# Research Papers — 2026-01 · bundle page 184 of 189 > Full-text markdown of papers #9151–9200 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/184 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/183.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/185.md) ### Multi-Level Feature Fusion for Continual Learning in Visual Quality Inspection Authors: Johannes C. Bauer, Paul Geng, Stephan Trattnig, Petr Dokládal, Rüdiger Daub Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00725v1 Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in more volatile scenarios, such as remanufacturing, where the inspected products and defect patterns often change. In such settings, deployed models require frequent adaptation to novel conditions, effectively posing a continual learning problem. To enable quick adaptation, the necessary training processes must be computationally efficient while still avoiding effects like catastrophic forgetting. This work presents a multi-level feature fusion (MLFF) approach that aims to improve both aspects simultaneously by utilizing representations from different depths of a pretrained network. We show that our approach is able to match the performance of end-to-end training for different quality inspection problems while using significantly less trainable parameters. Furthermore, it reduces catastrophic forgetting and improves generalization robustness to new product types or defects. --- ### Detecting Performance Degradation under Data Shift in Pathology Vision-Language Model Authors: Hao Guan, Li Zhou Published: 2026-01-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.00716v1 Vision-Language Models have demonstrated strong potential in medical image analysis and disease diagnosis. However, after deployment, their performance may deteriorate when the input data distribution shifts from that observed during development. Detecting such performance degradation is essential for clinical reliability, yet remains challenging for large pre-trained VLMs operating without labeled data. In this study, we investigate performance degradation detection under data shift in a state-of-the-art pathology VLM. We examine both input-level data shift and output-level prediction behavior to understand their respective roles in monitoring model reliability. To facilitate systematic analysis of input data shift, we develop DomainSAT, a lightweight toolbox with a graphical interface that integrates representative shift detection algorithms and enables intuitive exploration of data shift. Our analysis shows that while input data shift detection is effective at identifying distributional changes and providing early diagnostic signals, it does not always correspond to actual performance degradation. Motivated by this observation, we further study output-based monitoring and introduce a label-free, confidence-based degradation indicator that directly captures changes in model prediction confidence. We find that this indicator exhibits a close relationship with performance degradation and serves as an effective complement to input shift detection. Experiments on a large-scale pathology dataset for tumor classification demonstrate that combining input data shift detection and output confidence-based indicators enables more reliable detection and interpretation of performance degradation in VLMs under data shift. These findings provide a practical and complementary framework for monitoring the reliability of foundation models in digital pathology. --- ### Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks Authors: Cory Fan, Wenchao Zhang Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00703v2 In digital imaging, image demosaicing is a crucial first step which recovers the RGB information from a color filter array (CFA). Oftentimes, deep learning is utilized to perform image demosaicing. Given that most modern digital imaging applications occur on mobile platforms, applying deep learning to demosaicing requires lightweight and efficient networks. Isotropic networks, also known as residual-in-residual networks, have been often employed for image demosaicing and joint-demosaicing-and-denoising (JDD). Most demosaicing isotropic networks avoid spatial downsampling entirely, and thus are often prohibitively expensive computationally for mobile applications. Contrary to previous isotropic network designs, this paper claims that spatial downsampling to a signficant degree can improve the efficiency and performance of isotropic networks. To validate this claim, we design simple fully convolutional networks with and without downsampling using a mathematical architecture design technique adapted from DeepMAD, and find that downsampling improves empirical performance. Additionally, empirical testing of the downsampled variant, JD3Net, of our fully convolutional networks reveals strong empirical performance on a variety of image demosaicing and JDD tasks. --- ### Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks Authors: Cory Fan, Wenchao Zhang Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00703v1 In digital imaging, image demosaicing is a crucial first step which recovers the RGB information from a color filter array (CFA). Oftentimes, deep learning is utilized to perform image demosaicing. Given that most modern digital imaging applications occur on mobile platforms, applying deep learning to demosaicing requires lightweight and efficient networks. Isotropic networks, also known as residual-in-residual networks, have been often employed for image demosaicing and joint-demosaicing-and-denoising (JDD). Most demosaicing isotropic networks avoid spatial downsampling entirely, and thus are often prohibitively expensive computationally for mobile applications. Contrary to previous isotropic network designs, this paper claims that spatial downsampling to a signficant degree can improve the efficiency and performance of isotropic networks. To validate this claim, we design simple fully convolutional networks with and without downsampling using a mathematical architecture design technique adapted from DeepMAD, and find that downsampling improves empirical performance. Additionally, empirical testing of the downsampled variant, JD3Net, of our fully convolutional networks reveals strong empirical performance on a variety of image demosaicing and JDD tasks. --- ### DefVINS: Visual-Inertial Odometry for Deformable Scenes Authors: Samuel Cerezo, Javier Civera Published: 2026-01-02 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.00702v4 Deformable scenes violate the rigidity assumptions underpinning classical visual--inertial odometry (VIO), often leading to over-fitting to local non-rigid motion or to severe camera pose drift when deformation dominates visual parallax. In this paper, we introduce DefVINS, the first visual-inertial odometry pipeline designed to operate in deformable environments. Our approach models the odometry state by decomposing it into a rigid, IMU-anchored component and a non-rigid scene warp represented by an embedded deformation graph. As a second contribution, we present VIMandala, the first benchmark containing real images and ground-truth camera poses for visual-inertial odometry in deformable scenes. In addition, we augment the synthetic Drunkard's benchmark with simulated inertial measurements to further evaluate our pipeline under controlled conditions. We also provide an observability analysis of the visual-inertial deformable odometry problem, characterizing how inertial measurements constrain camera motion and render otherwise unobservable modes identifiable in the presence of deformation. This analysis motivates the use of IMU anchoring and leads to a conditioning-based activation strategy that avoids ill-posed updates under poor excitation. Experimental results on both the synthetic Drunkard's and our real VIMandala benchmarks show that DefVINS outperforms rigid visual--inertial and non-rigid visual odometry baselines. Our source code and data will be released upon acceptance. --- ### DefVINS: Visual-Inertial Odometry for Deformable Scenes Authors: Samuel Cerezo, Javier Civera Published: 2026-01-02 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.00702v1 Deformable scenes violate the rigidity assumptions underpinning classical visual-inertial odometry (VIO), often leading to over-fitting to local non-rigid motion or severe drift when deformation dominates visual parallax. We introduce DefVINS, a visual-inertial odometry framework that explicitly separates a rigid, IMU-anchored state from a non--rigid warp represented by an embedded deformation graph. The system is initialized using a standard VIO procedure that fixes gravity, velocity, and IMU biases, after which non-rigid degrees of freedom are activated progressively as the estimation becomes well conditioned. An observability analysis is included to characterize how inertial measurements constrain the rigid motion and render otherwise unobservable modes identifiable in the presence of deformation. This analysis motivates the use of IMU anchoring and informs a conditioning-based activation strategy that prevents ill-posed updates under poor excitation. Ablation studies demonstrate the benefits of combining inertial constraints with observability-aware deformation activation, resulting in improved robustness under non-rigid environments. --- ### BSAT: B-Spline Adaptive Tokenizer for Long-Term Time Series Forecasting Authors: Maximilian Reinwardt, Michael Eichelbeck, Matthias Althoff Published: 2026-01-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00698v1 Long-term time series forecasting using transformers is hampered by the quadratic complexity of self-attention and the rigidity of uniform patching, which may be misaligned with the data's semantic structure. In this paper, we introduce the \textit{B-Spline Adaptive Tokenizer (BSAT)}, a novel, parameter-free method that adaptively segments a time series by fitting it with B-splines. BSAT algorithmically places tokens in high-curvature regions and represents each variable-length basis function as a fixed-size token, composed of its coefficient and position. Further, we propose a hybrid positional encoding that combines a additive learnable positional encoding with Rotary Positional Embedding featuring a layer-wise learnable base: L-RoPE. This allows each layer to attend to different temporal dependencies. Our experiments on several public benchmarks show that our model is competitive with strong performance at high compression rates. This makes it particularly well-suited for use cases with strong memory constraints. --- ### Bayesian Inverse Games with High-Dimensional Multi-Modal Observations Authors: Yash Jain, Xinjie Liu, Lasse Peters, David Fridovich-Keil, Ufuk Topcu Published: 2026-01-02 Categories: cs.LG, cs.GT, cs.RO arXiv: https://arxiv.org/abs/2601.00696v1 Many multi-agent interaction scenarios can be naturally modeled as noncooperative games, where each agent's decisions depend on others' future actions. However, deploying game-theoretic planners for autonomous decision-making requires a specification of all agents' objectives. To circumvent this practical difficulty, recent work develops maximum likelihood techniques for solving inverse games that can identify unknown agent objectives from interaction data. Unfortunately, these methods only infer point estimates and do not quantify estimator uncertainty; correspondingly, downstream planning decisions can overconfidently commit to unsafe actions. We present an approximate Bayesian inference approach for solving the inverse game problem, which can incorporate observation data from multiple modalities and be used to generate samples from the Bayesian posterior over the hidden agent objectives given limited sensor observations in real time. Concretely, the proposed Bayesian inverse game framework trains a structured variational autoencoder with an embedded differentiable Nash game solver on interaction datasets and does not require labels of agents' true objectives. Extensive experiments show that our framework successfully learns prior and posterior distributions, improves inference quality over maximum likelihood estimation-based inverse game approaches, and enables safer downstream decision-making without sacrificing efficiency. When trajectory information is uninformative or unavailable, multimodal inference further reduces uncertainty by exploiting additional observation modalities. --- ### A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference Authors: Qingwen Pu, Kun Xie, Hong Yang, Guocong Zhai Published: 2026-01-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.00694v1 Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizability and perform inadequately on new sites. Recent advances in Large Language Models (LLMs) offer a shift from numerical pattern fitting to semantic, context-aware behavioral reasoning, yet existing LLM applications lack domain-specific adaptation and visual context. This study introduces Pedestrian Crossing LLM (PedX-LLM), a vision-and-knowledge enhanced framework designed to transform pedestrian crossing inference from site-specific pattern recognition to generalizable behavioral reasoning. By integrating LLaVA-extracted visual features with textual data and transportation domain knowledge, PedX-LLM fine-tunes a LLaMA-2-7B foundation model via Low-Rank Adaptation (LoRA) to infer crossing decisions. PedX-LLM achieves 82.0% balanced accuracy, outperforming the best statistical and supervised learning methods. Results demonstrate that the vision-augmented module contributes a 2.9% performance gain by capturing the built environment and integrating domain knowledge yields an additional 4.1% improvement. To evaluate generalizability across unseen environments, cross-site validation was conducted using site-based partitioning. The zero-shot PedX-LLM configuration achieves 66.9% balanced accuracy on five unseen test sites, outperforming the baseline data-driven methods by at least 18 percentage points. Incorporating just five validation examples via few-shot learning to PedX-LLM further elevates the balanced accuracy to 72.2%. PedX-LLM demonstrates strong generalizability to unseen scenarios, confirming that vision-and-knowledge-enhanced reasoning enables the model to mimic human-like decision logic and overcome the limitations of purely data-driven methods. --- ### ARISE: Adaptive Reinforcement Integrated with Swarm Exploration Authors: Rajiv Chaitanya M, D R Ramesh Babu Published: 2026-01-02 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2601.00693v1 Effective exploration remains a key challenge in RL, especially with non-stationary rewards or high-dimensional policies. We introduce ARISE, a lightweight framework that enhances reinforcement learning by augmenting standard policy-gradient methods with a compact swarm-based exploration layer. ARISE blends policy actions with particle-driven proposals, where each particle represents a candidate policy trajectory sampled in the action space, and modulates exploration adaptively using reward-variance cues. While easy benchmarks exhibit only slight improvements (e.g., +0.7% on CartPole-v1), ARISE yields substantial gains on more challenging tasks, including +46% on LunarLander-v3 and +22% on Hopper-v4, while preserving stability on Walker2d and Ant. Under non-stationary reward shifts, ARISE provides marked robustness advantages, outperforming PPO by +75 points on CartPole and improving LunarLander accordingly. Ablation studies confirm that both the swarm component and the adaptive mechanism contribute to the performance. Overall, ARISE offers a simple, architecture-agnostic route to more exploratory and resilient RL agents without altering core algorithmic structures. --- ### TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications Authors: Mohamed Trabelsi, Huseyin Uzunalioglu Published: 2026-01-02 Categories: cs.LG, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2601.00691v1 Ticket troubleshooting refers to the process of analyzing and resolving problems that are reported through a ticketing system. In large organizations offering a wide range of services, this task is highly complex due to the diversity of submitted tickets and the need for specialized domain knowledge. In particular, troubleshooting in telecommunications (telecom) is a very time-consuming task as it requires experts to interpret ticket content, consult documentation, and search historical records to identify appropriate resolutions. This human-intensive approach not only delays issue resolution but also hinders overall operational efficiency. To enhance the effectiveness and efficiency of ticket troubleshooting in telecom, we propose TeleDoCTR, a novel telecom-related, domain-specific, and contextual troubleshooting system tailored for end-to-end ticket resolution in telecom. TeleDoCTR integrates both domain-specific ranking and generative models to automate key steps of the troubleshooting workflow which are: routing tickets to the appropriate expert team responsible for resolving the ticket (classification task), retrieving contextually and semantically similar historical tickets (retrieval task), and generating a detailed fault analysis report outlining the issue, root cause, and potential solutions (generation task). We evaluate TeleDoCTR on a real-world dataset from a telecom infrastructure and demonstrate that it achieves superior performance over existing state-of-the-art methods, significantly enhancing the accuracy and efficiency of the troubleshooting process. --- ### Cost Optimization in Production Line Using Genetic Algorithm Authors: Alireza Rezaee Published: 2026-01-02 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.00689v1 This paper presents a genetic algorithm (GA) approach to cost-optimal task scheduling in a production line. The system consists of a set of serial processing tasks, each with a given duration, unit execution cost, and precedence constraints, which must be assigned to an unlimited number of stations subject to a per-station duration bound. The objective is to minimize the total production cost, modeled as a station-wise function of task costs and the duration bound, while strictly satisfying all prerequisite and capacity constraints. Two chromosome encoding strategies are investigated: a station-based representation implemented using the JGAP library with SuperGene validity checks, and a task-based representation in which genes encode station assignments directly. For each encoding, standard GA operators (crossover, mutation, selection, and replacement) are adapted to preserve feasibility and drive the population toward lower-cost schedules. Experimental results on three classes of precedence structures-tightly coupled, loosely coupled, and uncoupled-demonstrate that the task-based encoding yields smoother convergence and more reliable cost minimization than the station-based encoding, particularly when the number of valid schedules is large. The study highlights the advantages of GA over gradient-based and analytical methods for combinatorial scheduling problems, especially in the presence of complex constraints and non-differentiable cost landscapes. --- ### Sigmoid Head for Quality Estimation under Language Ambiguity Authors: Tu Anh Dinh, Jan Niehues Published: 2026-01-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.00680v2 Language model (LM) probability is not a reliable quality estimator, as natural language is ambiguous. When multiple output options are valid, the model's probability distribution is spread across them, which can misleadingly indicate low output quality. This issue is caused by two reasons: (1) LMs' final output activation is softmax, which does not allow multiple correct options to receive high probabilities simultaneuously and (2) LMs' training data is single, one-hot encoded references, indicating that there is only one correct option at each output step. We propose training a module for Quality Estimation on top of pre-trained LMs to address these limitations. The module, called Sigmoid Head, is an extra unembedding head with sigmoid activation to tackle the first limitation. To tackle the second limitation, during the negative sampling process to train the Sigmoid Head, we use a heuristic to avoid selecting potentially alternative correct tokens. Our Sigmoid Head is computationally efficient during training and inference. The probability from Sigmoid Head is notably better quality signal compared to the original softmax head. As the Sigmoid Head does not rely on human-annotated quality data, it is more robust to out-of-domain settings compared to supervised QE. --- ### Sigmoid Head for Quality Estimation under Language Ambiguity Authors: Tu Anh Dinh, Jan Niehues Published: 2026-01-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.00680v1 Language model (LM) probability is not a reliable quality estimator, as natural language is ambiguous. When multiple output options are valid, the model's probability distribution is spread across them, which can misleadingly indicate low output quality. This issue is caused by two reasons: (1) LMs' final output activation is softmax, which does not allow multiple correct options to receive high probabilities simultaneuously and (2) LMs' training data is single, one-hot encoded references, indicating that there is only one correct option at each output step. We propose training a module for Quality Estimation on top of pre-trained LMs to address these limitations. The module, called Sigmoid Head, is an extra unembedding head with sigmoid activation to tackle the first limitation. To tackle the second limitation, during the negative sampling process to train the Sigmoid Head, we use a heuristic to avoid selecting potentially alternative correct tokens. Our Sigmoid Head is computationally efficient during training and inference. The probability from Sigmoid Head is notably better quality signal compared to the original softmax head. As the Sigmoid Head does not rely on human-annotated quality data, it is more robust to out-of-domain settings compared to supervised QE. --- ### QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models Authors: Rachmad Vidya Wicaksana Putra, Pasindu Wickramasinghe, Muhammad Shafique Published: 2026-01-02 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.00679v2 Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs. However, their large computational cost, huge memory footprints, and high processing power/energy make it challenging for their embedded deployments. Amid several tinyLLMs, recent works have proposed spike-driven language models (SLMs) for significantly reducing the processing power/energy of LLMs. However, their memory footprints still remain too large for low-cost and resource-constrained embedded devices. Manual quantization approach may effectively compress SLM memory footprints, but it requires a huge design time and compute power to find the quantization setting for each network, hence making this approach not-scalable for handling different networks, performance requirements, and memory budgets. To bridge this gap, we propose QSLM, a novel framework that performs automated quantization for compressing pre-trained SLMs, while meeting the performance and memory constraints. To achieve this, QSLM first identifies the hierarchy of the given network architecture and the sensitivity of network layers under quantization, then employs a tiered quantization strategy (e.g., global-, block-, and module-level quantization) while leveraging a multi-objective performance-and-memory trade-off function to select the final quantization setting. Experimental results indicate that our QSLM reduces memory footprint by up to 86.5%, reduces power consumption by up to 20%, maintains high performance across different tasks (i.e., by up to 84.4% accuracy of sentiment classification on the SST-2 dataset and perplexity score of 23.2 for text generation on the WikiText-2 dataset) close to the original non-quantized model while meeting the performance and memory constraints. --- ### QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models Authors: Rachmad Vidya Wicaksana Putra, Pasindu Wickramasinghe, Muhammad Shafique Published: 2026-01-02 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.00679v1 Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs. However, their large computational cost, huge memory footprints, and high processing power/energy make it challenging for their embedded deployments. Amid several tinyLLMs, recent works have proposed spike-driven language models (SLMs) for significantly reducing the processing power/energy of LLMs. However, their memory footprints still remain too large for low-cost and resource-constrained embedded devices. Manual quantization approach may effectively compress SLM memory footprints, but it requires a huge design time and compute power to find the quantization setting for each network, hence making this approach not-scalable for handling different networks, performance requirements, and memory budgets. To bridge this gap, we propose QSLM, a novel framework that performs automated quantization for compressing pre-trained SLMs, while meeting the performance and memory constraints. To achieve this, QSLM first identifies the hierarchy of the given network architecture and the sensitivity of network layers under quantization, then employs a tiered quantization strategy (e.g., global-, block-, and module-level quantization) while leveraging a multi-objective performance-and-memory trade-off function to select the final quantization setting. Experimental results indicate that our QSLM reduces memory footprint by up to 86.5%, reduces power consumption by up to 20%, maintains high performance across different tasks (i.e., by up to 84.4% accuracy of sentiment classification on the SST-2 dataset and perplexity score of 23.2 for text generation on the WikiText-2 dataset) close to the original non-quantized model while meeting the performance and memory constraints. --- ### Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians Authors: Melonie de Almeida, Daniela Ivanova, Tong Shi, John H. Williamson, Paul Henderson Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00678v3 Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, and preserving geometric integrity. Leveraging explicit intermediate 3D representations offers a promising solution by enabling coherent video generation aligned with a given camera trajectory. Although these methods often use 3D point clouds to render scenes and introduce object motion in a later stage, this two-step process still falls short in achieving full temporal consistency, despite allowing precise control over camera movement. We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames. Extensive experiments on the KITTI, Waymo, RealEstate10K and DL3DV-10K datasets demonstrate that our method achieves state-of-the-art video quality and inference efficiency. The project page is available at https://melonienimasha.github.io/Pixel-to-4D-Website. --- ### Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians Authors: Melonie de Almeida, Daniela Ivanova, Tong Shi, John H. Williamson, Paul Henderson Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00678v1 Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, and preserving geometric integrity. Leveraging explicit intermediate 3D representations offers a promising solution by enabling coherent video generation aligned with a given camera trajectory. Although these methods often use 3D point clouds to render scenes and introduce object motion in a later stage, this two-step process still falls short in achieving full temporal consistency, despite allowing precise control over camera movement. We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames. Extensive experiments on the KITTI, Waymo, RealEstate10K and DL3DV-10K datasets demonstrate that our method achieves state-of-the-art video quality and inference efficiency. The project page is available at https://melonienimasha.github.io/Pixel-to-4D-Website. --- ### IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models Authors: Haonan Song, Qingchen Xie, Huan Zhu, Feng Xiao, Luxi Xing, Liu Kang, Fuzhen Li, Zhiyong Zheng, Feng Jiang, Ziheng Li, Kun Yan, Qingyi Si et al. Published: 2026-01-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00677v2 Generative Reward Models (GRMs) have demonstrated strong performance in reward modeling, due to their interpretability and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck in reinforcement learning from human feedback (RLHF), when calibrating or aggregating preference signals over n candidates, often incurring O(n^2) pairwise judgments. To address this issue, we propose Intergroup Relative Preference Modeling (IRPM), an RL-based method that extends the Bradley--Terry preference-learning paradigm via intergroup comparisons to train pointwise GRMs from pairwise preference data. IRPM derives pointwise reward for each response by contrasting groups of chosen vs. rejected samples, enabling pointwise scores comparable across candidate sets and O(n) reward evaluation for a variable number of candidates during RL training, while preserving interpretability and scalability. Experiments show that IRPM achieves state-of-the-art performance among pointwise GRMs on RM-Bench, JudgeBench and RewardBench, and approaches the performance of leading pairwise GRMs. In addition, IRPM achieves substantial gains in post-training evaluations, demonstrating its effectiveness. --- ### IRPO: Scaling the Bradley-Terry Model via Reinforcement Learning Authors: Haonan Song, Qingchen Xie, Huan Zhu, Feng Xiao, Luxi Xing, Fuzhen Li, Liu Kang, Feng Jiang, Zhiyong Zheng, Fan Yang Published: 2026-01-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00677v1 Generative Reward Models (GRMs) have attracted considerable research interest in reward modeling due to their interpretability, inference-time scalability, and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck when integrated with RL algorithms such as Group Relative Policy Optimization (GRPO). This bottleneck arises from two factors: (i) the O(n^2) time complexity of pairwise comparisons required to obtain relative scores, and (ii) the computational overhead of repeated sampling or additional chain-of-thought (CoT) reasoning to improve performance. To address the first factor, we propose Intergroup Relative Preference Optimization (IRPO), a novel RL framework that incorporates the well-established Bradley-Terry model into GRPO. By generating a pointwise score for each response, IRPO enables efficient evaluation of arbitrarily many candidates during RL training while preserving interpretability and fine-grained reward signals. Experimental results demonstrate that IRPO achieves state-of-the-art (SOTA) performance among pointwise GRMs across multiple benchmarks, with performance comparable to that of current leading pairwise GRMs. Furthermore, we show that IRPO significantly outperforms pairwise GRMs in post-training evaluations. --- ### Sparse FEONet: A Low-Cost, Memory-Efficient Operator Network via Finite-Element Local Sparsity for Parametric PDEs Authors: Seungchan Ko, Jiyeon Kim, Dongwook Shin Published: 2026-01-02 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2601.00672v2 In this paper, we study the finite element operator network (FEONet), an operator-learning method for parametric problems, originally introduced in J. Y. Lee, S. Ko, and Y. Hong, Finite Element Operator Network for Solving Elliptic-Type Parametric PDEs, SIAM J. Sci. Comput., 47(2), C501-C528, 2025. FEONet realizes the parameter-to-solution map on a finite element space and admits a training procedure that does not require training data, while exhibiting high accuracy and robustness across a broad class of problems. However, its computational cost increases and accuracy may deteriorate as the number of elements grows, posing notable challenges for large-scale problems. In this paper, we propose a new sparse network architecture motivated by the structure of the finite elements to address this issue. Throughout extensive numerical experiments, we show that the proposed sparse network achieves substantial improvements in computational cost and efficiency while maintaining comparable accuracy. We also establish theoretical results demonstrating that the sparse architecture can approximate the target operator effectively and provide a stability analysis ensuring reliable training and prediction. --- ### Sparse FEONet: A Low-Cost, Memory-Efficient Operator Network via Finite-Element Local Sparsity for Parametric PDEs Authors: Seungchan Ko, Jiyeon Kim, Dongwook Shin Published: 2026-01-02 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2601.00672v1 In this paper, we study the finite element operator network (FEONet), an operator-learning method for parametric problems, originally introduced in J. Y. Lee, S. Ko, and Y. Hong, Finite Element Operator Network for Solving Elliptic-Type Parametric PDEs, SIAM J. Sci. Comput., 47(2), C501-C528, 2025. FEONet realizes the parameter-to-solution map on a finite element space and admits a training procedure that does not require training data, while exhibiting high accuracy and robustness across a broad class of problems. However, its computational cost increases and accuracy may deteriorate as the number of elements grows, posing notable challenges for large-scale problems. In this paper, we propose a new sparse network architecture motivated by the structure of the finite elements to address this issue. Throughout extensive numerical experiments, we show that the proposed sparse network achieves substantial improvements in computational cost and efficiency while maintaining comparable accuracy. We also establish theoretical results demonstrating that the sparse architecture can approximate the target operator effectively and provide a stability analysis ensuring reliable training and prediction. --- ### Fast-weight Product Key Memory Authors: Tianyu Zhao, Llion Jones Published: 2026-01-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.00671v2 Sequence modeling layers in modern language models typically face a trade-off between storage capacity and computational efficiency. While softmax attention offers unbounded storage at prohibitive quadratic cost, linear variants are more efficient but suffer from limited, fixed-size storage. We introduce Fast-weight Product Key Memory (FwPKM), a sparse fast-weight memory layer that resolves this tension. FwPKM updates sparsely activated parameters at both training and inference time using chunk-level gradient descent on a local memory-rewrite objective. This performs Test-Time Training (TTT)-style gradient updates on activated slots in a sparse memory, enabling rapid memorization and retrieval of many new key-value associations while keeping per-token compute low and fixed. Experiments show that FwPKM functions as an effective episodic memory that complements the semantic memory of standard modules, yielding significant perplexity reductions on long-context datasets. Notably, in Needle-in-a-Haystack evaluations, FwPKM generalizes to 128K-token contexts despite being trained on only 4K-token sequences. --- ### Fast-weight Product Key Memory Authors: Tianyu Zhao, Llion Jones Published: 2026-01-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.00671v1 Sequence modeling layers in modern language models typically face a trade-off between storage capacity and computational efficiency. While Softmax attention offers unbounded storage at prohibitive quadratic costs, linear variants provide efficiency but suffer from limited, fixed-size storage. We propose Fast-weight Product Key Memory (FwPKM), a novel architecture that resolves this tension by transforming the sparse Product Key Memory (PKM) from a static module into a dynamic, "fast-weight" episodic memory. Unlike PKM, FwPKM updates its parameters dynamically at both training and inference time via local chunk-level gradient descent, allowing the model to rapidly memorize and retrieve new key-value pairs from input sequences. Experiments reveal that FwPKM functions as an effective episodic memory that complements the semantic memory of standard modules, yielding significant perplexity reductions on long-context datasets. Notably, in Needle in a Haystack evaluations, FwPKM generalizes to 128K-token contexts despite being trained on only 4K-token sequences. --- ### Three factor delay learning rules for spiking neural networks Authors: Luke Vassallo, Nima Taherinejad Published: 2026-01-02 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.00668v2 Spiking Neural Networks (SNNs) are dynamical systems that operate on spatiotemporal data, yet their learnable parameters are often limited to synaptic weights, contributing little to temporal pattern recognition. Learnable parameters that delay spike times can improve classification performance in temporal tasks, but existing methods rely on large networks and offline learning, making them unsuitable for real-time operation in resource-constrained environments. In this paper, we introduce synaptic and axonal delays to leaky integrate and fire (LIF)-based feedforward and recurrent SNNs, and propose three-factor learning rules to simultaneously learn delay parameters online. We employ a smooth Gaussian surrogate to approximate spike derivatives exclusively for the eligibility trace calculation, and together with a top-down error signal determine parameter updates. Our experiments show that incorporating delays improves accuracy by up to 20% over a weights-only baseline, and for networks with similar parameter counts, jointly learning weights and delays yields up to 14% higher accuracy. On the SHD speech recognition dataset, our method achieves similar accuracy to offline backpropagation-based approaches. Compared to state-of-the-art methods, it reduces model size by 6.6x and inference latency by 67%, with only a 2.4% drop in classification accuracy. Our findings benefit the design of power and area-constrained neuromorphic processors by enabling on-device learning and lowering memory requirements. --- ### Three factor delay learning rules for spiking neural networks Authors: Luke Vassallo, Nima Taherinejad Published: 2026-01-02 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2601.00668v1 Spiking Neural Networks (SNNs) are dynamical systems that operate on spatiotemporal data, yet their learnable parameters are often limited to synaptic weights, contributing little to temporal pattern recognition. Learnable parameters that delay spike times can improve classification performance in temporal tasks, but existing methods rely on large networks and offline learning, making them unsuitable for real-time operation in resource-constrained environments. In this paper, we introduce synaptic and axonal delays to leaky integrate and fire (LIF)-based feedforward and recurrent SNNs, and propose three-factor learning rules to simultaneously learn delay parameters online. We employ a smooth Gaussian surrogate to approximate spike derivatives exclusively for the eligibility trace calculation, and together with a top-down error signal determine parameter updates. Our experiments show that incorporating delays improves accuracy by up to 20% over a weights-only baseline, and for networks with similar parameter counts, jointly learning weights and delays yields up to 14% higher accuracy. On the SHD speech recognition dataset, our method achieves similar accuracy to offline backpropagation-based approaches. Compared to state-of-the-art methods, it reduces model size by 6.6x and inference latency by 67%, with only a 2.4% drop in classification accuracy. Our findings benefit the design of power and area-constrained neuromorphic processors by enabling on-device learning and lowering memory requirements. --- ### Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation Authors: Taekyung Ki, Sangwon Jang, Jaehyeong Jo, Jaehong Yoon, Sung Ju Hwang Published: 2026-01-02 Categories: cs.LG, cs.AI, cs.CV, cs.HC, cs.MM arXiv: https://arxiv.org/abs/2601.00664v2 Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models do not yet convey the feeling of truly interactive communication, often generating one-way responses that lack emotional engagement. We identify two key challenges toward truly interactive avatars: generating motion in real-time under causal constraints and learning expressive, vibrant reactions without additional labeled data. To address these challenges, we propose Avatar Forcing, a new framework for interactive head avatar generation that models real-time user-avatar interactions through diffusion forcing. This design allows the avatar to process real-time multimodal inputs, including the user's audio and motion, with low latency for instant reactions to both verbal and non-verbal cues such as speech, nods, and laughter. Furthermore, we introduce a direct preference optimization method that leverages synthetic losing samples constructed by dropping user conditions, enabling label-free learning of expressive interaction. Experimental results demonstrate that our framework enables real-time interaction with low latency (approximately 500ms), achieving 6.8X speedup compared to the baseline, and produces reactive and expressive avatar motion, which is preferred over 80% against the baseline. --- ### Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation Authors: Taekyung Ki, Sangwon Jang, Jaehyeong Jo, Jaehong Yoon, Sung Ju Hwang Published: 2026-01-02 Categories: cs.LG, cs.AI, cs.CV, cs.HC, cs.MM arXiv: https://arxiv.org/abs/2601.00664v1 Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models do not yet convey the feeling of truly interactive communication, often generating one-way responses that lack emotional engagement. We identify two key challenges toward truly interactive avatars: generating motion in real-time under causal constraints and learning expressive, vibrant reactions without additional labeled data. To address these challenges, we propose Avatar Forcing, a new framework for interactive head avatar generation that models real-time user-avatar interactions through diffusion forcing. This design allows the avatar to process real-time multimodal inputs, including the user's audio and motion, with low latency for instant reactions to both verbal and non-verbal cues such as speech, nods, and laughter. Furthermore, we introduce a direct preference optimization method that leverages synthetic losing samples constructed by dropping user conditions, enabling label-free learning of expressive interaction. Experimental results demonstrate that our framework enables real-time interaction with low latency (approximately 500ms), achieving 6.8X speedup compared to the baseline, and produces reactive and expressive avatar motion, which is preferred over 80% against the baseline. --- ### CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models Authors: Neeraj Anand, Samyak Jha, Udbhav Bamba, Rahul Rahaman Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00659v1 Despite the rapid success of Large Vision-Language Models (LVLMs), a persistent challenge is their tendency to generate hallucinated content, undermining reliability in real-world use. Existing training-free methods address hallucinations but face two limitations: (i) they rely on narrow assumptions about hallucination sources, and (ii) their effectiveness declines toward the end of generation, where hallucinations are most likely to occur. A common strategy is to build hallucinated models by completely or partially removing visual tokens and contrasting them with the original model. Yet, this alone proves insufficient, since visual information still propagates into generated text. Building on this insight, we propose a novel hallucinated model that captures hallucination effects by selectively removing key text tokens. We further introduce Generalized Contrastive Decoding, which integrates multiple hallucinated models to represent diverse hallucination sources. Together, these ideas form CRoPS, a training-free hallucination mitigation framework that improves CHAIR scores by 20% and achieves consistent gains across six benchmarks and three LVLM families, outperforming state-of-the-art training-free methods. --- ### Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Network Authors: Zhaiyu Chen, Yuanyuan Wang, Yilei Shi, Xiao Xiang Zhu Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00658v1 Reliable building height estimation is essential for various urban applications. Spaceborne SAR tomography (TomoSAR) provides weather-independent, side-looking observations that capture facade-level structure, offering a promising alternative to conventional optical methods. However, TomoSAR point clouds often suffer from noise, anisotropic point distributions, and data voids on incoherent surfaces, all of which hinder accurate height reconstruction. To address these challenges, we introduce a learning-based framework for converting raw TomoSAR points into high-resolution building height maps. Our dual-topology network alternates between a point branch that models irregular scatterer features and a grid branch that enforces spatial consistency. By jointly processing these representations, the network denoises the input points and inpaints missing regions to produce continuous height estimates. To our knowledge, this is the first proof of concept for large-scale urban height mapping directly from TomoSAR point clouds. Extensive experiments on data from Munich and Berlin validate the effectiveness of our approach. Moreover, we demonstrate that our framework can be extended to incorporate optical satellite imagery, further enhancing reconstruction quality. The source code is available at https://github.com/zhu-xlab/tomosar2height. --- ### Interpretability-Guided Bi-objective Optimization: Aligning Accuracy and Explainability Authors: Kasra Fouladi, Hamta Rahmani Published: 2026-01-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00655v3 This paper introduces Interpretability-Guided Bi-objective Optimization (IGBO), a framework that trains interpretable models by incorporating structured domain knowledge via a bi-objective formulation. IGBO encodes feature importance hierarchies as a Directed Acyclic Graph (DAG) via Central Limit Theorem-based construction and uses Temporal Integrated Gradients (TIG) to measure feature importance. The framework employs a novel Relative Importance Score Hk(X, θ) that quantifies the normalized cumulative attribution of each feature over time. We propose a geometric projection mapping P for combining task and interpretability gradients, and prove convergence to Pareto-stationary points. To address the Out-of-Distribution problem in TIG computation, we outline an Optimal Path Oracle architecture, which we leave for future work. Central Limit Theorem-based construction of the interpretability DAG provides statistical guarantees on acyclicity and transitivity, with an unconditional guarantee for the median threshold and conditional guarantees for higher confidence levels. --- ### Interpretability-Guided Bi-objective Optimization: Aligning Accuracy and Explainability Authors: Kasra Fouladi, Hamta Rahmani Published: 2026-01-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00655v1 This paper introduces Interpretability-Guided Bi-objective Optimization (IGBO), a framework that trains interpretable models by incorporating structured domain knowledge via a bi-objective formulation. IGBO encodes feature importance hierarchies as a Directed Acyclic Graph (DAG) and uses Temporal Integrated Gradients (TIG) to measure feature importance. To address the Out-of-Distribution (OOD) problem in TIG computation, we propose an Optimal Path Oracle that learns data-manifold-aware integration paths. Theoretical analysis proves convergence properties and robustness to mini-batch noise, while empirical results on time-series data demonstrate IGBO's effectiveness in enforcing DAG constraints with minimal accuracy loss, outperforming standard regularization baselines. --- ### Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations Authors: QiWei Meng Published: 2026-01-02 Categories: cs.CL, cs.CE, q-bio.QM arXiv: https://arxiv.org/abs/2601.00647v1 Large Protein Language Models have shown strong potential for generative protein design, yet they frequently produce structural hallucinations, generating sequences with high linguistic likelihood that fold into thermodynamically unstable conformations. Existing alignment approaches such as Direct Preference Optimization are limited in this setting, as they model preferences as binary labels and ignore the continuous structure of the physical energy landscape. We propose Physio-DPO, a physics informed alignment framework that grounds protein language models in thermodynamic stability. Physio-DPO introduces a magnitude aware objective that scales optimization updates according to the energy gap between native structures and physics perturbed hard negatives. Experiments show that Physio-DPO consistently outperforms strong baselines including SFT, PPO, and standard DPO, reducing self consistency RMSD to 1.28 Å and increasing foldability to 92.8%. Qualitative analysis further demonstrates that Physio-DPO effectively mitigates structural hallucinations by recovering biophysical interactions such as hydrophobic core packing and hydrogen bond networks. --- ### Quality Detection of Stored Potatoes via Transfer Learning: A CNN and Vision Transformer Approach Authors: Shrikant Kapse, Priyankkumar Dhrangdhariya, Priya Kedia, Manasi Patwardhan, Shankar Kausley, Soumyadipta Maiti, Beena Rai, Shirish Karande Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00645v1 Image-based deep learning provides a non-invasive, scalable solution for monitoring potato quality during storage, addressing key challenges such as sprout detection, weight loss estimation, and shelf-life prediction. In this study, images and corresponding weight data were collected over a 200-day period under controlled temperature and humidity conditions. Leveraging powerful pre-trained architectures of ResNet, VGG, DenseNet, and Vision Transformer (ViT), we designed two specialized models: (1) a high-precision binary classifier for sprout detection, and (2) an advanced multi-class predictor to estimate weight loss and forecast remaining shelf-life with remarkable accuracy. DenseNet achieved exceptional performance, with 98.03% accuracy in sprout detection. Shelf-life prediction models performed best with coarse class divisions (2-5 classes), achieving over 89.83% accuracy, while accuracy declined for finer divisions (6-8 classes) due to subtle visual differences and limited data per class. These findings demonstrate the feasibility of integrating image-based models into automated sorting and inventory systems, enabling early identification of sprouted potatoes and dynamic categorization based on storage stage. Practical implications include improved inventory management, differential pricing strategies, and reduced food waste across supply chains. While predicting exact shelf-life intervals remains challenging, focusing on broader class divisions ensures robust performance. Future research should aim to develop generalized models trained on diverse potato varieties and storage conditions to enhance adaptability and scalability. Overall, this approach offers a cost-effective, non-destructive method for quality assessment, supporting efficiency and sustainability in potato storage and distribution. --- ### Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs Authors: Nils Rautenberg, Sven Schippkus Published: 2026-01-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.00641v1 Large language models (LLMs) frequently produce contextual hallucinations, where generated content contradicts or ignores information explicitly stated in the prompt. Such errors are particularly problematic in deterministic automation workflows, where inputs are fixed and correctness is unambiguous. We introduce a simple and model-agnostic framework that provides explicit probabilistic guarantees for reducing hallucinations in this setting. We formalize the notion of a specific task, defined by a fixed input and a deterministic correctness criterion, and show that issuing the same prompt in independent context windows yields an exponential reduction in the probability that all model outputs are incorrect. To identify a correct answer among repeated runs, we incorporate an LLM-as-a-judge and prove that the probability that the judged pipeline fails decays at a rate determined by the judge's true- and false-positive probabilities. When the judge is imperfect, we strengthen it through majority vote over independent judge calls, obtaining ensemble-level error rates that decrease exponentially in the number of votes. This yields an explicit bound on the probability that the pipeline selects a hallucinated answer. Experiments on controlled extraction tasks with synthetic noisy judges match these predictions exactly: pipeline failure decreases exponentially with the number of repetitions, and hallucination-selection decreases exponentially with the number of judges in the ensemble. Together, these results provide a lightweight, modular, and theoretically grounded method for driving hallucination probabilities arbitrarily low in fixed-input LLM workflows-without modifying model weights, decoding strategies, or prompt engineering. --- ### HyperPriv-EPN: Hypergraph Learning with Privileged Knowledge for Ependymoma Prognosis Authors: Shuren Gabriel Yu, Sikang Ren, Yongji Tian Published: 2026-01-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.00626v1 Preoperative prognosis of Ependymoma is critical for treatment planning but challenging due to the lack of semantic insights in MRI compared to post-operative surgical reports. Existing multimodal methods fail to leverage this privileged text data when it is unavailable during inference. To bridge this gap, we propose HyperPriv-EPN, a hypergraph-based Learning Using Privileged Information (LUPI) framework. We introduce a Severed Graph Strategy, utilizing a shared encoder to process both a Teacher graph (enriched with privileged post-surgery information) and a Student graph (restricted to pre-operation data). Through dual-stream distillation, the Student learns to hallucinate semantic community structures from visual features alone. Validated on a multi-center cohort of 311 patients, HyperPriv-EPN achieves state-of-the-art diagnostic accuracy and survival stratification. This effectively transfers expert knowledge to the preoperative setting, unlocking the value of historical post-operative data to guide the diagnosis of new patients without requiring text at inference. --- ### RePose: A Real-Time 3D Human Pose Estimation and Biomechanical Analysis Framework for Rehabilitation Authors: Junxiao Xue, Pavel Smirnov, Ziao Li, Yunyun Shi, Shi Chen, Xinyi Yin, Xiaohan Yue, Lei Wang, Yiduo Wang, Feng Lin, Yijia Chen, Xiao Ma et al. Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00625v1 We propose a real-time 3D human pose estimation and motion analysis method termed RePose for rehabilitation training. It is capable of real-time monitoring and evaluation of patients'motion during rehabilitation, providing immediate feedback and guidance to assist patients in executing rehabilitation exercises correctly. Firstly, we introduce a unified pipeline for end-to-end real-time human pose estimation and motion analysis using RGB video input from multiple cameras which can be applied to the field of rehabilitation training. The pipeline can help to monitor and correct patients'actions, thus aiding them in regaining muscle strength and motor functions. Secondly, we propose a fast tracking method for medical rehabilitation scenarios with multiple-person interference, which requires less than 1ms for tracking for a single frame. Additionally, we modify SmoothNet for real-time posture estimation, effectively reducing pose estimation errors and restoring the patient's true motion state, making it visually smoother. Finally, we use Unity platform for real-time monitoring and evaluation of patients' motion during rehabilitation, and to display the muscle stress conditions to assist patients with their rehabilitation training. --- ### Do Chatbot LLMs Talk Too Much? The YapBench Benchmark Authors: Vadim Borisov, Michael Gröger, Mina Mikhael, Richard H. Schreiber Published: 2026-01-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00624v1 Large Language Models (LLMs) such as ChatGPT, Claude, and Gemini increasingly act as general-purpose copilots, yet they often respond with unnecessary length on simple requests, adding redundant explanations, hedging, or boilerplate that increases cognitive load and inflates token-based inference cost. Prior work suggests that preference-based post-training and LLM-judged evaluations can induce systematic length bias, where longer answers are rewarded even at comparable quality. We introduce YapBench, a lightweight benchmark for quantifying user-visible over-generation on brevity-ideal prompts. Each item consists of a single-turn prompt, a curated minimal-sufficient baseline answer, and a category label. Our primary metric, YapScore, measures excess response length beyond the baseline in characters, enabling comparisons across models without relying on any specific tokenizer. We summarize model performance via the YapIndex, a uniformly weighted average of category-level median YapScores. YapBench contains over three hundred English prompts spanning three common brevity-ideal settings: (A) minimal or ambiguous inputs where the ideal behavior is a short clarification, (B) closed-form factual questions with short stable answers, and (C) one-line coding tasks where a single command or snippet suffices. Evaluating 76 assistant LLMs, we observe an order-of-magnitude spread in median excess length and distinct category-specific failure modes, including vacuum-filling on ambiguous inputs and explanation or formatting overhead on one-line technical requests. We release the benchmark and maintain a live leaderboard for tracking verbosity behavior over time. --- ### DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations Authors: Longtian Qiu, Shan Ning, Chuyu Zhang, Jiaxuan Sun, Xuming He Published: 2026-01-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.00623v1 Direct Preference Optimization (DPO) has shown strong potential for mitigating hallucinations in Multimodal Large Language Models (MLLMs). However, existing multimodal DPO approaches often suffer from overfitting due to the difficulty imbalance in preference data. Our analysis shows that MLLMs tend to overemphasize easily distinguishable preference pairs, which hinders fine-grained hallucination suppression and degrades overall performance. To address this issue, we propose Difficulty-Aware Direct Preference Optimization (DA-DPO), a cost-effective framework designed to balance the learning process. DA-DPO consists of two main components: (1) Difficulty Estimation leverages pre-trained vision--language models with complementary generative and contrastive objectives, whose outputs are integrated via a distribution-aware voting strategy to produce robust difficulty scores without additional training; and (2) Difficulty-Aware Training reweights preference pairs based on their estimated difficulty, down-weighting easy samples while emphasizing harder ones to alleviate overfitting. This framework enables more effective preference optimization by prioritizing challenging examples, without requiring new data or extra fine-tuning stages. Extensive experiments demonstrate that DA-DPO consistently improves multimodal preference optimization, yielding stronger robustness to hallucinations and better generalization across standard benchmarks, while remaining computationally efficient. The project page is available at https://artanic30.github.io/project_pages/DA-DPO/. --- ### Noise-Robust Tiny Object Localization with Flows Authors: Huixin Sun, Linlin Yang, Ronyu Chen, Kerui Gu, Baochang Zhang, Angela Yao, Xianbin Cao Published: 2026-01-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.00617v1 Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects are highly sensitive to annotation noise, where optimizing strict localization objectives risks noise overfitting. To address this, we propose Tiny Object Localization with Flows (TOLF), a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization. Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision. An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training. Extensive experiments across three datasets validate our approach's effectiveness. Especially, TOLF boosts the DINO baseline by 1.2% AP on the AI-TOD dataset. --- ### Integrating Multi-Armed Bandit, Active Learning, and Distributed Computing for Scalable Optimization Authors: Foo Hui-Mean, Yuan-chin Ivan Chang Published: 2026-01-02 Categories: stat.CO, stat.ML arXiv: https://arxiv.org/abs/2601.00615v1 Modern optimization problems in scientific and engineering domains often rely on expensive black-box evaluations, such as those arising in physical simulations or deep learning pipelines, where gradient information is unavailable or unreliable. In these settings, conventional optimization methods quickly become impractical due to prohibitive computational costs and poor scalability. We propose ALMAB-DC, a unified and modular framework for scalable black-box optimization that integrates active learning, multi-armed bandits, and distributed computing, with optional GPU acceleration. The framework leverages surrogate modeling and information-theoretic acquisition functions to guide informative sample selection, while bandit-based controllers dynamically allocate computational resources across candidate evaluations in a statistically principled manner. These decisions are executed asynchronously within a distributed multi-agent system, enabling high-throughput parallel evaluation. We establish theoretical regret bounds for both UCB-based and Thompson-sampling-based variants and develop a scalability analysis grounded in Amdahl's and Gustafson's laws. Empirical results across synthetic benchmarks, reinforcement learning tasks, and scientific simulation problems demonstrate that ALMAB-DC consistently outperforms state-of-the-art black-box optimizers. By design, ALMAB-DC is modular, uncertainty-aware, and extensible, making it particularly well suited for high-dimensional, resource-intensive optimization challenges. --- ### Stronger Approximation Guarantees for Non-Monotone γ-Weakly DR-Submodular Maximization Authors: Hareshkumar Jadav, Ranveer Singh, Vaneet Aggarwal Published: 2026-01-02 Categories: cs.LG, cs.AI, cs.CC, math.OC arXiv: https://arxiv.org/abs/2601.00611v1 Maximizing submodular objectives under constraints is a fundamental problem in machine learning and optimization. We study the maximization of a nonnegative, non-monotone $γ$-weakly DR-submodular function over a down-closed convex body. Our main result is an approximation algorithm whose guarantee depends smoothly on $γ$; in particular, when $γ=1$ (the DR-submodular case) our bound recovers the $0.401$ approximation factor, while for $γ<1$ the guarantee degrades gracefully and, it improves upon previously reported bounds for $γ$-weakly DR-submodular maximization under the same constraints. Our approach combines a Frank-Wolfe-guided continuous-greedy framework with a $γ$-aware double-greedy step, yielding a simple yet effective procedure for handling non-monotonicity. This results in state-of-the-art guarantees for non-monotone $γ$-weakly DR-submodular maximization over down-closed convex bodies. --- ### Traffic-Aware Optimal Taxi Placement Using Graph Neural Network-Based Reinforcement Learning Authors: Sonia Khetarpaul, P Y Sharan Published: 2026-01-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00607v1 In the context of smart city transportation, efficient matching of taxi supply with passenger demand requires real-time integration of urban traffic network data and mobility patterns. Conventional taxi hotspot prediction models often rely solely on historical demand, overlooking dynamic influences such as traffic congestion, road incidents, and public events. This paper presents a traffic-aware, graph-based reinforcement learning (RL) framework for optimal taxi placement in metropolitan environments. The urban road network is modeled as a graph where intersections represent nodes, road segments serve as edges, and node attributes capture historical demand, event proximity, and real-time congestion scores obtained from live traffic APIs. Graph Neural Network (GNN) embeddings are employed to encode spatial-temporal dependencies within the traffic network, which are then used by a Q-learning agent to recommend optimal taxi hotspots. The reward mechanism jointly optimizes passenger waiting time, driver travel distance, and congestion avoidance. Experiments on a simulated Delhi taxi dataset, generated using real geospatial boundaries and historic ride-hailing request patterns, demonstrate that the proposed model reduced passenger waiting time by about 56% and reduced travel distance by 38% compared to baseline stochastic selection. The proposed approach is adaptable to multi-modal transport systems and can be integrated into smart city platforms for real-time urban mobility optimization. --- ### Cycling Race Time Prediction: A Personalized Machine Learning Approach Using Route Topology and Training Load Authors: Francisco Aguilera Moreno Published: 2026-01-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00604v2 Predicting cycling duration for a given route is essential for training planning and event preparation. Existing solutions rely on physics-based models that require extensive parameterization, including aerodynamic drag coefficients and real-time wind forecasts, parameters impractical for most amateur cyclists. This work presents a machine learning approach that predicts ride duration using route topology features combined with the athlete's current fitness state derived from training load metrics. The model learns athlete-specific performance patterns from historical data, substituting complex physical measurements with historical performance proxies. We evaluate the approach using a single-athlete dataset (N=96 rides) in an N-of-1 study design. After rigorous feature engineering to eliminate data leakage, we find that Lasso regression with Topology + Fitness features achieves MAE=6.60 minutes and R2=0.922. Notably, integrating fitness metrics (Chronic Training Load (CTL), Acute Training Load (ATL)) reduces error by 14% compared to topology alone (MAE=7.66 min), demonstrating that physiological state meaningfully constrains performance even in self-paced efforts. Progressive checkpoint predictions enable dynamic race planning as route difficulty becomes apparent. --- ### Cycling Race Time Prediction: A Personalized Machine Learning Approach Using Route Topology and Training Load Authors: Francisco Aguilera Moreno Published: 2026-01-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00604v1 Predicting cycling duration for a given route is essential for training planning and event preparation. Existing solutions rely on physics-based models that require extensive parameterization, including aerodynamic drag coefficients and real-time wind forecasts, parameters impractical for most amateur cyclists. This work presents a machine learning approach that predicts ride duration using route topology features combined with the athlete's current fitness state derived from training load metrics. The model learns athlete-specific performance patterns from historical data, substituting complex physical measurements with historical performance proxies. We evaluate the approach using a single-athlete dataset (N=96 rides) in an N-of-1 study design. After rigorous feature engineering to eliminate data leakage, we find that Lasso regression with Topology + Fitness features achieves MAE=6.60 minutes and R2=0.922. Notably, integrating fitness metrics (CTL, ATL) reduces error by 14% compared to topology alone (MAE=7.66 min), demonstrating that physiological state meaningfully constrains performance even in self-paced efforts. Progressive checkpoint predictions enable dynamic race planning as route difficulty becomes apparent. --- ### Modality Dominance-Aware Optimization for Embodied RGB-Infrared Perception Authors: Xianhui Liu, Siqi Jiang, Yi Xie, Yuqing Lin, Siao Liu Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00598v1 RGB-Infrared (RGB-IR) multimodal perception is fundamental to embodied multimedia systems operating in complex physical environments. Although recent cross-modal fusion methods have advanced RGB-IR detection, the optimization dynamics caused by asymmetric modality characteristics remain underexplored. In practice, disparities in information density and feature quality introduce persistent optimization bias, leading training to overemphasize a dominant modality and hindering effective fusion. To quantify this phenomenon, we propose the Modality Dominance Index (MDI), which measures modality dominance by jointly modeling feature entropy and gradient contribution. Based on MDI, we develop a Modality Dominance-Aware Cross-modal Learning (MDACL) framework that regulates cross-modal optimization. MDACL incorporates Hierarchical Cross-modal Guidance (HCG) to enhance feature alignment and Adversarial Equilibrium Regularization (AER) to balance optimization dynamics during fusion. Extensive experiments on three RGB-IR benchmarks demonstrate that MDACL effectively mitigates optimization bias and achieves SOTA performance. --- ### Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence Authors: Sumanth Balaji, Piyush Mishra, Aashraya Sachdeva, Suraj Agrawal Published: 2026-01-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.00596v1 Traditional customer support systems, such as Interactive Voice Response (IVR), rely on rigid scripts and lack the flexibility required for handling complex, policy-driven tasks. While large language model (LLM) agents offer a promising alternative, evaluating their ability to act in accordance with business rules and real-world support workflows remains an open challenge. Existing benchmarks primarily focus on tool usage or task completion, overlooking an agent's capacity to adhere to multi-step policies, navigate task dependencies, and remain robust to unpredictable user or environment behavior. In this work, we introduce JourneyBench, a benchmark designed to assess policy-aware agents in customer support. JourneyBench leverages graph representations to generate diverse, realistic support scenarios and proposes the User Journey Coverage Score, a novel metric to measure policy adherence. We evaluate multiple state-of-the-art LLMs using two agent designs: a Static-Prompt Agent (SPA) and a Dynamic-Prompt Agent (DPA) that explicitly models policy control. Across 703 conversations in three domains, we show that DPA significantly boosts policy adherence, even allowing smaller models like GPT-4o-mini to outperform more capable ones like GPT-4o. Our findings demonstrate the importance of structured orchestration and establish JourneyBench as a critical resource to advance AI-driven customer support beyond IVR-era limitations. --- ### Uncertainty-Adjusted Sorting for Asset Pricing with Machine Learning Authors: Yan Liu, Ye Luo, Zigan Wang, Xiaowei Zhang Published: 2026-01-02 Categories: q-fin.PM, stat.ML arXiv: https://arxiv.org/abs/2601.00593v1 Machine learning is central to empirical asset pricing, but portfolio construction still relies on point predictions and largely ignores asset-specific estimation uncertainty. We propose a simple change: sort assets using uncertainty-adjusted prediction bounds instead of point predictions alone. Across a broad set of ML models and a U.S. equity panel, this approach improves portfolio performance relative to point-prediction sorting. These gains persist even when bounds are built from partial or misspecified uncertainty information. They arise mainly from reduced volatility and are strongest for flexible machine learning models. Identification and robustness exercises show that these improvements are driven by asset-level rather than time or aggregate predictive uncertainty. --- ### SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation Authors: Yiling Wang, Zeyu Zhang, Yiran Wang, Hao Tang Published: 2026-01-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00590v1 Text-to-motion (T2M) generation with diffusion backbones achieves strong realism and alignment. Safety concerns in T2M methods have been raised in recent years; existing methods replace discrete VQ-VAE codebook entries to steer the model away from unsafe behaviors. However, discrete codebook replacement-based methods have two critical flaws: firstly, replacing codebook entries which are reused by benign prompts leads to drifts on everyday tasks, degrading the model's benign performance; secondly, discrete token-based methods introduce quantization and smoothness loss, resulting in artifacts and jerky transitions. Moreover, existing text-to-motion datasets naturally contain unsafe intents and corresponding motions, making them unsuitable for safety-driven machine learning. To address these challenges, we propose SafeMo, a trustworthy motion generative framework integrating Minimal Motion Unlearning (MMU), a two-stage machine unlearning strategy, enabling safe human motion generation in continuous space, preserving continuous kinematics without codebook loss and delivering strong safety-utility trade-offs compared to current baselines. Additionally, we present the first safe text-to-motion dataset SafeMoVAE-29K integrating rewritten safe text prompts and continuous refined motion for trustworthy human motion unlearning. Built upon DiP, SafeMo efficiently generates safe human motions with natural transitions. Experiments demonstrate effective unlearning performance of SafeMo by showing strengthened forgetting on unsafe prompts, reaching 2.5x and 14.4x higher forget-set FID on HumanML3D and Motion-X respectively, compared to the previous SOTA human motion unlearning method LCR, with benign performance on safe prompts being better or comparable. Code: https://github.com/AIGeeksGroup/SafeMo. Website: https://aigeeksgroup.github.io/SafeMo. --- ### CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns Authors: Zhenhong Zhou, Shilinlu Yan, Chuanpu Liu, Qiankun Li, Kun Wang, Zhigang Zeng Published: 2026-01-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.00588v2 Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese malicious queries typically conceal intent via homophones, pinyin, symbol-based splitting, and other Chinese-specific patterns. These Chinese-specific adversarial patterns create the safety evaluation gap that is not well captured by existing benchmarks focused on English. This gap is particularly concerning for lightweight models, which may be more vulnerable to such specific adversarial perturbations. To bridge this gap, we introduce the Chinese-Specific Safety Benchmark (CSSBench) that emphasizes these adversarial patterns and evaluates the safety of lightweight LLMs in Chinese. Our benchmark covers six domains that are common in real Chinese scenarios, including illegal activities and compliance, privacy leakage, health and medical misinformation, fraud and hate, adult content, and public and political safety, and organizes queries into multiple task types. We evaluate a set of popular lightweight LLMs and measure over-refusal behavior to assess safety-induced performance degradation. Our results show that the Chinese-specific adversarial pattern is a critical challenge for lightweight LLMs. This benchmark offers a comprehensive evaluation of LLM safety in Chinese, assisting robust deployments in practice. ---