# Research Papers — 2025-12 · bundle page 125 of 175 > Full-text markdown of papers #6201–6250 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/125 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/124.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/126.md) ### GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring Authors: Maximilian Schall, Felix Leonard Knöfel, Noah Elias König, Jan Jonas Kubeler, Maximilian von Klinski, Joan Wilhelm Linnemann, Xiaoshi Liu, Iven Jelle Schlegelmilch, Ole Woyciniuk, Alexandra Schild, Dante Wasmuht, Magdalena Bermejo Espinet et al. Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07776v2 Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals from vast archives of camera trap footage. The primary obstacle to automating this process has been the lack of large-scale, "in-the-wild" video datasets suitable for training robust deep learning models. To address this gap, we introduce a comprehensive benchmark with three novel datasets: Gorilla-SPAC-Wild, the largest video dataset for wild primate re-identification to date; Gorilla-Berlin-Zoo, for assessing cross-domain re-identification generalization; and Gorilla-SPAC-MoT, for evaluating multi-object tracking in camera trap footage. Building on these datasets, we present GorillaWatch, an end-to-end pipeline integrating detection, tracking, and re-identification. To exploit temporal information, we introduce a multi-frame self-supervised pretraining strategy that leverages consistency in tracklets to learn domain-specific features without manual labels. To ensure scientific validity, a differentiable adaptation of AttnLRP verifies that our model relies on discriminative biometric traits rather than background correlations. Extensive benchmarking subsequently demonstrates that aggregating features from large-scale image backbones outperforms specialized video architectures. Finally, we address unsupervised population counting by integrating spatiotemporal constraints into standard clustering to mitigate over-segmentation. We publicly release all code and datasets to facilitate scalable, non-invasive monitoring of endangered species --- ### Distribution-informed Online Conformal Prediction Authors: Dongjian Hu, Junxi Wu, Shu-Tao Xia, Changliang Zou Published: 2025-12-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.07770v2 Conformal prediction provides a pivotal and flexible technique for uncertainty quantification by constructing prediction sets with a predefined coverage rate. Many online conformal prediction methods have been developed to address data distribution shifts in fully adversarial environments, resulting in overly conservative prediction sets. We propose Conformal Optimistic Prediction (COP), an online conformal prediction algorithm incorporating underlying data pattern into the update rule. Through estimated cumulative distribution function of non-conformity scores, COP produces tighter prediction sets when predictable pattern exists, while retaining valid coverage guarantees even when estimates are inaccurate. We establish a joint bound on coverage and regret, which further confirms the validity of our approach. We also prove that COP achieves distribution-free, finite-sample coverage under arbitrary learning rates and can converge when scores are $i.i.d.$. The experimental results also show that COP can achieve valid coverage and construct shorter prediction intervals than other baselines. --- ### Formalized Hopfield Networks and Boltzmann Machines Authors: Matteo Cipollina, Michail Karatarakis, Freek Wiedijk Published: 2025-12-08 Categories: cs.LG, cs.LO arXiv: https://arxiv.org/abs/2512.07766v2 Neural networks are widely used, yet their analysis and verification remain challenging. We present a Lean~4 formalization covering both deterministic and stochastic models. We first formalize Hopfield networks -- recurrent networks that store patterns as stable states -- and prove their convergence, and the correctness of Hebbian learning, the rule that updates parameters to encode patterns. We then turn to stochastic networks, whose probabilistic updates converge to a stationary distribution: we formalize the dynamics and learning of Boltzmann machines and prove their ergodicity -- convergence to a \emph{unique} stationary distribution -- via a new formalization of the Perron--Frobenius theorem. --- ### TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards Authors: Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng Published: 2025-12-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.07761v3 Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety vulnerabilities. However, existing approaches typically rely on turn-level optimization, which is insufficient for learning long-term attack strategies. To bridge this gap, we formulate this task as a multi-turn reinforcement learning problem, directly optimizing the harmfulness of the final-turn response as the outcome reward. To address the sparse supervision of the outcome reward, we introduce TROJail, which employs two process rewards to evaluate the utility of intermediate prompts and integrate them into advantage estimation. These rewards (1) penalize overly harmful prompts that trigger the model's refusal mechanism, and (2) encourage steering the semantic relevance of responses toward the targeted harmful content. Experimental results show improved attack success rates across multiple models and benchmarks, highlighting the effectiveness of our approach. The code is available at https://github.com/xxiqiao/TROJail. Warning: This paper contains examples of harmful content. --- ### Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification Authors: Menglin Wang, Xiaojin Gong, Jiachen Li, Genlin Ji Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07760v1 Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation. Given the significant gap across visible and infrared modality, estimating reliable cross-modality association becomes a major challenge in USVI-ReID. Existing methods usually adopt optimal transport to associate the intra-modality clusters, which is prone to propagating the local cluster errors, and also overlooks global instance-level relations. By mining and attending to the visible-infrared modality bias, this paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning. Motivated by the camera-aware distance rectification in single-modality re-ID, we propose modality-aware Jaccard distance to mitigate the distance bias caused by modality discrepancy, so that more reliable cross-modality associations can be estimated through global clustering. To further improve cross-modality representation learning, a `split-and-contrast' strategy is designed to obtain modality-specific global prototypes. By explicitly aligning these prototypes under global association guidance, modality-invariant yet ID-discriminative representation learning can be achieved. While conceptually simple, our method obtains state-of-the-art performance on benchmark VI-ReID datasets and outperforms existing methods by a significant margin, validating its effectiveness. --- ### UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction Authors: Mayank Anand, Ujair Alam, Surya Prakash, Priya Shukla, Gora Chand Nandi, Domenec Puig Published: 2025-12-08 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.07756v1 Clinical ultrasound acquisition is highly operator-dependent, where rapid probe motion and brightness fluctuations often lead to reconstruction errors that reduce trust and clinical utility. We present UltrasODM, a dual-stream framework that assists sonographers during acquisition through calibrated per-frame uncertainty, saliency-based diagnostics, and actionable prompts. UltrasODM integrates (i) a contrastive ranking module that groups frames by motion similarity, (ii) an optical-flow stream fused with Dual-Mamba temporal modules for robust 6-DoF pose estimation, and (iii) a Human-in-the-Loop (HITL) layer combining Bayesian uncertainty, clinician-calibrated thresholds, and saliency maps highlighting regions of low confidence. When uncertainty exceeds the threshold, the system issues unobtrusive alerts suggesting corrective actions such as re-scanning highlighted regions or slowing the sweep. Evaluated on a clinical freehand ultrasound dataset, UltrasODM reduces drift by 15.2%, distance error by 12.1%, and Hausdorff distance by 10.1% relative to UltrasOM, while producing per-frame uncertainty and saliency outputs. By emphasizing transparency and clinician feedback, UltrasODM improves reconstruction reliability and supports safer, more trustworthy clinical workflows. Our code is publicly available at https://github.com/AnandMayank/UltrasODM. --- ### Physics-Informed Neural Networks for Joint Source and Parameter Estimation in Advection-Diffusion Equations Authors: Brenda Anague, Bamdad Hosseini, Issa Karambal, Jean Medard Ngnotchouye Published: 2025-12-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.07755v3 Recent studies have demonstrated the success of deep learning in solving forward and inverse problems in engineering and scientific computing domains, such as physics-informed neural networks (PINNs). Source inversion problems under sparse measurements for parabolic partial differential equations (PDEs) are particularly challenging to solve using PINNs, due to their severe ill-posedness and the multiple unknowns involved including the source function and the PDE parameters. Although the neural tangent kernel (NTK) of PINNs has been widely used in forward problems involving a single neural network, its extension to inverse problems involving multiple neural networks remains less explored. In this work, we propose a weighted adaptive approach based on the NTK of PINNS including multiple separate networks representing the solution, the unknown source, and the PDE parameters. The key idea behind our methodology is to simultaneously solve the joint recovery of the solution, the source function along with the unknown parameters thereby using the underlying partial differential equation as a constraint that couples multiple unknown functional parameters, leading to more efficient use of the limited information in the measurements. We apply our method on the advection-diffusion equation and we present various 2D and 3D numerical experiments using different types of measurements data that reflect practical engineering systems. Our proposed method is successful in estimating the unknown source function, the velocity and diffusion parameters as well as recovering the solution of the equation, while remaining robust to additional noise in the measurements. --- ### Unison: A Fully Automatic, Task-Universal, and Low-Cost Framework for Unified Understanding and Generation Authors: Shihao Zhao, Yitong Chen, Zeyinzi Jiang, Bojia Zi, Shaozhe Hao, Yu Liu, Chaojie Mao, Kwan-Yee K. Wong Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07747v1 Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive paradigm, and the other adopts a two-stage scheme connecting pre-trained understanding and generative models for alignment fine-tuning. The former demands massive data and computing resources unaffordable for ordinary researchers. Though the latter requires a lower training cost, existing works often suffer from limited task coverage or poor generation quality. Both approaches lack the ability to parse input meta-information (such as task type, image resolution, video duration, etc.) and require manual parameter configuration that is tedious and non-intelligent. In this paper, we propose Unison which adopts the two-stage scheme while preserving the capabilities of the pre-trained models well. With an extremely low training cost, we cover a variety of multimodal understanding tasks, including text, image, and video understanding, as well as diverse generation tasks, such as text-to-visual content generation, editing, controllable generation, and IP-based reference generation. We also equip our model with the ability to automatically parse user intentions, determine the target task type, and accurately extract the meta-information required for the corresponding task. This enables full automation of various multimodal tasks without human intervention. Experiments demonstrate that, under a low-cost setting of only 500k training samples and 50 GPU hours, our model can accurately and automatically identify tasks and extract relevant parameters, and achieve superior performance across a variety of understanding and generation tasks. --- ### DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving Authors: Jialv Zou, Shaoyu Chen, Bencheng Liao, Zhiyu Zheng, Yuehao Song, Lefei Zhang, Qian Zhang, Wenyu Liu, Xinggang Wang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07745v1 Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined anchors representing different driving intentions to partition the action space and generate diverse trajectories, its reliance on imitation learning lacks sufficient constraints, resulting in a dilemma between diversity and consistent high quality. In this work, we propose DiffusionDriveV2, which leverages reinforcement learning to both constrain low-quality modes and explore for superior trajectories. This significantly enhances the overall output quality while preserving the inherent multimodality of its core Gaussian Mixture Model. First, we use scale-adaptive multiplicative noise, ideal for trajectory planning, to promote broad exploration. Second, we employ intra-anchor GRPO to manage advantage estimation among samples generated from a single anchor, and inter-anchor truncated GRPO to incorporate a global perspective across different anchors, preventing improper advantage comparisons between distinct intentions (e.g., turning vs. going straight), which can lead to further mode collapse. DiffusionDriveV2 achieves 91.2 PDMS on the NAVSIM v1 dataset and 85.5 EPDMS on the NAVSIM v2 dataset in closed-loop evaluation with an aligned ResNet-34 backbone, setting a new record. Further experiments validate that our approach resolves the dilemma between diversity and consistent high quality for truncated diffusion models, achieving the best trade-off. Code and model will be available at https://github.com/hustvl/DiffusionDriveV2 --- ### A multimodal Bayesian Network for symptom-level depression and anxiety prediction from voice and speech data Authors: Agnes Norbury, George Fairs, Alexandra L. Georgescu, Matthew M. Nour, Emilia Molimpakis, Stefano Goria Published: 2025-12-08 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2512.07741v1 During psychiatric assessment, clinicians observe not only what patients report, but important nonverbal signs such as tone, speech rate, fluency, responsiveness, and body language. Weighing and integrating these different information sources is a challenging task and a good candidate for support by intelligence-driven tools - however this is yet to be realized in the clinic. Here, we argue that several important barriers to adoption can be addressed using Bayesian network modelling. To demonstrate this, we evaluate a model for depression and anxiety symptom prediction from voice and speech features in large-scale datasets (30,135 unique speakers). Alongside performance for conditions and symptoms (for depression, anxiety ROC-AUC=0.842,0.831 ECE=0.018,0.015; core individual symptom ROC-AUC>0.74), we assess demographic fairness and investigate integration across and redundancy between different input modality types. Clinical usefulness metrics and acceptability to mental health service users are explored. When provided with sufficiently rich and large-scale multimodal data streams and specified to represent common mental conditions at the symptom rather than disorder level, such models are a principled approach for building robust assessment support tools: providing clinically-relevant outputs in a transparent and explainable format that is directly amenable to expert clinical supervision. --- ### HLTCOE Evaluation Team at TREC 2025: VQA Track Authors: Dengjia Zhang, Charles Weng, Katherine Guerrerio, Yi Lu, Kenton Murray, Alexander Martin, Reno Kriz, Benjamin Van Durme Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07738v1 The HLTCOE Evaluation team participated in TREC VQA's Answer Generation (AG) task, for which we developed a listwise learning framework that aims to improve semantic precision and ranking consistency in answer generation. Given a video-question pair, a base multimodal model first generates multiple candidate answers, which are then reranked using a model trained with a novel Masked Pointer Cross-Entropy Loss with Rank Weights. This objective integrates pointer-based candidate selection, rank-dependent weighting, and masked cross-entropy under vocabulary restriction, enabling stable and interpretable listwise optimization. By bridging generative modeling with discriminative ranking, our method produces coherent, fine-grained answer lists. Experiments reveal consistent gains in accuracy and ranking stability, especially for questions requiring temporal reasoning and semantic disambiguation. --- ### A scalable and real-time neural decoder for topological quantum codes Authors: Andrew W. Senior, Thomas Edlich, Francisco J. H. Heras, Lei M. Zhang, Oscar Higgott, James S. Spencer, Taylor Applebaum, Sam Blackwell, Justin Ledford, Akvilė Žemgulytė, Augustin Žídek, Noah Shutty et al. Published: 2025-12-08 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2512.07737v2 Fault-tolerant quantum computing will require error rates far below those achievable with physical qubits. Quantum error correction (QEC) bridges this gap, but depends on decoders being simultaneously fast, accurate, and scalable. This combination of requirements remains unmet by a machine-learning decoder, nor by any decoder for promising resource-efficient codes such as the color code. Here we introduce AlphaQubit 2, a neural-network decoder that achieves near-optimal logical error rates for both surface and color codes at scale under realistic noise. For the color code, it is orders of magnitude faster than other high-accuracy decoders. We demonstrate real-time decoding faster than 1μs per cycle on commercial accelerators: for the surface code to distance 11, with better accuracy than leading real-time decoders; and the first real-time decoding of the color code to distance 9. These results support the practical application of a wider class of promising QEC codes, and establish a credible path towards high-accuracy, real-time neural decoding at the scales required for fault-tolerant quantum computation. --- ### SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery Authors: Meng Cao, Xingyu Li, Xue Liu, Ian Reid, Xiaodan Liang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07733v1 Despite advancements in Multi-modal Large Language Models (MLLMs) for scene understanding, their performance on complex spatial reasoning tasks requiring mental simulation remains significantly limited. Current methods often rely on passive observation of spatial data, failing to internalize an active mental imagery process. To bridge this gap, we propose SpatialDreamer, a reinforcement learning framework that enables spatial reasoning through a closedloop process of active exploration, visual imagination via a world model, and evidence-grounded reasoning. To address the lack of fine-grained reward supervision in longhorizontal reasoning tasks, we propose Geometric Policy Optimization (GeoPO), which introduces tree-structured sampling and step-level reward estimation with geometric consistency constraints. Extensive experiments demonstrate that SpatialDreamer delivers highly competitive results across multiple challenging benchmarks, signifying a critical advancement in human-like active spatial mental simulation for MLLMs. --- ### SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination Authors: Sangha Park, Seungryong Yoo, Jisoo Mok, Sungroh Yoon Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07730v2 Although Multimodal Large Language Models (MLLMs) have advanced substantially, they remain vulnerable to object hallucination caused by language priors and visual information loss. To address this, we propose SAVE (Sparse Autoencoder-Driven Visual Information Enhancement), a framework that mitigates hallucination by steering the model along Sparse Autoencoder (SAE) latent features. A binary object-presence question-answering probe identifies the SAE features most indicative of the model's visual information processing, referred to as visual understanding features. Steering the model along these identified features reinforces grounded visual understanding and effectively reduces hallucination. With its simple design, SAVE outperforms state-of-the-art training-free methods on standard benchmarks, achieving a 10\%p improvement in CHAIR\_S and consistent gains on POPE and MMHal-Bench. Extensive evaluations across multiple models and layers confirm the robustness and generalizability of our approach. Further analysis reveals that steering along visual understanding features suppresses the generation of uncertain object tokens and increases attention to image tokens, mitigating hallucination. Code is released at https://github.com/wiarae/SAVE. --- ### Improving action classification with brain-inspired deep networks Authors: Aidas Aglinskas, Stefano Anzellotti Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07729v1 Action recognition is also key for applications ranging from robotics to healthcare monitoring. Action information can be extracted from the body pose and movements, as well as from the background scene. However, the extent to which deep neural networks (DNNs) make use of information about the body and information about the background remains unclear. Since these two sources of information may be correlated within a training dataset, DNNs might learn to rely predominantly on one of them, without taking full advantage of the other. Unlike DNNs, humans have domain-specific brain regions selective for perceiving bodies, and regions selective for perceiving scenes. The present work tests whether humans are thus more effective at extracting information from both body and background, and whether building brain-inspired deep network architectures with separate domain-specific streams for body and scene perception endows them with more human-like performance. We first demonstrate that DNNs trained using the HAA500 dataset perform almost as accurately on versions of the stimuli that show both body and background and on versions of the stimuli from which the body was removed, but are at chance-level for versions of the stimuli from which the background was removed. Conversely, human participants (N=28) can recognize the same set of actions accurately with all three versions of the stimuli, and perform significantly better on stimuli that show only the body than on stimuli that show only the background. Finally, we implement and test a novel architecture patterned after domain specificity in the brain with separate streams to process body and background information. We show that 1) this architecture improves action recognition performance, and 2) its accuracy across different versions of the stimuli follows a pattern that matches more closely the pattern of accuracy observed in human participants. --- ### The Native Spiking Microarchitecture: From Iontronic Primitives to Bit-Exact FP8 Arithmetic Authors: Zhengzheng Tang Published: 2025-12-08 Categories: cs.ET, cs.AI arXiv: https://arxiv.org/abs/2512.07724v1 The 2025 Nobel Prize in Chemistry for Metal-Organic Frameworks (MOFs) and recent breakthroughs by Huanting Wang's team at Monash University establish angstrom-scale channels as promising post-silicon substrates with native integrate-and-fire (IF) dynamics. However, utilizing these stochastic, analog materials for deterministic, bit-exact AI workloads (e.g., FP8) remains a paradox. Existing neuromorphic methods often settle for approximation, failing Transformer precision standards. To traverse the gap "from stochastic ions to deterministic floats," we propose a Native Spiking Microarchitecture. Treating noisy neurons as logic primitives, we introduce a Spatial Combinational Pipeline and a Sticky-Extra Correction mechanism. Validation across all 16,129 FP8 pairs confirms 100% bit-exact alignment with PyTorch. Crucially, our architecture reduces Linear layer latency to O(log N), yielding a 17x speedup. Physical simulations further demonstrate robustness against extreme membrane leakage (beta approx 0.01), effectively immunizing the system against the stochastic nature of the hardware. --- ### Enabling Delayed-Full Charging Through Transformer-Based Real-Time-to-Departure Modeling for EV Battery Longevity Authors: Yonggeon Lee, Jibin Hwang, Alfred Malengo Kondoro, Juhyun Song, Youngtae Noh Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07723v2 Electric vehicles (EVs) are key to sustainable mobility, yet their lithium-ion batteries (LIBs) degrade more rapidly under prolonged high states of charge (SOC). This can be mitigated by delaying full charging \ours until just before departure, which requires accurate prediction of user departure times. In this work, we propose Transformer-based real-time-to-event (TTE) model for accurate EV departure prediction. Our approach represents each day as a TTE sequence by discretizing time into grid-based tokens. Unlike previous methods primarily dependent on temporal dependency from historical patterns, our method leverages streaming contextual information to predict departures. Evaluation on a real-world study involving 93 users and passive smartphone data demonstrates that our method effectively captures irregular departure patterns within individual routines, outperforming baseline models. These results highlight the potential for practical deployment of the \ours algorithm and its contribution to sustainable transportation systems. --- ### ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation Authors: Fan Yang, Heyuan Li, Peihao Li, Weihao Yuan, Lingteng Qiu, Chaoyue Song, Cheng Chen, Yisheng He, Shifeng Zhang, Xiaoguang Han, Steven Hoi, Guosheng Lin Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07720v2 Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction models, are fast and capable of producing stable body structures, but they often suffer from artifacts such as blurry textures and stiff, unnatural motion. In contrast, generative video models show promising performance by synthesizing photorealistic and dynamic results, but they frequently struggle with unstable behavior, including body structural errors and identity drift. To address these limitations, we propose a novel approach that combines the strengths of both paradigms. Our framework employs a 3D reconstruction model to provide robust structural and appearance priors, which in turn guides a real-time autoregressive video diffusion model for rendering. This process enables the model to synthesize high-frequency, photorealistic details and fluid dynamics in real time, effectively reducing texture blur and motion stiffness while preventing the structural inconsistencies common in video generation methods. By uniting the geometric stability of 3D reconstruction with the generative capabilities of video models, our method produces high-fidelity digital avatars with realistic appearance and dynamic, temporally coherent motion. Experiments demonstrate that our approach significantly reduces artifacts and achieves substantial improvements in visual quality over leading methods, providing a robust and efficient solution for real-time applications such as gaming and virtual reality. Project page: https://lhyfst.github.io/visa --- ### UnCageNet: Tracking and Pose Estimation of Caged Animal Authors: Sayak Dutta, Harish Katti, Shashikant Verma, Shanmuganathan Raman Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07712v2 Animal tracking and pose estimation systems, such as STEP (Simultaneous Tracking and Pose Estimation) and ViTPose, experience substantial performance drops when processing images and videos with cage structures and systematic occlusions. We present a three-stage preprocessing pipeline that addresses this limitation through: (1) cage segmentation using a Gabor-enhanced ResNet-UNet architecture with tunable orientation filters, (2) cage inpainting using CRFill for content-aware reconstruction of occluded regions, and (3) evaluation of pose estimation and tracking on the uncaged frames. Our Gabor-enhanced segmentation model leverages orientation-aware features with 72 directional kernels to accurately identify and segment cage structures that severely impair the performance of existing methods. Experimental validation demonstrates that removing cage occlusions through our pipeline enables pose estimation and tracking performance comparable to that in environments without occlusions. We also observe significant improvements in keypoint detection accuracy and trajectory consistency. --- ### Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE Authors: Anxiang Zeng, Haibo Zhang, Hailing Zhang, Kaixiang Mo, Liang Yao, Ling Hu, Long Zhang, Shuman Liu, Shuyi Xie, Yanshi Li, Yizhang Chen, Yuepeng Sheng et al. Published: 2025-12-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.07710v1 We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this size exposes critical inefficiencies-zero-variance prompts that waste rollouts, unstable importance sampling over long horizons, advantage inversion from standard reward models, and systemic bottlenecks in rollout processing. To overcome these challenges, we introduce several unified innovations: (1) Multi-Stage Zero-Variance Elimination, which filters out non-informative prompts and stabilizes group-based policy optimization (e.g. GRPO) by removing wasted rollouts; (2) ESPO, an entropy-adaptive optimization method that balances token-level and sequence-level importance sampling to maintain stable learning dynamics; (3) a Router Replay strategy that aligns training-time MoE router decisions with inference-time behavior to mitigate train-infer discrepancies, coupled with a reward model adjustment to prevent advantage inversion; (4) a high-throughput RL system with FP8-precision rollouts, overlapped reward computation, and length-aware scheduling to eliminate performance bottlenecks. Together, these contributions form a cohesive pipeline that makes RL on hundred-billion-scale MoE models stable and efficient. The resulting model delivers strong performance across both internal and public evaluations. --- ### In-Context and Few-Shots Learning for Forecasting Time Series Data based on Large Language Models Authors: Saroj Gopali, Bipin Chhetri, Deepika Giri, Sima Siami-Namini, Akbar Siami Namin Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07705v1 Existing data-driven approaches in modeling and predicting time series data include ARIMA (Autoregressive Integrated Moving Average), Transformer-based models, LSTM (Long Short-Term Memory) and TCN (Temporal Convolutional Network). These approaches, and in particular deep learning-based models such as LSTM and TCN, have shown great results in predicting time series data. With the advancement of leveraging pre-trained foundation models such as Large Language Models (LLMs) and more notably Google's recent foundation model for time series data, {\it TimesFM} (Time Series Foundation Model), it is of interest to investigate whether these foundation models have the capability of outperforming existing modeling approaches in analyzing and predicting time series data. This paper investigates the performance of using LLM models for time series data prediction. We investigate the in-context learning methodology in the training of LLM models that are specific to the underlying application domain. More specifically, the paper explores training LLMs through in-context, zero-shot and few-shot learning and forecasting time series data with OpenAI {\tt o4-mini} and Gemini 2.5 Flash Lite, as well as the recent Google's Transformer-based TimesFM, a time series-specific foundation model, along with two deep learning models, namely TCN and LSTM networks. The findings indicate that TimesFM has the best overall performance with the lowest RMSE value (0.3023) and the competitive inference time (266 seconds). Furthermore, OpenAI's o4-mini also exhibits a good performance based on Zero Shot learning. These findings highlight pre-trained time series foundation models as a promising direction for real-time forecasting, enabling accurate and scalable deployment with minimal model adaptation. --- ### PVeRA: Probabilistic Vector-Based Random Matrix Adaptation Authors: Leo Fillioux, Enzo Ferrante, Paul-Henry Cournède, Maria Vakalopoulou, Stergios Christodoulidis Published: 2025-12-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.07703v2 Large foundation models have emerged in the last years and are pushing performance boundaries for a variety of tasks. Training or even finetuning such models demands vast datasets and computational resources, which are often scarce and costly. Adaptation methods provide a computationally efficient solution to address these limitations by allowing such models to be finetuned on small amounts of data and computing power. This is achieved by appending new trainable modules to frozen backbones with only a fraction of the trainable parameters and fitting only these modules on novel tasks. Recently, the VeRA adapter was shown to excel in parameter-efficient adaptations by utilizing a pair of frozen random low-rank matrices shared across all layers. In this paper, we propose PVeRA, a probabilistic version of the VeRA adapter, which modifies the low-rank matrices of VeRA in a probabilistic manner. This modification naturally allows handling inherent ambiguities in the input and allows for different sampling configurations during training and testing. A comprehensive evaluation was performed on the VTAB-1k benchmark and seven adapters, with PVeRA outperforming VeRA and other adapters. Our code for training models with PVeRA and benchmarking all adapters is available https://github.com/leofillioux/pvera. --- ### Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment Authors: Sangha Park, Eunji Kim, Yeongtak Oh, Jooyoung Choi, Sungroh Yoon Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07702v2 Despite substantial progress in text-to-image generation, achieving precise text-image alignment remains challenging, particularly for prompts with rich compositional structure or imaginative elements. To address this, we introduce Negative Prompting for Image Correction (NPC), an automated pipeline that improves alignment by identifying and applying negative prompts that suppress unintended content. We begin by analyzing cross-attention patterns to explain why both targeted negatives-those directly tied to the prompt's alignment error-and untargeted negatives-tokens unrelated to the prompt but present in the generated image-can enhance alignment. To discover useful negatives, NPC generates candidate prompts using a verifier-captioner-proposer framework and ranks them with a salient text-space score, enabling effective selection without requiring additional image synthesis. On GenEval++ and Imagine-Bench, NPC outperforms strong baselines, achieving 0.571 vs. 0.371 on GenEval++ and the best overall performance on Imagine-Bench. By guiding what not to generate, NPC provides a principled, fully automated route to stronger text-image alignment in diffusion models. Code is released at https://github.com/wiarae/NPC. --- ### sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only Authors: Arslan Artykov, Tom Ravaud, Corentin Sautier, Vincent Lepetit Published: 2025-12-08 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.07698v3 Understanding articulated objects from monocular video is a crucial yet challenging task in robotics and digital twin creation. Existing methods often rely on complex multi-view setups, high-fidelity object scans, or fragile long-term point tracks that frequently fail in casual real-world captures. In this paper, we present sim2art, a data-driven framework that recovers the 3D part segmentation and joint parameters of articulated objects from a single monocular video captured by a freely moving camera. Our core insight is a robust representation based on per-frame surface point sampling, which we augment with short-term scene flow and DINOv3 semantic features. Unlike previous works that depend on error-prone long-term correspondences, our representation is easy to obtain and exhibits a negligible difference between simulation and reality without requiring domain adaptation. Also, by construction, our method relies on single-viewpoint visibility, ensuring that the geometric representation remains consistent across synthetic and real data despite noise and occlusions. Leveraging a suitable Transformer-based architecture, sim2art is trained exclusively on synthetic data yet generalizes strongly to real-world sequences. To address the lack of standardized benchmarks in the field, we introduce two datasets featuring a significantly higher diversity of object categories and instances than prior work. Our evaluations show that sim2art effectively handles large camera motions and complex articulations, outperforming state-of-the-art optimization-based and tracking-dependent methods. sim2art offers a scalable solution that can be easily extended to new object categories without the need for cumbersome real-world annotations. Project webpage: https://aartykov.github.io/sim2art/ --- ### Delay-Aware Diffusion Policy: Bridging the Observation-Execution Gap in Dynamic Tasks Authors: Aileen Liao, Dong-Ki Kim, Max Olan Smith, Ali-akbar Agha-mohammadi, Shayegan Omidshafiei Published: 2025-12-08 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.07697v2 As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization from zero delay to measured delay during training and inference. We introduce Delay-Aware Diffusion Policy (DA-DP), a framework for explicitly incorporating inference delays into policy learning. DA-DP corrects zero-delay trajectories to their delay-compensated counterparts, and augments the policy with delay conditioning. We empirically validate DA-DP on a variety of tasks, robots, and delays and find its success rate more robust to delay than delay-unaware methods. DA-DP is architecture agnostic and transfers beyond diffusion policies, offering a general pattern for delay-aware imitation learning. More broadly, DA-DP encourages evaluation protocols that report performance as a function of measured latency, not just task difficulty. --- ### Automated Generation of Custom MedDRA Queries Using SafeTerm Medical Map Authors: Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla, Elena Hadjicosta Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07694v1 In pre-market drug safety review, grouping related adverse event terms into standardised MedDRA queries or the FDA Office of New Drugs Custom Medical Queries (OCMQs) is critical for signal detection. We present a novel quantitative artificial intelligence system that understands and processes medical terminology and automatically retrieves relevant MedDRA Preferred Terms (PTs) for a given input query, ranking them by a relevance score using multi-criteria statistical methods. The system (SafeTerm) embeds medical query terms and MedDRA PTs in a multidimensional vector space, then applies cosine similarity and extreme-value clustering to generate a ranked list of PTs. Validation was conducted against the FDA OCMQ v3.0 (104 queries), restricted to valid MedDRA PTs. Precision, recall and F1 were computed across similarity-thresholds. High recall (>95%) is achieved at moderate thresholds. Higher thresholds improve precision (up to 86%). The optimal threshold (~0.70 - 0.75) yielded recall ~50% and precision ~33%. Narrow-term PT subsets performed similarly but required slightly higher similarity thresholds. The SafeTerm AI-driven system provides a viable supplementary method for automated MedDRA query generation. A similarity threshold of ~0.60 is recommended initially, with increased thresholds for refined term selection. --- ### HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs Authors: Sujoy Nath, Arkaprabha Basu, Sharanya Dasgupta, Swagatam Das Published: 2025-12-08 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.07687v1 Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding tasks. While these models often produce linguistically coherent output, they often suffer from hallucinations, generating descriptions that are factually inconsistent with the visual content, potentially leading to adverse consequences. Therefore, the assessment of hallucinations in MLLM has become increasingly crucial in the model development process. Contemporary methodologies predominantly depend on external LLM evaluators, which are themselves susceptible to hallucinations and may present challenges in terms of domain adaptation. In this study, we propose the hypothesis that hallucination manifests as measurable irregularities within the internal layer dynamics of MLLMs, not merely due to distributional shifts but also in the context of layer-wise analysis of specific assumptions. By incorporating such modifications, \textsc{\textsc{HalluShift++}} broadens the efficacy of hallucination detection from text-based large language models (LLMs) to encompass multimodal scenarios. Our codebase is available at https://github.com/C0mRD/HalluShift_Plus. --- ### When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks Authors: Zihan Chen, Lanyu Yu Published: 2025-12-08 Categories: cs.CL, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2512.07684v2 Online incivility has emerged as a widespread and persistent problem in digital communities, imposing substantial social and psychological burdens on users. Although many platforms attempt to curb incivility through moderation and automated detection, the performance of existing approaches often remains limited in both accuracy and efficiency. To address this challenge, we propose a Graph Neural Network (GNN) framework for detecting three types of uncivil behavior (i.e., toxicity, aggression, and personal attacks) within the English Wikipedia community. Our model represents each user comment as a node, with textual similarity between comments defining the edges, allowing the network to jointly learn from both linguistic content and relational structures among comments. We also introduce a dynamically adjusted attention mechanism that adaptively balances nodal and topological features during information aggregation. Empirical evaluations demonstrate that our proposed architecture outperforms 12 state-of-the-art Large Language Models (LLMs) across multiple metrics while requiring significantly lower inference cost. These findings highlight the crucial role of structural context in detecting online incivility and address the limitations of text-only LLM paradigms in behavioral prediction. All datasets and comparative outputs will be publicly available in our repository to support further research and reproducibility. --- ### A Bootstrap Perspective on Stochastic Gradient Descent Authors: Hongjian Lan, Yucong Liu, Florian Schäfer Published: 2025-12-08 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.07676v1 Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the statistical bootstrap: SGD uses gradient variability under batch sampling as a proxy for solution variability under the randomness of the data collection process. We use empirical results and theoretical analysis to substantiate this claim. In idealized experiments on empirical risk minimization, we show that SGD is drawn to parameter choices that are robust under resampling and thus avoids spurious solutions even if they lie in wider and deeper minima of the training loss. We prove rigorously that by implicitly regularizing the trace of the gradient covariance matrix, SGD controls the algorithmic variability. This regularization leads to solutions that are less sensitive to sampling noise, thereby improving generalization. Numerical experiments on neural network training show that explicitly incorporating the estimate of the algorithmic variability as a regularizer improves test performance. This fact supports our claim that bootstrap estimation underpins SGD's generalization advantages. --- ### DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations Authors: Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez, Paul Wright, Mehmet Yigitsoy, Sebastien Ourselin, Jorge Cardoso Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07674v1 Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This is particularly true in Magnetic Resonance Imaging, where scanner hardware differences, diverse acquisition protocols, and varying sequence parameters introduce substantial domain shifts that obscure underlying biological signals. Data harmonization methods aim to reduce these instrumental and acquisition variability, but existing approaches remain insufficient. When applied to imaging data, image-based harmonization approaches are often restricted by the need for target images, while existing text-guided methods rely on simplistic labels that fail to capture complex acquisition details or are typically restricted to datasets with limited variability, failing to capture the heterogeneity of real-world clinical environments. To address these limitations, we propose DIST-CLIP (Disentangled Style Transfer with CLIP Guidance), a unified framework for MRI harmonization that flexibly uses either target images or DICOM metadata for guidance. Our framework explicitly disentangles anatomical content from image contrast, with the contrast representations being extracted using pre-trained CLIP encoders. These contrast embeddings are then integrated into the anatomical content via a novel Adaptive Style Transfer module. We trained and evaluated DIST-CLIP on diverse real-world clinical datasets, and showed significant improvements in performance when compared against state-of-the-art methods in both style translation fidelity and anatomical preservation, offering a flexible solution for style transfer and standardizing MRI data. Our code and weights will be made publicly available upon publication. --- ### EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset Authors: Ronan John, Aditya Kesari, Vincenzo DiMatteo, Kristin Dana Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07668v2 We address the challenge of predicting human visual attention during real-world navigation by measuring and modeling egocentric pedestrian eye gaze in an outdoor campus setting. We introduce the EgoCampus dataset, which spans 25 unique outdoor paths over 6 km across a university campus with recordings from more than 80 distinct human pedestrians, resulting in a diverse set of gaze-annotated videos. The system used for collection, Meta's Project Aria glasses, integrates eye tracking, front-facing RGB cameras, inertial sensors, and GPS to provide rich data from the human perspective. Unlike many prior egocentric datasets that focus on indoor tasks or exclude eye gaze information, our work emphasizes visual attention while subjects walk in outdoor campus paths. Using this data, we develop EgoCampusNet, a novel method to predict eye gaze of navigating pedestrians as they move through outdoor environments. Our contributions provide both a new resource for studying real-world attention and a resource for future work in gaze prediction models for navigation. Dataset and code will be made publicly available at a later date at https://github.com/ComputerVisionRutgers/EgoCampus . --- ### Depth-Wise Activation Steering for Honest Language Models Authors: Gracjan Góral, Marysia Winkels, Steven Basart Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07667v1 Large language models sometimes assert falsehoods despite internally representing the correct answer, failures of honesty rather than accuracy, which undermines auditability and safety. Existing approaches largely optimize factual correctness or depend on retraining and brittle single-layer edits, offering limited leverage over truthful reporting. We present a training-free activation steering method that weights steering strength across network depth using a Gaussian schedule. On the MASK benchmark, which separates honesty from knowledge, we evaluate seven models spanning the LLaMA, Qwen, and Mistral families and find that Gaussian scheduling improves honesty over no-steering and single-layer baselines in six of seven models. Equal-budget ablations on LLaMA-3.1-8B-Instruct and Qwen-2.5-7B-Instruct show the Gaussian schedule outperforms random, uniform, and box-filter depth allocations, indicating that how intervention is distributed across depth materially affects outcomes beyond total strength. The method is simple, model-agnostic, requires no finetuning, and provides a low-cost control knob for eliciting truthful reporting from models' existing capabilities. --- ### Bridging Code Graphs and Large Language Models for Better Code Understanding Authors: Zeqi Chen, Zhaoyang Chu, Yi Gui, Feng Guo, Yao Wan, Chuan Shi Published: 2025-12-08 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2512.07666v1 Large Language Models (LLMs) have demonstrated remarkable performance in code intelligence tasks such as code generation, summarization, and translation. However, their reliance on linearized token sequences limits their ability to understand the structural semantics of programs. While prior studies have explored graphaugmented prompting and structure-aware pretraining, they either suffer from prompt length constraints or require task-specific architectural changes that are incompatible with large-scale instructionfollowing LLMs. To address these limitations, this paper proposes CGBridge, a novel plug-and-play method that enhances LLMs with Code Graph information through an external, trainable Bridge module. CGBridge first pre-trains a code graph encoder via selfsupervised learning on a large-scale dataset of 270K code graphs to learn structural code semantics. It then trains an external module to bridge the modality gap among code, graph, and text by aligning their semantics through cross-modal attention mechanisms. Finally, the bridge module generates structure-informed prompts, which are injected into a frozen LLM, and is fine-tuned for downstream code intelligence tasks. Experiments show that CGBridge achieves notable improvements over both the original model and the graphaugmented prompting method. Specifically, it yields a 16.19% and 9.12% relative gain in LLM-as-a-Judge on code summarization, and a 9.84% and 38.87% relative gain in Execution Accuracy on code translation. Moreover, CGBridge achieves over 4x faster inference than LoRA-tuned models, demonstrating both effectiveness and efficiency in structure-aware code understanding. --- ### Optimization-Guided Diffusion for Interactive Scene Generation Authors: Shihao Li, Naisheng Ye, Tianyu Li, Kashyap Chitta, Tuo An, Peng Su, Boyang Wang, Haiou Liu, Chen Lv, Hongyang Li Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07661v4 Realistic and diverse multi-agent driving scenes are crucial for evaluating autonomous vehicles, but safety-critical events which are essential for this task are rare and underrepresented in driving datasets. Data-driven scene generation offers a low-cost alternative by synthesizing complex traffic behaviors from existing driving logs. However, existing models often lack controllability or yield samples that violate physical or social constraints, limiting their usability. We present OMEGA, an optimization-guided, training-free framework that enforces structural consistency and interaction awareness during diffusion-based sampling from a scene generation model. OMEGA re-anchors each reverse diffusion step via constrained optimization, steering the generation towards physically plausible and behaviorally coherent trajectories. Building on this framework, we formulate ego-attacker interactions as a game-theoretic optimization in the distribution space, approximating Nash equilibria to generate realistic, safety-critical adversarial scenarios. Experiments on nuPlan and Waymo show that OMEGA improves generation realism, consistency, and controllability, increasing the ratio of physically and behaviorally valid scenes from 32.35% to 72.27% for free exploration capabilities, and from 11% to 80% for controllability-focused generation. Our approach can also generate $5\times$ more near-collision frames with a time-to-collision under three seconds while maintaining the overall scene realism. --- ### An AI-Powered Autonomous Underwater System for Sea Exploration and Scientific Research Authors: Hamad Almazrouei, Mariam Al Nasseri, Maha Alzaabi Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07652v1 Traditional sea exploration faces significant challenges due to extreme conditions, limited visibility, and high costs, resulting in vast unexplored ocean regions. This paper presents an innovative AI-powered Autonomous Underwater Vehicle (AUV) system designed to overcome these limitations by automating underwater object detection, analysis, and reporting. The system integrates YOLOv12 Nano for real-time object detection, a Convolutional Neural Network (CNN) (ResNet50) for feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and K-Means++ clustering for grouping marine objects based on visual characteristics. Furthermore, a Large Language Model (LLM) (GPT-4o Mini) is employed to generate structured reports and summaries of underwater findings, enhancing data interpretation. The system was trained and evaluated on a combined dataset of over 55,000 images from the DeepFish and OzFish datasets, capturing diverse Australian marine environments. Experimental results demonstrate the system's capability to detect marine objects with a mAP@0.5 of 0.512, a precision of 0.535, and a recall of 0.438. The integration of PCA effectively reduced feature dimensionality while preserving 98% variance, facilitating K-Means clustering which successfully grouped detected objects based on visual similarities. The LLM integration proved effective in generating insightful summaries of detections and clusters, supported by location data. This integrated approach significantly reduces the risks associated with human diving, increases mission efficiency, and enhances the speed and depth of underwater data analysis, paving the way for more effective scientific research and discovery in challenging marine environments. --- ### Liver Fibrosis Quantification and Analysis: The LiQA Dataset and Baseline Method Authors: Yuanye Liu, Hanxiao Zhang, Jiyao Liu, Nannan Shi, Yuxin Shi, Arif Mahmood, Murtaza Taj, Xiahai Zhuang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07651v2 Liver fibrosis represents a significant global health burden, necessitating accurate staging for effective clinical management. This report introduces the LiQA (Liver Fibrosis Quantification and Analysis) dataset, established as part of the CARE 2024 challenge. Comprising $440$ patients with multi-phase, multi-center MRI scans, the dataset is curated to benchmark algorithms for Liver Segmentation (LiSeg) and Liver Fibrosis Staging (LiFS) under complex real-world conditions, including domain shifts, missing modalities, and spatial misalignment. We further describe the challenge's top-performing methodology, which integrates a semi-supervised learning framework with external data for robust segmentation, and utilizes a multi-view consensus approach with Class Activation Map (CAM)-based regularization for staging. Evaluation of this baseline demonstrates that leveraging multi-source data and anatomical constraints significantly enhances model robustness in clinical settings. --- ### Exploring Test-time Scaling via Prediction Merging on Large-Scale Recommendation Authors: Fuyuan Lyu, Zhentai Chen, Jingyan Jiang, Lingjie Li, Xing Tang, Xiuqiang He, Xue Liu Published: 2025-12-08 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2512.07650v1 Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However, how to efficiently utilize and scale up computational resources during test time remains underexplored, which can prove to be a scaling-efficient approach and bring orthogonal improvements in LM domains. The key point in applying test-time scaling to DLRS lies in effectively generating diverse yet meaningful outputs for the same instance. We propose two ways: One is to explore the heterogeneity of different model architectures. The other is to utilize the randomness of model initialization under a homogeneous architecture. The evaluation is conducted across eight models, including both classic and SOTA models, on three benchmarks. Sufficient evidence proves the effectiveness of both solutions. We further prove that under the same inference budget, test-time scaling can outperform parameter scaling. Our test-time scaling can also be seamlessly accelerated with the increase in parallel servers when deployed online, without affecting the inference time on the user side. Code is available. --- ### A Mathematical Theory of Top-$k$ Sparse Attention via Total Variation Distance Authors: Georgios Tzachristas, Lei Deng, Ioannis Tzachristas, Gong Zhang, Renhai Chen Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07647v1 We develop a unified mathematical framework for certified Top-$k$ attention truncation that quantifies approximation error at both the distribution and output levels. For a single attention distribution $P$ and its Top-$k$ truncation $\hat P$, we show that the total-variation distance coincides with the discarded softmax tail mass and satisfies $\mathrm{TV}(P,\hat P)=1-e^{-\mathrm{KL}(\hat P\Vert P)}$, yielding sharp Top-$k$-specific bounds in place of generic inequalities. From this we derive non-asymptotic deterministic bounds -- from a single boundary gap through multi-gap and blockwise variants -- that control $\mathrm{TV}(P,\hat P)$ using only the ordered logits. Using an exact head-tail decomposition, we prove that the output error factorizes as $\|\mathrm{Attn}(q,K,V)-\mathrm{Attn}_k(q,K,V)\|_2=τ\|μ_{\mathrm{tail}}-μ_{\mathrm{head}}\|_2$ with $τ=\mathrm{TV}(P,\hat P)$, yielding a new head-tail diameter bound $\|\mathrm{Attn}(q,K,V)-\mathrm{Attn}_k(q,K,V)\|_2\leτ\,\mathrm{diam}_{H,T}$ and refinements linking the error to $\mathrm{Var}_P(V)$. Under an i.i.d. Gaussian score model $s_i\sim\mathcal N(μ,σ^2)$ we derive closed-form tail masses and an asymptotic rule for the minimal $k_\varepsilon$ ensuring $\mathrm{TV}(P,\hat P)\le\varepsilon$, namely $k_\varepsilon/n\approxΦ_c(σ+Φ^{-1}(\varepsilon))$. Experiments on bert-base-uncased and synthetic logits confirm the predicted scaling of $k_\varepsilon/n$ and show that certified Top-$k$ can reduce scored keys by 2-4$\times$ on average while meeting the prescribed total-variation budget. --- ### The Agent Capability Problem: Predicting Solvability Through Information-Theoretic Bounds Authors: Shahar Lutati Published: 2025-12-08 Categories: cs.AI, cs.CC, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2512.07631v1 When should an autonomous agent commit resources to a task? We introduce the Agent Capability Problem (ACP), a framework for predicting whether an agent can solve a problem under resource constraints. Rather than relying on empirical heuristics, ACP frames problem-solving as information acquisition: an agent requires $\Itotal$ bits to identify a solution and gains $\Istep$ bits per action at cost $\Cstep$, yielding an effective cost $\Ceff = (\Itotal/\Istep), \Cstep$ that predicts resource requirements before search. We prove that $\Ceff$ lower-bounds expected cost and provide tight probabilistic upper bounds. Experimental validation shows that ACP predictions closely track actual agent performance, consistently bounding search effort while improving efficiency over greedy and random strategies. The framework generalizes across LLM-based and agentic workflows, linking principles from active learning, Bayesian optimization, and reinforcement learning through a unified information-theoretic lens. \ --- ### MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation Authors: Zhiqi Li, Wenhuan Li, Tengfei Wang, Zhenwei Wang, Junta Wu, Haoyuan Wang, Yunhan Yang, Zehuan Huang, Yang Li, Peidong Liu, Chunchao Guo Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07628v1 Compositionality is critical for 3D object and scene generation, but existing part-aware 3D generation methods suffer from poor scalability due to quadratic global attention costs when increasing the number of components. In this work, we present MoCA, a compositional 3D generative model with two key designs: (1) importance-based component routing that selects top-k relevant components for sparse global attention, and (2) unimportant components compression that preserve contextual priors of unselected components while reducing computational complexity of global attention. With these designs, MoCA enables efficient, fine-grained compositional 3D asset creation with scalable number of components. Extensive experiments show MoCA outperforms baselines on both compositional object and scene generation tasks. Project page: https://lizhiqi49.github.io/MoCA --- ### Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization Authors: Maximos Kaliakatsos-Papakostas, Konstantinos Soiledis, Theodoros Tsamis, Dimos Makris, Vassilis Katsouros, Emilios Cambouropoulos Published: 2025-12-08 Categories: cs.SD, cs.AI, cs.SC arXiv: https://arxiv.org/abs/2512.07627v1 Transformer architectures offer significant advantages regarding the generation of symbolic music; their capabilities for incorporating user preferences toward what they generate is being studied under many aspects. This paper studies the inclusion of predefined chord constraints in melodic harmonization, i.e., where a desired chord at a specific location is provided along with the melody as inputs and the autoregressive transformer model needs to incorporate the chord in the harmonization that it generates. The peculiarities of involving such constraints is discussed and an algorithm is proposed for tackling this task. This algorithm is called B* and it combines aspects of beam search and A* along with backtracking to force pretrained transformers to satisfy the chord constraints, at the correct onset position within the correct bar. The algorithm is brute-force and has exponential complexity in the worst case; however, this paper is a first attempt to highlight the difficulties of the problem and proposes an algorithm that offers many possibilities for improvements since it accommodates the involvement of heuristics. --- ### Time Series Foundation Models for Process Model Forecasting Authors: Yongbo Yu, Jari Peeperkorn, Johannes De Smedt, Jochen De Weerdt Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07624v3 Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of directly-follows (DF) relations, complementing predictive process monitoring that focuses on single-case prefixes. Prior benchmarks show that machine learning and deep learning models provide only modest gains over statistical baselines, mainly due to the sparsity and heterogeneity of the DF time series. We investigate Time Series Foundation Models (TSFMs), large pre-trained models for generic time series, as an alternative for PMF. Using DF time series derived from real-life event logs, we compare zero-shot use of TSFMs, without additional training, with fine-tuned variants adapted on PMF-specific data. TSFMs generally achieve lower forecasting errors (MAE and RMSE) than traditional and specialized models trained from scratch on the same logs, indicating effective transfer of temporal structure from non-process domains. While fine-tuning can further improve accuracy, the gains are often small and may disappear on smaller or more complex datasets, so zero-shot use remains a strong default. Our study highlights the generalization capability and data efficiency of TSFMs for process-related time series and, to the best of our knowledge, provides the first systematic evaluation of temporal foundation models for PMF. --- ### PCMind-2.1-Kaiyuan-2B Technical Report Authors: Kairong Luo, Zhenbo Sun, Xinyu Shi, Shengqi Chen, Bowen Yu, Yunyi Chen, Chenyi Dang, Hengtao Tao, Hui Wang, Fangming Liu, Kaifeng Lyu, Wenguang Chen Published: 2025-12-08 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.07612v1 The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relies on closed-source, high-quality data and training recipes. To address this, we introduce PCMind-2.1-Kaiyuan-2B, a fully open-source 2-billion-parameter model focused on improving training efficiency and effectiveness under resource constraints. Our methodology includes three key innovations: a Quantile Data Benchmarking method for systematically comparing heterogeneous open-source datasets and providing insights on data mixing strategies; a Strategic Selective Repetition scheme within a multi-phase paradigm to effectively leverage sparse, high-quality data; and a Multi-Domain Curriculum Training policy that orders samples by quality. Supported by a highly optimized data preprocessing pipeline and architectural modifications for FP16 stability, Kaiyuan-2B achieves performance competitive with state-of-the-art fully open-source models, demonstrating practical and scalable solutions for resource-limited pretraining. We release all assets (including model weights, data, and code) under Apache 2.0 license at https://huggingface.co/thu-pacman/PCMind-2.1-Kaiyuan-2B. --- ### Comparative Analysis and Parametric Tuning of PPO, GRPO, and DAPO for LLM Reasoning Enhancement Authors: Yongsheng Lian Published: 2025-12-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.07611v1 This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning evaluation: models are first fine-tuned on the specialized Countdown Game and then assessed on a suite of general-purpose reasoning benchmarks. Across all tasks, RL-trained models outperform their corresponding base models, although the degree of improvement differs by benchmark. Our parametric analysis offers practical guidance for RL-based LLM training. Increasing the group size in GRPO and DAPO leads to more stable training dynamics and higher accuracy, while the impact of the KL-penalty coefficient is non-monotonic. Additionally, we find that the Dynamic Sampling (DS) component in DAPO does not improve performance; in fact, the best overall results are achieved with DAPO when DS is disabled. --- ### Metric-Fair Prompting: Treating Similar Samples Similarly Authors: Jing Wang, Jie Shen, Xing Niu, Tong Zhang, Jeremy Weiss Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07608v1 We introduce \emph{Metric-Fair Prompting}, a fairness-aware prompting framework that guides large language models (LLMs) to make decisions under metric-fairness constraints. In the application of multiple-choice medical question answering, each {(question, option)} pair is treated as a binary instance with label $+1$ (correct) or $-1$ (incorrect). To promote {individual fairness}~--~treating similar instances similarly~--~we compute question similarity using NLP embeddings and solve items in \emph{joint pairs of similar questions} rather than in isolation. The prompt enforces a global decision protocol: extract decisive clinical features, map each \((\text{question}, \text{option})\) to a score $f(x)$ that acts as confidence, and impose a Lipschitz-style constraint so that similar inputs receive similar scores and, hence, consistent outputs. Evaluated on the {MedQA (US)} benchmark, Metric-Fair Prompting is shown to improve performance over standard single-item prompting, demonstrating that fairness-guided, confidence-oriented reasoning can enhance LLM accuracy on high-stakes clinical multiple-choice questions. --- ### Decomposition Sampling for Efficient Region Annotations in Active Learning Authors: Jingna Qiu, Frauke Wilm, Mathias Öttl, Jonas Utz, Maja Schlereth, Moritz Schillinger, Marc Aubreville, Katharina Breininger Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07606v1 Active learning improves annotation efficiency by selecting the most informative samples for annotation and model training. While most prior work has focused on selecting informative images for classification tasks, we investigate the more challenging setting of dense prediction, where annotations are more costly and time-intensive, especially in medical imaging. Region-level annotation has been shown to be more efficient than image-level annotation for these tasks. However, existing methods for representative annotation region selection suffer from high computational and memory costs, irrelevant region choices, and heavy reliance on uncertainty sampling. We propose decomposition sampling (DECOMP), a new active learning sampling strategy that addresses these limitations. It enhances annotation diversity by decomposing images into class-specific components using pseudo-labels and sampling regions from each class. Class-wise predictive confidence further guides the sampling process, ensuring that difficult classes receive additional annotations. Across ROI classification, 2-D segmentation, and 3-D segmentation, DECOMP consistently surpasses baseline methods by better sampling minority-class regions and boosting performance on these challenging classes. Code is in https://github.com/JingnaQiu/DECOMP.git. --- ### Algorithm-hardware co-design of neuromorphic networks with dual memory pathways Authors: Pengfei Sun, Zhe Su, Jascha Achterberg, Giacomo Indiveri, Dan F. M. Goodman, Danyal Akarca Published: 2025-12-08 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.07602v3 Spiking neural networks excel at event-driven sensing. Yet, maintaining task-relevant context over long timescales both algorithmically and in hardware, while respecting both tight energy and memory budgets, remains a core challenge in the field. We address this challenge through an algorithm-hardware co-design effort. At the algorithm level, inspired by the cortical fast-slow organization in the brain, we introduce a neural network with an explicit slow memory pathway that, combined with fast spiking activity, enables a dual memory pathway (DMP) architecture in which each layer maintains a compact low-dimensional state that summarizes recent activity and modulates spiking dynamics. This explicit memory stabilizes learning while preserving event-driven sparsity, achieving competitive accuracy on long-sequence benchmarks with 40-60% fewer parameters than equivalent state-of-the-art spiking neural networks. At the hardware level, we introduce a near-memory-compute architecture that fully leverages the advantages of the DMP architecture by retaining its compact shared state while optimizing dataflow, across heterogeneous sparse-spike and dense-memory pathways. We show experimental results that demonstrate more than a 4X increase in throughput and over a 5X improvement in energy efficiency compared with state-of-the-art implementations. Together, these contributions demonstrate that biological principles can guide functional abstractions that are both algorithmically effective and hardware-efficient, establishing a scalable co-design framework for real-time neuromorphic computation and learning. --- ### Online Segment Any 3D Thing as Instance Tracking Authors: Hanshi Wang, Zijian Cai, Jin Gao, Yiwei Zhang, Weiming Hu, Ke Wang, Zhipeng Zhang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07599v1 Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to aggregate semantic information from Vision Foundation Models (VFMs) outputs that are lifted into 3D point clouds, facilitating spatial information propagation through inter-query interactions. Nevertheless, perception is an inherently dynamic process, rendering temporal understanding a critical yet overlooked dimension within these prevailing query-based pipelines. Therefore, to further unlock the temporal environmental perception capabilities of embodied agents, our work reconceptualizes online 3D segmentation as an instance tracking problem (AutoSeg3D). Our core strategy involves utilizing object queries for temporal information propagation, where long-term instance association promotes the coherence of features and object identities, while short-term instance update enriches instant observations. Given that viewpoint variations in embodied robotics often lead to partial object visibility across frames, this mechanism aids the model in developing a holistic object understanding beyond incomplete instantaneous views. Furthermore, we introduce spatial consistency learning to mitigate the fragmentation problem inherent in VFMs, yielding more comprehensive instance information for enhancing the efficacy of both long-term and short-term temporal learning. The temporal information exchange and consistency learning facilitated by these sparse object queries not only enhance spatial comprehension but also circumvent the computational burden associated with dense temporal point cloud interactions. Our method establishes a new state-of-the-art, surpassing ESAM by 2.8 AP on ScanNet200 and delivering consistent gains on ScanNet, SceneNN, and 3RScan datasets. --- ### More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery Authors: Wenzhen Dong, Jieming Yu, Yiming Huang, Hongqiu Wang, Lei Zhu, Albert C. S. Chung, Hongliang Ren, Long Bai Published: 2025-12-08 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.07596v2 The recent SAM 3 and SAM 3D have introduced significant advancements over the predecessor, SAM 2, particularly with the integration of language-based segmentation and enhanced 3D perception capabilities. SAM 3 supports zero-shot segmentation across a wide range of prompts, including point, bounding box, and language-based prompts, allowing for more flexible and intuitive interactions with the model. In this empirical evaluation, we assess the performance of SAM 3 in robot-assisted surgery, benchmarking its zero-shot segmentation with point and bounding box prompts and exploring its effectiveness in dynamic video tracking, alongside its newly introduced language prompt segmentation. While language prompts show potential, their performance in the surgical domain is currently suboptimal, highlighting the need for further domain-specific training. Additionally, we investigate SAM 3D's depth reconstruction abilities, demonstrating its capacity to process surgical scene data and reconstruct 3D anatomical structures from 2D images. Through comprehensive testing on the MICCAI EndoVis 2017 and EndoVis 2018 benchmarks, SAM 3 shows clear improvements over SAM and SAM 2 in both image and video segmentation under spatial prompts, while the zero-shot evaluations of SAM 3D on SCARED, StereoMIS, and EndoNeRF indicate strong monocular depth estimation and realistic 3D instrument reconstruction, yet also reveal remaining limitations in complex, highly dynamic surgical scenes. --- ### Robust Variational Model Based Tailored UNet: Leveraging Edge Detector and Mean Curvature for Improved Image Segmentation Authors: Kaili Qi, Zhongyi Huang, Wenli Yang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07590v1 To address the challenge of segmenting noisy images with blurred or fragmented boundaries, this paper presents a robust version of Variational Model Based Tailored UNet (VM_TUNet), a hybrid framework that integrates variational methods with deep learning. The proposed approach incorporates physical priors, an edge detector and a mean curvature term, into a modified Cahn-Hilliard equation, aiming to combine the interpretability and boundary-smoothing advantages of variational partial differential equations (PDEs) with the strong representational ability of deep neural networks. The architecture consists of two collaborative modules: an F module, which conducts efficient frequency domain preprocessing to alleviate poor local minima, and a T module, which ensures accurate and stable local computations, backed by a stability estimate. Extensive experiments on three benchmark datasets indicate that the proposed method achieves a balanced trade-off between performance and computational efficiency, which yields competitive quantitative results and improved visual quality compared to pure convolutional neural network (CNN) based models, while achieving performance close to that of transformer-based method with reasonable computational expense. ---