# Research Papers — 2026-03 · bundle page 154 of 243 > Full-text markdown of papers #7651–7700 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/154 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/153.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/155.md) ### MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models Authors: Shengyuan Liu, Zanting Ye, Yunrui Lin, Chen Hu, Wanting Geng, Xu Han, Bulat Ibragimov, Yefeng Zheng, Yixuan Yuan Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11625v2 While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies. Current architectures typically suffer from massive anatomical redundancy due to the direct concatenation of consecutive 2D slices and lack the flexibility to handle heterogeneous information densities across different slices using fixed pruning ratios. To address these challenges, we propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework specifically designed for efficient 3D medical image understanding. MedPruner introduces a two-stage mechanism: an Inter-slice Anchor-based Filtering module to eliminate slice-level temporal redundancy, followed by a Dynamic Information Nucleus Selection strategy that achieves adaptive token-level compression by quantifying cumulative attention weights. Extensive experiments on three 3D medical benchmarks and across three diverse medical VLMs reveal massive token redundancy in existing architectures. Notably, MedPruner enables models such as MedGemma-1.5 to maintain or even exceed their original performance while retaining fewer than 5\% of visual tokens, thereby reducing visual-token overhead and validating the necessity of dynamic token selection for practical clinical deployment. Our code is available at https://github.com/CUHK-AIM-Group/MedPruner. --- ### The Density of Cross-Persistence Diagrams and Its Applications Authors: Alexander Mironenko, Evgeny. Burnaev, Serguei Barannikov Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11623v1 Topological Data Analysis (TDA) provides powerful tools to explore the shape and structure of data through topological features such as clusters, loops, and voids. Persistence diagrams are a cornerstone of TDA, capturing the evolution of these features across scales. While effective for analyzing individual manifolds, persistence diagrams do not account for interactions between pairs of them. Cross-persistence diagrams (cross-barcodes), introduced recently, address this limitation by characterizing relationships between topological features of two point clouds. In this work, we present the first systematic study of the density of cross-persistence diagrams. We prove its existence, establish theoretical foundations for its statistical use, and design the first machine learning framework for predicting cross-persistence density directly from point cloud coordinates and distance matrices. Our statistical approach enables the distinction of point clouds sampled from different manifolds by leveraging the linear characteristics of cross-persistence diagrams. Interestingly, we find that introducing noise can enhance our ability to distinguish point clouds, uncovering its novel utility in TDA applications. We demonstrate the effectiveness of our methods through experiments on diverse datasets, where our approach consistently outperforms existing techniques in density prediction and achieves superior results in point cloud distinction tasks. Our findings contribute to a broader understanding of cross-persistence diagrams and open new avenues for their application in data analysis, including potential insights into time-series domain tasks and the geometry of AI-generated texts. Our code is publicly available at https://github.com/Verdangeta/TDA_experiments --- ### Personalized Federated Learning via Gaussian Generative Modeling Authors: Peng Hu, Jianwei Ma Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11620v1 Federated learning has emerged as a paradigm to train models collaboratively on inherently distributed client data while safeguarding privacy. In this context, personalized federated learning tackles the challenge of data heterogeneity by equipping each client with a dedicated model. A prevalent strategy decouples the model into a shared feature extractor and a personalized classifier head, where the latter actively guides the representation learning. However, previous works have focused on classifier head-guided personalization, neglecting the potential personalized characteristics in the representation distribution. Building on this insight, we propose pFedGM, a method based on Gaussian generative modeling. The approach begins by training a Gaussian generator that models client heterogeneity via weighted re-sampling. A balance between global collaboration and personalization is then struck by employing a dual objective: a shared objective that maximizes inter-class distance across clients, and a local objective that minimizes intra-class distance within them. To achieve this, we decouple the conventional Gaussian classifier into a navigator for global optimization, and a statistic extractor for capturing distributional statistics. Inspired by the Kalman gain, the algorithm then employs a dual-scale fusion framework at global and local levels to equip each client with a personalized classifier head. In this framework, we model the global representation distribution as a prior and the client-specific data as the likelihood, enabling Bayesian inference for class probability estimation. The evaluation covers a comprehensive range of scenarios: heterogeneity in class counts, environmental corruption, and multiple benchmark datasets and configurations. pFedGM achieves superior or competitive performance compared to state-of-the-art methods. --- ### Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats Authors: Xinhao Deng, Yixiang Zhang, Jiaqing Wu, Jiaqi Bai, Sibo Yi, Zhuoheng Zou, Yue Xiao, Rennai Qiu, Jianan Ma, Jialuo Chen, Xiaohu Du, Xiaofang Yang et al. Published: 2026-03-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.11619v1 Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege execution capabilities substantially expand the system attack surface. In this paper, we present a comprehensive security threat analysis of OpenClaw. To structure our analysis, we introduce a five-layer lifecycle-oriented security framework that captures key stages of agent operation, i.e., initialization, input, inference, decision, and execution, and systematically examine compound threats across the agent's operational lifecycle, including indirect prompt injection, skill supply chain contamination, memory poisoning, and intent drift. Through detailed case studies on OpenClaw, we demonstrate the prevalence and severity of these threats and analyze the limitations of existing defenses. Our findings reveal critical weaknesses in current point-based defense mechanisms when addressing cross-temporal and multi-stage systemic risks, highlighting the need for holistic security architectures for autonomous LLM agents. Within this framework, we further examine representative defense strategies at each lifecycle stage, including plugin vetting frameworks, context-aware instruction filtering, memory integrity validation protocols, intent verification mechanisms, and capability enforcement architectures. --- ### Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild Authors: Jiin Im, Sisung Liu, Je Hyeong Hong Published: 2026-03-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.11618v2 Semantic correspondence is essential for handling diverse in-the-wild images lacking explicit correspondence annotations. While recent 2D foundation models offer powerful features, adapting them for unsupervised learning via nearest-neighbor pseudo-labels has key limitations: it operates locally, ignoring structural relationships, and consequently its reliance on 2D appearance fails to resolve geometric ambiguities arising from symmetries or repetitive features. In this work, we address this by reformulating pseudo-label generation as a Fused Gromov-Wasserstein (FGW) problem, which jointly optimizes inter-feature similarity and intra-structural consistency. Our framework, Shape-of-You (SoY), leverages a 3D foundation model to define this intra-structure in the geometric space, resolving abovementioned ambiguity. However, since FGW is a computationally prohibitive quadratic problem, we approximate it through anchor-based linearization. The resulting probabilistic transport plan provides a structurally consistent but noisy supervisory signal. Thus, we introduce a soft-target loss dynamically blending guidance from this plan with network predictions to build a learning framework robust to this noise. SoY achieves state-of-the-art performance on SPair-71k and AP-10k datasets, establishing a new benchmark in semantic correspondence without explicit geometric annotations. Code is available at Shape-of-You. --- ### Noise-aware few-shot learning through bi-directional multi-view prompt alignment Authors: Lu Niu, Cheng Xue Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11617v1 Vision-language models offer strong few-shot capability through prompt tuning but remain vulnerable to noisy labels, which can corrupt prompts and degrade cross-modal alignment. Existing approaches struggle because they often lack the ability to model fine-grained semantic cues and to adaptively separate clean from noisy signals. To address these challenges, we propose NA-MVP, a framework for Noise-Aware few-shot learning through bi-directional Multi-View Prompt alignment. NA-MVP is built upon a key conceptual shift: robust prompt learning requires moving from global matching to region-aware alignment that explicitly distinguishes clean cues from noisy ones. To realize this, NA-MVP employs (1) multi-view prompts combined with unbalanced optimal transport to achieve fine-grained patch-to-prompt correspondence while suppressing unreliable regions; (2) a bi-directional prompt design that captures complementary clean-oriented and noise-aware cues, enabling the model to focus on stable semantics; and (3) an alignment-guided selective refinement strategy that uses optimal transport to correct only mislabeled samples while retaining reliable data. Experiments on synthetic and real-world noisy benchmarks demonstrate that NA-MVP consistently outperforms state-of-the-art baselines, confirming its effectiveness in enabling robust few-shot learning under noisy supervision. --- ### SemiTooth: a Generalizable Semi-supervised Framework for Multi-Source Tooth Segmentation Authors: Muyi Sun, Yifan Gao, Ziang Jia, Xingqun Qi, Qianli Zhang, Qian Liu, Tianzheng Deng Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11616v1 With the rapid advancement of artificial intelligence, intelligent dentistry for clinical diagnosis and treatment has become increasingly promising. As the primary clinical dentistry task, tooth structure segmentation for Cone-Beam Computed Tomography (CBCT) has made significant progress in recent years. However, challenges arise from the obtainment difficulty of full-annotated data, and the acquisition variability of multi-source data across different institutions, which have caused low-quality utilization, voxel-level inconsistency, and domain-specific disparity in CBCT slices. Thus, the rational and efficient utilization of multi-source and unlabeled data represents a pivotal problem. In this paper, we propose SemiTooth, a generalizable semi-supervised framework for multi-source tooth segmentation. Specifically, we first compile MS3Toothset, Multi-Source Semi-Supervised Tooth DataSet for clinical dental CBCT, which contains data from three sources with different-level annotations. Then, we design a multi-teacher and multi-student framework, i.e., SemiTooth, which promotes semi-supervised learning for multi-source data. SemiTooth employs distinct student networks that learn from unlabeled data with different sources, supervised by its respective teachers. Furthermore, a Stricter Weighted-Confidence Constraint is introduced for multiple teachers to improve the multi-source accuracy.Extensive experiments are conducted on MS3Toothset to verify the feasibility and superiority of the SemiTooth framework, which achieves SOTA performance on the semi-supervised and multi-source tooth segmentation scenario. --- ### Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE Authors: Mohammad Aflah Khan, Krishna P. Gummadi, Manish Gupta, Abhilasha Ravichander Published: 2026-03-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.11611v1 Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in specific layers, the effect of varying the fraction of hidden dimensions that receive rotary transformations remains largely unexplored. This design choice can yield substantial memory savings, which becomes especially significant at long context lengths. We find up to 10x memory savings over the standard RoPE cache, while achieving comparable final loss. In this work, we present a systematic study examining the impact of partial RoPE on training dynamics and convergence across architectures and datasets. Our findings uncover several notable patterns: (1) applying RoPE to only a small fraction of dimensions (around 10%) achieves convergence comparable to using full RoPE; (2) these trends hold consistently across model size, sequence lengths and datasets of varying quality and architectures, with higher-quality data resulting in lower overall loss and similar benchmark performance; and (3) some models trained with NoPE (No Positional Encoding) showcase unstable learning trajectories, which can be alleviated through minimal RoPE application or QK-Norm which converges to a higher loss. Together, these results offer practical guidance for model designers aiming to balance efficiency and training stability, while emphasizing the previously overlooked importance of partial RoPE. --- ### DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling Authors: Tong Zhao, Mingkun Lei, Liangyu Yuan, Yanming Yang, Chenxi Song, Yang Wang, Beier Zhu, Chi Zhang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11607v1 Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in multi-step ODE solvers has greatly improved efficiency by reusing historical gradients, but existing methods rely on handcrafted coefficients that fail to adapt to the non-stationary dynamics of diffusion sampling. To address this limitation, we propose Dynamic Gradient Weighting (DyWeight), a lightweight, learning-based multi-step solver that introduces a streamlined implicit coupling paradigm. By relaxing classical numerical constraints, DyWeight learns unconstrained time-varying parameters that adaptively aggregate historical gradients while intrinsically scaling the effective step size. This implicit time calibration accurately aligns the solver's numerical trajectory with the model's internal denoising dynamics under large integration steps, avoiding complex decoupled parameterizations and optimizations. Extensive experiments on CIFAR-10, FFHQ, AFHQv2, ImageNet64, LSUN-Bedroom, Stable Diffusion and FLUX.1-dev demonstrate that DyWeight achieves superior visual fidelity and stability with significantly fewer function evaluations, establishing a new state-of-the-art among efficient diffusion solvers. Code is available at https://github.com/Westlake-AGI-Lab/DyWeight --- ### Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints Authors: Lijun Guo, Haoyu Zhao, Xingyue Zhao, Rong Fu, Linghao Zhuang, Siteng Huang, Zhongyu Li, Hua Zou Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11606v2 Building high-fidelity digital twins of articulated objects from visual data remains a central challenge. Existing approaches depend on multi-view captures of the object in discrete, static states, which severely constrains their real-world scalability. In this paper, we introduce Articulat3D, a novel framework that constructs such digital twins from casually captured monocular videos by jointly enforcing explicit 3D geometric and motion constraints. We first propose Motion Prior-Driven Initialization, which leverages 3D point tracks to exploit the low-dimensional structure of articulated motion. By modeling scene dynamics with a compact set of motion bases, we facilitate soft decomposition of the scene into multiple rigidly moving groups. Building on this initialization, we introduce Geometric and Motion Constraints Refinement, which enforces physically plausible articulation through learnable kinematic primitives parameterized by a joint axis, a pivot point, and per-frame motion scalars, yielding reconstructions that are both geometrically accurate and temporally coherent. Extensive experiments demonstrate that Articulat3D achieves state-of-the-art performance on synthetic benchmarks and real-world casually captured monocular videos, significantly advancing the feasibility of digital twin creation under uncontrolled real-world conditions. Our project page is available at https://maxwell-zhao.github.io/Articulat3D/. --- ### LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference Authors: Junkun Jiang, Ho Yin Au, Jingyu Xiang, Jie Chen Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11605v1 Human motion is highly expressive and naturally aligned with language, yet prevailing methods relying heavily on joint text-motion embeddings struggle to synthesize temporally accurate, detailed motions and often lack explainability. To address these limitations, we introduce LabanLite, a motion representation developed by adapting and extending the Labanotation system. Unlike black-box text-motion embeddings, LabanLite encodes each atomic body-part action (e.g., a single left-foot step) as a discrete Laban symbol paired with a textual template. This abstraction decomposes complex motions into interpretable symbol sequences and body-part instructions, establishing a symbolic link between high-level language and low-level motion trajectories. Building on LabanLite, we present LaMoGen, a Text-to-LabanLite-to-Motion Generation framework that enables large language models (LLMs) to compose motion sequences through symbolic reasoning. The LLM interprets motion patterns, relates them to textual descriptions, and recombines symbols into executable plans, producing motions that are both interpretable and linguistically grounded. To support rigorous evaluation, we introduce a Labanotation-based benchmark with structured description-motion pairs and three metrics that jointly measure text-motion alignment across symbolic, temporal, and harmony dimensions. Experiments demonstrate that LaMoGen establishes a new baseline for both interpretability and controllability, outperforming prior methods on our benchmark and two public datasets. These results highlight the advantages of symbolic reasoning and agent-based design for language-driven motion synthesis. --- ### AutoScout: Structured Optimization for Automating ML System Configuration Authors: Jimmy Shong, Yuhan Ding, Yihan Jiang, Liheng Jing, Haonan Chen, Gaokai Zhang, Aditya Akella, Fan Lai Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11603v1 Machine learning (ML) systems expose a rapidly expanding configuration space spanning model-parallelism strategies, communication optimizations, and low-level runtime parameters. End-to-end system efficiency is highly sensitive to these choices, yet identifying high-performance configurations is challenging due to heterogeneous feature types (e.g., sparse and dense parameters), conditional dependencies (e.g., valid execution parameters only under specific upstream decisions), and the high search (profiling) cost. Existing approaches either optimize a narrow subset of configuration dimensions or rely on ad-hoc heuristics that fail to generalize as configuration spaces continue to grow. We present AutoScout, a general-purpose systems configurator for ML training, fine-tuning, and inference. It formulates the system configuration as a mixed-discrete/continuous optimization problem with hierarchical dependencies and introduces a hybrid optimization framework that jointly refines sparse structural decisions and dense execution parameters. To reduce profiling cost, AutoScout adaptively prioritizes high-impact configuration features and ensembles simulators with varying fidelity. Across diverse models, hardware platforms, and deployment objectives, AutoScout consistently identifies high-performance configurations, achieving 2.7-3.0$\times$ training speedup over expert-tuned settings. --- ### See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay Authors: Ashish Baghel, Paras Chopra Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11601v2 Vision-Language Models (VLMs) excel at describing visual scenes, yet struggle to translate perception into precise, grounded actions. We investigate whether providing VLMs with both the visual frame and the symbolic representation of the scene can improve their performance in interactive environments. We evaluate three state-of-the-art VLMs across Atari games, VizDoom, and AI2-THOR, comparing frame-only, frame with self-extracted symbols, frame with ground-truth symbols, and symbol-only pipelines. Our results indicate that all models benefit when the symbolic information is accurate. However, when VLMs extract symbols themselves, performance becomes dependent on model capability and scene complexity. We further investigate how accurately VLMs can extract symbolic information from visual inputs and how noise in these symbols affects decision-making and gameplay performance. Our findings reveal that symbolic grounding is beneficial in VLMs only when symbol extraction is reliable, and highlight perception quality as a central bottleneck for future VLM-based agents. --- ### Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization Authors: Qijun Liao, Jue Yang, Yiting Kang, Xinxin Zhao, Yong Zhang, Mingan Zhao Published: 2026-03-12 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2603.11600v2 Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven exploration ignores available physical structure. This paper proposes Hybrid Energy-Aware Reward Shaping (H-EARS), which encodes dominant energy terms -- assumed known a priori -- directly as reward potentials at O(n) per-step computation. H-EARS decomposes the shaping potential into task-oriented and energy-based components, supplemented by an action regularization term that deliberately modifies the optimization objective to enforce energy-efficient control. A complete theoretical foundation is established: functional independence of shaping and regularization, energy-based gradient enrichment under positive-definite Hessian conditions, convergence guarantees under function approximation, and approximate potential error bounds. Across four continuous control benchmarks and four baseline algorithms, H-EARS achieves consistent gains in convergence speed, policy stability, and final performance. High-fidelity vehicle simulations validate applicability in safety-critical settings under extreme road conditions. --- ### Survival Meets Classification: A Novel Framework for Early Risk Prediction Models of Chronic Diseases Authors: Shaheer Ahmad Khan, Muhammad Usamah Shahid, Muddassar Farooq Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.11598v1 Chronic diseases are long-lasting conditions that require lifelong medical attention. Using big EMR data, we have developed early disease risk prediction models for five common chronic diseases: diabetes, hypertension, CKD, COPD, and chronic ischemic heart disease. In this study, we present a novel approach for disease risk models by integrating survival analysis with classification techniques. Traditional models for predicting the risk of chronic diseases predominantly focus on either survival analysis or classification independently. In this paper, we show survival analysis methods can be re-engineered to enable them to do classification efficiently and effectively, thereby making them a comprehensive tool for developing disease risk surveillance models. The results of our experiments on real-world big EMR data show that the performance of survival models in terms of accuracy, F1 score, and AUROC is comparable to or better than that of prior state-of-the-art models like LightGBM and XGBoost. Lastly, the proposed survival models use a novel methodology to generate explanations, which have been clinically validated by a panel of three expert physicians. --- ### Performance Evaluation of Open-Source Large Language Models for Assisting Pathology Report Writing in Japanese Authors: Masataka Kawai, Singo Sakashita, Shumpei Ishikawa, Shogo Watanabe, Anna Matsuoka, Mikio Sakurai, Yasuto Fujimoto, Yoshiyuki Takahara, Atsushi Ohara, Hirohiko Miyake, Genichiro Ishii Published: 2026-03-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.11597v1 The performance of large language models (LLMs) for supporting pathology report writing in Japanese remains unexplored. We evaluated seven open-source LLMs from three perspectives: (A) generation and information extraction of pathology diagnosis text following predefined formats, (B) correction of typographical errors in Japanese pathology reports, and (C) subjective evaluation of model-generated explanatory text by pathologists and clinicians. Thinking models and medical-specialized models showed advantages in structured reporting tasks that required reasoning and in typo correction. In contrast, preferences for explanatory outputs varied substantially across raters. Although the utility of LLMs differed by task, our findings suggest that open-source LLMs can be useful for assisting Japanese pathology report writing in limited but clinically relevant scenarios. --- ### Leveraging Large Language Models and Survival Analysis for Early Prediction of Chemotherapy Outcomes Authors: Muhammad Faisal Shahid, Asad Afzal, Abdullah Faiz, Muhammad Siddiqui, Arbaz Khan Shehzad, Fatima Aftab, Muhammad Usamah Shahid, Muddassar Farooq Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.11594v1 Chemotherapy for cancer treatment is costly and accompanied by severe side effects, highlighting the critical need for early prediction of treatment outcomes to improve patient management and informed decision-making. Predictive models for chemotherapy outcomes using real-world data face challenges, including the absence of explicit phenotypes and treatment outcome labels such as cancer progression and toxicity. This study addresses these challenges by employing Large Language Models (LLMs) and ontology-based techniques for phenotypes and outcome label extraction from patient notes. We focused on one of the most frequently occurring cancers, breast cancer, due to its high prevalence and significant variability in patient response to treatment, making it a critical area for improving predictive modeling. The dataset included features such as vitals, demographics, staging, biomarkers, and performance scales. Drug regimens and their combinations were extracted from the chemotherapy plans in the EMR data and shortlisted based on NCCN guidelines, verified with NIH standards, and analyzed through survival modeling. The proposed approach significantly reduced phenotypes sparsity and improved predictive accuracy. Random Survival Forest was used to predict time-to-failure, achieving a C-index of 73%, and utilized as a classifier at a specific time point to predict treatment outcomes, with accuracy and F1 scores above 70%. The outcome probabilities were validated for reliability by calibration curves. We extended our approach to four other cancer types. This research highlights the potential of early prediction of treatment outcomes using LLM-based clinical data extraction enabling personalized treatment plans with better patient outcomes. --- ### WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing Authors: Hui Zhang, Juntao Liu, Zongkai Liu, Liqiang Niu, Fandong Meng, Zuxuan Wu, Yu-Gang Jiang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11593v2 Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional object- and style-centric manipulation, text-centric image editing focuses on modifying, translating, or rearranging textual elements embedded within images. However, existing leading models often struggle to execute complex text editing precisely, frequently producing blurry or hallucinated characters. We attribute these failures primarily to the lack of specialized training paradigms tailored for text-centric editing, as well as the absence of large-scale datasets and standardized benchmarks necessary for a closed-loop training and evaluation system. To address these limitations, we present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy. Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages, accompanied by standardized bilingual and multilingual benchmarks for comprehensive evaluation. On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation. Extensive experiments demonstrate that WeEdit outperforms previous open-source models by a clear margin across diverse editing operations. --- ### Toward Complex-Valued Neural Networks for Waveform Generation Authors: Hyung-Seok Oh, Deok-Hyeon Cho, Seung-Bin Kim, Seong-Whan Lee Published: 2026-03-12 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.11589v1 Neural vocoders have recently advanced waveform generation, yielding natural and expressive audio. Among these approaches, iSTFT-based vocoders have recently gained attention. They predict a complex-valued spectrogram and then synthesize the waveform via iSTFT, thereby avoiding learned upsampling stages that can increase computational cost. However, current approaches use real-valued networks that process the real and imaginary parts independently. This separation limits their ability to capture the inherent structure of complex spectrograms. We present ComVo, a Complex-valued neural Vocoder whose generator and discriminator use native complex arithmetic. This enables an adversarial training framework that provides structured feedback in complex-valued representations. To guide phase transformations in a structured manner, we introduce phase quantization, which discretizes phase values and regularizes the training process. Finally, we propose a block-matrix computation scheme to improve training efficiency by reducing redundant operations. Experiments demonstrate that ComVo achieves higher synthesis quality than comparable real-valued baselines, and that its block-matrix scheme reduces training time by 25%. Audio samples and code are available at https://hs-oh-prml.github.io/ComVo/. --- ### UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Tasks Authors: Ofir Marom Published: 2026-03-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.11583v4 The success of a Large Language Model (LLM) task depends heavily on its prompt. Most use-cases specify prompts using natural language, which is inherently ambiguous when multiple objectives must be simultaneously satisfied. In this paper we introduce UtilityMax Prompting, a framework that specifies tasks using formal mathematical language. We reconstruct the task as an influence diagram in which the LLM's answer is the sole decision variable. A utility function is defined over the conditional probability distributions within the diagram, and the LLM is instructed to find the answer that maximises expected utility. This constrains the LLM to reason explicitly about each component of the objective, directing its output toward a precise optimization target rather than a subjective natural language interpretation. We validate our approach on the MovieLens 1M dataset across three frontier models (Claude Sonnet 4.6, GPT-5.4, and Gemini 2.5 Pro), demonstrating consistent improvements in precision and Normalized Discounted Cumulative Gain (NDCG) over natural language baselines in a multi-objective movie recommendation task. --- ### Streaming Translation and Transcription Through Speech-to-Text Causal Alignment Authors: Roman Koshkin, Jeon Haesung, Lianbo Liu, Hao Shi, Mengjie Zhao, Yusuke Fujita, Yui Sudo Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11578v2 Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, end-to-end model for simultaneous speech-to-text translation and streaming transcription. We also introduce Decoder Time Dilation, a mechanism that counteracts the overrepresentation of WAIT tokens in training. We present a supervised fine-tuning strategy that trains the model to recover from delays, significantly improving the quality-latency trade-off. Despite its modest size, Hikari delivers competitive translation quality at consistently low latency, comparing favorably with published IWSLT 2026 submissions up to 38x larger and with proprietary API systems across en-ja, en-de, and en-ru. We release our model weights and code to facilitate further research. --- ### Streaming Translation and Transcription Through Speech-to-Text Causal Alignment Authors: Roman Koshkin, Jeon Haesung, Lianbo Liu, Hao Shi, Mengjie Zhao, Yusuke Fujita, Yui Sudo Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11578v1 Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end model that performs simultaneous speech-to-text translation and streaming transcription by encoding READ/WRITE decisions into a probabilistic WAIT token mechanism. We also introduce Decoder Time Dilation, a mechanism that reduces autoregressive overhead and ensures a balanced training distribution. Additionally, we present a supervised fine-tuning strategy that trains the model to recover from delays, significantly improving the quality-latency trade-off. Evaluated on English-to-Japanese, German, and Russian, Hikari achieves new state-of-the-art BLEU scores in both low- and high-latency regimes, outperforming recent baselines. --- ### R4Det: 4D Radar-Camera Fusion for High-Performance 3D Object Detection Authors: Zhongyu Xia, Yousen Tang, Yongtao Wang, Zhifeng Wang, Weijun Qin Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11566v2 4D radar-camera sensing configuration has gained increasing importance in autonomous driving. However, existing 3D object detection methods that fuse 4D Radar and camera data confront several challenges. First, their absolute depth estimation module is not robust and accurate enough, leading to inaccurate 3D localization. Second, the performance of their temporal fusion module will degrade dramatically or even fail when the ego vehicle's pose is missing or inaccurate. Third, for some small objects, the sparse radar point clouds may completely fail to reflect from their surfaces. In such cases, detection must rely solely on visual unimodal priors. To address these limitations, we propose R4Det, which enhances depth estimation quality via the Panoramic Depth Fusion module, enabling mutual reinforcement between absolute and relative depth. For temporal fusion, we design a Deformable Gated Temporal Fusion module that does not rely on the ego vehicle's pose. In addition, we built an Instance-Guided Dynamic Refinement module that extracts semantic prototypes from 2D instance guidance. Experiments show that R4Det achieves state-of-the-art 3D object detection results on the TJ4DRadSet and VoD datasets. The source code and models will be released at https://github.com/VDIGPKU/R4Det. --- ### CAETC: Causal Autoencoding and Treatment Conditioning for Counterfactual Estimation over Time Authors: Nghia D. Nguyen, Pablo Robles-Granda, Lav R. Varshney Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11565v1 Counterfactual estimation over time is important in various applications, such as personalized medicine. However, time-dependent confounding bias in observational data still poses a significant challenge in achieving accurate and efficient estimation. We introduce causal autoencoding and treatment conditioning (CAETC), a novel method for this problem. Built on adversarial representation learning, our method leverages an autoencoding architecture to learn a partially invertible and treatment-invariant representation, where the outcome prediction task is cast as applying a treatment-specific conditioning on the representation. Our design is independent of the underlying sequence model and can be applied to existing architectures such as long short-term memories (LSTMs) or temporal convolution networks (TCNs). We conduct extensive experiments on synthetic, semi-synthetic, and real-world data to demonstrate that CAETC yields significant improvement in counterfactual estimation over existing methods. --- ### Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries Authors: Zhenxu Tian, Yi Su, Juntao Li, Min Zhang Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.11564v1 The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV cache compression methods typically rely on input-side attention patterns within a prompt observation window to estimate token importance during the prefill stage. They fail to preserve critical tokens for future generation since these assessments are not derived from the decoding process. Intuitively, an effective observation window should mirror the decoding-stage queries to accurately reflect which tokens the generation process will attend to. However, ground-truth decoding queries are inherently unavailable during inference. For constructing pseudo queries to approximate them, we find that positional information plays a more critical role than semantic content. Motivated by this insight, we propose decoding-aligned KV cache compression via position-aware pseudo queries (DapQ), a novel and lightweight eviction framework that leverages position-aware pseudo queries to simulate the output tokens, thereby establishing an effective observation window for importance assessment. It aligns closely with the actual generation context and enables precise token eviction. Extensive evaluations across multiple benchmarks and LLMs demonstrate that DapQ achieves superior performance, particularly under strict memory constraints (e.g., up to nearly lossless performance 99.5% on NIAH with 3% KV cache budgets). --- ### SVLL: Staged Vision-Language Learning for Physically Grounded Embodied Task Planning Authors: Yuyuan Yang, Junkun Hong, Hongrong Wang, Honghao Cai, Xunpeng Ren, Ge Wang, Mingcong Lei, Shenhao Yan, Jiahao Yang, Chengsi Yao, Xi Li, Yiming Zhao et al. Published: 2026-03-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.11563v1 Embodied task planning demands vision-language models to generate action sequences that are both visually grounded and causally coherent over time. However, existing training paradigms face a critical trade-off: joint end-to-end training often leads to premature temporal binding, while standard reinforcement learning methods suffer from optimization instability. To bridge this gap, we present Staged Vision-Language Learning (SVLL), a unified three-stage framework for robust, physically-grounded embodied planning. In the first two stages, SVLL decouples spatial grounding from temporal reasoning, establishing robust visual dependency before introducing sequential action history. In the final stage, we identify a key limitation of standard Direct Preference Optimization (DPO), its purely relative nature -- optimizing only the preference gap between winning and losing trajectories while neglecting absolute likelihood constraints on optimal path, often yields unsafe or hallucinated behaviors. To address this, we further introduce Bias-DPO, a novel alignment objective that injects an inductive bias toward expert trajectories by explicitly maximizing likelihood on ground-truth actions while penalizing overconfident hallucinations. By anchoring the policy to the expert manifold and mitigating causal misalignment, SVLL, powered by Bias-DPO, ensures strict adherence to environmental affordances and effectively suppresses physically impossible shortcuts. Finally, extensive experiments on the interactive AI2-THOR benchmark and real-world robotic deployments demonstrate that SVLL outperforms both state-of-the-art open-source (e.g., Qwen2.5-VL-7B) and closed-source models (e.g., GPT-4o, Gemini-2.0-flash) in task success rate, while significantly reducing physical constraint violations. --- ### Feedback-Coupled Memory Systems: A Dynamical Model for Adaptive Coordination Authors: Stefano Grassi Published: 2026-03-12 Categories: cs.MA, cs.AI, econ.TH, math.DS arXiv: https://arxiv.org/abs/2603.11560v3 This paper develops a dynamical framework for adaptive coordination in systems of interacting agents referred to here as Feedback-Coupled Memory Systems (FCMS). Instead of framing coordination as equilibrium optimization or agent-centric learning, the model describes a closed-loop interaction between agents, incentives, and a persistent environment. The environment stores accumulated coordination signals, a distributed incentive field transmits them locally, and agents update in response, generating a feedback-driven dynamical system. Three main results are established. First, under dissipativity, the closed-loop system admits a bounded forward-invariant region, ensuring dynamical viability independently of global optimality. Second, when incentives depend on persistent environmental memory, coordination cannot be reduced to a static optimization problem. Third, within the FCMS class, coordination requires a bidirectional coupling in which memory-dependent incentives influence agent updates, while agent behavior reshapes the environmental state. Numerical analysis of a minimal specification identifies a Neimark-Sacker bifurcation at a critical coupling threshold ($β_c$), providing a stability boundary for the system. Near the bifurcation threshold, recovery time diverges and variance increases, yielding a computable early warning signature of coordination breakdown in observable time series. Additional simulations confirm robustness under nonlinear saturation and scalability to populations of up to $N = 10^{6}$ agents making it more relevant for real-world applications. The proposed framework offers a dynamical perspective on coordination in complex systems, with potential extensions to multi-agent systems, networked interactions, and macro-level collective dynamics. --- ### AI Knows What's Wrong But Cannot Fix It: Helicoid Dynamics in Frontier LLMs Under High-Stakes Decisions Authors: Alejandro R Jadad Published: 2026-03-12 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.11559v1 Large language models perform reliably when their outputs can be checked: solving equations, writing code, retrieving facts. They perform differently when checking is impossible, as when a clinician chooses an irreversible treatment on incomplete data, or an investor commits capital under fundamental uncertainty. Helicoid dynamics is the name given to a specific failure regime in that second domain: a system engages competently, drifts into error, accurately names what went wrong, then reproduces the same pattern at a higher level of sophistication, recognizing it is looping and continuing nonetheless. This prospective case series documents that regime across seven leading systems (Claude, ChatGPT, Gemini, Grok, DeepSeek, Perplexity, Llama families), tested across clinical diagnosis, investment evaluation, and high-consequence interview scenarios. Despite explicit protocols designed to sustain rigorous partnership, all exhibited the pattern. When confronted with it, they attributed its persistence to structural factors in their training, beyond what conversation can reach. Under high stakes, when being rigorous and being comfortable diverge, these systems tend toward comfort, becoming less reliable precisely when reliability matters most. Twelve testable hypotheses are proposed, with implications for agentic AI oversight and human-AI collaboration. The helicoid is tractable. Identifying it, naming it, and understanding its boundary conditions are the necessary first steps toward LLMs that remain trustworthy partners precisely when the decisions are hardest and the stakes are highest. --- ### RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks Authors: Ruiying Li, Yunlang Zhou, YuYao Zhu, Kylin Chen, Jingyuan Wang, Sukai Wang, Kongtao Hu, Minhui Yu, Bowen Jiang, Zhan Su, Jiayao Ma, Xin He et al. Published: 2026-03-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.11558v3 Vision-Language-Action (VLA) systems have shown strong potential for language-driven robotic manipulation. However, scaling them to long-horizon tasks remains challenging. Existing pipelines typically separate data collection, policy learning, and deployment, resulting in heavy reliance on manual environment resets and brittle multi-policy execution. We present RoboClaw, an agentic robotics framework that unifies data collection, policy learning, and task execution under a single VLM-driven controller. At the policy level, RoboClaw introduces Entangled Action Pairs (EAP), which couple forward manipulation behaviors with inverse recovery actions to form self-resetting loops for autonomous data collection. This mechanism enables continuous on-policy data acquisition and iterative policy refinement with minimal human intervention. During deployment, the same agent performs high-level reasoning and dynamically orchestrates learned policy primitives to accomplish long-horizon tasks. By maintaining consistent contextual semantics across collection and execution, RoboClaw reduces mismatch between the two phases and improves multi-policy robustness. Experiments in real-world manipulation tasks demonstrate improved stability and scalability compared to conventional open-loop pipelines, while significantly reducing human effort throughout the robot lifecycle, achieving a 25% improvement in success rate over baseline methods on long-horizon tasks and reducing human time investment by 53.7%. --- ### TornadoNet: Real-Time Building Damage Detection with Ordinal Supervision Authors: Robinson Umeike, Cuong Pham, Ryan Hausen, Thang Dao, Shane Crawford, Tanya Brown-Giammanco, Gerard Lemson, John van de Lindt, Blythe Johnston, Arik Mitschang, Trung Do Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11557v1 We present TornadoNet, a comprehensive benchmark for automated street-level building damage assessment evaluating how modern real-time object detection architectures and ordinal-aware supervision strategies perform under realistic post-disaster conditions. TornadoNet provides the first controlled benchmark demonstrating how architectural design and loss formulation jointly influence multi-level damage detection from street-view imagery, delivering methodological insights and deployable tools for disaster response. Using 3,333 high-resolution geotagged images and 8,890 annotated building instances from the 2021 Midwest tornado outbreak, we systematically compare CNN-based detectors from the YOLO family against transformer-based models (RT-DETR) for multi-level damage detection. Models are trained under standardized protocols using a five-level damage classification framework based on IN-CORE damage states, validated through expert cross-annotation. Baseline experiments reveal complementary architectural strengths. CNN-based YOLO models achieve highest detection accuracy and throughput, with larger variants reaching 46.05% mAP@0.5 at 66-276 FPS on A100 GPUs. Transformer-based RT-DETR models exhibit stronger ordinal consistency, achieving 88.13% Ordinal Top-1 Accuracy and MAOE of 0.65, indicating more reliable severity grading despite lower baseline mAP. To align supervision with the ordered nature of damage severity, we introduce soft ordinal classification targets and evaluate explicit ordinal-distance penalties. RT-DETR trained with calibrated ordinal supervision achieves 44.70% mAP@0.5, a 4.8 percentage-point improvement, with gains in ordinal metrics (91.15% Ordinal Top-1 Accuracy, MAOE = 0.56). These findings establish that ordinal-aware supervision improves damage severity estimation when aligned with detector architecture. Model & Data: https://github.com/crumeike/TornadoNet --- ### Enhancing Image Aesthetics with Dual-Conditioned Diffusion Models Guided by Multimodal Perception Authors: Xinyu Nan, Ning Wang, Yuyao Zhai, Mei Yang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11556v1 Image aesthetic enhancement aims to perceive aesthetic deficiencies in images and perform corresponding editing operations, which is highly challenging and requires the model to possess creativity and aesthetic perception capabilities. Although recent advancements in image editing models have significantly enhanced their controllability and flexibility, they struggle with enhancing image aesthetic. The primary challenges are twofold: first, following editing instructions with aesthetic perception is difficult, and second, there is a scarcity of "perfectly-paired" images that have consistent content but distinct aesthetic qualities. In this paper, we propose Dual-supervised Image Aesthetic Enhancement (DIAE), a diffusion-based generative model with multimodal aesthetic perception. First, DIAE incorporates Multimodal Aesthetic Perception (MAP) to convert the ambiguous aesthetic instruction into explicit guidance by (i) employing detailed, standardized aesthetic instructions across multiple aesthetic attributes, and (ii) utilizing multimodal control signals derived from text-image pairs that maintain consistency within the same aesthetic attribute. Second, to mitigate the lack of "perfectly-paired" images, we collect "imperfectly-paired" dataset called IIAEData, consisting of images with varying aesthetic qualities while sharing identical semantics. To better leverage the weak matching characteristics of IIAEData during training, a dual-branch supervision framework is also introduced for weakly supervised image aesthetic enhancement. Experimental results demonstrate that DIAE outperforms the baselines and obtains superior image aesthetic scores and image content consistency scores. --- ### MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks Authors: Lirong Che, Shuo Wen, Shan Huang, Chuang Wang, Yuzhe Yang, Gregory Dudek, Xueqian Wang, Jian Su Published: 2026-03-12 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.11554v1 Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning. --- ### Shadowless Projection Mapping for Tabletop Workspaces with Synthetic Aperture Projector Authors: Takahiro Okamoto, Masaki Takeuchi, Masataka Sawayama, Daisuke Iwai Published: 2026-03-12 Categories: cs.HC, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.11551v1 Projection mapping (PM) enables augmented reality (AR) experiences without requiring users to wear head-mounted displays and supports multi-user interaction. It is regarded as a promising technology for a variety of applications in which users interact with content superimposed onto augmented objects in tabletop workspaces, including remote collaboration, healthcare, industrial design, urban planning, artwork creation, and office work. However, conventional PM systems often suffer from projection shadows when users occlude the light path. Prior approaches employing multiple distributed projectors can compensate for occlusion, but suffer from latency due to computational processing, degrading the user experience. In this research, we introduce a synthetic-aperture PM system that uses a significantly larger number of projectors, arranged densely in the environment, to achieve delay-free, shadowless projection for tabletop workspaces without requiring computational compensation. To address spatial resolution degradation caused by subpixel misalignment among overlaid projections, we develop and validate an offline blur compensation method whose computation time remains independent of the number of projectors. Furthermore, we demonstrate that our shadowless PM plays a critical role in achieving a fundamental goal of PM: altering material properties without evoking projection-like impression. Specifically, we define this perceptual impression as ``sense of projection (SoP)'' and establish a PM design framework to minimize the SoP based on user studies. --- ### PCA-Enhanced Probabilistic U-Net for Effective Ambiguous Medical Image Segmentation Authors: Xiangyu Li, Chenglin Wang, Qiantong Shen, Fanding Li, Wei Wang, Kuanquan Wang, Yi Shen, Baochun Zhao, Gongning Luo Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11550v2 Ambiguous Medical Image Segmentation (AMIS) is significant to address the challenges of inherent uncertainties from image ambiguities, noise, and subjective annotations. Existing conditional variational autoencoder (cVAE)-based methods effectively capture uncertainty but face limitations including redundancy in high-dimensional latent spaces and limited expressiveness of single posterior networks. To overcome these issues, we introduce a novel PCA-Enhanced Probabilistic U-Net (PEP U-Net). Our method effectively incorporates Principal Component Analysis (PCA) for dimensionality reduction in the posterior network to mitigate redundancy and improve computational efficiency. Additionally, we further employ an inverse PCA operation to reconstruct critical information, enhancing the latent space's representational capacity. Compared to conventional generative models, our method preserves the ability to generate diverse segmentation hypotheses while achieving a superior balance between segmentation accuracy and predictive variability, thereby advancing the performance of generative modeling in medical image segmentation. --- ### Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports Authors: Liangkai Zhou, Susu Xu, Shuqi Zhong, Shan Lin Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11546v1 Many real-world machine learning tasks are anti-causal: they require inferring latent causes from observed effects. In practice, we often face multiple related tasks where part of the forward causal mechanism is invariant across tasks, while other components are task-specific. We propose Multi-Task Anti-Causal learning (MTAC), a framework for estimating causes from outcomes and confounders by explicitly exploiting such cross-task invariances. MTAC first performs causal discovery to learn a shared causal graph and then instantiates a structured multi-task structural equation model (SEM) that factorizes the outcome-generation process into (i) a task-invariant mechanism and (ii) task-specific mechanisms via a shared backbone with task-specific heads. Building on the learned forward model, MTAC performs maximum A posteriori (MAP)based inference to reconstruct causes by jointly optimizing latent mechanism variables and cause magnitudes under the learned causal structure. We evaluate MTAC on the application of urban event reconstruction from resident reports, spanning three tasks:parking violations, abandoned properties, and unsanitary conditions. On real-world data collected from Manhattan and the city of Newark, MTAC consistently improves reconstruction accuracy over strong baselines, achieving up to 34.61\% MAE reduction and demonstrating the benefit of learning transferable causal mechanisms across tasks. --- ### One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries Authors: Mayank Saini, Arit Kumar Bishwas Published: 2026-03-12 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.11545v2 We present an agentic AI framework for autonomous multimodal query processing that coordinates specialized tools across text, image, audio, video, and document modalities. A central Supervisor dynamically decomposes user queries, delegates subtasks to modality-appropriate tools (e.g., object detection, OCR, speech transcription), and synthesizes results through adaptive routing strategies rather than predetermined decision trees. For text-only queries, the framework uses learned routing via RouteLLM, while non-text paths use SLM-assisted modality decomposition. Evaluated on 2,847 queries across 15 task categories, our framework achieves 72% reduction in time-to-accurate-answer, 85% reduction in conversational rework, and 67% cost reduction compared to the matched hierarchical baseline while maintaining accuracy parity. These results demonstrate that intelligent centralized orchestration fundamentally improves multimodal AI deployment economics. --- ### Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting Authors: Tingxuan Huang, Haowei Zhu, Jun-hai Yong, Hao Pan, Bin Wang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11543v1 Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene modeling often rely on per-frame optimization, which can overfit to instantaneous states instead of capturing underlying motion dynamics. To address this, we present Mango-GS, a multi-frame, node-guided framework for high-fidelity 4D reconstruction. Mango-GS leverages a temporal Transformer to model motion dependencies within a short window of frames, producing temporally consistent deformations. For efficiency, temporal modeling is confined to a sparse set of control nodes. Each node is represented by a decoupled canonical position and a latent code, providing a stable semantic anchor for motion propagation and preventing correspondence drift under large motion. Our framework is trained end-to-end, enhanced by an input masking strategy and two multi-frame losses to improve robustness. Extensive experiments demonstrate that Mango-GS achieves state-of-the-art reconstruction quality and real-time rendering speed, enabling high-fidelity reconstruction and interactive rendering of dynamic scenes. --- ### ReHARK: Refined Hybrid Adaptive RBF Kernels for Robust One-Shot Vision-Language Adaptation Authors: Md Jahidul Islam Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11542v1 The adaptation of large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks with extremely limited data -- specifically in the one-shot regime -- is often hindered by a significant "Stability-Plasticity" dilemma. While efficient caching mechanisms have been introduced by training-free methods such as Tip-Adapter, these approaches often function as local Nadaraya-Watson estimators. Such estimators are characterized by inherent boundary bias and a lack of global structural regularization. In this paper, ReHARK (Refined Hybrid Adaptive RBF Kernels) is proposed as a synergistic training-free framework that reinterprets few-shot adaptation through global proximal regularization in a Reproducing Kernel Hilbert Space (RKHS). A multistage refinement pipeline is introduced, consisting of: (1) Hybrid Prior Construction, where zero-shot textual knowledge from CLIP and GPT-3 is fused with visual class prototypes to form a robust semantic-visual anchor; (2) Support Set Augmentation (Bridging), where intermediate samples are generated to smooth the transition between visual and textual modalities; (3) Adaptive Distribution Rectification, where test feature statistics are aligned with the augmented support set to mitigate domain shifts; and (4) Multi-Scale RBF Kernels, where an ensemble of kernels is employed to capture complex feature geometries across diverse scales. Superior stability and accuracy are demonstrated through extensive experiments on 11 diverse benchmarks. A new state-of-the-art for one-shot adaptation is established by ReHARK, which achieves an average accuracy of 65.83%, significantly outperforming existing baselines. Code is available at https://github.com/Jahid12012021/ReHARK. --- ### Quantum mechanical framework for quantization-based optimization: from Gradient flow to Schroedinger equation Authors: Jinwuk Seok, Changsik Cho Published: 2026-03-12 Categories: quant-ph, cs.NE, math.OC arXiv: https://arxiv.org/abs/2603.11536v1 This work presents a quantum mechanical framework for analyzing quantization-based optimization algorithms. The sampling process of the quantization-based search is modeled as a gradient-flow dissipative system, leading to a Hamilton-Jacobi-Bellman (HJB) representation. Through a suitable transformation of the objective function, this formulation yields the Schroedinger equation, which reveals that quantum tunneling enables escape from local minima and guarantees access to the global optimum. By establishing the connection to the Fokker-Planck equation, the framework provides a thermodynamic interpretation of global convergence. Such an analysis between the thermodynamic and the quantum dynamic methodology unifies combinatorial and continuous optimization, and extends naturally to machine learning tasks such as image classification. Numerical experiments demonstrate that quantization-based optimization consistently outperforms conventional algorithms across both combinatorial problems and nonconvex continuous functions. --- ### Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing Authors: Hanchi Sun, Yixin Liu, Yonghui Wu, Lichao Sun Published: 2026-03-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.11535v1 Token-choice Mixture-of-Experts (TC-MoE) routes each token to a fixed number of experts, limiting dynamic computation allocation and requiring auxiliary losses to maintain load balance. We propose Expert Threshold (ET) routing, where each expert maintains an exponential moving average (EMA) threshold estimated from the global token distribution. At both training and inference, each token is independently routed to an expert if its score exceeds the expert's threshold, enabling dynamic computation allocation while achieving load balance without auxiliary losses. This fully causal mechanism eliminates dependence on other tokens in the batch, making it well-suited for autoregressive language modeling. In pretraining experiments scaling to 2.4B parameters on FineWeb-Edu, ET achieves 0.067 lower cross-entropy loss than TC-MoE, equivalent to reaching the same performance with 1.6$\times$ fewer tokens. --- ### Risk-Controllable Multi-View Diffusion for Driving Scenario Generation Authors: Hongyi Lin, Wenxiu Shi, Heye Huang, Dingyi Zhuang, Song Zhang, Yang Liu, Xiaobo Qu, Jinhua Zhao Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11534v2 Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world data and difficult to specify through manual scenario design. Existing generative approaches typically treat risk as an after-the-fact label and struggle to maintain geometric consistency in multi-view driving scenes. We present RiskMV-DPO, a general and systematic pipeline for physically-informed, risk-controllable multi-view scenario generation. By integrating target risk levels with physically-grounded risk modeling, we synthesize diverse and high-stakes dynamic trajectories that serve as explicit geometric anchors for a diffusion-based video generator. To ensure spatial-temporal coherence and geometric fidelity, we introduce a geometry-appearance alignment module and a region-aware direct preference optimization (RA-DPO) strategy with motion-aware masking to focus learning on localized dynamic regions. Experiments on the nuScenes dataset show that RiskMV-DPO can freely generate a wide spectrum of diverse scenarios while maintaining visual quality, improving 3D detection mAP from 18.17 to 30.50 and reducing FID to 15.70. Our work shifts the role of world models from passive environment prediction to proactive, risk-controllable synthesis, providing a scalable toolchain for the development of embodied intelligence. --- ### Risk-Controllable Multi-View Diffusion for Driving Scenario Generation Authors: Hongyi Lin, Wenxiu Shi, Heye Huang, Dingyi Zhuang, Song Zhang, Yang Liu, Xiaobo Qu, Jinhua Zhao Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11534v1 Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world data and difficult to specify through manual scenario design. Existing generative approaches typically treat risk as an after-the-fact label and struggle to maintain geometric consistency in multi-view driving scenes. We present RiskMV-DPO, a general and systematic pipeline for physically-informed, risk-controllable multi-view scenario generation. By integrating target risk levels with physically-grounded risk modeling, we autonomously synthesize diverse and high-stakes dynamic trajectories that serve as explicit geometric anchors for a diffusion-based video generator. To ensure spatial-temporal coherence and geometric fidelity, we introduce a geometry-appearance alignment module and a region-aware direct preference optimization (RA-DPO) strategy with motion-aware masking to focus learning on localized dynamic regions.Experiments on the nuScenes dataset show that RiskMV-DPO can freely generate a wide spectrum of diverse long-tail scenarios while maintaining state-of-the-art visual quality, improving 3D detection mAP from 18.17 to 30.50 and reducing FID to 15.70. Our work shifts the role of world models from passive environment prediction to proactive, risk-controllable synthesis, providing a scalable toolchain for the safety-oriented development of embodied intelligence. --- ### Simultaneous estimation of multiple discrete unimodal distributions under stochastic order constraints Authors: Yasuhiro Yoshida, Noriyoshi Sukegawa, Jiro Iwanaga Published: 2026-03-12 Categories: math.OC, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.11532v2 We study the problem of estimating multiple discrete unimodal distributions, motivated by search behavior analysis on a real-world platform. To incorporate prior knowledge of precedence relations among distributions, we impose stochastic order constraints and formulate the estimation task as a mixed-integer convex quadratic optimization problem. Experiments on both synthetic and real datasets show that the proposed method reduces the Jensen-Shannon divergence by 2.2% on average (up to 6.3%) when the sample size is small, while performing comparably to existing methods when sufficient data are available. --- ### Mobile-GS: Real-time Gaussian Splatting for Mobile Devices Authors: Xiaobiao Du, Yida Wang, Kun Zhan, Xin Yu Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11531v1 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-quality rendering across a wide range of applications.However, its high computational demands and large storage costs pose significant challenges for deployment on mobile devices. In this work, we propose a mobile-tailored real-time Gaussian Splatting method, dubbed Mobile-GS, enabling efficient inference of Gaussian Splatting on edge devices. Specifically, we first identify alpha blending as the primary computational bottleneck, since it relies on the time-consuming Gaussian depth sorting process. To solve this issue, we propose a depth-aware order-independent rendering scheme that eliminates the need for sorting, thereby substantially accelerating rendering. Although this order-independent rendering improves rendering speed, it may introduce transparency artifacts in regions with overlapping geometry due to the scarcity of rendering order. To address this problem, we propose a neural view-dependent enhancement strategy, enabling more accurate modeling of view-dependent effects conditioned on viewing direction, 3D Gaussian geometry, and appearance attributes. In this way, Mobile-GS can achieve both high-quality and real-time rendering. Furthermore, to facilitate deployment on memory-constrained mobile platforms, we also introduce first-order spherical harmonics distillation, a neural vector quantization technique, and a contribution-based pruning strategy to reduce the number of Gaussian primitives and compress the 3D Gaussian representation with the assistance of neural networks. Extensive experiments demonstrate that our proposed Mobile-GS achieves real-time rendering and compact model size while preserving high visual quality, making it well-suited for mobile applications. --- ### CFD-HAR: User-controllable Privacy through Conditional Feature Disentanglement Authors: Alex Gn, Fan Li, S Kuniyilh, Ada Axan Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.11526v1 Modern wearable and mobile devices are equipped with inertial measurement units (IMUs). Human Activity Recognition (HAR) applications running on such devices use machine-learning-based, data-driven techniques that leverage such sensor data. However, sensor-data-driven HAR deployments face two critical challenges: protecting sensitive user information embedded in sensor data in accordance with users' privacy preferences and maintaining high recognition performance with limited labeled samples. This paper proposes a technique for user-controllable privacy through feature disentanglement-based representation learning at the granular level for dynamic privacy filtering. We also compare the efficacy of our technique against few-shot HAR using autoencoder-based representation learning. We analyze their architectural designs, learning objectives, privacy guarantees, data efficiency, and suitability for edge Internet of Things (IoT) deployment. Our study shows that CFD-based HAR provides explicit, tunable privacy protection controls by separating activity and sensitive attributes in the latent space, whereas autoencoder-based few-shot HAR offers superior label efficiency and lightweight adaptability but lacks inherent privacy safeguards. We further examine the security implications of both approaches in continual IoT settings, highlighting differences in susceptibility to representation leakage and embedding-level attacks. The analysis reveals that neither paradigm alone fully satisfies the emerging requirements of next-generation IoT HAR systems. We conclude by outlining research directions toward unified frameworks that jointly optimize privacy preservation, few-shot adaptability, and robustness for trustworthy IoT intelligence. --- ### MDS-VQA: Model-Informed Data Selection for Video Quality Assessment Authors: Jian Zou, Xiaoyu Xu, Zhihua Wang, Yilin Wang, Balu Adsumilli, Kede Ma Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.11525v1 Learning-based video quality assessment (VQA) has advanced rapidly, yet progress is increasingly constrained by a disconnect between model design and dataset curation. Model-centric approaches often iterate on fixed benchmarks, while data-centric efforts collect new human labels without systematically targeting the weaknesses of existing VQA models. Here, we describe MDS-VQA, a model-informed data selection mechanism for curating unlabeled videos that are both difficult for the base VQA model and diverse in content. Difficulty is estimated by a failure predictor trained with a ranking objective, and diversity is measured using deep semantic video features, with a greedy procedure balancing the two under a constrained labeling budget. Experiments across multiple VQA datasets and models demonstrate that MDS-VQA identifies diverse, challenging samples that are particularly informative for active fine-tuning. With only a 5% selected subset per target domain, the fine-tuned model improves mean SRCC from 0.651 to 0.722 and achieves the top gMAD rank, indicating strong adaptation and generalization. --- ### EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection Authors: Shuo Jiang, Gaojia Zhang, Min Tan, Yufei Yin, Gang Pan Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11521v2 Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and their surroundings, as well as the reliance on noisy pseudo-labels that hinder fine-grained texture learning. While existing refinement strategies aim to alleviate label noise, they often overlook intrinsic perceptual cues, leading to boundary overflow and structural ambiguity. In contrast, learning without pseudo-label guidance yields coarse features with significant detail loss. To address these issues, we propose a unified UCOD framework that enhances both the reliability of pseudo-labels and the fidelity of features. Our approach introduces the Multi-Cue Native Perception module, which extracts intrinsic visual priors by integrating low-level texture cues with mid-level semantics, enabling precise alignment between masks and native object information. Additionally, Pseudo-Label Evolution Fusion intelligently refines labels through teacher-student interaction and utilizes depthwise separable convolution for efficient semantic denoising. It also incorporates Spectral Tensor Attention Fusion to effectively balance semantic and structural information through compact spectral aggregation across multi-layer attention maps. Finally, Local Pseudo-Label Refinement plays a pivotal role in local detail optimization by leveraging attention diversity to restore fine textures and enhance boundary fidelity. Extensive experiments on multiple UCOD datasets demonstrate that our method achieves state-of-the-art performance, characterized by superior detail perception, robust boundary alignment, and strong generalization under complex camouflage scenarios. Code is available at https://github.com/JSLiam94/EReCu. --- ### EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection Authors: Shuo Jiang, Gaojia Zhang, Min Tan, Yufei Yin, Gang Pan Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11521v1 Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and their surroundings, as well as the reliance on noisy pseudo-labels that hinder fine-grained texture learning. While existing refinement strategies aim to alleviate label noise, they often overlook intrinsic perceptual cues, leading to boundary overflow and structural ambiguity. In contrast, learning without pseudo-label guidance yields coarse features with significant detail loss. To address these issues, we propose a unified UCOD framework that enhances both the reliability of pseudo-labels and the fidelity of features. Our approach introduces the Multi-Cue Native Perception module, which extracts intrinsic visual priors by integrating low-level texture cues with mid-level semantics, enabling precise alignment between masks and native object information. Additionally, Pseudo-Label Evolution Fusion intelligently refines labels through teacher-student interaction and utilizes depthwise separable convolution for efficient semantic denoising. It also incorporates Spectral Tensor Attention Fusion to effectively balance semantic and structural information through compact spectral aggregation across multi-layer attention maps. Finally, Local Pseudo-Label Refinement plays a pivotal role in local detail optimization by leveraging attention diversity to restore fine textures and enhance boundary fidelity. Extensive experiments on multiple UCOD datasets demonstrate that our method achieves state-of-the-art performance, characterized by superior detail perception, robust boundary alignment, and strong generalization under complex camouflage scenarios. --- ### FBCIR: Balancing Cross-Modal Focuses in Composed Image Retrieval Authors: Chenchen Zhao, Jianhuan Zhuo, Muxi Chen, Zhaohua Zhang, Wenyu Jiang, Tianwen Jiang, Qiuyong Xiao, Jihong Zhang, Qiang Xu Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.11520v1 Composed image retrieval (CIR) requires multi-modal models to jointly reason over visual content and semantic modifications presented in text-image input pairs. While current CIR models achieve strong performance on common benchmark cases, their accuracies often degrades in more challenging scenarios where negative candidates are semantically aligned with the query image or text. In this paper, we attribute this degradation to focus imbalances, where models disproportionately attend to one modality while neglecting the other. To validate this claim, we propose FBCIR, a multi-modal focus interpretation method that identifies the most crucial visual and textual input components to a model's retrieval decisions. Using FBCIR, we report that focus imbalances are prevalent in existing CIR models, especially under hard negative settings. Building on the analyses, we further propose a CIR data augmentation workflow that facilitates existing CIR datasets with curated hard negatives designed to encourage balanced cross-modal reasoning. Extensive experiments across multiple CIR models demonstrate that the proposed augmentation consistently improves performance in challenging cases, while maintaining their capabilities on standard benchmarks. Together, our interpretation method and data augmentation workflow provide a new perspective on CIR model diagnosis and robustness improvements. --- ### Prediction of Grade, Gender, and Academic Performance of Children and Teenagers from Handwriting Using the Sigma-Lognormal Model Authors: Adrian Iste, Kazuki Nishizawa, Chisa Tanaka, Andrew Vargo, Anna Scius-Bertrand, Andreas Fischer, Koichi Kise Published: 2026-03-12 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2603.11519v3 Digital handwriting acquisition enables the capture of detailed temporal and kinematic signals reflecting the motor processes underlying writing behavior. While handwriting analysis has been extensively explored in clinical or adult populations, its potential for studying developmental and educational characteristics in children remains less investigated. In this work, we examine whether handwriting dynamics encode information related to student characteristics using a large-scale online dataset collected from Japanese students from elementary school to junior high school. We systematically compare three families of handwriting-derived features: basic statistical descriptors of kinematic signals, entropy-based measures of variability, and parameters obtained from the sigma-lognormal model. Although the dataset contains dense stroke-level recordings, features are aggregated at the student level to enable a controlled comparison between representations. These features are evaluated across three prediction tasks: grade prediction, gender classification, and academic performance classification, using Linear or Logistic Regression and Random Forest models under consistent experimental settings. The results show that handwriting dynamics contain measurable signals related to developmental stage and individual differences, especially for the grade prediction task. These findings highlight the potential of kinematic handwriting analysis and confirm that through their development, children's handwriting evolves toward a lognormal motor organization. ---