# Research Papers — 2025-12 · bundle page 8 of 175

> Full-text markdown of papers #351–400 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/8
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/7.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/9.md)

### DRL-TH: Jointly Utilizing Temporal Graph Attention and Hierarchical Fusion for UGV Navigation in Crowded Environments

Authors: Ruitong Li, Lin Zhang, Yuenan Zhao, Chengxin Liu, Ran Song, Wei Zhang
Published: 2025-12-30
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.24284v1

Deep reinforcement learning (DRL) methods have demonstrated potential for autonomous navigation and obstacle avoidance of unmanned ground vehicles (UGVs) in crowded environments. Most existing approaches rely on single-frame observation and employ simple concatenation for multi-modal fusion, which limits their ability to capture temporal context and hinders dynamic adaptability. To address these challenges, we propose a DRL-based navigation framework, DRL-TH, which leverages temporal graph attention and hierarchical graph pooling to integrate historical observations and adaptively fuse multi-modal information. Specifically, we introduce a temporal-guided graph attention network (TG-GAT) that incorporates temporal weights into attention scores to capture correlations between consecutive frames, thereby enabling the implicit estimation of scene evolution. In addition, we design a graph hierarchical abstraction module (GHAM) that applies hierarchical pooling and learnable weighted fusion to dynamically integrate RGB and LiDAR features, achieving balanced representation across multiple scales. Extensive experiments demonstrate that our DRL-TH outperforms existing methods in various crowded environments. We also implemented DRL-TH control policy on a real UGV and showed that it performed well in real world scenarios.

---

### One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training

Authors: Jia Yu, Yan Zhu, Peiyao Fu, Tianyi Chen, Zhihua Wang, Fei Wu, Quanlin Li, Pinghong Zhou, Shuo Wang, Xian Yang
Published: 2025-12-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.24278v1

Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, restricting the data available for developing reliable artificial intelligence (AI) models and training novice clinicians. Here we present EndoRare, a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image. By leveraging language-guided concept disentanglement, EndoRare separates pathognomonic lesion features from non-diagnostic attributes, encoding the former into a learnable prototype embedding while varying the latter to ensure diversity. We validated the framework across four rare pathologies (calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome). Synthetic images were judged clinically plausible by experts and, when used for data augmentation, significantly enhanced downstream AI classifiers, improving the true positive rate at low false-positive rates. Crucially, a blinded reader study demonstrated that novice endoscopists exposed to EndoRare-generated cases achieved a 0.400 increase in recall and a 0.267 increase in precision. These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.

---

### LiftProj: Space Lifting and Projection-Based Panorama Stitching

Authors: Yuan Jia, Ruimin Wu, Rui Song, Jiaojiao Li, Bin Song
Published: 2025-12-30
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2512.24276v1

Traditional image stitching techniques have predominantly utilized two-dimensional homography transformations and mesh warping to achieve alignment on a planar surface. While effective for scenes that are approximately coplanar or exhibit minimal parallax, these approaches often result in ghosting, structural bending, and stretching distortions in non-overlapping regions when applied to real three-dimensional scenes characterized by multiple depth layers and occlusions. Such challenges are exacerbated in multi-view accumulations and 360° closed-loop stitching scenarios. In response, this study introduces a spatially lifted panoramic stitching framework that initially elevates each input image into a dense three-dimensional point representation within a unified coordinate system, facilitating global cross-view fusion augmented by confidence metrics. Subsequently, a unified projection center is established in three-dimensional space, and an equidistant cylindrical projection is employed to map the fused data onto a single panoramic manifold, thereby producing a geometrically consistent 360° panoramic layout. Finally, hole filling is conducted within the canvas domain to address unknown regions revealed by viewpoint transitions, restoring continuous texture and semantic coherence. This framework reconceptualizes stitching from a two-dimensional warping paradigm to a three-dimensional consistency paradigm and is designed to flexibly incorporate various three-dimensional lifting and completion modules. Experimental evaluations demonstrate that the proposed method substantially mitigates geometric distortions and ghosting artifacts in scenarios involving significant parallax and complex occlusions, yielding panoramic results that are more natural and consistent.

---

### Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

Authors: Zhe Huang, Hao Wen, Aiming Hao, Bingze Song, Meiqi Wu, Jiahong Wu, Xiangxiang Chu, Sheng Lu, Haoqian Wang
Published: 2025-12-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.24271v1

Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an over-reliance on language priors, which can lead to visual ungrounded hallucinations, especially when processing counterfactual videos that defy common sense. This limitation, stemming from the intrinsic data imbalance between text and video, is challenging to address due to the substantial cost of collecting and annotating counterfactual data. To address this, we introduce DualityForge, a novel counterfactual data synthesis framework that employs controllable, diffusion-based video editing to transform real-world videos into counterfactual scenarios. By embedding structured contextual information into the video editing and QA generation processes, the framework automatically produces high-quality QA pairs together with original-edited video pairs for contrastive training. Based on this, we build DualityVidQA, a large-scale video dataset designed to reduce MLLM hallucinations. In addition, to fully exploit the contrastive nature of our paired data, we propose Duality-Normalized Advantage Training (DNA-Train), a two-stage SFT-RL training regime where the RL phase applies pair-wise $\ell_1$ advantage normalization, thereby enabling a more stable and efficient policy optimization. Experiments on DualityVidQA-Test demonstrate that our method substantially reduces model hallucinations on counterfactual videos, yielding a relative improvement of 24.0% over the Qwen2.5-VL-7B baseline. Moreover, our approach achieves significant gains across both hallucination and general-purpose benchmarks, indicating strong generalization capability. We will open-source our dataset and code.

---

### Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning

Authors: Ziqing Fan, Yuqiao Xian, Yan Sun, Li Shen
Published: 2025-12-30
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.24265v1

A fine-grained data recipe is crucial for pre-training large language models, as it can significantly enhance training efficiency and model performance. One important ingredient in the recipe is to select samples based on scores produced by defined rules, LLM judgment, or statistical information in embeddings, which can be roughly categorized into quality and diversity metrics. Due to the high computational cost when applied to trillion-scale token pre-training datasets such as FineWeb and DCLM, these two or more types of metrics are rarely considered jointly in a single selection process. However, in our empirical study, selecting samples based on quality metrics exhibit severe diminishing returns during long-term pre-training, while selecting on diversity metrics removes too many valuable high-quality samples, both of which limit pre-trained LLMs' capabilities. Therefore, we introduce DATAMASK, a novel and efficient joint learning framework designed for large-scale pre-training data selection that can simultaneously optimize multiple types of metrics in a unified process, with this study focusing specifically on quality and diversity metrics. DATAMASK approaches the selection process as a mask learning problem, involving iterative sampling of data masks, computation of policy gradients based on predefined objectives with sampled masks, and updating of mask sampling logits. Through policy gradient-based optimization and various acceleration enhancements, it significantly reduces selection time by 98.9% compared to greedy algorithm, enabling our study to explore joint learning within trillion-scale tokens. With DATAMASK, we select a subset of about 10% from the 15 trillion-token FineWeb dataset, termed FineWeb-Mask. Evaluated across 12 diverse tasks, we achieves significant improvements of 3.2% on a 1.5B dense model and 1.9% on a 7B MoE model.

---

### Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment

Authors: Lijun Zhang, Lin Li, Wei Wei, Yajie Qi, Huizhong Song, Jun Wang, Yaodong Yang, Jiye Liang
Published: 2025-12-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.24263v1

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO, typically operate under a risk-neutral paradigm that is insufficient to address the risks arising from deviations from the reference policy and offers limited robustness against rare but potentially catastrophic harmful behaviors. To address this limitation, we propose Risk-aware Stepwise Alignment (RSA), a novel alignment method that explicitly incorporates risk awareness into the policy optimization process by leveraging a class of nested risk measures. Specifically, RSA formulates safety alignment as a token-level risk-aware constrained policy optimization problem and solves it through a stepwise alignment procedure that yields token-level policy updates derived from the nested risk measures. This design offers two key benefits: (1) it mitigates risks induced by excessive model shift away from a reference policy, and (2) it explicitly suppresses low-probability yet high-impact harmful behaviors. Moreover, we provide theoretical analysis on policy optimality under mild assumptions. Experimental results demonstrate that our method achieves high levels of helpfulness while ensuring strong safety and significantly suppresses tail risks, namely low-probability yet high-impact unsafe responses.

---

### Physically-Grounded Manifold Projection Model for Generalizable Metal Artifact Reduction in Dental CBCT

Authors: Zhi Li, Yaqi Wang, Bingtao Ma, Yifan Zhang, Huiyu Zhou, Shuai Wang
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24260v2

Metal artifacts in Dental CBCT severely obscure anatomical structures, hindering diagnosis. Current deep learning for Metal Artifact Reduction (MAR) faces limitations: supervised methods suffer from spectral blurring due to "regression-to-the-mean", while unsupervised ones risk structural hallucinations. Denoising Diffusion Models (DDPMs) offer realism but rely on slow, stochastic iterative sampling, unsuitable for clinical use. To resolve this, we propose the Physically-Grounded Manifold Projection (PGMP) framework. First, our Anatomically-Adaptive Physics Simulation (AAPS) pipeline synthesizes high-fidelity training pairs via Monte Carlo spectral modeling and patient-specific digital twins, bridging the synthetic-to-real gap. Second, our DMP-Former adapts the Direct x-Prediction paradigm, reformulating restoration as a deterministic manifold projection to recover clean anatomy in a single forward pass, eliminating stochastic sampling. Finally, a Semantic-Structural Alignment (SSA) module anchors the solution using priors from medical foundation models (MedDINOv3), ensuring clinical plausibility. Experiments on synthetic and multi-center clinical datasets show PGMP outperforms state-of-the-art methods on unseen anatomy, setting new benchmarks in efficiency and diagnostic reliability. Code and data: https://github.com/ricoleehduu/PGMP.

---

### Tracing the Flow of Knowledge From Science to Technology Using Deep Learning

Authors: Michael E. Rose, Mainak Ghosh, Sebastian Erhardt, Cheng Li, Erik Buunk, Dietmar Harhoff
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.24259v1

We develop a language similarity model suitable for working with patents and scientific publications at the same time. In a horse race-style evaluation, we subject eight language (similarity) models to predict credible Patent-Paper Citations. We find that our Pat-SPECTER model performs best, which is the SPECTER2 model fine-tuned on patents. In two real-world scenarios (separating patent-paper-pairs and predicting patent-paper-pairs) we demonstrate the capabilities of the Pat-SPECTER. We finally test the hypothesis that US patents cite papers that are semantically less similar than in other large jurisdictions, which we posit is because of the duty of candor. The model is open for the academic community and practitioners alike.

---

### Early Prediction of Sepsis using Heart Rate Signals and Genetic Optimized LSTM Algorithm

Authors: Alireza Rafiei, Farshid Hajati, Alireza Rezaee, Amirhossien Panahi, Shahadat Uddin
Published: 2025-12-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.24253v1

Sepsis, characterized by a dysregulated immune response to infection, results in significant mortality, morbidity, and healthcare costs. The timely prediction of sepsis progression is crucial for reducing adverse outcomes through early intervention. Despite the development of numerous models for Intensive Care Unit (ICU) patients, there remains a notable gap in approaches for the early detection of sepsis in non-ward settings. This research introduces and evaluates four novel machine learning algorithms designed for predicting the onset of sepsis on wearable devices by analyzing heart rate data. The architecture of these models was refined through a genetic algorithm, optimizing for performance, computational complexity, and memory requirements. Performance metrics were subsequently extracted for each model to evaluate their feasibility for implementation on wearable devices capable of accurate heart rate monitoring. The models were initially tailored for a prediction window of one hour, later extended to four hours through transfer learning. The encouraging outcomes of this study suggest the potential for wearable technology to facilitate early sepsis detection outside ICU and ward environments.

---

### Deep Reinforcement Learning for Solving the Fleet Size and Mix Vehicle Routing Problem

Authors: Pengfu Wan, Jiawei Chen, Gangyan Xu
Published: 2025-12-30
Categories: cs.AI, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2512.24251v1

The Fleet Size and Mix Vehicle Routing Problem (FSMVRP) is a prominent variant of the Vehicle Routing Problem (VRP), extensively studied in operations research and computational science. FSMVRP requires simultaneous decisions on fleet composition and routing, making it highly applicable to real-world scenarios such as short-term vehicle rental and on-demand logistics. However, these requirements also increase the complexity of FSMVRP, posing significant challenges, particularly in large-scale and time-constrained environments. In this paper, we propose a deep reinforcement learning (DRL)-based approach for solving FSMVRP, capable of generating near-optimal solutions within a few seconds. Specifically, we formulate the problem as a Markov Decision Process (MDP) and develop a novel policy network, termed FRIPN, that seamlessly integrates fleet composition and routing decisions. Our method incorporates specialized input embeddings designed for distinctdecision objectives, including a remaining graph embedding to facilitate effective vehicle employment decisions. Comprehensive experiments are conducted on both randomly generated instances and benchmark datasets. The experimental results demonstrate that our method exhibits notable advantages in terms of computational efficiency and scalability, particularly in large-scale and time-constrained scenarios. These strengths highlight the potential of our approach for practical applications and provide valuable inspiration for extending DRL-based techniques to other variants of VRP.

---

### MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation

Authors: Fuqiang Gu, Yuanke Li, Xianlei Long, Kangping Ji, Chao Chen, Qingyi Gu, Zhenliang Ni
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24243v1

Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception.

---

### LAILA: A Large Trait-Based Dataset for Arabic Automated Essay Scoring

Authors: May Bashendy, Walid Massoud, Sohaila Eltanbouly, Salam Albatarni, Marwan Sayed, Abrar Abir, Houda Bouamor, Tamer Elsayed
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.24235v2

Automated Essay Scoring (AES) has gained increasing attention in recent years, yet research on Arabic AES remains limited due to the lack of publicly available datasets. To address this, we introduce LAILA, the largest publicly available Arabic AES dataset to date, comprising 7,859 essays annotated with holistic and trait-specific scores on seven dimensions: relevance, organization, vocabulary, style, development, mechanics, and grammar. We detail the dataset design, collection, and annotations, and provide benchmark results using state-of-the-art Arabic and English models in prompt-specific and cross-prompt settings. LAILA fills a critical need in Arabic AES research, supporting the development of robust scoring systems.

---

### MotivNet: Evolving Meta-Sapiens into an Emotionally Intelligent Foundation Model

Authors: Rahul Medicharla, Alper Yilmaz
Published: 2025-12-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.24231v1

In this paper, we introduce MotivNet, a generalizable facial emotion recognition model for robust real-world application. Current state-of-the-art FER models tend to have weak generalization when tested on diverse data, leading to deteriorated performance in the real world and hindering FER as a research domain. Though researchers have proposed complex architectures to address this generalization issue, they require training cross-domain to obtain generalizable results, which is inherently contradictory for real-world application. Our model, MotivNet, achieves competitive performance across datasets without cross-domain training by using Meta-Sapiens as a backbone. Sapiens is a human vision foundational model with state-of-the-art generalization in the real world through large-scale pretraining of a Masked Autoencoder. We propose MotivNet as an additional downstream task for Sapiens and define three criteria to evaluate MotivNet's viability as a Sapiens task: benchmark performance, model similarity, and data similarity. Throughout this paper, we describe the components of MotivNet, our training approach, and our results showing MotivNet is generalizable across domains. We demonstrate that MotivNet can be benchmarked against existing SOTA models and meets the listed criteria, validating MotivNet as a Sapiens downstream task, and making FER more incentivizing for in-the-wild application. The code is available at https://github.com/OSUPCVLab/EmotionFromFaceImages.

---

### Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes

Authors: Shuyun Wang, Haiyang Sun, Bing Wang, Hangjun Ye, Xin Yu
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24227v1

Vision-centric autonomous driving systems rely on diverse and scalable training data to achieve robust performance. While video object editing offers a promising path for data augmentation, existing methods often struggle to maintain both high visual fidelity and temporal coherence. In this work, we propose \textbf{Mirage}, a one-step video diffusion model for photorealistic and coherent asset editing in driving scenes. Mirage builds upon a text-to-video diffusion prior to ensure temporal consistency across frames. However, 3D causal variational autoencoders often suffer from degraded spatial fidelity due to compression, and directly passing 3D encoder features to decoder layers breaks temporal causality. To address this, we inject temporally agnostic latents from a pretrained 2D encoder into the 3D decoder to restore detail while preserving causal structures. Furthermore, because scene objects and inserted assets are optimized under different objectives, their Gaussians exhibit a distribution mismatch that leads to pose misalignment. To mitigate this, we introduce a two-stage data alignment strategy combining coarse 3D alignment and fine 2D refinement, thereby improving alignment and providing cleaner supervision. Extensive experiments demonstrate that Mirage achieves high realism and temporal consistency across diverse editing scenarios. Beyond asset editing, Mirage can also generalize to other video-to-video translation tasks, serving as a reliable baseline for future research. Our code is available at https://github.com/wm-research/mirage.

---

### ARM: A Learnable, Plug-and-Play Module for CLIP-based Open-vocabulary Semantic Segmentation

Authors: Ziquan Liu, Zhewei Zhu, Xuyang Shi
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24224v1

Open-vocabulary semantic segmentation (OVSS) is fundamentally hampered by the coarse, image-level representations of CLIP, which lack precise pixel-level details. Existing training-free methods attempt to resolve this by either importing priors from costly external foundation models (e.g., SAM, DINO) or by applying static, hand-crafted heuristics to CLIP's internal features. These approaches are either computationally expensive or sub-optimal. We propose the Attention Refinement Module (ARM), a lightweight, learnable module that effectively unlocks and refines CLIP's internal potential. Unlike static-fusion methods, ARM learns to adaptively fuse hierarchical features. It employs a semantically-guided cross-attention block, using robust deep features (K, V) to select and refine detail-rich shallow features (Q), followed by a self-attention block. The key innovation lies in a ``train once, use anywhere" paradigm. Trained once on a general-purpose dataset (e.g., COCO-Stuff), ARM acts as a universal plug-and-play post-processor for diverse training-free frameworks. Extensive experiments show that ARM consistently boosts baseline performance on multiple benchmarks with negligible inference overhead, establishing an efficient and effective paradigm for training-free OVSS.

---

### Medical Image Classification on Imbalanced Data Using ProGAN and SMA-Optimized ResNet: Application to COVID-19

Authors: Sina Jahromi, Farshid Hajati, Alireza Rezaee, Javaher Nourian
Published: 2025-12-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.24214v1

The challenge of imbalanced data is prominent in medical image classification. This challenge arises when there is a significant disparity in the number of images belonging to a particular class, such as the presence or absence of a specific disease, as compared to the number of images belonging to other classes. This issue is especially notable during pandemics, which may result in an even more significant imbalance in the dataset. Researchers have employed various approaches in recent years to detect COVID-19 infected individuals accurately and quickly, with artificial intelligence and machine learning algorithms at the forefront. However, the lack of sufficient and balanced data remains a significant obstacle to these methods. This study addresses the challenge by proposing a progressive generative adversarial network to generate synthetic data to supplement the real ones. The proposed method suggests a weighted approach to combine synthetic data with real ones before inputting it into a deep network classifier. A multi-objective meta-heuristic population-based optimization algorithm is employed to optimize the hyper-parameters of the classifier. The proposed model exhibits superior cross-validated metrics compared to existing methods when applied to a large and imbalanced chest X-ray image dataset of COVID-19. The proposed model achieves 95.5% and 98.5% accuracy for 4-class and 2-class imbalanced classification problems, respectively. The successful experimental outcomes demonstrate the effectiveness of the proposed model in classifying medical images using imbalanced data during pandemics.

---

### RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation

Authors: Ming-Ming Yu, Yi Chen, Börje F. Karlsson, Wenjun Wu
Published: 2025-12-30
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2512.24212v3

Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation, allowing robots to search for arbitrary objects without fine-tuning, existing methods face two key limitations: (1) heavy reliance on ground-truth depth and pose information, which restricts applicability in real-world scenarios; and (2) lack of visual in-context learning (VICL) capability to extract geometric and semantic priors from environmental context, as in a short traversal video. To address these challenges, we propose RANGER, a novel zero-shot, open-vocabulary semantic navigation framework that operates using only a monocular camera. Leveraging powerful 3D foundation models, RANGER eliminates the dependency on depth and pose while exhibiting strong VICL capability. By simply observing a short video of the target environment, the system can also significantly improve task efficiency without requiring architectural modifications or task-specific retraining. The framework integrates several key components: keyframe-based 3D reconstruction, semantic point cloud generation, vision-language model (VLM)-driven exploration value estimation, high-level adaptive waypoint selection, and low-level action execution. Experiments on the HM3D benchmark and real-world environments demonstrate that RANGER achieves competitive performance in terms of navigation success rate and exploration efficiency, while showing superior VICL adaptability, with no previous 3D mapping of the environment required.

---

### Micro-Macro Tensor Neural Surrogates for Uncertainty Quantification in Collisional Plasma

Authors: Wei Chen, Giacomo Dimarco, Lorenzo Pareschi
Published: 2025-12-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.24205v1

Plasma kinetic equations exhibit pronounced sensitivity to microscopic perturbations in model parameters and data, making reliable and efficient uncertainty quantification (UQ) essential for predictive simulations. However, the cost of uncertainty sampling, the high-dimensional phase space, and multiscale stiffness pose severe challenges to both computational efficiency and error control in traditional numerical methods. These aspects are further emphasized in presence of collisions where the high-dimensional nonlocal collision integrations and conservation properties pose severe constraints. To overcome this, we present a variance-reduced Monte Carlo framework for UQ in the Vlasov--Poisson--Landau (VPL) system, in which neural network surrogates replace the multiple costly evaluations of the Landau collision term. The method couples a high-fidelity, asymptotic-preserving VPL solver with inexpensive, strongly correlated surrogates based on the Vlasov--Poisson--Fokker--Planck (VPFP) and Euler--Poisson (EP) equations. For the surrogate models, we introduce a generalization of the separable physics-informed neural network (SPINN), developing a class of tensor neural networks based on an anisotropic micro-macro decomposition, to reduce velocity-moment costs, model complexity, and the curse of dimensionality. To further increase correlation with VPL, we calibrate the VPFP model and design an asymptotic-preserving SPINN whose small- and large-Knudsen limits recover the EP and VP systems, respectively. Numerical experiments show substantial variance reduction over standard Monte Carlo, accurate statistics with far fewer high-fidelity samples, and lower wall-clock time, while maintaining robustness to stochastic dimension.

---

### CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformers

Authors: Yonglak Son, Suhyeok Kim, Seungryong Kim, Young Geun Kim
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24195v1

Diffusion transformer (DiT) achieves remarkable performance in visual generation, but its iterative denoising process combined with larger capacity leads to a high inference cost. Recent works have demonstrated that the iterative denoising process of DiT models involves substantial redundant computation across steps. To effectively reduce the redundant computation in DiT, we propose CorGi (Contribution-Guided Block-Wise Interval Caching), training-free DiT inference acceleration framework that selectively reuses the outputs of transformer blocks in DiT across denoising steps. CorGi caches low-contribution blocks and reuses them in later steps within each interval to reduce redundant computation while preserving generation quality. For text-to-image tasks, we further propose CorGi+, which leverages per-block cross-attention maps to identify salient tokens and applies partial attention updates to protect important object details. Evaluation on the state-of-the-art DiT models demonstrates that CorGi and CorGi+ achieve up to 2.0x speedup on average, while preserving high generation quality.

---

### PointRAFT: 3D deep learning for high-throughput prediction of potato tuber weight from partial point clouds

Authors: Pieter M. Blok, Haozhou Wang, Hyun Kwon Suh, Peicheng Wang, James Burridge, Wei Guo
Published: 2025-12-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.24193v1

Potato yield is a key indicator for optimizing cultivation practices in agriculture. Potato yield can be estimated on harvesters using RGB-D cameras, which capture three-dimensional (3D) information of individual tubers moving along the conveyor belt. However, point clouds reconstructed from RGB-D images are incomplete due to self-occlusion, leading to systematic underestimation of tuber weight. To address this, we introduce PointRAFT, a high-throughput point cloud regression network that directly predicts continuous 3D shape properties, such as tuber weight, from partial point clouds. Rather than reconstructing full 3D geometry, PointRAFT infers target values directly from raw 3D data. Its key architectural novelty is an object height embedding that incorporates tuber height as an additional geometric cue, improving weight prediction under practical harvesting conditions. PointRAFT was trained and evaluated on 26,688 partial point clouds collected from 859 potato tubers across four cultivars and three growing seasons on an operational harvester in Japan. On a test set of 5,254 point clouds from 172 tubers, PointRAFT achieved a mean absolute error of 12.0 g and a root mean squared error of 17.2 g, substantially outperforming a linear regression baseline and a standard PointNet++ regression network. With an average inference time of 6.3 ms per point cloud, PointRAFT supports processing rates of up to 150 tubers per second, meeting the high-throughput requirements of commercial potato harvesters. Beyond potato weight estimation, PointRAFT provides a versatile regression network applicable to a wide range of 3D phenotyping and robotic perception tasks. The code, network weights, and a subset of the dataset are publicly available at https://github.com/pieterblok/pointraft.git.

---

### SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents

Authors: Yankai Jiang, Wenjie Lou, Lilong Wang, Zhenyu Tang, Shiyang Feng, Jiaxuan Lu, Haoran Sun, Yaning Pan, Shuang Gu, Haoyang Su, Feng Liu, Wangxu Wei et al.
Published: 2025-12-30
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2512.24189v1

We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical instruments. This protocol-level standardization enables AI agents and applications to discover, call, and compose capabilities seamlessly across disparate platforms and institutional boundaries. (2) Orchestrated Experiment Lifecycle Management: SCP complements the protocol with a secure service architecture, which comprises a centralized SCP Hub and federated SCP Servers. This architecture manages the complete experiment lifecycle (registration, planning, execution, monitoring, and archival), enforces fine-grained authentication and authorization, and orchestrates traceable, end-to-end workflows that bridge computational and physical laboratories. Based on SCP, we have constructed a scientific discovery platform that offers researchers and agents a large-scale ecosystem of more than 1,600 tool resources. Across diverse use cases, SCP facilitates secure, large-scale collaboration between heterogeneous AI systems and human researchers while significantly reducing integration overhead and enhancing reproducibility. By standardizing scientific context and tool orchestration at the protocol level, SCP establishes essential infrastructure for scalable, multi-institution, agent-driven science.

---

### MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring

Authors: Qipeng Wang, Rui Sheng, Yafei Li, Huamin Qu, Yushi Sun, Min Zhu
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.24181v2

Recent advancements in Large Language Models (LLMs) have demonstrated significant promise in clinical diagnosis. However, current models struggle to emulate the iterative, diagnostic hypothesis-driven reasoning of real clinical scenarios. Specifically, current LLMs suffer from three critical limitations: (1) generating hallucinated medical content due to weak grounding in verified knowledge, (2) asking redundant or inefficient questions rather than discriminative ones that hinder diagnostic progress, and (3) losing coherence over multi-turn dialogues, leading to contradictory or inconsistent conclusions. To address these challenges, we propose MedKGI, a diagnostic framework grounded in clinical practices. MedKGI integrates a medical knowledge graph (KG) to constrain reasoning to validated medical ontologies, selects questions based on information gain to maximize diagnostic efficiency, and adopts an OSCE-format structured state to maintain consistent evidence tracking across turns. Experiments on clinical benchmarks show that MedKGI outperforms strong LLM baselines in both diagnostic accuracy and inquiry efficiency, improving dialogue efficiency by 30% on average while maintaining state-of-the-art accuracy.

---

### Guiding a Diffusion Transformer with the Internal Dynamics of Itself

Authors: Xingyu Zhou, Qifan Li, Xiaobin Hu, Hai Chen, Shuhang Gu
Published: 2025-12-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.24176v2

The diffusion model presents a powerful ability to capture the entire (conditional) data distribution. However, due to the lack of sufficient training and data to learn to cover low-probability areas, the model will be penalized for failing to generate high-quality images corresponding to these areas. To achieve better generation quality, guidance strategies such as classifier free guidance (CFG) can guide the samples to the high-probability areas during the sampling stage. However, the standard CFG often leads to over-simplified or distorted samples. On the other hand, the alternative line of guiding diffusion model with its bad version is limited by carefully designed degradation strategies, extra training and additional sampling steps. In this paper, we proposed a simple yet effective strategy Internal Guidance (IG), which introduces an auxiliary supervision on the intermediate layer during training process and extrapolates the intermediate and deep layer's outputs to obtain generative results during sampling process. This simple strategy yields significant improvements in both training efficiency and generation quality on various baselines. On ImageNet 256x256, SiT-XL/2+IG achieves FID=5.31 and FID=1.75 at 80 and 800 epochs. More impressively, LightningDiT-XL/1+IG achieves FID=1.34 which achieves a large margin between all of these methods. Combined with CFG, LightningDiT-XL/1+IG achieves the current state-of-the-art FID of 1.19.

---

### Variational Quantum Brushes

Authors: Jui-Ting Lu, Henrique Ennes, Chih-Kang Huang, Ali Abbassi
Published: 2025-12-30
Categories: quant-ph, cs.GR, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2512.24173v1

Quantum brushes are computational arts software introduced by Ferreira et al (2025) that leverage quantum behavior to generate novel artistic effects. In this outreach paper, we introduce the mathematical framework and describe the implementation of two quantum brushes based on variational quantum algorithms, Steerable and Chemical. While Steerable uses quantum geometric control theory to merge two works of art, Chemical mimics variational eigensolvers for estimating molecular ground energies to evolve colors on an underlying canvas. The implementation of both brushes is available open-source at https://github.com/moth-quantum/QuantumBrush and is fully compatible with the original quantum brushes.

---

### Deep Global Clustering for Hyperspectral Image Segmentation: Concepts, Applications, and Open Challenges

Authors: Yu-Tang Chang, Pin-Wei Chen, Shih-Fang Chen
Published: 2025-12-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.24172v1

Hyperspectral imaging (HSI) analysis faces computational bottlenecks due to massive data volumes that exceed available memory. While foundation models pre-trained on large remote sensing datasets show promise, their learned representations often fail to transfer to domain-specific applications like close-range agricultural monitoring where spectral signatures, spatial scales, and semantic targets differ fundamentally. This report presents Deep Global Clustering (DGC), a conceptual framework for memory-efficient HSI segmentation that learns global clustering structure from local patch observations without pre-training. DGC operates on small patches with overlapping regions to enforce consistency, enabling training in under 30 minutes on consumer hardware while maintaining constant memory usage. On a leaf disease dataset, DGC achieves background-tissue separation (mean IoU 0.925) and demonstrates unsupervised disease detection through navigable semantic granularity. However, the framework suffers from optimization instability rooted in multi-objective loss balancing: meaningful representations emerge rapidly but degrade due to cluster over-merging in feature space. We position this work as intellectual scaffolding - the design philosophy has merit, but stable implementation requires principled approaches to dynamic loss balancing. Code and data are available at https://github.com/b05611038/HSI_global_clustering.

---

### DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

Authors: Zefeng He, Xiaoye Qu, Yafu Li, Tong Zhu, Siyuan Huang, Yu Cheng
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24165v1

While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon, vision-centric tasks. In this paper, we establish a novel Generative Multimodal Reasoning paradigm and introduce DiffThinker, a diffusion-based reasoning framework. Conceptually, DiffThinker reformulates multimodal reasoning as a native generative image-to-image task, achieving superior logical consistency and spatial precision in vision-centric tasks. We perform a systematic comparison between DiffThinker and MLLMs, providing the first in-depth investigation into the intrinsic characteristics of this paradigm, revealing four core properties: efficiency, controllability, native parallelism, and collaboration. Extensive experiments across four domains (sequential planning, combinatorial optimization, constraint satisfaction, and spatial configuration) demonstrate that DiffThinker significantly outperforms leading closed source models including GPT-5 (+314.2\%) and Gemini-3-Flash (+111.6\%), as well as the fine-tuned Qwen3-VL-32B baseline (+39.0\%), highlighting generative multimodal reasoning as a promising approach for vision-centric reasoning.

---

### Deep Probabilistic Supervision for Image Classification

Authors: Anton Adelöw, Matteo Gamba, Atsuto Maki
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24162v2

Supervised training of deep neural networks for classification typically relies on hard targets, which promote overconfidence and can limit calibration, generalization, and robustness. Self-distillation methods aim to mitigate this by leveraging inter-class and sample-specific information present in the model's own predictions, but often remain dependent on hard targets without explicitly modeling predictive uncertainty. With this in mind, we propose Deep Probabilistic Supervision (DPS), a principled learning framework constructing sample-specific target distributions via statistical inference on the model's own predictions, remaining independent of hard targets after initialization. We show that DPS consistently yields higher test accuracy (e.g., +2.0% for DenseNet-264 on ImageNet) and significantly lower Expected Calibration Error (ECE) (-40% ResNet-50, CIFAR-100) than existing self-distillation methods. When combined with a contrastive loss, DPS achieves state-of-the-art robustness under label noise.

---

### Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset

Authors: TsaiChing Ni, ZhenQi Chen, YuanFu Yang
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24160v2

We present IMDD-1M, the first large-scale Industrial Multimodal Defect Dataset comprising 1,000,000 aligned image-text pairs, designed to advance multimodal learning for manufacturing and quality inspection. IMDD-1M contains high-resolution real-world defects spanning over 60 material categories and more than 400 defect types, each accompanied by expert-verified annotations and fine-grained textual descriptions detailing defect location, severity, and contextual attributes. This dataset enables a wide spectrum of applications, including classification, segmentation, retrieval, captioning, and generative modeling. Building upon IMDD-1M, we train a diffusion-based vision-language foundation model from scratch, specifically tailored for industrial scenarios. The model serves as a generalizable foundation that can be efficiently adapted to specialized domains through lightweight fine-tuning. With less than 5% of the task-specific data required by dedicated expert models, it achieves comparable performance, highlighting the potential of data-efficient foundation model adaptation for industrial inspection and generation, paving the way for scalable, domain-adaptive, and knowledge-grounded manufacturing intelligence. Additional details and resources can be found in this URL: https://ninaneon.github.io/projectpage/

---

### Developing controlled natural language for formal specification patterns using AI assistants

Authors: Natalia Garanina, Vladimir Zyubin, Igor Anureev
Published: 2025-12-30
Categories: cs.SE, cs.AI, cs.FL
arXiv: https://arxiv.org/abs/2512.24159v1

Using an AI assistant, we developed a method for systematically constructing controlled natural language for requirements based on formal specification patterns containing logical attributes. The method involves three stages: 1) compiling a generalized natural language requirement pattern that utilizes all attributes of the formal specification template; 2) generating, using the AI assistant, a corpus of natural language requirement patterns, reduced by partially evaluating attributes (the developed prompt utilizes the generalized template, attribute definitions, and specific formal semantics of the requirement patterns); and 3) formalizing the syntax of the controlled natural language based on an analysis of the grammatical structure of the resulting patterns. The method has been tested for event-driven temporal requirements.

---

### Training Report of TeleChat3-MoE

Authors: Xinzhang Liu, Chao Wang, Zhihao Yang, Zhuo Jiang, Xuncheng Zhao, Haoran Wang, Lei Li, Dongdong He, Luobin Liu, Kaizhe Yuan, Han Gao, Zihan Wang et al.
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.24157v1

TeleChat3-MoE is the latest series of TeleChat large language models, featuring a Mixture-of-Experts (MoE) architecture with parameter counts ranging from 105 billion to over one trillion,trained end-to-end on Ascend NPU cluster. This technical report mainly presents the underlying training infrastructure that enables reliable and efficient scaling to frontier model sizes. We detail systematic methodologies for operator-level and end-to-end numerical accuracy verification, ensuring consistency across hardware platforms and distributed parallelism strategies. Furthermore, we introduce a suite of performance optimizations, including interleaved pipeline scheduling, attention-aware data scheduling for long-sequence training,hierarchical and overlapped communication for expert parallelism, and DVM-based operator fusion. A systematic parallelization framework, leveraging analytical estimation and integer linear programming, is also proposed to optimize multi-dimensional parallelism configurations. Additionally, we present methodological approaches to cluster-level optimizations, addressing host- and device-bound bottlenecks during large-scale training tasks. These infrastructure advancements yield significant throughput improvements and near-linear scaling on clusters comprising thousands of devices, providing a robust foundation for large-scale language model development on hardware ecosystems.

---

### Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks

Authors: Evgenii Rudakov, Jonathan Shock, Benjamin Ultan Cowley
Published: 2025-12-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.24156v1

We present a training-free graph-based approach for solving interactive reasoning tasks in the ARC-AGI-3 benchmark. ARC-AGI-3 comprises game-like tasks where agents must infer task mechanics through limited interactions, and adapt to increasing complexity as levels progress. Success requires forming hypotheses, testing them, and tracking discovered mechanics. The benchmark has revealed that state-of-the-art LLMs are currently incapable of reliably solving these tasks. Our method combines vision-based frame processing with systematic state-space exploration using graph-structured representations. It segments visual frames into meaningful components, prioritizes actions based on visual salience, and maintains a directed graph of explored states and transitions. By tracking visited states and tested actions, the agent prioritizes actions that provide the shortest path to untested state-action pairs. On the ARC-AGI-3 Preview Challenge, this structured exploration strategy solves a median of 30 out of 52 levels across six games and ranks 3rd on the private leaderboard, substantially outperforming frontier LLM-based agents. These results demonstrate that explicit graph-structured exploration, even without learning, can serve as a strong baseline for interactive reasoning and underscore the importance of systematic state tracking and action prioritization in sparse-feedback environments where current LLMs fail to capture task dynamics. The code is open source and available at https://github.com/dolphin-in-a-coma/arc-agi-3-just-explore.

---

### Fast Score-Based Sampling via Log-Concave Reductions

Authors: M. J. Wainwright
Published: 2025-12-30
Categories: math.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.24152v2

Sampling based on score diffusions has led to striking empirical results, and has attracted considerable attention from various research communities. It depends on availability of (approximate) Stein score functions for various levels of additive noise. We show how in some generality, the availability of scores allows the general problem to be ``reduced'' to sampling from an adaptively constructed sequence of $K$ strongly log-concave (SLC) sub-problems. The reduction is simple, constructive and algorithm-independent, so that any SLC sampler can be used as a subroutine. Various bounds on score-based sampling complexity follow directly: for instance, high-accuracy SLC samplers yield $\tilde{\mathcal{O}}(K \sqrt{d} \operatorname{polylog}(1/\varepsilon))$ guarantees for accuracy $\varepsilon$ in dimension $d$, where randomized midpoint SLC schemes yield $\tilde{\mathcal{O}}(K d^{1/3} \operatorname{poly}(1/\varepsilon))$ guarantees. When the original distribution itself is SLC, we prove that $K \leq 1 + \log_2(κ)$, thereby obtaining the first efficient procedure with logarithmic dependence on condition number $κ$; for general distributions, the quantity $K$ depends on the geometry of score Hessian across the trajectory. Our analysis is direct and simple, involving techniques and insights complementary to those in standard analyses of discretized diffusions.

---

### Large Emotional World Model

Authors: Changhao Song, Yazhou Zhang, Hui Gao, Chang Yang, Peng Zhang
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.24149v2

The world is governed by both physical laws and affective dynamics. Physical laws govern state transitions, while affective dynamics shape human actions, decisions, and interactions. A world model that learns only physical laws can approximate the physical world, but not the human world. In this paper, we introduce human emotion as a key state variable in world models, enabling them to capture both future state transitions and their emotional causes. We first construct Emotion-Why-How (EWH), the first world model dataset centered on emotional state transitions, containing 10,850 emotion-aware transition tuples. Each tuple encodes the pre-state, pre-emotion, action, post-emotion, and post-state, supporting reasoning about why actions occur and how emotions reshape future states. Based on EWH, we propose the Large Emotional World Model (LEWM), which factorizes future prediction into two coupled steps: first predicting the future emotional state from the current context, and then conditioning future world-state prediction on the predicted emotion. Experiments show that LEWM brings consistent gains across world-state prediction, emotion understanding, and general reasoning tasks. It achieves up to 45.72% accuracy improvement on EWH, 3.94% on WorldNet, 17.47% F1 improvement on MELD, and a 6.10% gain on specific MMLU categories. These results demonstrate that incorporating emotion into world models enables more realistic simulation of human-centered environments and expands the predictive understanding of intelligent agents.

---

### Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning

Authors: Chubin Chen, Sujie Hu, Jiashu Zhu, Meiqi Wu, Jintao Chen, Yanxun Li, Nisha Huang, Chengyu Fang, Jiahong Wu, Xiangxiang Chu, Xiu Li
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24146v2

Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, while existing methods achieve high scores on automated reward metrics, they often lead to Preference Mode Collapse (PMC)-a specific form of reward hacking where models converge on narrow, high-scoring outputs (e.g., images with monolithic styles or pervasive overexposure), severely degrading generative diversity. In this work, we introduce and quantify this phenomenon, proposing DivGenBench, a novel benchmark designed to measure the extent of PMC. We posit that this collapse is driven by over-optimization along the reward model's inherent biases. Building on this analysis, we propose Directional Decoupling Alignment (D$^2$-Align), a novel framework that mitigates PMC by directionally correcting the reward signal. Specifically, our method first learns a directional correction within the reward model's embedding space while keeping the model frozen. This correction is then applied to the reward signal during the optimization process, preventing the model from collapsing into specific modes and thereby maintaining diversity. Our comprehensive evaluation, combining qualitative analysis with quantitative metrics for both quality and diversity, reveals that D$^2$-Align achieves superior alignment with human preference.

---

### When Does Pairing Seeds Reduce Variance? Evidence from a Multi-Agent Economic Simulation

Authors: Udit Sharma
Published: 2025-12-30
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.24145v3

Machine learning systems appear stochastic but are deterministically random, as seeded pseudorandom number generators produce identical realisations across repeated executions. Standard evaluation practice typically treats runs across alternatives as independent and does not exploit shared sources of randomness. This paper analyses the statistical structure of comparative evaluation under shared random seeds. Under this design, competing systems are evaluated using identical seeds, inducing matched stochastic realisations and yielding strict variance reduction whenever outcomes are positively correlated at the seed level. We demonstrate these effects using an extended learning-based multi-agent economic simulator, where paired evaluation exposes systematic differences in aggregate and distributional outcomes that remain statistically inconclusive under independent evaluation at fixed budgets.

---

### Activation Steering for Masked Diffusion Language Models

Authors: Adi Shnaidman, Erin Feiglin, Osher Yaari, Efrat Mentel, Amit Levi, Raz Lapid
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.24143v3

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level mechanisms for inference-time control in MDLMs remain largely unexplored. To address this gap, we introduce an activation steering primitive for MDLMs: we extract a single low-dimensional direction from contrastive prompt sets using one prompt-only forward pass, and apply a global intervention on residual-stream activations throughout reverse diffusion, without performing optimization or altering the diffusion sampling procedure. Using safety refusal as a deployment-relevant case study, we find that refusal behavior in multiple MDLMs is governed by a consistent, approximately one-dimensional activation subspace. Applying the corresponding direction yields large and systematic behavioral shifts and is substantially more effective than prompt-based and optimization-based baselines. We further uncover diffusion-specific accessibility: effective directions can be extracted not only from post-instruction tokens, but also from pre-instruction tokens that are typically ineffective in autoregressive models due to causal attention. Ablations localize maximal leverage to early denoising steps and mid-to-late transformer layers, with early diffusion blocks contributing disproportionately. Finally, in an MDLM trained on English and Chinese, extracted directions transfer strongly between English and Chinese, but do not reliably generalize to an autoregressive architecture, highlighting architecture-dependent representations of safety constraints.

---

### Colorful Pinball: Density-Weighted Quantile Regression for Conditional Guarantee of Conformal Prediction

Authors: Qianyi Chen, Bo Li
Published: 2025-12-30
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2512.24139v5

Although conformal prediction provides robust marginal coverage guarantees, achieving reliable conditional coverage for specific inputs remains challenging. While exact distribution-free conditional coverage is impossible with finite samples, recent work has focused on improving the conditional coverage of standard conformal procedures. Distinct from approaches that target relaxed notions of conditional coverage, we directly target the mean squared error of conditional coverage by refining the quantile regression components that underpin many conformal methods. Leveraging a Taylor expansion, we derive a sharp surrogate objective for quantile regression: a density-weighted pinball loss, where the weights are given by the conditional density of the nonconformity score evaluated at the true quantile. We propose a three-headed quantile network that estimates these weights via finite differences using auxiliary quantile levels at $1-α\pm δ$, subsequently fine-tuning the central quantile by optimizing the weighted loss. We provide a theoretical analysis with exact non-asymptotic guarantees characterizing the resulting excess risk. Extensive experiments on diverse high-dimensional real-world datasets demonstrate remarkable improvements in conditional coverage performance.

---

### GARDO: Reinforcing Diffusion Models without Reward Hacking

Authors: Haoran He, Yuxiao Ye, Jie Liu, Jiajun Liang, Zhiyong Wang, Ziyang Yuan, Xintao Wang, Hangyu Mao, Pengfei Wan, Ling Pan
Published: 2025-12-30
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2512.24138v1

Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment. However, since precisely specifying a ground-truth objective for visual tasks remains challenging, the models are often optimized using a proxy reward that only partially captures the true goal. This mismatch often leads to reward hacking, where proxy scores increase while real image quality deteriorates and generation diversity collapses. While common solutions add regularization against the reference policy to prevent reward hacking, they compromise sample efficiency and impede the exploration of novel, high-reward regions, as the reference policy is usually sub-optimal. To address the competing demands of sample efficiency, effective exploration, and mitigation of reward hacking, we propose Gated and Adaptive Regularization with Diversity-aware Optimization (GARDO), a versatile framework compatible with various RL algorithms. Our key insight is that regularization need not be applied universally; instead, it is highly effective to selectively penalize a subset of samples that exhibit high uncertainty. To address the exploration challenge, GARDO introduces an adaptive regularization mechanism wherein the reference model is periodically updated to match the capabilities of the online policy, ensuring a relevant regularization target. To address the mode collapse issue in RL, GARDO amplifies the rewards for high-quality samples that also exhibit high diversity, encouraging mode coverage without destabilizing the optimization process. Extensive experiments across diverse proxy rewards and hold-out unseen metrics consistently show that GARDO mitigates reward hacking and enhances generation diversity without sacrificing sample efficiency or exploration, highlighting its effectiveness and robustness.

---

### Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training

Authors: Yi Liu, Sukai Wang, Dafeng Wei, Xiaowei Cai, Linqing Zhong, Jiange Yang, Guanghui Ren, Jinyu Zhang, Maoqing Yao, Chuankang Li, Xindong He, Liliang Chen et al.
Published: 2025-12-30
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.24125v3

General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models. While large Vision-Language Models (VLMs) improve semantic generalization, insufficient embodied reasoning leads to brittle behavior, and conversely, strong reasoning alone is inadequate without precise control. To provide a decoupled and quantitative assessment of this bottleneck, we introduce Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodied reasoning benchmark in robotic manipulation, comprising 6K+ question-answer pairs across four reasoning dimensions. By decoupling reasoning from execution, ERIQ enables systematic evaluation and reveals a strong positive correlation between embodied reasoning capability and end-to-end VLA generalization. To bridge the gap from reasoning to precise execution, we propose FACT, a flow-matching-based action tokenizer that converts continuous control into discrete sequences while preserving high-fidelity trajectory reconstruction. The resulting GenieReasoner jointly optimizes reasoning and action in a unified space, outperforming both continuous-action and prior discrete-action baselines in real-world tasks. Together, ERIQ and FACT provide a principled framework for diagnosing and overcoming the reasoning-precision trade-off, advancing robust, general-purpose robotic manipulation. Project page: https://geniereasoner.github.io/GenieReasoner/

---

### OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization

Authors: Advait Gadhikar, Riccardo Grazzi, James Hensman
Published: 2025-12-30
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.24124v2

The presence of outliers in Large Language Models (LLMs) weights and activations makes them difficult to quantize. Recent work has leveraged rotations to mitigate these outliers. In this work, we propose methods that learn fusible rotations by minimizing principled and cheap proxy objectives to the weight quantization error. We primarily focus on GPTQ as the quantization method. Our main method is OptRot, which reduces weight outliers simply by minimizing the element-wise fourth power of the rotated weights. We show that OptRot outperforms both Hadamard rotations and more expensive, data-dependent methods like SpinQuant and OSTQuant for weight quantization. It also improves activation quantization in the W4A8 setting. We also propose a data-dependent method, OptRot$^{+}$, that further improves performance by incorporating information on the activation covariance. In the W4A4 setting, we see that both OptRot and OptRot$^{+}$ perform worse, highlighting a trade-off between weight and activation quantization.

---

### Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design

Authors: Raghuvir Duvvuri, Chandini Vysyaraju, Avi Goyal, Dmitry Ignatov, Radu Timofte
Published: 2025-12-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.24120v2

Automated neural network architecture design remains a significant challenge in computer vision. Task diversity and computational constraints require both effective architectures and efficient search methods. Large Language Models (LLMs) present a promising alternative to computationally intensive Neural Architecture Search (NAS), but their application to architecture generation in computer vision has not been systematically studied, particularly regarding prompt engineering and validation strategies. Building on the task-agnostic NNGPT/LEMUR framework, this work introduces and validates two key contributions for computer vision. First, we present Few-Shot Architecture Prompting (FSAP), the first systematic study of the number of supporting examples (n = 1, 2, 3, 4, 5, 6) for LLM-based architecture generation. We find that using n = 3 examples best balances architectural diversity and context focus for vision tasks. Second, we introduce Whitespace-Normalized Hash Validation, a lightweight deduplication method (less than 1 ms) that provides a 100x speedup over AST parsing and prevents redundant training of duplicate computer vision architectures. In large-scale experiments across seven computer vision benchmarks (MNIST, CIFAR-10, CIFAR-100, CelebA, ImageNette, SVHN, Places365), we generated 1,900 unique architectures. We also introduce a dataset-balanced evaluation methodology to address the challenge of comparing architectures across heterogeneous vision tasks. These contributions provide actionable guidelines for LLM-based architecture search in computer vision and establish rigorous evaluation practices, making automated design more accessible to researchers with limited computational resources.

---

### GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation

Authors: Yuan Feng, Yue Yang, Xiaohan He, Jiatong Zhao, Jianlong Chen, Zijun Chen, Daocheng Fu, Qi Liu, Renqiu Xia, Bo Zhang, Junchi Yan
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.24119v1

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations, including the risk of test data contamination from textbook-based benchmarks, overemphasis on final answers over reasoning processes, and insufficient diagnostic granularity. To address these issues, we present GeoBench, a hierarchical benchmark featuring four reasoning levels in geometric problem-solving: Visual Perception, Goal-Oriented Planning, Rigorous Theorem Application, and Self-Reflective Backtracking. Through six formally verified tasks generated via TrustGeoGen, we systematically assess capabilities ranging from attribute extraction to logical error correction. Experiments reveal that while reasoning models like OpenAI-o3 outperform general MLLMs, performance declines significantly with increasing task complexity. Key findings demonstrate that sub-goal decomposition and irrelevant premise filtering critically influence final problem-solving accuracy, whereas Chain-of-Thought prompting unexpectedly degrades performance in some tasks. These findings establish GeoBench as a comprehensive benchmark while offering actionable guidelines for developing geometric problem-solving systems.

---

### Targeted Semantic Segmentation of Himalayan Glacial Lakes Using Time-Series SAR: Towards Automated GLOF Early Warning

Authors: Pawan Adhikari, Satish Raj Regmi, Hari Ram Shrestha
Published: 2025-12-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2512.24117v1

Glacial Lake Outburst Floods (GLOFs) are one of the most devastating climate change induced hazards. Existing remote monitoring approaches often prioritise maximising spatial coverage to train generalistic models or rely on optical imagery hampered by persistent cloud coverage. This paper presents an end-to-end, automated deep learning pipeline for the targeted monitoring of high-risk Himalayan glacial lakes using time-series Sentinel-1 SAR. We introduce a "temporal-first" training strategy, utilising a U-Net with an EfficientNet-B3 backbone trained on a curated dataset of a cohort of 4 lakes (Tsho Rolpa, Chamlang Tsho, Tilicho and Gokyo Lake). The model achieves an IoU of 0.9130 validating the success and efficacy of the "temporal-first" strategy required for transitioning to Early Warning Systems. Beyond the model, we propose an operational engineering architecture: a Dockerised pipeline that automates data ingestion via the ASF Search API and exposes inference results via a RESTful endpoint. This system shifts the paradigm from static mapping to dynamic and automated early warning, providing a scalable architectural foundation for future development in Early Warning Systems.

---

### Quantitative Understanding of PDF Fits and their Uncertainties

Authors: Amedeo Chiefa, Luigi Del Debbio, Richard Kenway
Published: 2025-12-30
Categories: hep-ph, cs.LG
arXiv: https://arxiv.org/abs/2512.24116v3

Parton Distribution Functions (PDFs) play a central role in describing experimental data at colliders and provide insight into the structure of nucleons. As the LHC enters an era of high-precision measurements, a robust PDF determination with a reliable uncertainty quantification has become mandatory in order to match the experimental precision. The NNPDF collaboration has pioneered the use of Machine Learning (ML) techniques for PDF determinations, using Neural Networks (NNs) to parametrise the unknown PDFs in a flexible and unbiased way. The NNs are then trained on experimental data by means of stochastic gradient descent algorithms. The statistical robustness of the results is validated by extensive closure tests using synthetic data. In this work, we develop a theoretical framework based on the Neural Tangent Kernel (NTK) to analyse the training dynamics of neural networks. This approach allows us to derive, under precise assumptions, an analytical description of the neural network evolution during training, enabling a quantitative understanding of the training process. Having an analytical handle on the training dynamics allows us to clarify the role of the NN architecture and the impact of the experimental data in a transparent way. Similarly, we are able to describe the evolution of the covariance of the NN output during training, providing a quantitative description of how uncertainties are propagated from the data to the fitted function. While our results are not a substitute for PDF fitting, they do provide a powerful diagnostic tool to assess the robustness of current fitting methodologies. Beyond its relevance for particle physics phenomenology, our analysis of PDF determinations provides a testbed to apply theoretical ideas about the learning process developed in the ML community.

---

### CogRec: A Cognitive Recommender Agent Fusing Large Language Models and Soar for Explainable Recommendation

Authors: Jiaxin Hu, Tao Wang, Bingsan Yang, Hongrun Wang
Published: 2025-12-30
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2512.24113v1

Large Language Models (LLMs) have demonstrated a remarkable capacity in understanding user preferences for recommendation systems. However, they are constrained by several critical challenges, including their inherent "Black-Box" characteristics, susceptibility to knowledge hallucination, and limited online learning capacity. These factors compromise their trustworthiness and adaptability. Conversely, cognitive architectures such as Soar offer structured and interpretable reasoning processes, yet their knowledge acquisition is notoriously laborious. To address these complementary challenges, we propose a novel cognitive recommender agent called CogRec which synergizes the strengths of LLMs with the Soar cognitive architecture. CogRec leverages Soar as its core symbolic reasoning engine and leverages an LLM for knowledge initialization to populate its working memory with production rules. The agent operates on a Perception-Cognition-Action(PCA) cycle. Upon encountering an impasse, it dynamically queries the LLM to obtain a reasoned solution. This solution is subsequently transformed into a new symbolic production rule via Soar's chunking mechanism, thereby enabling robust online learning. This learning paradigm allows the agent to continuously evolve its knowledge base and furnish highly interpretable rationales for its recommendations. Extensive evaluations conducted on three public datasets demonstrate that CogRec demonstrates significant advantages in recommendation accuracy, explainability, and its efficacy in addressing the long-tail problem.

---

### Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attacks

Authors: Yongtao Chen, Yanbo Wang, Wentao Zhao, Guole Shen, Tianchen Deng, Jingchuan Wang
Published: 2025-12-30
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.24111v1

Monocular Depth Estimation (MDE) serves as a core perception module in autonomous driving systems, but it remains highly susceptible to adversarial attacks. Errors in depth estimation may propagate through downstream decision making and influence overall traffic safety. Existing physical attacks primarily rely on texture-based patches, which impose strict placement constraints and exhibit limited realism, thereby reducing their effectiveness in complex driving environments. To overcome these limitations, this work introduces a training-free generative adversarial attack framework that generates naturalistic, scene-consistent adversarial objects via a diffusion-based conditional generation process. The framework incorporates a Salient Region Selection module that identifies regions most influential to MDE and a Jacobian Vector Product Guidance mechanism that steers adversarial gradients toward update directions supported by the pre-trained diffusion model. This formulation enables the generation of physically plausible adversarial objects capable of inducing substantial adversarial depth shifts. Extensive digital and physical experiments demonstrate that our method significantly outperforms existing attacks in effectiveness, stealthiness, and physical deployability, underscoring its strong practical implications for autonomous driving safety assessment.

---

### Constructive Approximation of Random Process via Stochastic Interpolation Neural Network Operators

Authors: Sachin Saini, Uaday Singh
Published: 2025-12-30
Categories: stat.ML, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2512.24106v1

In this paper, we construct a class of stochastic interpolation neural network operators (SINNOs) with random coefficients activated by sigmoidal functions. We establish their boundedness, interpolation accuracy, and approximation capabilities in the mean square sense, in probability, as well as path-wise within the space of second-order stochastic (random) processes \( L^2(Ω, \mathcal{F},\mathbb{P}) \). Additionally, we provide quantitative error estimates using the modulus of continuity of the processes. These results highlight the effectiveness of SINNOs for approximating stochastic processes with potential applications in COVID-19 case prediction.

---

### Multilevel Fair Allocation with Matroid-Rank Preferences

Authors: Maxime Lucet, Nawal Benabbou, Aurélie Beynier, Nicolas Maudet
Published: 2025-12-30
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2512.24105v2

We introduce the concept of multilevel fair allocation of resources with tree-structured hierarchical relations among agents. While at each level it is possible to consider the problem locally as an allocation of an agent to its children, the multilevel allocation can be seen as a trace capturing the fact that the process is iterated until the leaves of the tree. In principle, each intermediary node may have its own local allocation mechanism. The main challenge is then to design algorithms which can retain good fairness and efficiency properties. In this paper we propose two original algorithms under the assumption that leaves of the tree have matroid-rank utility functions and the utility of any internal node is the sum of the utilities of its children. The first one is a generic polynomial-time sequential algorithm that comes with theoretical guarantees in terms of efficiency and fairness. It operates in a top-down fashion -- as commonly observed in real-world applications -- and is compatible with various local algorithms. The second one extends the recently proposed General Yankee Swap to the multilevel setting. This extension comes with efficiency guarantees only, but we show that it preserves excellent fairness properties in practice.

---

### Enhancing LLM Planning Capabilities through Intrinsic Self-Critique

Authors: Bernd Bohnet, Pierre-Alexandre Kamienny, Hanie Sedghi, Dilan Gorur, Pranjal Awasthi, Aaron Parisi, Kevin Swersky, Rosanne Liu, Azade Nova, Noah Fiedel
Published: 2025-12-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.24103v1

We demonstrate an approach for LLMs to critique their \emph{own} answers with the goal of enhancing their performance that leads to significant improvements over established planning benchmarks. Despite the findings of earlier research that has cast doubt on the effectiveness of LLMs leveraging self critique methods, we show significant performance gains on planning datasets in the Blocksworld domain through intrinsic self-critique, without external source such as a verifier. We also demonstrate similar improvements on Logistics and Mini-grid datasets, exceeding strong baseline accuracies. We employ a few-shot learning technique and progressively extend it to a many-shot approach as our base method and demonstrate that it is possible to gain substantial improvement on top of this already competitive approach by employing an iterative process for correction and refinement. We illustrate how self-critique can significantly boost planning performance. Our empirical results present new state-of-the-art on the class of models considered, namely LLM model checkpoints from October 2024. Our primary focus lies on the method itself, demonstrating intrinsic self-improvement capabilities that are applicable regardless of the specific model version, and we believe that applying our method to more complex search techniques and more capable models will lead to even better performance.

---

### Autoregressivity in the Latent Space of a GP-VAE Language Model: An Empirical Ablation Study

Authors: Yves Ruffenach
Published: 2025-12-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.24102v1

This paper provides an ablation-based analysis of latent autoregression in GP-VAE models, building upon our previous work introducing the architecture. Language models typically rely on an autoregressive factorization over tokens. In contrast, our prior work proposed shifting sequential structure to the latent space through a causal Gaussian process, while using a non-autoregressive decoder. Here, we conduct a systematic ablation study of the role played by latent autoregression. We compare (i) a full GP-VAE model with autoregressive latent dynamics, (ii) a non-autoregressive ablation in which latent variables are independent, and (iii) a standard token-level autoregressive Transformer. Our results show that, within the considered regime (medium-scale corpora and short training contexts), latent autoregression induces latent trajectories that are significantly more compatible with the Gaussian-process prior and exhibit greater long-horizon stability. In contrast, removing autoregression leads to degraded latent structure and unstable long-range behavior. These findings highlight the role of latent autoregression as an effective mechanism for organizing long-range structure, while remaining complementary to token-level autoregressive modeling. They should be interpreted as an empirical analysis of representational structure rather than as a proposal for a new architecture.

---