InpaintHuman: Reconstructing Occluded Humans with Multi-Scale UV Mapping and Identity-Preserving Diffusion Inpainting Authors: Jinlong Fan, Shanshan Zhao, Liang Zheng, Jing Zhang, Yuxiang Yang, Mingming Gong Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02098v1 Reconstructing complete and animatable 3D human avatars from monocular videos remains challenging, particularly under severe occlusions. While 3D Gaussian Splatting has enabled photorealistic human rendering, existing methods struggle with incomplete observations, often producing corrupted geometry and temporal inconsistencies. We present InpaintHuman, a novel method for generating high-fidelity, complete, and animatable avatars from occluded monocular videos. Our approach introduces two key innovations: (i) a multi-scale UV-parameterized representation with hierarchical coarse-to-fine feature interpolation, enabling robust reconstruction of occluded regions while preserving geometric details; and (ii) an identity-preserving diffusion inpainting module that integrates textual inversion with semantic-conditioned guidance for subject-specific, temporally coherent completion. Unlike SDS-based methods, our approach employs direct pixel-level supervision to ensure identity fidelity. Experiments on synthetic benchmarks (PeopleSnapshot, ZJU-MoCap) and real-world scenarios (OcMotion) demonstrate competitive performance with consistent improvements in reconstruction quality across diverse poses and viewpoints. --- ### Dancing Points: Synthesizing Ballroom Dancing with Three-Point Inputs Authors: Peizhuo Li, Sebastian Starke, Yuting Ye, Olga Sorkine-Hornung Published: 2026-01-05 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2601.02096v2 Ballroom dancing is a structured yet expressive motion category. Its highly diverse movement and complex interactions between leader and follower dancers make the understanding and synthesis challenging. We demonstrate that the three-point trajectory available from a virtual reality (VR) device can effectively serve as a dancer's motion descriptor, simplifying the modeling and synthesis of interplay between dancers' full-body motions down to sparse trajectories. Thanks to the low dimensionality, we can employ an efficient MLP network to predict the follower's three-point trajectory directly from the leader's three-point input for certain types of ballroom dancing, addressing the challenge of modeling high-dimensional full-body interaction. It also prevents our method from overfitting thanks to its compact yet explicit representation. By leveraging the inherent structure of the movements and carefully planning the autoregressive procedure, we show a deterministic neural network is able to translate three-point trajectories into a virtual embodied avatar, which is typically considered under-constrained and requires generative models for common motions. In addition, we demonstrate this deterministic approach generalizes beyond small, structured datasets like ballroom dancing, and performs robustly on larger, more diverse datasets such as LaFAN. Our method provides a computationally- and data-efficient solution, opening new possibilities for immersive paired dancing applications. Code and pre-trained models for this paper are available at https://peizhuoli.github.io/dancing-points. --- ### Horizon Activation Mapping for Neural Networks in Time Series Forecasting Authors: Krupakar Hans, V A Kandappan Published: 2026-01-05 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2601.02094v4 Neural networks for time series forecasting have relied on error metrics and architecture-specific interpretability approaches for model selection that don't apply across models of different families. To interpret forecasting models agnostic to the types of layers across state-of-the-art model families, we introduce Horizon Activation Mapping (HAM), a visual interpretability technique inspired by grad-CAM that uses gradient norm averages to study the horizon's subseries where grad-CAM studies attention maps over image data. We introduce causal and anti-causal modes to calculate gradient update norm averages across subseries at every timestep and lines of proportionality signifying uniform distributions of the norm averages. Optimization landscape studies with respect to changes in batch sizes, early stopping, train-val-test splits, architectural choices, univariate forecasting and dropouts are studied with respect to performances and subseries in HAM. Interestingly, batch size based differences in activities seem to indicate potential for existence of an exponential approximation across them per epoch relative to each other. Multivariate forecasting models including MLP-based CycleNet, N-Linear, N-HITS, self attention-based FEDformer, Pyraformer, SSM-based SpaceTime and diffusion-based Multi-Resolution DDPM over different horizon sizes trained over the ETTm2 dataset are used for HAM plots in this study. NHITS' neural approximation theorem and SpaceTime's exponential autoregressive activities have been attributed to trends in HAM plots over their training, validation and test sets. In general, HAM can be used for granular model selection, validation set choices and comparisons across different neural network model families. --- ### MCD-Net: A Lightweight Deep Learning Baseline for Optical-Only Moraine Segmentation Authors: Zhehuan Cao, Fiseha Berhanu Tesema, Ping Fu, Jianfeng Ren, Ahmed Nasr Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02091v2 Glacial segmentation is essential for reconstructing past glacier dynamics and evaluating climate-driven landscape change. However, weak optical contrast and the limited availability of high-resolution DEMs hinder automated mapping. This study introduces the first large-scale optical-only moraine segmentation dataset, comprising 3,340 manually annotated high-resolution images from Google Earth covering glaciated regions of Sichuan and Yunnan, China. We develop MCD-Net, a lightweight baseline that integrates a MobileNetV2 encoder, a Convolutional Block Attention Module (CBAM), and a DeepLabV3+ decoder. Benchmarking against deeper backbones (ResNet152, Xception) shows that MCD-Net achieves 62.3% mean Intersection over Union (mIoU) and 72.8% Dice coefficient while reducing computational cost by more than 60%. Although ridge delineation remains constrained by sub-pixel width and spectral ambiguity, the results demonstrate that optical imagery alone can provide reliable moraine-body segmentation. The dataset and code are publicly available at https://github.com/Lyra-alpha/MCD-Net, establishing a reproducible benchmark for moraine-specific segmentation and offering a deployable baseline for high-altitude glacial monitoring. --- ### PhysSFI-Net: Physics-informed Geometric Learning of Skeletal and Facial Interactions for Orthognathic Surgical Outcome Prediction Authors: Jiahao Bao, Huazhen Liu, Yu Zhuang, Leran Tao, Xinyu Xu, Yongtao Shi, Mengjia Cheng, Yiming Wang, Congshuang Ku, Ting Zeng, Yilang Du, Siyi Chen et al. Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02088v3 Orthognathic surgery repositions jaw bones to restore occlusion and enhance facial aesthetics. Accurate simulation of postoperative facial morphology is essential for preoperative planning. This study aims to develop and validate a physics-informed geometric deep learning framework named PhysSFI-Net for precise prediction of soft tissue deformation following orthognathic surgery. The model integrates a hierarchical feature extraction module with attention mechanisms to capture skeletal-facial interactions, an LSTM-based sequential predictor for incremental deformation, and a biomechanics-inspired reconstruction module for high-resolution facial modeling. The model was trained on 135 patients and externally validated on an independent cohort of 33 patients. Model performance was assessed using point cloud shape error, surface deviation error and landmark error between predicted facial shapes with corresponding ground truths. Quantitative analysis demonstrated that PhysSFI-Net achieved a global shape error of 1.070 +/- 0.088 mm, a surface deviation error of 1.296 +/- 0.349 mm and a landmark error of 2.445 +/- 1.326 mm. Comparative experiments indicated that PhysSFI-Net outperformed the state-of-the-art method ACMT-Net and baseline models. External validation further confirmed its robustness with a global HD of 1.431 +/- 0.087 mm and consistently lower subregional and mesh-based errors. In conclusion, PhysSFI-Net enables interpretable, high-resolution prediction of postoperative facial morphology, showing strong potential for clinical application in orthognathic surgical planning. --- ### Vision-Based Early Fault Diagnosis and Self-Recovery for Strawberry Harvesting Robots Authors: Meili Sun, Chunjiang Zhao, Lichao Yang, Hao Liu, Shimin Hu, Ya Xiong Published: 2026-01-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.02085v3 Strawberry-harvesting robots faced challenges such as poor visual perception, gripper misalignment, empty grasp/misgrasp, and slippage, which reduced harvesting stability and efficiency.To overcome these issues, this paper proposes a visual fault diagnosis and self-recovery framework. An end-to-end SRR-Net achieved unified perception and fault diagnosis through joint detection, segmentation, and ripeness regression of the fruit and gripper. Leveraging this integrated perception, a relative error compensation method driven by simultaneous target-gripper detection was designed to correct positional misalignments exceeding the tolerance threshold. A micro-optical camera integrated within the end-effector delivered real-time visual feedback. Based on the micro-optical camera, a MobileNet V3-Small classifier was utilized for grasp adjustment during the deflating stage, enabling the early abort of the harvesting cycle in cases of empty grasp/misgrasps. Furthermore, a time-series LSTM classifier was applied during the snap-off stage to predict strawberry slippage. Based on these predictions, the system executed re-inflation and a secondary snap-off attempt for slipping strawberries, or aborted the cycle for slipped strawberries. Experiments demonstrated that the mean absolute errors between the end-effector and the picking point were reduced to 3.12 mm and 4.06 mm from 11.50 mm and 5.25 mm along the x- and y-axes, respectively, at the cost of a time increment of 0.64 $pm$ 0.24 s. The grasp adjustment module reduced the grasping phase by approximately 0.5 s and avoided empty-placement for failure cases. The strawberry slip prediction module handled slipped cases with an 88.89% success rate, saving approximately 4.00 s per harvesting cycle for failure cases. Also, it achieved an 81.25% recovery rate for slipping strawberries, requiring additional 0.63 s for re-grasping. --- ### ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction Authors: Jiacheng Lyu, Bihua Bao, Shiyun Yan Published: 2026-01-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.02081v3 Massive datasets often contain redundancy that inflates computational costs without improving generalization. Existing data reduction methods are typically task-agnostic, discarding informative boundary samples and yielding suboptimal performance. We propose Adversarial Soft-Selection Subsampling (ASSS), a differentiable framework that casts data reduction as a minimax game between a learnable selector and a task network. Using Gumbel-Softmax relaxation, ASSS enables end-to-end gradient flow and is theoretically grounded in the information bottleneck principle. Experiments on multiple benchmarks show that ASSS achieves a performance retention rate (PRR) of 98.9% while using only 30% of the data, significantly outperforming random sampling, K-means, and gradient-based methods. Visualizations confirm that ASSS preferentially retains samples near decision boundaries. The framework is scalable, fully differentiable, and easily integrated into existing training pipelines. This work introduces a new paradigm for task-aware data reduction that directly optimizes subset selection for the downstream objective, offering a principled and practical solution to the scalability challenges in modern deep learning. --- ### The Homogeneity Trap: Spectral Collapse in Doubly-Stochastic Deep Networks Authors: Yizhi Liu Published: 2026-01-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.02080v1 Doubly-stochastic matrices (DSM) are increasingly utilized in structure-preserving deep architectures -- such as Optimal Transport layers and Sinkhorn-based attention -- to enforce numerical stability and probabilistic interpretability. In this work, we identify a critical spectral degradation phenomenon inherent to these constraints, termed the Homogeneity Trap. We demonstrate that the maximum-entropy bias, typical of Sinkhorn-based projections, drives the mixing operator towards the uniform barycenter, thereby suppressing the subdominant singular value σ_2 and filtering out high-frequency feature components. We derive a spectral bound linking σ_2 to the network's effective depth, showing that high-entropy constraints restrict feature transformation to a shallow effective receptive field. Furthermore, we formally demonstrate that Layer Normalization fails to mitigate this collapse in noise-dominated regimes; specifically, when spectral filtering degrades the Signal-to-Noise Ratio (SNR) below a critical threshold, geometric structure is irreversibly lost to noise-induced orthogonal collapse. Our findings highlight a fundamental trade-off between entropic stability and spectral expressivity in DSM-constrained networks. --- ### Deferred Commitment Decoding for Diffusion Language Models Authors: Yingte Shu, Yuchuan Tian, Chao Xu, Yunhe Wang, Hanting Chen Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.02076v2 Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV-cache compatibility, prior work commonly adopts block-based diffusion, decoding tokens block by block. However, this paradigm suffers from a structural limitation that we term Boundary-Induced Context Truncation (BICT): undecoded tokens near block boundaries are forced to commit without access to nearby future context, even when such context could substantially reduce uncertainty. This limitation degrades decoding certainty and generation quality, especially for tasks requiring precise reasoning, such as mathematical problem solving and code generation. We propose Deferred Commitment Decoding (DCD), a novel, training-free decoding strategy that mitigates this issue. DCD maintains a certainty-aware sliding window over masked tokens, resolving low-uncertainty tokens early while deferring high-uncertainty tokens until sufficient contextual evidence becomes available. Extensive experiments across multiple diffusion language models, benchmarks, and caching configurations show that DCD improves generation accuracy by 1.73% with comparable time on average compared to fixed block-based diffusion methods, with the most significant improvement reaching 16.5%. These results demonstrate that deferring token commitment based on uncertainty is a simple yet effective principle for improving both the quality and efficiency of diffusion language model decoding. --- ### MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics Authors: Zhuofan Shi, Hubao A, Yufei Shao, Dongliang Huang, Hongxu An, Chunxiao Xin, Haiyang Shen, Zhenyu Wang, Yunshan Na, Gang Huang, Xiang Jing Published: 2026-01-05 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2601.02075v4 Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized and time-consuming tasks. Although LLMs show promise in code generation and domain-specific question answering, their performance in MD scenarios is limited by scarce domain data, the high deployment cost of state-of-the-art LLMs, and low code executability. Building upon our prior MDAgent, we present MDAgent2, the first end-to-end framework capable of performing both knowledge Q&A and code generation within the MD domain. We construct a domain-specific data-construction pipeline that yields three high-quality datasets spanning MD knowledge, question answering, and code generation. Based on these datasets, we adopt a three stage post-training strategy--continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL)--to train two domain-adapted models, MD-Instruct and MD-Code. Furthermore, we introduce MD-GRPO, a closed-loop RL method that leverages simulation outcomes as reward signals and recycles low-reward trajectories for continual refinement. We further build MDAgent2-RUNTIME, a deployable multi-agent system that integrates code generation, execution, evaluation, and self-correction. Together with MD-EvalBench proposed in this work, the first benchmark for LAMMPS code generation and question answering, our models and system achieve performance surpassing several strong baselines.This work systematically demonstrates the adaptability and generalization capability of large language models in industrial simulation tasks, laying a methodological foundation for automatic code generation in AI for Science and industrial-scale simulations. URL: https://github.com/FredericVAN/PKU_MDAgent2 --- ### SketchRodGS: Sketch-based Extraction of Slender Geometries for Animating Gaussian Splatting Scenes Authors: Haato Watanabe, Nobuyuki Umetani Published: 2026-01-05 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2601.02072v1 Physics simulation of slender elastic objects often requires discretization as a polyline. However, constructing a polyline from Gaussian splatting is challenging as Gaussian splatting lacks connectivity information and the configuration of Gaussian primitives contains much noise. This paper presents a method to extract a polyline representation of the slender part of the objects in a Gaussian splatting scene from the user's sketching input. Our method robustly constructs a polyline mesh that represents the slender parts using the screen-space shortest path analysis that can be efficiently solved using dynamic programming. We demonstrate the effectiveness of our approach in several in-the-wild examples. --- ### FormuLLA: A Large Language Model Approach to Generating Novel 3D Printable Formulations Authors: Adeshola Okubena, Yusuf Ali Mohammed, Moe Elbadawi Published: 2026-01-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.02071v3 Pharmaceutical three-dimensional (3D) printing is an advanced fabrication technology with the potential to enable truly personalised dosage forms. Recent studies have integrated artificial intelligence (AI) to accelerate formulation and process development, drastically transforming current approaches to pharmaceutical 3D printing. To date, most AI-driven efforts remain narrowly focused, while failing to account for the broader formulation challenges inherent to the technology. Recent advances in AI have introduced artificial general intelligence concepts, wherein systems extend beyond conventional predictive modelling toward more generalised, human-like reasoning. In this work, we investigate the application of large language models (LLMs), fine-tuned on a fused deposition modelling (FDM) dataset comprising over 1400 formulations, to recommend suitable excipients based on active pharmaceutical ingredient (API) dose, and predict filament mechanical properties. Four LLM architectures were fine-tuned, with systematic evaluation of both fine-tuning and generative parameter configurations. Our results demonstrate that Llama2 was best suited for recommending excipients for FDM formulations. Additionally, model selection and parameterisation significantly influence performance, with smaller LLMs exhibiting instances of catastrophic forgetting. Furthermore, we demonstrate: (i) even with relatively small dataset of over 1400 formulations, it can lead to model catastrophic forgetting; (ii) standard LLM metrics only evaluate linguistic performance but not formulation processability; and (iii) LLMs trained on biomedically-related data do not always produce the best results. Addressing these challenges is essential to advancing LLMs beyond linguistic proficiency and toward reliable systems for pharmaceutical formulation development. --- ### Cost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural Advisory Authors: Md. Asif Hossain, Nabil Subhan, Mantasha Rahman Mahi, Jannatul Ferdous Nabila Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.02065v1 Access to reliable agricultural advisory remains limited in many developing regions due to a persistent language barrier: authoritative agricultural manuals are predominantly written in English, while farmers primarily communicate in low-resource local languages such as Bengali. Although recent advances in Large Language Models (LLMs) enable natural language interaction, direct generation in low-resource languages often exhibits poor fluency and factual inconsistency, while cloud-based solutions remain cost-prohibitive. This paper presents a cost-efficient, cross-lingual Retrieval-Augmented Generation (RAG) framework for Bengali agricultural advisory that emphasizes factual grounding and practical deployability. The proposed system adopts a translation-centric architecture in which Bengali user queries are translated into English, enriched through domain-specific keyword injection to align colloquial farmer terminology with scientific nomenclature, and answered via dense vector retrieval over a curated corpus of English agricultural manuals (FAO, IRRI). The generated English response is subsequently translated back into Bengali to ensure accessibility. The system is implemented entirely using open-source models and operates on consumer-grade hardware without reliance on paid APIs. Experimental evaluation demonstrates reliable source-grounded responses, robust rejection of out-of-domain queries, and an average end-to-end latency below 20 seconds. The results indicate that cross-lingual retrieval combined with controlled translation offers a practical and scalable solution for agricultural knowledge access in low-resource language settings --- ### Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management Authors: Faizan Ahmed, Aniket Dixit, James Brusey Published: 2026-01-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.02061v1 Deep reinforcement learning agents often exhibit erratic, high-frequency control behaviors that hinder real-world deployment due to excessive energy consumption and mechanical wear. We systematically investigate action smoothness regularization through higher-order derivative penalties, progressing from theoretical understanding in continuous control benchmarks to practical validation in building energy management. Our comprehensive evaluation across four continuous control environments demonstrates that third-order derivative penalties (jerk minimization) consistently achieve superior smoothness while maintaining competitive performance. We extend these findings to HVAC control systems where smooth policies reduce equipment switching by 60%, translating to significant operational benefits. Our work establishes higher-order action regularization as an effective bridge between RL optimization and operational constraints in energy-critical applications. --- ### Perish or Flourish? A Holistic Evaluation of Large Language Models for Code Generation in Functional Programming Authors: Nguyet-Anh H. Lang, Eric Lang, Thanh Le-Cong, Bach Le, Quyet-Thang Huynh Published: 2026-01-05 Categories: cs.PL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.02060v1 Functional programming provides strong foundations for developing reliable and secure software systems, yet its adoption remains not widespread due to the steep learning curve. Recent advances in Large Language Models (LLMs) for code generation present new opportunities to lower these barriers. However, extensive evaluations of LLMs largely focus on imperative programming languages, and their capabilities in functional programming languages (FP) remain underexplored. To address this gap, we introduce FPEval, a holistic evaluation framework built on FPBench, a new benchmark of 721 programming tasks across three difficulty levels on three mainstream FP languages: Haskell, Ocaml and Scala. FPEval provides compehensive evaluation infrastructures with both test validations with comprehensive test suites and static analysis tools to assess both functional correctness and code style and maintainability. Using this framework, we evaluate state-of-the-art LLMs, including GPT-3.5, GPT-4o, and GPT-5, for code generation in functional programming languages and Java as an imperative baseline. Our results demonstrate that LLM performance in functional programming improves substantially with model advancement; however, error rates remain significantly higher in purely functional languages (Haskell and OCaml) than in hybrid (Scala) or imperative (Java) languages. Moreover, LLMs frequently generate non-idiomatic functional code that follows imperative patterns, raising concerns about code style and long-term maintainability. Finally, we show that LLMs can partially self-repair both correctness and quality issues when provided with static analysis feedback and hand-crafted instructions for common types of issues. --- ### Explore the Ideology of Deep Learning in ENSO Forecasts Authors: Yanhai Gan, Yipeng Chen, Ning Li, Xingguo Liu, Junyu Dong, Xianyao Chen Published: 2026-01-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.02050v1 The El Ni{~n}o-Southern Oscillation (ENSO) exerts profound influence on global climate variability, yet its prediction remains a grand challenge. Recent advances in deep learning have significantly improved forecasting skill, but the opacity of these models hampers scientific trust and operational deployment. Here, we introduce a mathematically grounded interpretability framework based on bounded variation function. By rescuing the "dead" neurons from the saturation zone of the activation function, we enhance the model's expressive capacity. Our analysis reveals that ENSO predictability emerges dominantly from the tropical Pacific, with contributions from the Indian and Atlantic Oceans, consistent with physical understanding. Controlled experiments affirm the robustness of our method and its alignment with established predictors. Notably, we probe the persistent Spring Predictability Barrier (SPB), finding that despite expanded sensitivity during spring, predictive performance declines-likely due to suboptimal variable selection. These results suggest that incorporating additional ocean-atmosphere variables may help transcend SPB limitations and advance long-range ENSO prediction. --- ### Agentic Retoucher for Text-To-Image Generation Authors: Shaocheng Shen, Jianfeng Liang, Chunlei Cai, Cong Geng, Huiyu Duan, Xiaoyun Zhang, Qiang Hu, Guangtao Zhai Published: 2026-01-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.02046v3 Text-to-image (T2I) diffusion models such as SDXL and FLUX have achieved impressive photorealism, yet small-scale distortions remain pervasive in limbs, face, text and so on. Existing refinement approaches either perform costly iterative re-generation or rely on vision-language models (VLMs) with weak spatial grounding, leading to semantic drift and unreliable local edits. To close this gap, we propose Agentic Retoucher, a hierarchical decision-driven framework that reformulates post-generation correction as a human-like perception-reasoning-action loop. Specifically, we design (1) a perception agent that learns contextual saliency for fine-grained distortion localization under text-image consistency cues, (2) a reasoning agent that performs human-aligned inferential diagnosis via progressive preference alignment, and (3) an action agent that adaptively plans localized inpainting guided by user preference. This design integrates perceptual evidence, linguistic reasoning, and controllable correction into a unified, self-corrective decision process. To enable fine-grained supervision and quantitative evaluation, we further construct GenBlemish-27K, a dataset of 6K T2I images with 27K annotated artifact regions across 12 categories. Extensive experiments demonstrate that Agentic Retoucher consistently outperforms state-of-the-art methods in perceptual quality, distortion localization and human preference alignment, establishing a new paradigm for self-corrective and perceptually reliable T2I generation. --- ### The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers Authors: Shuoming Zhang, Jiacheng Zhao, Qiuchu Yu, Chunwei Xia, Zheng Wang, Xiaobing Feng, Huimin Cui Published: 2026-01-05 Categories: cs.PL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.02045v1 This survey has provided a systematic overview of the emerging field of LLM-enabled compilation by addressing several key research questions. We first answered how LLMs are being integrated by proposing a comprehensive, multi-dimensional taxonomy that categorizes works based on their Design Philosophy (Selector, Translator, Generator), LLM Methodology, their operational Level of Code Abstraction, and the specific Task Type they address. In answering what advancements these approaches offer, we identified three primary benefits: the democratization of compiler development, the discovery of novel optimization strategies, and the broadening of the compiler's traditional scope. Finally, in addressing the field's challenges and opportunities, we highlighted the critical hurdles of ensuring correctness and achieving scalability, while identifying the development of hybrid systems as the most promising path forward. By providing these answers, this survey serves as a foundational roadmap for researchers and practitioners, charting the course for a new generation of LLM-powered, intelligent, adaptive and synergistic compilation tools. --- ### Simulated Reasoning is Reasoning Authors: Hendrik Kempt, Alon Lavie Published: 2026-01-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.02043v1 Reasoning has long been understood as a pathway between stages of understanding. Proper reasoning leads to understanding of a given subject. This reasoning was conceptualized as a process of understanding in a particular way, i.e., "symbolic reasoning". Foundational Models (FM) demonstrate that this is not a necessary condition for many reasoning tasks: they can "reason" by way of imitating the process of "thinking out loud", testing the produced pathways, and iterating on these pathways on their own. This leads to some form of reasoning that can solve problems on its own or with few-shot learning, but appears fundamentally different from human reasoning due to its lack of grounding and common sense, leading to brittleness of the reasoning process. These insights promise to substantially alter our assessment of reasoning and its necessary conditions, but also inform the approaches to safety and robust defences against this brittleness of FMs. This paper offers and discusses several philosophical interpretations of this phenomenon, argues that the previously apt metaphor of the "stochastic parrot" has lost its relevance and thus should be abandoned, and reflects on different normative elements in the safety- and appropriateness-considerations emerging from these reasoning models and their growing capacity. --- ### AlignVTOFF: Texture-Spatial Feature Alignment for High-Fidelity Virtual Try-Off Authors: Yihan Zhu, Mengying Ge Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02038v1 Virtual Try-Off (VTOFF) is a challenging multimodal image generation task that aims to synthesize high-fidelity flat-lay garments under complex geometric deformation and rich high-frequency textures. Existing methods often rely on lightweight modules for fast feature extraction, which struggles to preserve structured patterns and fine-grained details, leading to texture attenuation during generation.To address these issues, we propose AlignVTOFF, a novel parallel U-Net framework built upon a Reference U-Net and Texture-Spatial Feature Alignment (TSFA). The Reference U-Net performs multi-scale feature extraction and enhances geometric fidelity, enabling robust modeling of deformation while retaining complex structured patterns. TSFA then injects the reference garment features into a frozen denoising U-Net via a hybrid attention design, consisting of a trainable cross-attention module and a frozen self-attention module. This design explicitly aligns texture and spatial cues and alleviates the loss of high-frequency information during the denoising process.Extensive experiments across multiple settings demonstrate that AlignVTOFF consistently outperforms state-of-the-art methods, producing flat-lay garment results with improved structural realism and high-frequency detail fidelity. --- ### Multivariate Time-series Anomaly Detection via Dynamic Model Pool & Ensembling Authors: Wei Hu, Zewei Yu, Jianqiu Xu Published: 2026-01-05 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2601.02037v1 Multivariate time-series (MTS) anomaly detection is critical in domains such as service monitor, IoT, and network security. While multi-model methods based on selection or ensembling outperform single-model ones, they still face limitations: (i) selection methods rely on a single chosen model and are sensitive to the strategy; (ii) ensembling methods often combine all models or are restricted to univariate data; and (iii) most methods depend on fixed data dimensionality, limiting scalability. To address these, we propose DMPEAD, a Dynamic Model Pool and Ensembling framework for MTS Anomaly Detection. The framework first (i) constructs a diverse model pool via parameter transfer and diversity metric, then (ii) updates it with a meta-model and similarity-based strategy for adaptive pool expansion, subset selection, and pool merging, finally (iii) ensembles top-ranked models through proxy metric ranking and top-k aggregation in the selected subset, outputting the final anomaly detection result. Extensive experiments on 8 real-world datasets show that our model outperforms all baselines, demonstrating superior adaptability and scalability. --- ### GDRO: Group-level Reward Post-training Suitable for Diffusion Models Authors: Yiyang Wang, Xi Chen, Xiaogang Xu, Yu Liu, Hengshuang Zhao Published: 2026-01-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.02036v1 Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it faces challenges including low efficiency, dependency on stochastic samplers, and reward hacking. The problem is that rectified flow models are fundamentally different from LLMs: 1) For efficiency, online image sampling takes much more time and dominates the time of training. 2) For stochasticity, rectified flow is deterministic once the initial noise is fixed. Aiming at these problems and inspired by the effects of group-level rewards from LLMs, we design Group-level Direct Reward Optimization (GDRO). GDRO is a new post-training paradigm for group-level reward alignment that combines the characteristics of rectified flow models. Through rigorous theoretical analysis, we point out that GDRO supports full offline training that saves the large time cost for image rollout sampling. Also, it is diffusion-sampler-independent, which eliminates the need for the ODE-to-SDE approximation to obtain stochasticity. We also empirically study the reward hacking trap that may mislead the evaluation, and involve this factor in the evaluation using a corrected score that not only considers the original evaluation reward but also the trend of reward hacking. Extensive experiments demonstrate that GDRO effectively and efficiently improves the reward score of the diffusion model through group-wise offline optimization across the OCR and GenEval tasks, while demonstrating strong stability and robustness in mitigating reward hacking. --- ### Output Embedding Centering for Stable LLM Pretraining Authors: Felix Stollenwerk, Anna Lokrantz, Niclas Hertzberg Published: 2026-01-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.02031v3 Pretraining of large language models is not only expensive but also prone to certain training instabilities. A specific instability that often occurs at the end of training is output logit divergence. The most widely used mitigation strategies, z-loss and logit soft-capping, merely address the symptoms rather than the underlying cause of the problem. In this paper, we analyze the instability from the perspective of the output embeddings' geometry and identify anisotropic embeddings as its source. Based on this, we propose output embedding centering (OEC) as a new mitigation strategy, and demonstrate that it suppresses output logit divergence. OEC can be implemented in two different ways: as a deterministic operation called $μ$-centering, or a regularization method called $μ$-loss. Our experiments show that both variants outperform z-loss in terms of training stability, while being on par with logit soft-capping. This holds true both in the presence and the absence of weight tying. As a secondary result, we find that $μ$-loss is significantly less sensitive to regularization hyperparameter tuning than z-loss. --- ### Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding Authors: Toshihiko Nishimura, Hirofumi Abe, Kazuhiko Murasaki, Taiga Yoshida, Ryuichi Tanida Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02029v1 This paper presents a novel 3D semantic segmentation method for large-scale point cloud data that does not require annotated 3D training data or paired RGB images. The proposed approach projects 3D point clouds onto 2D images using virtual cameras and performs semantic segmentation via a foundation 2D model guided by natural language prompts. 3D segmentation is achieved by aggregating predictions from multiple viewpoints through weighted voting. Our method outperforms existing training-free approaches and achieves segmentation accuracy comparable to supervised methods. Moreover, it supports open-vocabulary recognition, enabling users to detect objects using arbitrary text queries, thus overcoming the limitations of traditional supervised approaches. --- ### Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs Authors: Amirali Ebrahimzadeh, Seyyed M. Salili Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.02023v2 As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctuates significantly depending on how information is distributed in real-world corpora. We investigate how fact placement, corpus-level distributions, and anti-hallucination ("Don't Make It Up") prompts influence model behavior by introducing a model-agnostic extended needle-in-a-haystack benchmark designed for scalability, which we apply to evaluate Gemini-2.5-flash, ChatGPT-5-mini, Claude-4.5-haiku, and Deepseek-v3.2-chat. Unlike prior work, we separately evaluate literal extraction, logical inference, and hallucination risk. We identify two critical failure modes: Distributional Collapse, where performance degrades significantly when evidence is dispersed; and a Safety Tax, where anti-hallucination prompts cause over-conservative refusal of present facts and evidence, sharply reducing accuracy. Our results suggest that many failures stem from ineffective context utilization, as models struggle to prioritize relevant information even when it is present. These findings highlight the need for model-specific robustness and effective context management to ensure reliable deployment in long-horizon agentic workflows. --- ### Prior Diffusiveness and Regret in the Linear-Gaussian Bandit Authors: Yifan Zhu, John C. Duchi, Benjamin Van Roy Published: 2026-01-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.02022v2 We prove that Thompson sampling exhibits $\tilde{O}(σd \sqrt{T} + d r \sqrt{\mathrm{Tr}(Σ_0)})$ Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(μ_0, Σ_0)$ prior distribution on the coefficients, where $d$ is the dimension, $T$ is the time horizon, $r$ is the maximum $\ell_2$ norm of the actions, and $σ^2$ is the noise variance. In contrast to existing regret bounds, this shows that to within logarithmic factors, the prior-dependent ``burn-in'' term $d r \sqrt{\mathrm{Tr}(Σ_0)}$ decouples additively from the minimax (long run) regret $σd \sqrt{T}$. Previous regret bounds exhibit a multiplicative dependence on these terms. We establish these results via a new ``elliptical potential'' lemma, and also provide a lower bound indicating that the burn-in term is unavoidable. --- ### Adapting Depth Anything to Adverse Imaging Conditions with Events Authors: Shihan Peng, Yuyang Xiong, Hanyu Zhou, Zhiwei Shi, Haoyue Liu, Gang Chen, Luxin Yan, Yi Chang Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02020v1 Robust depth estimation under dynamic and adverse lighting conditions is essential for robotic systems. Currently, depth foundation models, such as Depth Anything, achieve great success in ideal scenes but remain challenging under adverse imaging conditions such as extreme illumination and motion blur. These degradations corrupt the visual signals of frame cameras, weakening the discriminative features of frame-based depths across the spatial and temporal dimensions. Typically, existing approaches incorporate event cameras to leverage their high dynamic range and temporal resolution, aiming to compensate for corrupted frame features. However, such specialized fusion models are predominantly trained from scratch on domain-specific datasets, thereby failing to inherit the open-world knowledge and robust generalization inherent to foundation models. In this work, we propose ADAE, an event-guided spatiotemporal fusion framework for Depth Anything in degraded scenes. Our design is guided by two key insights: 1) Entropy-Aware Spatial Fusion. We adaptively merge frame-based and event-based features using an information entropy strategy to indicate illumination-induced degradation. 2) Motion-Guided Temporal Correction. We resort to the event-based motion cue to recalibrate ambiguous features in blurred regions. Under our unified framework, the two components are complementary to each other and jointly enhance Depth Anything under adverse imaging conditions. Extensive experiments have been performed to verify the superiority of the proposed method. Our code will be released upon acceptance. --- ### Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement Authors: Guangqian Guo, Aixi Ren, Yong Guo, Xuehui Yu, Jiacheng Tian, Wenli Li, Chaowei Wang, Yaoxing Wang, Shan Gao Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.02018v2 Segment Anything Models (SAMs), known for their exceptional zero-shot segmentation performance, have garnered significant attention in the research community. Nevertheless, their performance drops significantly on severely degraded, low-quality images, limiting their effectiveness in real-world scenarios. To address this, we propose GleSAM++, which utilizes Generative Latent space Enhancement to boost robustness on low-quality images, thus enabling generalization across various image qualities. Additionally, to improve compatibility between the pre-trained diffusion model and the segmentation framework, we introduce two techniques, i.e., Feature Distribution Alignment (FDA) and Channel Replication and Expansion (CRE). However, the above components lack explicit guidance regarding the degree of degradation. The model is forced to implicitly fit a complex noise distribution that spans conditions from mild noise to severe artifacts, which substantially increases the learning burden and leads to suboptimal reconstructions. To address this issue, we further introduce a Degradation-aware Adaptive Enhancement (DAE) mechanism. The key principle of DAE is to decouple the reconstruction process for arbitrary-quality features into two stages: degradation-level prediction and degradation-aware reconstruction. Our method can be applied to pre-trained SAM and SAM2 with only minimal additional learnable parameters, allowing for efficient optimization. Extensive experiments demonstrate that GleSAM++ significantly improves segmentation robustness on complex degradations while maintaining generalization to clear images. Furthermore, GleSAM++ also performs well on unseen degradations, underscoring the versatility of our approach and dataset. --- ### Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach Authors: Matthias Bartolo, Dylan Seychell, Gabriel Hili, Matthew Montebello, Carl James Debono, Saviour Formosa, Konstantinos Makantasis Published: 2026-01-05 Categories: cs.CV, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2601.02016v1 This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings. --- ### Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets Authors: Omar Momen, Emilie Sitter, Berenike Herrmann, Sina Zarrieß Published: 2026-01-05 Categories: cs.CL, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2601.02015v3 Novel metaphor comprehension involves complex semantic processes and linguistic creativity, making it an interesting task for studying language models (LMs). This study investigates whether surprisal, a probabilistic measure of predictability in LMs, correlates with annotations of metaphor novelty in different datasets. We analyse the surprisal of metaphoric words in corpus-based and synthetic metaphor datasets using 16 causal LM variants. We propose a cloze-style surprisal method that conditions on full-sentence context. Results show that LM surprisal yields significant moderate correlations with scores/labels of metaphor novelty. We further identify divergent scaling patterns: on corpus-based data, correlation strength decreases with model size (inverse scaling effect), whereas on synthetic data it increases (quality-power hypothesis). We conclude that while surprisal can partially account for annotations of metaphor novelty, it remains limited as a metric of linguistic creativity. Code and data are publicly available: https://github.com/OmarMomen14/surprisal-metaphor-novelty --- ### A neural network for modeling human concept formation, understanding and communication Authors: Liangxuan Guo, Haoyang Chen, Yang Chen, Yanchao Bi, Shan Yu Published: 2026-01-05 Categories: q-bio.NC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.02010v1 A remarkable capability of the human brain is to form more abstract conceptual representations from sensorimotor experiences and flexibly apply them independent of direct sensory inputs. However, the computational mechanism underlying this ability remains poorly understood. Here, we present a dual-module neural network framework, the CATS Net, to bridge this gap. Our model consists of a concept-abstraction module that extracts low-dimensional conceptual representations, and a task-solving module that performs visual judgement tasks under the hierarchical gating control of the formed concepts. The system develops transferable semantic structure based on concept representations that enable cross-network knowledge transfer through conceptual communication. Model-brain fitting analyses reveal that these emergent concept spaces align with both neurocognitive semantic model and brain response structures in the human ventral occipitotemporal cortex, while the gating mechanisms mirror that in the semantic control brain network. This work establishes a unified computational framework that can offer mechanistic insights for understanding human conceptual cognition and engineering artificial systems with human-like conceptual intelligence. --- ### XAI-MeD: Explainable Knowledge Guided Neuro-Symbolic Framework for Domain Generalization and Rare Class Detection in Medical Imaging Authors: Midhat Urooj, Ayan Banerjee, Sandeep Gupta Published: 2026-01-05 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.02008v1 Explainability domain generalization and rare class reliability are critical challenges in medical AI where deep models often fail under real world distribution shifts and exhibit bias against infrequent clinical conditions This paper introduces XAIMeD an explainable medical AI framework that integrates clinically accurate expert knowledge into deep learning through a unified neuro symbolic architecture XAIMeD is designed to improve robustness under distribution shift enhance rare class sensitivity and deliver transparent clinically aligned interpretations The framework encodes clinical expertise as logical connectives over atomic medical propositions transforming them into machine checkable class specific rules Their diagnostic utility is quantified through weighted feature satisfaction scores enabling a symbolic reasoning branch that complements neural predictions A confidence weighted fusion integrates symbolic and deep outputs while a Hunt inspired adaptive routing mechanism guided by Entropy Imbalance Gain EIG and Rare Class Gini mitigates class imbalance high intra class variability and uncertainty We evaluate XAIMeD across diverse modalities on four challenging tasks i Seizure Onset Zone SOZ localization from rs fMRI ii Diabetic Retinopathy grading across 6 multicenter datasets demonstrate substantial performance improvements including 6 percent gains in cross domain generalization and a 10 percent improved rare class F1 score far outperforming state of the art deep learning baselines Ablation studies confirm that the clinically grounded symbolic components act as effective regularizers ensuring robustness to distribution shifts XAIMeD thus provides a principled clinically faithful and interpretable approach to multimodal medical AI. --- ### Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models Authors: Antonio Colacicco, Vito Guida, Dario Di Palma, Fedelucio Narducci, Tommaso Di Noia Published: 2026-01-05 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.02002v1 Large Language Models (LLMs) are increasingly applied in recommendation scenarios due to their strong natural language understanding and generation capabilities. However, they are trained on vast corpora whose contents are not publicly disclosed, raising concerns about data leakage. Recent work has shown that the MovieLens-1M dataset is memorized by both the LLaMA and OpenAI model families, but the extraction of such memorized data has so far relied exclusively on manual prompt engineering. In this paper, we pose three main questions: Is it possible to enhance manual prompting? Can LLM memorization be detected through methods beyond manual prompting? And can the detection of data leakage be automated? To address these questions, we evaluate three approaches: (i) jailbreak prompt engineering; (ii) unsupervised latent knowledge discovery, probing internal activations via Contrast-Consistent Search (CCS) and Cluster-Norm; and (iii) Automatic Prompt Engineering (APE), which frames prompt discovery as a meta-learning process that iteratively refines candidate instructions. Experiments on MovieLens-1M using LLaMA models show that jailbreak prompting does not improve the retrieval of memorized items and remains inconsistent; CCS reliably distinguishes genuine from fabricated movie titles but fails on numerical user and rating data; and APE retrieves item-level information with moderate success yet struggles to recover numerical interactions. These findings suggest that automatically optimizing prompts is the most promising strategy for extracting memorized samples. --- ### Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priors Authors: Chen Zhu, Huiwen Zhang, Mu He, Yujie Li, Xiaotian Qiao Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01998v1 Enhancing the visibility of nighttime hazy images is challenging due to the complex degradation distributions. Existing methods mainly address a single type of degradation (e.g., haze or low-light) at a time, ignoring the interplay of different degradation types and resulting in limited visibility improvement. We observe that the domain knowledge shared between low-light and haze priors can be reinforced mutually for better visibility. Based on this key insight, in this paper, we propose a novel framework that enhances visibility in nighttime hazy images by reinforcing the intrinsic consistency between haze and low-light priors mutually and progressively. In particular, our model utilizes image-, patch-, and pixel-level experts that operate across visual and frequency domains to recover global scene structure, regional patterns, and fine-grained details progressively. A frequency-aware router is further introduced to adaptively guide the contribution of each expert, ensuring robust image restoration. Extensive experiments demonstrate the superior performance of our model on nighttime dehazing benchmarks both quantitatively and qualitatively. Moreover, we showcase the generalizability of our model in daytime dehazing and low-light enhancement tasks. --- ### Exploring Diversity, Novelty, and Popularity Bias in ChatGPT's Recommendations Authors: Dario Di Palma, Giovanni Maria Biancofiore, Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia Published: 2026-01-05 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.01997v1 ChatGPT has emerged as a versatile tool, demonstrating capabilities across diverse domains. Given these successes, the Recommender Systems (RSs) community has begun investigating its applications within recommendation scenarios primarily focusing on accuracy. While the integration of ChatGPT into RSs has garnered significant attention, a comprehensive analysis of its performance across various dimensions remains largely unexplored. Specifically, the capabilities of providing diverse and novel recommendations or exploring potential biases such as popularity bias have not been thoroughly examined. As the use of these models continues to expand, understanding these aspects is crucial for enhancing user satisfaction and achieving long-term personalization. This study investigates the recommendations provided by ChatGPT-3.5 and ChatGPT-4 by assessing ChatGPT's capabilities in terms of diversity, novelty, and popularity bias. We evaluate these models on three distinct datasets and assess their performance in Top-N recommendation and cold-start scenarios. The findings reveal that ChatGPT-4 matches or surpasses traditional recommenders, demonstrating the ability to balance novelty and diversity in recommendations. Furthermore, in the cold-start scenario, ChatGPT models exhibit superior performance in both accuracy and novelty, suggesting they can be particularly beneficial for new users. This research highlights the strengths and limitations of ChatGPT's recommendations, offering new perspectives on the capacity of these models to provide recommendations beyond accuracy-focused metrics. --- ### Towards Privacy-Preserving Mental Health Support with Large Language Models Authors: Dong Xue, Jicheng Tu, Ming Wang, Xin Yan, Fangzhou Liu, Jie Hu Published: 2026-01-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01993v2 Large language models (LLMs) have shown promise for mental health support, yet training such models is constrained by the scarcity and sensitivity of real counseling dialogues. In this article, we present MindChat, a privacy-preserving LLM for mental health support, together with MindCorpus, a synthetic multi-turn counseling dataset constructed via a multi-agent role-playing framework. To synthesize high-quality counseling data, the developed dialogue-construction framework employs a dual closed-loop feedback design to integrate psychological expertise and counseling techniques through role-playing: (i) turn-level critique-and-revision to improve coherence and counseling appropriateness within a session, and (ii) session-level strategy refinement to progressively enrich counselor behaviors across sessions. To mitigate privacy risks under decentralized data ownership, we fine-tune the base model using federated learning with parameter-efficient LoRA adapters and incorporate differentially private optimization to reduce membership and memorization risks. Experiments on synthetic-data quality assessment and counseling capability evaluation show that MindCorpus improves training effectiveness and that MindChat is competitive with existing general and counseling-oriented LLM baselines under both automatic LLM-judge and human evaluation protocols, while exhibiting reduced privacy leakage under membership inference attacks. --- ### API: Empowering Generalizable Real-World Image Dehazing via Adaptive Patch Importance Learning Authors: Chen Zhu, Huiwen Zhang, Yujie Li, Mu He, Xiaotian Qiao Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01992v1 Real-world image dehazing is a fundamental yet challenging task in low-level vision. Existing learning-based methods often suffer from significant performance degradation when applied to complex real-world hazy scenes, primarily due to limited training data and the intrinsic complexity of haze density distributions.To address these challenges, we introduce a novel Adaptive Patch Importance-aware (API) framework for generalizable real-world image dehazing. Specifically, our framework consists of an Automatic Haze Generation (AHG) module and a Density-aware Haze Removal (DHR) module. AHG provides a hybrid data augmentation strategy by generating realistic and diverse hazy images as additional high-quality training data. DHR considers hazy regions with varying haze density distributions for generalizable real-world image dehazing in an adaptive patch importance-aware manner. To alleviate the ambiguity of the dehazed image details, we further introduce a new Multi-Negative Contrastive Dehazing (MNCD) loss, which fully utilizes information from multiple negative samples across both spatial and frequency domains. Extensive experiments demonstrate that our framework achieves state-of-the-art performance across multiple real-world benchmarks, delivering strong results in both quantitative metrics and qualitative visual quality, and exhibiting robust generalization across diverse haze distributions. --- ### VIT-Ped: Visionary Intention Transformer for Pedestrian Behavior Analysis Authors: Aly R. Elkammar, Karim M. Gamaleldin, Catherine M. Elias Published: 2026-01-05 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.01989v1 Pedestrian Intention prediction is one of the key technologies in the transition from level 3 to level 4 autonomous driving. To understand pedestrian crossing behaviour, several elements and features should be taken into consideration to make the roads of tomorrow safer for everybody. We introduce a transformer / video vision transformer based algorithm of different sizes which uses different data modalities .We evaluated our algorithms on popular pedestrian behaviour dataset, JAAD, and have reached SOTA performance and passed the SOTA in metrics like Accuracy, AUC and F1-score. The advantages brought by different model design choices are investigated via extensive ablation studies. --- ### Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation Authors: Weijian Ma, Shizhao Sun, Tianyu Yu, Ruiyu Wang, Tat-Seng Chua, Jiang Bian Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01984v1 Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image patches, improving fine-grained perception but weakening global spatial awareness, or mark isolated coordinates, which capture object locations but overlook their overall organization. In this work, we integrate the cognitive concept of an object-centric blueprint into VLMs to enhance spatial reasoning. Given an image and a question, the model first constructs a JSON-style blueprint that records the positions, sizes, and attributes of relevant objects, and then reasons over this structured representation to produce the final answer. To achieve this, we introduce three key techniques: (1) blueprint-embedded reasoning traces for supervised fine-tuning to elicit basic reasoning skills; (2) blueprint-aware rewards in reinforcement learning to encourage the blueprint to include an appropriate number of objects and to align final answers with this causal reasoning; and (3) anti-shortcut data augmentation that applies targeted perturbations to images and questions, discouraging reliance on superficial visual or linguistic cues. Experiments show that our method consistently outperforms existing VLMs and specialized spatial reasoning models. --- ### ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems Authors: Noel Thomas Published: 2026-01-05 Categories: cs.AI, cs.IT arXiv: https://arxiv.org/abs/2601.01982v2 Large language models (LLMs) excel at natural language tasks but remain brittle in domains requiring precise logical and symbolic reasoning. Chaotic dynamical systems provide an especially demanding test because chaos is deterministic yet often misinterpreted as randomness or complexity. We introduce ChaosBench-Logic, a benchmark that evaluates LLM reasoning across 30 diverse dynamical systems using a unified first-order logic (FOL) ontology. Each system is annotated with truth assignments for 11 semantic predicates, and 621 questions are generated across seven reasoning categories, including multi-hop implications, cross-system analogies, counterfactual reasoning, bias probes, and multi-turn dialogues. We define metrics for logical accuracy, implication consistency, dialogue coherence, and contradiction, and we release an open-source evaluation pipeline. Initial experiments show that frontier LLMs such as GPT-4, Claude 3.5 Sonnet, Gemini 2.5 Flash, and the open-source LLaMA-3 70B achieve 91-94% per-item accuracy, yet still score 0% on compositional items and exhibit fragile global coherence. Dialogue-level accuracy ranges from 53.1% (GPT-4 CoT) to 75.5% (LLaMA-3 zero-shot). ChaosBench-Logic provides a rigorous testbed for diagnosing such failures and a foundation for developing neuro-symbolic approaches that improve scientific reasoning in LLMs. ---