Showing 1–50 of 535 results for author: Cao, L

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

Authors: Hanbing Liu, Lang Cao, Yang Li

Abstract: Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, and events change over time, models may experience continuous knowledge drift, resulting not only in outdated predictions but also in temporally inconsistent reasoning. Although exi… ▽ More Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, and events change over time, models may experience continuous knowledge drift, resulting not only in outdated predictions but also in temporally inconsistent reasoning. Although existing approaches, such as continual finetuning, knowledge editing, and retrieval-augmented generation (RAG), aim to update or supplement model knowledge, they are rarely evaluated in settings that reflect chronological, evolving, and real-world knowledge evolution. In this work, we introduce a new benchmark of real-world dynamic events, constructed from time-stamped evidence that captures how knowledge evolves over time, which enables systematic evaluation of model adaptation under continuous knowledge drift. The benchmark reveals that most existing methods, including vanilla RAG and several learning-based approaches, struggle under this setting, exposing critical limitations such as catastrophic forgetting and temporal inconsistency. To mitigate these limitations, we propose a time-aware retrieval baseline, Chronos, which progressively organizes retrieved evidence into an Event Evolution Graph to enable more temporally consistent understanding in LLMs without additional training. Overall, this work provides a foundation for analyzing and advancing LLM adaptation to continuous knowledge drift in realistic settings. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Adaptive Cost-Efficient Evaluation for Reliable Patent Claim Validation

Authors: Yongmin Yoo, Qiongkai Xu, Longbing Cao

Abstract: Automated validation of patent claims demands zero-defect tolerance, as even a single structural flaw can render a claim legally defective. Existing evaluation paradigms suffer from a rigidity-resource dilemma: lightweight encoders struggle with nuanced legal dependencies, while exhaustive verification via Large Language Models (LLMs) is prohibitively costly. To bridge this gap, we propose ACE (Ad… ▽ More Automated validation of patent claims demands zero-defect tolerance, as even a single structural flaw can render a claim legally defective. Existing evaluation paradigms suffer from a rigidity-resource dilemma: lightweight encoders struggle with nuanced legal dependencies, while exhaustive verification via Large Language Models (LLMs) is prohibitively costly. To bridge this gap, we propose ACE (Adaptive Cost-efficient Evaluation), a hybrid framework that uses predictive entropy to route only high-uncertainty claims to an expert LLM. The expert then executes a Chain of Patent Thought (CoPT) protocol grounded in 35 U.S.C. statutory standards. This design enables ACE to handle long-range legal dependencies more effectively while preserving efficiency. ACE achieves the best F1 among the evaluated methods at 94.95\%, while reducing operational costs by 78\% compared to standalone LLM deployments. We also construct ACE-40k, a 40,000-claim benchmark with MPEP-grounded error annotations, to facilitate further research. △ Less

Submitted 5 April, 2026; originally announced April 2026.

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models

Authors: Yansong Guo, Chaoyang Zhu, Jiayi Ji, Jianghang Lin, Liujuan Cao

Abstract: Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune video tokens at input level while neglecting the inherent information structure embedded in videos and large language models (LLMs). To address this, we propose… ▽ More Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune video tokens at input level while neglecting the inherent information structure embedded in videos and large language models (LLMs). To address this, we propose HieraVid, a hierarchical pruning framework that progressively and dynamically reduces visual redundancy. Based on two observations that videos possess the segment-frame structure and LLMs internally propagate multi-modal information unidirectionally, we decompose pruning into three levels: 1) segment-level, where video tokens are first temporally segmented and spatially merged; 2) frame-level, where similar frames within the same segment are jointly pruned to preserve diversity; 3) layer-level, redundancy gradually shrinks as LLM layer increases w/o compromising performance. We conduct extensive experiments on four widely used video understanding benchmarks to comprehensively evaluate the effectiveness of HieraVid. Remarkably, with only 30% of tokens retained, HieraVid achieves new state-of-the-art performance, while maintaining over 98% and 99% of the performance of LLaVA-Video-7B and LLaVA-OneVision-7B, respectively. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Universal computational thermal imaging overcoming the ghosting effect

Authors: Hongyi Xu, Du Wang, Chenjun Zhao, Jiashuo Chen, Jiale Lin, Liqin Cao, Yanfei Zhong, Yiyuan She, Fanglin Bao

Abstract: Thermal imaging is crucial for night vision but fundamentally hampered by the ghosting effect, a loss of detailed texture in cluttered photon streams. While conventional ghosting mitigation has relied on data post-processing, the recent breakthrough in heat-assisted detection and ranging (HADAR) opens a promising frontier for hyperspectral computational thermal imaging that produces night vision w… ▽ More Thermal imaging is crucial for night vision but fundamentally hampered by the ghosting effect, a loss of detailed texture in cluttered photon streams. While conventional ghosting mitigation has relied on data post-processing, the recent breakthrough in heat-assisted detection and ranging (HADAR) opens a promising frontier for hyperspectral computational thermal imaging that produces night vision with day-like visibility. However, universal anti-ghosting imaging remains elusive, as state-of-the-art HADAR applies only to limited scenes with uniform materials, whereas material non-uniformity is ubiquitous in the real world. Here, we propose a universal computational thermal imaging framework, TAG (thermal anti-ghosting), to address material non-uniformity and overcome ghosting for high-fidelity night vision. TAG takes hyperspectral photon streams for nonparametric texture recovery, enabling our experimental demonstration of unprecedented expression recovery in thus-far-elusive ghostly human faces -- the archetypal, long-recognized ghosting phenomenon. Strikingly, TAG not only universally outperforms HADAR across various scenes, but also reveals the influence of material non-uniformity, shedding light on HADAR's effectiveness boundary. We extensively test facial texture and expression recovery across day and night, and demonstrate, for the first time, thermal 3D topological alignment and mood detection. This work establishes a universal foundation for high-fidelity computational night vision, with potential applications in autonomous navigation, reconnaissance, healthcare, and wildlife monitoring. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Comments: 9 pages, 6 figures

StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision

Authors: Ziyang Chen, Yansong Qu, You Shen, Xuan Cheng, Liujuan Cao

Abstract: Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either monocular depth estimation (MDE) models or visual foundation models (VFMs). Crucially, these models are predominantly pretrained without explicit supervision of camera poses. Given th… ▽ More Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either monocular depth estimation (MDE) models or visual foundation models (VFMs). Crucially, these models are predominantly pretrained without explicit supervision of camera poses. Given that such geometric knowledge is indispensable for stereo vision, the absence of explicit spatial constraints constitutes a significant performance bottleneck for existing architectures. Recognizing that the Visual Geometry Grounded Transformer (VGGT) operates as a foundation model pretrained on extensive 3D priors, including camera poses, we investigate its potential as a robust backbone for stereo vision tasks. Nevertheless, empirical results indicate that its direct application to stereo vision yields suboptimal performance. We observe that VGGT suffers from a more significant degradation of geometric details during feature extraction. Such characteristics conflict with the requirements of binocular stereo vision, thereby constraining its efficacy for relative tasks. To bridge this gap, we propose StereoVGGT, a feature backbone specifically tailored for stereo vision. By leveraging the frozen VGGT and introducing a training-free feature adjustment pipeline, we mitigate geometric degradation and harness the latent camera calibration knowledge embedded within the model. StereoVGGT-based stereo matching network achieved the $1^{st}$ rank among all published methods on the KITTI benchmark, validating that StereoVGGT serves as a highly effective backbone for stereo vision. △ Less

Submitted 31 March, 2026; originally announced March 2026.

AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design

Authors: Zhenyuan Zhao, Yu Xing, Tianyang Xue, Lingxin Cao, Xin Yan, Lin Lu

Abstract: Designing microstructures that satisfy coupled cross-physics objectives is a fundamental challenge in material science. This inverse design problem involves a vast, discontinuous search space where traditional topology optimization is computationally prohibitive, and deep generative models often suffer from "physical hallucinations," lacking the capability to ensure rigorous validity. To address t… ▽ More Designing microstructures that satisfy coupled cross-physics objectives is a fundamental challenge in material science. This inverse design problem involves a vast, discontinuous search space where traditional topology optimization is computationally prohibitive, and deep generative models often suffer from "physical hallucinations," lacking the capability to ensure rigorous validity. To address this limitation, we introduce AutoMS, a multi-agent neuro-symbolic framework that reformulates inverse design as an LLM-driven evolutionary search. Unlike methods that treat LLMs merely as interfaces, AutoMS integrates them as "semantic navigators" to initialize search spaces and break local optima, while our novel Simulation-Aware Evolutionary Search (SAES) addresses the "blindness" of traditional evolutionary strategies. Specifically, SAES utilizes simulation feedback to perform local gradient approximation and directed parameter updates, effectively guiding the search toward physically valid Pareto frontiers. Orchestrating specialized agents (Manager, Parser, Generator, and Simulator), AutoMS achieves a state-of-the-art 83.8\% success rate on 17 diverse cross-physics tasks, nearly doubling the performance of traditional NSGA-II (43.7\%) and significantly outperforming ReAct-based LLM baselines (53.3\%). Furthermore, our hierarchical architecture reduces total execution time by 23.3\%. AutoMS demonstrates that autonomous agent systems can effectively navigate complex physical landscapes, bridging the gap between semantic design intent and rigorous physical validity. △ Less

Submitted 28 March, 2026; originally announced March 2026.

Lean Learning Beyond Clouds: Efficient Discrepancy-Conditioned Optical-SAR Fusion for Semantic Segmentation

Authors: Chenxing Meng, Wuzhou Quan, Yingjie Cai, Liqun Cao, Liyan Zhang, Mingqiang Wei

Abstract: Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations, achieving efficient global modeling and reliable cross-modal fusion under cloud interference remains challenging. Existing methods rely on dense global attention to capture long-range dependencies, yet such aggregation i… ▽ More Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations, achieving efficient global modeling and reliable cross-modal fusion under cloud interference remains challenging. Existing methods rely on dense global attention to capture long-range dependencies, yet such aggregation indiscriminately propagates cloud-induced noise. Improving robustness typically entails enlarging model capacity, which further increases computational overhead. Given the large-scale and high-resolution nature of remote sensing applications, such computational demands hinder practical deployment, leading to an efficiency-reliability trade-off. To address this dilemma, we propose EDC, an efficiency-oriented and discrepancy-conditioned optical-SAR semantic segmentation framework. A tri-stream encoder with Carrier Tokens enables compact global context modeling with reduced complexity. To prevent noise contamination, we introduce a Discrepancy-Conditioned Hybrid Fusion (DCHF) mechanism that selectively suppresses unreliable regions during global aggregation. In addition, an auxiliary cloud removal branch with teacher-guided distillation enhances semantic consistency under occlusion. Extensive experiments demonstrate that EDC achieves superior accuracy and efficiency, improving mIoU by 0.56\% and 0.88\% on M3M-CR and WHU-OPT-SAR, respectively, while reducing the number of parameters by 46.7\% and accelerating inference by 1.98$\times$. Our implementation is available at https://github.com/mengcx0209/EDC. △ Less

Submitted 21 March, 2026; originally announced March 2026.

Comments: 14 page, 7 figures

DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management

Authors: Yaqi Xie, Xinru Hao, Jiaxi Liu, Will Ma, Linwei Xin, Lei Cao, Yidong Zhang

Abstract: Deep Reinforcement Learning (DRL) provides a general-purpose methodology for training inventory policies that can leverage big data and compute. However, off-the-shelf implementations of DRL have seen mixed success, often plagued by high sensitivity to the hyperparameters used during training. In this paper, we show that by imposing policy regularizations, grounded in classical inventory concepts… ▽ More Deep Reinforcement Learning (DRL) provides a general-purpose methodology for training inventory policies that can leverage big data and compute. However, off-the-shelf implementations of DRL have seen mixed success, often plagued by high sensitivity to the hyperparameters used during training. In this paper, we show that by imposing policy regularizations, grounded in classical inventory concepts such as "Base Stock", we can significantly accelerate hyperparameter tuning and improve the final performance of several DRL methods. We report details from a 100% deployment of DRL with policy regularizations on Alibaba's e-commerce platform, Tmall. We also include extensive synthetic experiments, which show that policy regularizations reshape the narrative on what is the best DRL method for inventory management. △ Less

Submitted 19 March, 2026; originally announced March 2026.

CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

Authors: Weilin Chen, Jiahao Rao, Wenhao Wang, Xinyang Li, Xuan Cheng, Liujuan Cao

Abstract: The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. To overcome these limitations, we introduce CustomTex, a novel framework for instance-level, high-fi… ▽ More The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. To overcome these limitations, we introduce CustomTex, a novel framework for instance-level, high-fidelity scene texturing driven by reference images. CustomTex takes an untextured 3D scene and a set of reference images specifying the desired appearance for each object instance, and generates a unified, high-resolution texture map. The core of our method is a dual-distillation approach that separates semantic control from pixel-level enhancement. We employ semantic-level distillation, equipped with an instance cross-attention, to ensure semantic plausibility and ``reference-instance'' alignment, and pixel-level distillation to enforce high visual fidelity. Both are unified within a Variational Score Distillation (VSD) optimization framework. Experiments demonstrate that CustomTex achieves precise instance-level consistency with reference images and produces textures with superior sharpness, reduced artifacts, and minimal baked-in shading compared to state-of-the-art methods. Our work establishes a more direct and user-friendly path to high-quality, customizable 3D scene appearance editing. △ Less

Submitted 19 March, 2026; v1 submitted 19 March, 2026; originally announced March 2026.

Comments: Accepted to CVPR 2026. This version integrates the main paper and supplementary material

MLOW: Interpretable Low-Rank Frequency Magnitude Decomposition of Multiple Effects for Time Series Forecasting

Authors: Runze Yang, Longbing Cao, Xiaoming Wu, Xin You, Kun Fang, Jianxun Li, Jie Yang

Abstract: Separating multiple effects in time series is fundamental yet challenging for time-series forecasting (TSF). However, existing TSF models cannot effectively learn interpretable multi-effect decomposition by their smoothing-based temporal techniques. Here, a new interpretable frequency-based decomposition pipeline MLOW captures the insight: a time series can be represented as a magnitude spectrum m… ▽ More Separating multiple effects in time series is fundamental yet challenging for time-series forecasting (TSF). However, existing TSF models cannot effectively learn interpretable multi-effect decomposition by their smoothing-based temporal techniques. Here, a new interpretable frequency-based decomposition pipeline MLOW captures the insight: a time series can be represented as a magnitude spectrum multiplied by the corresponding phase-aware basis functions, and the magnitude spectrum distribution of a time series always exhibits observable patterns for different effects. MLOW learns a low-rank representation of the magnitude spectrum to capture dominant trending and seasonal effects. We explore low-rank methods, including PCA, NMF, and Semi-NMF, and find that none can simultaneously achieve interpretable, efficient and generalizable decomposition. Thus, we propose hyperplane-nonnegative matrix factorization (Hyperplane-NMF). Further, to address the frequency (spectral) leakage restricting high-quality low-rank decomposition, MLOW enables a flexible selection of input horizons and frequency levels via a mathematical mechanism. Visual analysis demonstrates that MLOW enables interpretable and hierarchical multiple-effect decomposition, robust to noises. It can also enable plug-and-play in existing TSF backbones with remarkable performance improvement but minimal architectural modifications. △ Less

Submitted 18 March, 2026; originally announced March 2026.

DISCOVER: A Solver for Distributional Counterfactual Explanations

Authors: Yikai Gu, Lele Cao, Bo Zhao, Lei Lei, Lei You

Abstract: Counterfactual explanations (CE) explain model decisions by identifying input modifications that lead to different predictions. Most existing methods operate at the instance level. Distributional Counterfactual Explanations (DCE) extend this setting by optimizing an optimal transport objective that balances proximity to a factual input distribution and alignment to a target output distribution, wi… ▽ More Counterfactual explanations (CE) explain model decisions by identifying input modifications that lead to different predictions. Most existing methods operate at the instance level. Distributional Counterfactual Explanations (DCE) extend this setting by optimizing an optimal transport objective that balances proximity to a factual input distribution and alignment to a target output distribution, with statistical certification via chance constrained bounds. However, DCE relies on gradient based optimization, while many real-world tabular pipelines are dominated by non-differentiable models. We propose DISCOVER, a model-agnostic solver for distributional counterfactual explanations. DISCOVER preserves the original DCE objective and certification while replacing gradient descent with a sparse propose-and-select search paradigm. It exploits a sample-wise decomposition of the transport objective to compute per-row impact scores and enforce a top-$k$ intervention budget, focusing edits on the most influential samples. To guide candidate generation without predictor gradients, DISCOVER introduces an OT-guided cone sampling primitive driven by input-side transport geometry. Experiments on multiple tabular datasets demonstrate strong joint alignment of input and output distributions, extending distributional counterfactual reasoning to modern black box learning pipelines. A code repository is available at https://github.com/understanding-ml/DCE. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: 20 pages, 8 figures, 4 tables

SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia

Authors: Pengfei Yue, Xingran Zhao, Juntao Chen, Peng Hou, Wang Longchao, Jianghang Lin, Shengchuan Zhang, Anxiang Zeng, Liujuan Cao

Abstract: Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in realistic multilingual environments. In Southeast Asia, the diversity of languages, complex writing systems, and highly varied document types make this challenge eve… ▽ More Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in realistic multilingual environments. In Southeast Asia, the diversity of languages, complex writing systems, and highly varied document types make this challenge even greater. We introduce SEA-Vision, a benchmark that jointly evaluates Document Parsing and Text-Centric Visual Question Answering (TEC-VQA) across 11 Southeast Asian languages. SEA-Vision contains 15,234 document parsing pages from nine representative document types, annotated with hierarchical page-, block-, and line-level labels. It also provides 7,496 TEC-VQA question-answer pairs that probe text recognition, numerical calculation, comparative analysis, logical reasoning, and spatial understanding. To make such multilingual, multi-task annotation feasible, we design a hybrid pipeline for Document Parsing and TEC-VQA. It combines automated filtering and scoring with MLLM-assisted labeling and lightweight native-speaker verification, greatly reducing manual labeling while maintaining high quality. We evaluate several leading multimodal models and observe pronounced performance degradation on low-resource Southeast Asian languages, highlighting substantial remaining gaps in multilingual document and scene text understanding. We believe SEA-Vision will help drive global progress in document and scene text understanding. △ Less

Submitted 16 March, 2026; originally announced March 2026.

Comments: Accepted By CVPR2026

ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation

Authors: You Wu, Zixuan Chen, Cunxu Ou, Wenxuan Wang, Wenbo Huang, Lin Cao, Yangtao Chen, Weichao Qiu, Xingyue Quan, Jieqi Shi, Jing Huo, Yang Gao

Abstract: Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect high-level reasoning with low-level control, but lack depth awareness and temporal consistency, limiting robustness in complex 3D scenes. We propose ST-VLA, a hierar… ▽ More Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect high-level reasoning with low-level control, but lack depth awareness and temporal consistency, limiting robustness in complex 3D scenes. We propose ST-VLA, a hierarchical VLA framework using a unified 3D-4D representation to bridge perception and action. ST-VLA converts 2D guidance into 3D trajectories and generates smooth spatial masks that capture 4D spatio-temporal context, providing a stable interface between semantic reasoning and continuous control. To enable effective learning of such representations, we introduce ST-Human, a large-scale human manipulation dataset with 14 tasks and 300k episodes, annotated with 2D, 3D, and 4D supervision via a semi-automated pipeline. Using ST-Human, we train ST-VLM, a spatio-temporal vision-language model that generates spatially grounded and temporally coherent 3D representations to guide policy execution. The smooth spatial masks focus on task-relevant geometry and stabilize latent representations, enabling online replanning and long-horizon reasoning. Experiments on RLBench and real-world manipulation tasks show that \method significantly outperforms state-of-the-art baselines, improving zero-shot success rates by 44.6% and 30.3%. These results demonstrate that offloading spatio-temporal reasoning to VLMs with unified 3D-4D representations substantially improves robustness and generalization for open-world robotic manipulation. Project website: https://oucx117.github.io/ST-VLA/. △ Less

Submitted 14 March, 2026; originally announced March 2026.

Comments: 25 pages, under review

Optimal Experimental Design for Reliable Learning of History-Dependent Constitutive Laws

Authors: Kaushik Bhattacharya, Lianghao Cao, Andrew Stuart

Abstract: History-dependent constitutive models serve as macroscopic closures for the aggregated effects of micromechanics. Their parameters are typically learned from experimental data. With a limited experimental budget, eliciting the full range of responses needed to characterize the constitutive relation can be difficult. As a result, the data can be well explained by a range of parameter choices, leadi… ▽ More History-dependent constitutive models serve as macroscopic closures for the aggregated effects of micromechanics. Their parameters are typically learned from experimental data. With a limited experimental budget, eliciting the full range of responses needed to characterize the constitutive relation can be difficult. As a result, the data can be well explained by a range of parameter choices, leading to parameter estimates that are uncertain or unreliable. To address this issue, we propose a Bayesian optimal experimental design framework to quantify, interpret, and maximize the utility of experimental designs for reliable learning of history-dependent constitutive models. In this framework, the design utility is defined as the expected reduction in parametric uncertainty or the expected information gain. This enables in silico design optimization using simulated data and reduces the cost of physical experiments for reliable parameter identification. We introduce two approximations that make this framework practical for advanced material testing with expensive forward models and high-dimensional data: (i) a Gaussian approximation of the expected information gain, and (ii) a surrogate approximation of the Fisher information matrix. The former enables efficient design optimization and interpretation, while the latter extends this approach to batched design optimization by amortizing the cost of repeated utility evaluations. Our numerical studies of uniaxial tests for viscoelastic solids show that optimized specimen geometries and loading paths yield image and force data that significantly improve parameter identifiability relative to random designs, especially for parameters associated with memory effects. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decoding

Authors: Shumeng Li, Jintao Guo, Jian Zhang, Yulin Zhou, Luyang Cao, Yinghuan Shi

Abstract: Cross-subject visual decoding aims to reconstruct visual experiences from brain activity across individuals, enabling more scalable and practical brain-computer interfaces. However, existing methods often suffer from degraded performance when adapting to new subjects with limited data, as they struggle to preserve both the semantic consistency of stimuli and the alignment of brain responses. To ad… ▽ More Cross-subject visual decoding aims to reconstruct visual experiences from brain activity across individuals, enabling more scalable and practical brain-computer interfaces. However, existing methods often suffer from degraded performance when adapting to new subjects with limited data, as they struggle to preserve both the semantic consistency of stimuli and the alignment of brain responses. To address these challenges, we propose Duala, a dual-level alignment framework designed to achieve stimulus-level consistency and subject-level alignment in fMRI-based cross-subject visual decoding. (1) At the stimulus level, Duala introduces a semantic alignment and relational consistency strategy that preserves intra-class similarity and inter-class separability, maintaining clear semantic boundaries during adaptation. (2) At the subject level, a distribution-based feature perturbation mechanism is developed to capture both global and subject-specific variations, enabling adaptation to individual neural representations without overfitting. Experiments on the Natural Scenes Dataset (NSD) demonstrate that Duala effectively improves alignment across subjects. Remarkably, even when fine-tuned with only about one hour of fMRI data, Duala achieves over 81.1% image-to-brain retrieval accuracy and consistently outperforms existing fine-tuning strategies in both retrieval and reconstruction. Our code is available at https://github.com/ShumengLI/Duala. △ Less

Submitted 8 March, 2026; originally announced March 2026.

Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving

Authors: Jiazhuo Li, Linjiang Cao, Qi Liu, Xi Xiong

Abstract: Data-efficient learning remains a central challenge in autonomous driving due to the high cost and safety risks of large-scale real-world interaction. Although world-model-based reinforcement learning enables policy optimization through latent imagination, existing approaches often lack explicit mechanisms to encode spatial and kinematic structure essential for driving tasks. In this work, we buil… ▽ More Data-efficient learning remains a central challenge in autonomous driving due to the high cost and safety risks of large-scale real-world interaction. Although world-model-based reinforcement learning enables policy optimization through latent imagination, existing approaches often lack explicit mechanisms to encode spatial and kinematic structure essential for driving tasks. In this work, we build upon the Recurrent State-Space Model (RSSM) and propose a kinematics-aware latent world model framework for autonomous driving. Vehicle kinematic information is incorporated into the observation encoder to ground latent transitions in physically meaningful motion dynamics, while geometry-aware supervision regularizes the RSSM latent state to capture task-relevant spatial structure beyond pixel reconstruction. The resulting structured latent dynamics improve long-horizon imagination fidelity and stabilize policy optimization. Experiments in a driving simulation benchmark demonstrate consistent gains over both model-free and pixel-based world-model baselines in terms of sample efficiency and driving performance. Ablation studies further verify that the proposed design enhances spatial representation quality within the latent space. These results suggest that integrating kinematic grounding into RSSM-based world models provides a scalable and physically grounded paradigm for autonomous driving policy learning. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Comments: 6 pages, 5 figures. Under review at IEEE ITSC

LeafInst - Unified Instance Segmentation Network for Fine-Grained Forestry Leaf Phenotype Analysis: A New UAV based Benchmark

Authors: Taige Luo, Junru Xie, Chenyang Fan, Bingrong Liu, Ruisheng Wang, Yang Shao, Sheng Xu, Lin Cao

Abstract: Intelligent forest tree breeding has advanced plant phenotyping, yet existing research largely focuses on large-leaf agricultural crops, with limited attention to fine-grained leaf analysis of sapling trees in open-field environments. Natural scenes introduce challenges including scale variation, illumination changes, and irregular leaf morphology. To address these issues, we collected UAV RGB ima… ▽ More Intelligent forest tree breeding has advanced plant phenotyping, yet existing research largely focuses on large-leaf agricultural crops, with limited attention to fine-grained leaf analysis of sapling trees in open-field environments. Natural scenes introduce challenges including scale variation, illumination changes, and irregular leaf morphology. To address these issues, we collected UAV RGB imagery of field-grown saplings and constructed the Poplar-leaf dataset, containing 1,202 branches and 19,876 pixel-level annotated leaf instances. To our knowledge, this is the first instance segmentation dataset specifically designed for forestry leaves in open-field conditions. We propose LeafInst, a novel segmentation framework tailored for irregular and multi-scale leaf structures. The model integrates an Asymptotic Feature Pyramid Network (AFPN) for multi-scale perception, a Dynamic Asymmetric Spatial Perception (DASP) module for irregular shape modeling, and a dual-residual Dynamic Anomalous Regression Head (DARH) with Top-down Concatenation decoder Feature Fusion (TCFU) to improve detection and segmentation performance. On Poplar-leaf, LeafInst achieves 68.4 mAP, outperforming YOLOv11 by 7.1 percent and MaskDINO by 6.5 percent. On the public PhenoBench benchmark, it reaches 52.7 box mAP, exceeding MaskDINO by 3.4 percent. Additional experiments demonstrate strong generalization and practical utility for large-scale leaf phenotyping. △ Less

Submitted 3 March, 2026; originally announced March 2026.

3D-DRES: Detailed 3D Referring Expression Segmentation

Authors: Qi Chen, Changli Wu, Jiayi Ji, Yiwei Ma, Liujuan Cao

Abstract: Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natural language expressions. To address this challenge, we introduce Detailed 3D Referring Expression Segmentation (3D-DRES), a new task that provides a phrase to 3D instance mapping, aiming at enhancing fine-grained 3D vis… ▽ More Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natural language expressions. To address this challenge, we introduce Detailed 3D Referring Expression Segmentation (3D-DRES), a new task that provides a phrase to 3D instance mapping, aiming at enhancing fine-grained 3D vision language understanding. To support 3D-DRES, we present DetailRefer, a new dataset comprising 54,432 descriptions spanning 11,054 distinct objects. Unlike previous datasets, DetailRefer implements a pioneering phrase-instance annotation paradigm where each referenced noun phrase is explicitly mapped to its corresponding 3D elements. Additionally, we introduce DetailBase, a purposefully streamlined yet effective baseline architecture that supports dual-mode segmentation at both sentence and phrase levels. Our experimental results demonstrate that models trained on DetailRefer not only excel at phrase-level segmentation but also show surprising improvements on traditional 3D-RES benchmarks. △ Less

Submitted 3 March, 2026; originally announced March 2026.

Comments: AAAI2026

Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities?

Authors: Hongbo Jiang, Jie Li, Yunhang Shen, Pingyang Dai, Xing Sun, Haoyu Cao, Liujuan Cao

Abstract: Unified Multimodal Large Language Models (U-MLLMs) integrate understanding and generation within a single architecture. However, existing evaluations typically assess these capabilities separately, overlooking semantic equivalence, i.e., the ability to manifest consistent reasoning results regardless of the output modality. In this work, we investigate whether current U-MLLMs satisfy this premise.… ▽ More Unified Multimodal Large Language Models (U-MLLMs) integrate understanding and generation within a single architecture. However, existing evaluations typically assess these capabilities separately, overlooking semantic equivalence, i.e., the ability to manifest consistent reasoning results regardless of the output modality. In this work, we investigate whether current U-MLLMs satisfy this premise. We observe that while models demonstrate robust textual reasoning, they fail to maintain semantic equivalence when required to render the same results in the image modality. To rigorously diagnose this discrepancy, we introduce VGUBench, a framework to decouple reasoning logic from generation fidelity. VGUBench comprises three diagnostic tasks: (1)Textual Generative Understanding, establishing a baseline for reasoning accuracy in textual response; (2)Visual Generative Understanding, evaluating the ability to generate visual responses that represent the correct answer; and (3)a Visual Rendering control task, which assesses the ability to directly render explicit visual descriptions into images without complex reasoning. Our evaluation reveals a significant disparity: despite strong performance in textual understanding and visual rendering, U-MLLMs exhibit a marked performance collapse when required to generate visual answers to questions. Furthermore, we find a negligible correlation between visual answering performance and basic rendering quality. These results suggest that the failure stems not from insufficient generation fidelity, but from a breakdown in cross-modal semantic alignment. We provide diagnostic insights to address this challenge in future Unified Generation and Understanding Models. △ Less

Submitted 27 February, 2026; originally announced February 2026.

Comments: Equal contribution by Jie Li

SPMamba-YOLO: An Underwater Object Detection Network Based on Multi-Scale Feature Enhancement and Global Context Modeling

Authors: Guanghao Liao, Zhen Liu, Liyuan Cao, Yonghui Yang, Qi Li

Abstract: Underwater object detection is a critical yet challenging research problem owing to severe light attenuation, color distortion, background clutter, and the small scale of underwater targets. To address these challenges, we propose SPMamba-YOLO, a novel underwater object detection network that integrates multi-scale feature enhancement with global context modeling. Specifically, a Spatial Pyramid P… ▽ More Underwater object detection is a critical yet challenging research problem owing to severe light attenuation, color distortion, background clutter, and the small scale of underwater targets. To address these challenges, we propose SPMamba-YOLO, a novel underwater object detection network that integrates multi-scale feature enhancement with global context modeling. Specifically, a Spatial Pyramid Pooling Enhanced Layer Aggregation Network (SPPELAN) module is introduced to strengthen multi-scale feature aggregation and expand the receptive field, while a Pyramid Split Attention (PSA) mechanism enhances feature discrimination by emphasizing informative regions and suppressing background interference. In addition, a Mamba-based state space modeling module is incorporated to efficiently capture long-range dependencies and global contextual information, thereby improving detection robustness in complex underwater environments. Extensive experiments on the URPC2022 dataset demonstrate that SPMamba-YOLO outperforms the YOLOv8n baseline by more than 4.9\% in mAP@0.5, particularly for small and densely distributed underwater objects, while maintaining a favorable balance between detection accuracy and computational cost. △ Less

Submitted 26 February, 2026; originally announced February 2026.

Comments: 31 pages, 10 figures, 6 tables. This paper presents SPMamba-YOLO, an underwater object detection framework integrating multi-scale feature enhancement and global context modeling. The work is under review

ACM Class: I.4.8; I.4.6; I.2.10

Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation

Authors: Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao

Abstract: Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLMs for camouflaged object discovery often leads to inaccurate localization, false positives, and missed detections. To address these issues, we propose the \textbf{D}iscover-\textbf… ▽ More Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLMs for camouflaged object discovery often leads to inaccurate localization, false positives, and missed detections. To address these issues, we propose the \textbf{D}iscover-\textbf{S}egment-\textbf{S}elect (\textbf{DSS}) mechanism, a progressive framework designed to refine segmentation step by step. The proposed method contains a Feature-coherent Object Discovery (FOD) module that leverages visual features to generate diverse object proposals, a segmentation module that refines these proposals through SAM segmentation, and a Semantic-driven Mask Selection (SMS) module that employs MLLMs to evaluate and select the optimal segmentation mask from multiple candidates. Without requiring any training or supervision, DSS achieves state-of-the-art performance on multiple COS benchmarks, especially in multiple-instance scenes. △ Less

Submitted 23 February, 2026; originally announced February 2026.

Comments: Accepted by CVPR 2026 (main conference)

Test-Time Computing for Referring Multimodal Large Language Models

Authors: Mingrui Wu, Hao Chen, Jiayi Ji, Xiaoshuai Sun, Zhiyuan Liu, Liujuan Cao, Ming-Ming Cheng, Rongrong Ji

Abstract: We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained region-based visual reasoning without any model retraining or fine-tuning. Leveraging the insight that cross-modal attention maps intrinsically encode semantic correspondences between textual tokens and visual regions, Co… ▽ More We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained region-based visual reasoning without any model retraining or fine-tuning. Leveraging the insight that cross-modal attention maps intrinsically encode semantic correspondences between textual tokens and visual regions, ControlMLLM++ optimizes a latent visual token modifier during inference via a task-specific energy function to steer model attention towards user-specified areas. To enhance optimization stability and mitigate language prompt biases, ControlMLLM++ incorporates an improved optimization strategy (Optim++) and a prompt debiasing mechanism (PromptDebias). Supporting diverse visual prompt types including bounding boxes, masks, scribbles, and points, our method demonstrates strong out-of-domain generalization and interpretability. The code is available at https://github.com/mrwu-mac/ControlMLLM. △ Less

Submitted 22 February, 2026; originally announced February 2026.

Comments: arXiv admin note: substantial text overlap with arXiv:2407.21534

Be Wary of Your Time Series Preprocessing

Authors: Sofiane Ennadir, Tianze Wang, Oleg Smirnov, Sahar Asadi, Lele Cao

Abstract: Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspective. In this work, we present the first formal analysis of how different normalization strategies, specifically instance-based and global scaling, impact the expressivity of Transformer-based architectures for time series… ▽ More Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspective. In this work, we present the first formal analysis of how different normalization strategies, specifically instance-based and global scaling, impact the expressivity of Transformer-based architectures for time series representation learning. We propose a novel expressivity framework tailored to time series, which quantifies a model's ability to distinguish between similar and dissimilar inputs in the representation space. Using this framework, we derive theoretical bounds for two widely used normalization methods: Standard and Min-Max scaling. Our analysis reveals that the choice of normalization strategy can significantly influence the model's representational capacity, depending on the task and data characteristics. We complement our theory with empirical validation on classification and forecasting benchmarks using multiple Transformer-based models. Our results show that no single normalization method consistently outperforms others, and in some cases, omitting normalization entirely leads to superior performance. These findings highlight the critical role of preprocessing in time series learning and motivate the need for more principled normalization strategies tailored to specific tasks and datasets. △ Less

Submitted 19 February, 2026; originally announced February 2026.

Comments: Accepted at the AI4TS workshop at AAAI-26

A Kung Fu Athlete Bot That Can Do It All Day: Highly Dynamic, Balance-Challenging Motion Dataset and Autonomous Fall-Resilient Tracking

Authors: Zhongxiang Lei, Lulu Cao, Xuyang Wang, Tianyi Qian, Jinyan Liu, Xuesong Li

Abstract: Current humanoid motion tracking systems can execute routine and moderately dynamic behaviors, yet significant gaps remain near hardware performance limits and algorithmic robustness boundaries. Martial arts represent an extreme case of highly dynamic human motion, characterized by rapid center-of-mass shifts, complex coordination, and abrupt posture transitions. However, datasets tailored to such… ▽ More Current humanoid motion tracking systems can execute routine and moderately dynamic behaviors, yet significant gaps remain near hardware performance limits and algorithmic robustness boundaries. Martial arts represent an extreme case of highly dynamic human motion, characterized by rapid center-of-mass shifts, complex coordination, and abrupt posture transitions. However, datasets tailored to such high-intensity scenarios remain scarce. To address this gap, we construct KungFuAthlete, a high-dynamic martial arts motion dataset derived from professional athletes' daily training videos. The dataset includes ground and jump subsets covering representative complex motion patterns. The jump subset exhibits substantially higher joint, linear, and angular velocities compared to commonly used datasets such as LAFAN1, PHUMA, and AMASS, indicating significantly increased motion intensity and complexity. Importantly, even professional athletes may fail during highly dynamic movements. Similarly, humanoid robots are prone to instability and falls under external disturbances or execution errors. Most prior work assumes motion execution remains within safe states and lacks a unified strategy for modeling unsafe states and enabling reliable autonomous recovery. We propose a novel training paradigm that enables a single policy to jointly learn high-dynamic motion tracking and fall recovery, unifying agile execution and stabilization within one framework. This framework expands robotic capability from pure motion tracking to recovery-enabled execution, promoting more robust and autonomous humanoid performance in real-world high-dynamic scenarios. △ Less

Submitted 14 February, 2026; originally announced February 2026.

Comments: 18 pages, 8 figures,5 tables

Hippocampus: An Efficient and Scalable Memory Module for Agentic AI

Authors: Yi Li, Lianjie Cao, Faraz Ahmed, Puneet Sharma, Bingzhe Li

Abstract: Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency and poor storage scalability. We introduce Hippocampus, an agentic memory management system that uses compact binary signatures for semantic search and lossless… ▽ More Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency and poor storage scalability. We introduce Hippocampus, an agentic memory management system that uses compact binary signatures for semantic search and lossless token-ID streams for exact content reconstruction. Its core is a Dynamic Wavelet Matrix (DWM) that compresses and co-indexes both streams to support ultra-fast search in the compressed domain, thus avoiding costly dense-vector or graph computations. This design scales linearly with memory size, making it suitable for long-horizon agentic deployments. Empirically, our evaluation shows that Hippocampus reduces end-to-end retrieval latency by up to 31$\times$ and cuts per-query token footprint by up to 14$\times$, while maintaining accuracy on both LoCoMo and LongMemEval benchmarks. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Learning Physiology-Informed Vocal Spectrotemporal Representations for Speech Emotion Recognition

Authors: Xu Zhang, Longbing Cao, Runze Yang, Zhangkai Wu

Abstract: Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient models are critical for safety and performance. Existing deep models trained on large datasets remain largely uninterpretable, often insufficiently modeling underlying emotional acoustic signals and failing to capture and… ▽ More Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient models are critical for safety and performance. Existing deep models trained on large datasets remain largely uninterpretable, often insufficiently modeling underlying emotional acoustic signals and failing to capture and analyze the core physiology of emotional vocal behaviors. Physiological research on human voices shows that the dynamics of vocal amplitude and phase correlate with emotions through the vocal tract filter and the glottal source. However, most existing deep models solely involve amplitude but fail to couple the physiological features of and between amplitude and phase. Here, we propose PhysioSER, a physiology-informed vocal spectrotemporal representation learning method, to address these issues with a compact, plug-and-play design. PhysioSER constructs amplitude and phase views informed by voice anatomy and physiology (VAP) to complement SSL models for SER. This VAP-informed framework incorporates two parallel workflows: a vocal feature representation branch to decompose vocal signals based on VAP, embed them into a quaternion field, and use Hamilton-structured quaternion convolutions for modeling their dynamic interactions; and a latent representation branch based on a frozen SSL backbone. Then, utterance-level features from both workflows are aligned by a Contrastive Projection and Alignment framework, followed by a shallow attention fusion head for SER classification. PhysioSER is shown to be interpretable and efficient for SER through extensive evaluations across 14 datasets, 10 languages, and 6 backbones, and its practical efficacy is validated by real-time deployment on a humanoid robotic platform. △ Less

Submitted 2 February, 2026; originally announced February 2026.

Comments: 13 pages, 5 figures

Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation

Authors: Hongbo Jiang, Jie Li, Xinqi Cai, Tianyu Xie, Yunhang Shen, Pingyang Dai, Liujuan Cao

Abstract: Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modalities. While Multi-Modal Large Language Models (MLLMs) offer strong unification potential, existing approaches fail to adapt them into a single end-to-end backbone and lack effective knowledge distillation strategies for… ▽ More Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modalities. While Multi-Modal Large Language Models (MLLMs) offer strong unification potential, existing approaches fail to adapt them into a single end-to-end backbone and lack effective knowledge distillation strategies for edge deployment. To address these limitations, we propose MLLMEmbed-ReID, a unified framework based on a powerful cloud-edge architecture. First, we adapt a foundational MLLM into a state-of-the-art cloud model. We leverage instruction-based prompting to guide the MLLM in generating a unified embedding space across RGB, infrared, sketch, and text modalities. This model is then trained efficiently with a hierarchical Low-Rank Adaptation finetuning (LoRA-SFT) strategy, optimized under a holistic cross-modal alignment objective. Second, to deploy its knowledge onto an edge-native student, we introduce a novel distillation strategy motivated by the low-rank property in the teacher's feature space. To prioritize essential information, this method employs a Principal Component Mapping loss, while relational structures are preserved via a Feature Relation loss. Our lightweight edge-based model achieves state-of-the-art performance on multiple visual CM-ReID benchmarks, while its cloud-based counterpart excels across all CM-ReID benchmarks. The MLLMEmbed-ReID framework thus presents a complete and effective solution for deploying unified MLLM-level intelligence on resource-constrained devices. The code and models will be open-sourced soon. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Comments: Equal contribution by Jie Li

From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness

Authors: Linbo Cao, Lihao Sun, Yang Yue

Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While persona-induced biases in text generation are well documented, their effects on agent task performance remain largely unexplored, even though such effects pose more direct operational risks. In this work, we present the first systematic case study sho… ▽ More Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While persona-induced biases in text generation are well documented, their effects on agent task performance remain largely unexplored, even though such effects pose more direct operational risks. In this work, we present the first systematic case study showing that demographic-based persona assignments can alter LLM agents' behavior and degrade performance across diverse domains. Evaluating widely deployed models on agentic benchmarks spanning strategic reasoning, planning, and technical operations, we uncover substantial performance variations - up to 26.2% degradation, driven by task-irrelevant persona cues. These shifts appear across task types and model architectures, indicating that persona conditioning and simple prompt injections can distort an agent's decision-making reliability. Our findings reveal an overlooked vulnerability in current LLM agentic systems: persona assignments can introduce implicit biases and increase behavioral volatility, raising concerns for the safe and robust deployment of LLM agents. △ Less

Submitted 20 January, 2026; originally announced February 2026.

Comments: Accepted to the AAAI 2026 TrustAgent Workshop. 6 pages, 4 figures

VividFace: Real-Time and Realistic Facial Expression Shadowing for Humanoid Robots

Authors: Peizhen Li, Longbing Cao, Xiao-Ming Wu, Yang Zhang

Abstract: Humanoid facial expression shadowing enables robots to realistically imitate human facial expressions in real time, which is critical for lifelike, facially expressive humanoid robots and affective human-robot interaction. Existing progress in humanoid facial expression imitation remains limited, often failing to achieve either real-time performance or realistic expressiveness due to offline video… ▽ More Humanoid facial expression shadowing enables robots to realistically imitate human facial expressions in real time, which is critical for lifelike, facially expressive humanoid robots and affective human-robot interaction. Existing progress in humanoid facial expression imitation remains limited, often failing to achieve either real-time performance or realistic expressiveness due to offline video-based inference designs and insufficient ability to capture and transfer subtle expression details. To address these limitations, we present VividFace, a real-time and realistic facial expression shadowing system for humanoid robots. An optimized imitation framework X2CNet++ enhances expressiveness by fine-tuning the human-to-humanoid facial motion transfer module and introducing a feature-adaptation training strategy for better alignment across different image sources. Real-time shadowing is further enabled by a video-stream-compatible inference pipeline and a streamlined workflow based on asynchronous I/O for efficient communication across devices. VividFace produces vivid humanoid faces by mimicking human facial expressions within 0.05 seconds, while generalizing across diverse facial configurations. Extensive real-world demonstrations validate its practical utility. Videos are available at: https://lipzh5.github.io/VividFace/. △ Less

Submitted 14 February, 2026; v1 submitted 7 February, 2026; originally announced February 2026.

Comments: Accepted to the 2026 IEEE International Conference on Robotics and Automation (ICRA)

SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management

Authors: Shengyue Guan, Yihao Liu, Lang Cao

Abstract: Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this settin… ▽ More Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this setting, we introduce SupChain-Bench, a unified real-world benchmark that assesses both supply chain domain knowledge and long-horizon tool-based orchestration grounded in standard operating procedures (SOPs). Our experiments reveal substantial gaps in execution reliability across models. We further propose SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieving the strongest and most consistent tool-calling performance. Our work establishes a principled benchmark for studying reliable long-horizon orchestration in real-world operational settings and highlights significant room for improvement in LLM-based supply chain agents. △ Less

Submitted 6 February, 2026; originally announced February 2026.

KRONE: Hierarchical and Modular Log Anomaly Detection

Authors: Lei Ma, Jinyang Liu, Tieying Zhang, Peter M. VanNostrand, Dennis M. Hofmann, Lei Cao, Elke A. Rundensteiner, Jianjun Chen

Abstract: Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when stored as flat sequences. As a result, state-of-the-art methods often miss true dependencies within executions while learning spurious correlations across unrelated events. We propose KRONE, the first hierarc… ▽ More Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when stored as flat sequences. As a result, state-of-the-art methods often miss true dependencies within executions while learning spurious correlations across unrelated events. We propose KRONE, the first hierarchical anomaly detection framework that automatically derives execution hierarchies from flat logs to enable modular, multi-level anomaly detection. At its core, the KRONE Log Abstraction Model extracts application-specific semantic hierarchies, which are used to recursively decompose log sequences into coherent execution units, referred to as KRONE Seqs. This transforms sequence-level detection into a set of modular KRONE Seq-level detection tasks. For each test KRONE Seq, KRONE adopts a hybrid modular detection strategy that routes between an efficient level-independent Local-Context detector for rapid filtering and a Nested-Aware detector that captures cross-level semantic dependencies, augmented with LLM-based anomaly detection and explanation. KRONE further optimizes detection through cached result reuse and early-exit strategies along the hierarchy. Experiments on three public benchmarks and one industrial dataset from ByteDance Cloud demonstrate that KRONE achieves substantial improvements in accuracy (42.49% to 87.98%), F1 score, data efficiency (117.3x reduction), resource efficiency (43.7x reduction), and interpretability. KRONE improves F1-score by 10.07% (82.76% to 92.83%) over prior methods while reducing LLM usage to only 1.1% to 3.3% of the test data. Code: https://github.com/LeiMa0324/KRONE Demo: https://leima0324.github.io/KRONE_Demo_official/ △ Less

Submitted 25 March, 2026; v1 submitted 6 February, 2026; originally announced February 2026.

Comments: Accepted at ICDE 2026

Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images

Authors: Jieyun Tan, Shuo Liu, Guibin Zhang, Ziqi Li, Jian Geng, Lei Zhang, Lei Cao

Abstract: Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, buil… ▽ More Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, building high-accuracy cleaning models. A Label Selection Module leverages discrepancies between crowdsourced labels and model predictions for both sample selection and instance-level noise grading. Experiments show our method achieves 67.18% AP\textsubscript{50} on a private dataset, an 18.83% improvement over training on noisy labels. This performance reaches 95.79% of that with full expert annotation while reducing annotation cost by 73.30%. The method provides a practical, cost-effective solution for developing reliable medical AI with limited expert resources. △ Less

Submitted 4 February, 2026; originally announced February 2026.

Comments: 10 pages, 6 figures

Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models

Authors: Yu Zhang, Xinchen Li, Jialei Zhou, Hongnan Ma, Zhongwei Wan, Yiwei Shi, Duoqian Miao, Qi Zhang, Longbing Cao

Abstract: Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which inevitably fragments complete semantic or syntactic constituents, leading to suboptimal performance.… ▽ More Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which inevitably fragments complete semantic or syntactic constituents, leading to suboptimal performance. Inspired by the entropy reduction hypothesis (ERH), we recognize that constituent boundaries offer greater opportunities for uncertainty reduction, which motivates us to employ entropy analysis for identifying constituent boundaries. Therefore, we propose Swordsman, an entropy-driven adaptive block-wise decoding framework for DLMs. Swordsman adaptively partitions blocks by identifying entropy shifts between adjacent tokens to better align with semantic or syntactic constituent boundaries. In addition, Swordsman dynamically adjusts unmasking thresholds conditioned on the real-time unmasking status within a block, further improving both efficiency and stability. As a training-free framework, supported by KV Cache, Swordsman demonstrates state-of-the-art performance across extensive evaluations. △ Less

Submitted 4 February, 2026; originally announced February 2026.

Referring Industrial Anomaly Segmentation

Authors: Pengfei Yue, Xiaokang Jiang, Yilin Lu, Jianghang Lin, Shengchuan Zhang, Liujuan Cao

Abstract: Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manual thresholds, while supervised methods overfit due to scarce, imbalanced data. Both suffer from the "One Anomaly Class, One Model" limitation. To address this, we propose Referring Industrial Anomaly Segmentation (RIAS)… ▽ More Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manual thresholds, while supervised methods overfit due to scarce, imbalanced data. Both suffer from the "One Anomaly Class, One Model" limitation. To address this, we propose Referring Industrial Anomaly Segmentation (RIAS), a paradigm leveraging language to guide detection. RIAS generates precise masks from text descriptions without manual thresholds and uses universal prompts to detect diverse anomalies with a single model. We introduce the MVTec-Ref dataset to support this, designed with diverse referring expressions and focusing on anomaly patterns, notably with 95% small anomalies. We also propose the Dual Query Token with Mask Group Transformer (DQFormer) benchmark, enhanced by Language-Gated Multi-Level Aggregation (LMA) to improve multi-scale segmentation. Unlike traditional methods using redundant queries, DQFormer employs only "Anomaly" and "Background" tokens for efficient visual-textual integration. Experiments demonstrate RIAS's effectiveness in advancing IAD toward open-set capabilities. Code: https://github.com/swagger-coder/RIAS-MVTec-Ref. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Lung Nodule Image Synthesis Driven by Two-Stage Generative Adversarial Networks

Authors: Lu Cao, Xiquan He, Junying Zeng, Chaoyun Mai, Min Luo

Abstract: The limited sample size and insufficient diversity of lung nodule CT datasets severely restrict the performance and generalization ability of detection models. Existing methods generate images with insufficient diversity and controllability, suffering from issues such as monotonous texture features and distorted anatomical structures. Therefore, we propose a two-stage generative adversarial networ… ▽ More The limited sample size and insufficient diversity of lung nodule CT datasets severely restrict the performance and generalization ability of detection models. Existing methods generate images with insufficient diversity and controllability, suffering from issues such as monotonous texture features and distorted anatomical structures. Therefore, we propose a two-stage generative adversarial network (TSGAN) to enhance the diversity and spatial controllability of synthetic data by decoupling the morphological structure and texture features of lung nodules. In the first stage, StyleGAN is used to generate semantic segmentation mask images, encoding lung nodules and tissue backgrounds to control the anatomical structure of lung nodule images; The second stage uses the DL-Pix2Pix model to translate the mask map into CT images, employing local importance attention to capture local features, while utilizing dynamic weight multi-head window attention to enhance the modeling capability of lung nodule texture and background. Compared to the original dataset, the accuracy improved by 4.6% and mAP by 4% on the LUNA16 dataset. Experimental results demonstrate that TSGAN can enhance the quality of synthetic images and the performance of detection models. △ Less

Submitted 2 February, 2026; originally announced February 2026.

Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis

Authors: Yu Zhang, Jingyi Liu, Feng Liu, Duoqian Miao, Qi Zhang, Kexue Fu, Changwei Wang, Longbing Cao

Abstract: Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive schedules, and limited acceleration scope, thereby leaving significant acceleration potential untapped.… ▽ More Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive schedules, and limited acceleration scope, thereby leaving significant acceleration potential untapped. Since entropy variation intrinsically reflects the transition of predictive uncertainty, it offers a principled measure to capture modeling dynamics evolution. Therefore, we propose NOVA, a training-free token reduction acceleration framework for VAR models via entropy analysis. NOVA adaptively determines the acceleration activation scale during inference by online identifying the inflection point of scale entropy growth. Through scale-linkage and layer-linkage ratio adjustment, NOVA dynamically computes distinct token reduction ratios for each scale and layer, pruning low-entropy tokens while reusing the cache derived from the residuals at the prior scale to accelerate inference and maintain generation quality. Extensive experiments and analyses validate NOVA as a simple yet effective training-free acceleration framework. △ Less

Submitted 1 February, 2026; originally announced February 2026.

Comments: 11 pages, 8 figures

Constructing BERT Models: How Team Dynamics and Focus Shape AI Model Impact

Authors: Likun Cao, Kai Li

Abstract: The rapid evolution of AI technologies, exemplified by BERT-family models, has transformed scientific research, yet little is known about their production and recognition dynamics in the scientific system. This study investigates the development and impact of BERT-family models, focusing on team size, topic specialization, and citation patterns behind the models. Using a dataset of 4,208 BERT-rela… ▽ More The rapid evolution of AI technologies, exemplified by BERT-family models, has transformed scientific research, yet little is known about their production and recognition dynamics in the scientific system. This study investigates the development and impact of BERT-family models, focusing on team size, topic specialization, and citation patterns behind the models. Using a dataset of 4,208 BERT-related papers from the Papers with Code (PWC) dataset, we analyze how the BERT-family models evolve across methodological generations and how the newness of models is correlated with their production and recognition. Our findings reveal that newer BERT models are developed by larger, more experienced, and institutionally diverse teams, reflecting the increasing complexity of AI research. Additionally, these models exhibit greater topical specialization, targeting niche applications, which aligns with broader trends in scientific specialization. However, newer models receive fewer citations, particularly over the long term, suggesting a "first-mover advantage," where early models like BERT garner disproportionate recognition. These insights highlight the need for equitable evaluation frameworks that value both foundational and incremental innovations. This study underscores the evolving interplay between collaboration, specialization, and recognition in AI research. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Comments: The paper has been accepted by Quantitative Science Studies

EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation

Authors: Lang Cao, Qingyu Chen, Yue Guo

Abstract: Electronic Health Records (EHRs) provide rich longitudinal clinical evidence that is central to medical decision-making, motivating the use of retrieval-augmented generation (RAG) to ground large language model (LLM) predictions. However, long-horizon EHRs often exceed LLM context limits, and existing approaches commonly rely on truncation or vanilla retrieval strategies that discard clinically re… ▽ More Electronic Health Records (EHRs) provide rich longitudinal clinical evidence that is central to medical decision-making, motivating the use of retrieval-augmented generation (RAG) to ground large language model (LLM) predictions. However, long-horizon EHRs often exceed LLM context limits, and existing approaches commonly rely on truncation or vanilla retrieval strategies that discard clinically relevant events and temporal dependencies. To address these challenges, we propose EHR-RAG, a retrieval-augmented framework designed for accurate interpretation of long-horizon structured EHR data. EHR-RAG introduces three components tailored to longitudinal clinical prediction tasks: Event- and Time-Aware Hybrid EHR Retrieval to preserve clinical structure and temporal dynamics, Adaptive Iterative Retrieval to progressively refine queries in order to expand broad evidence coverage, and Dual-Path Evidence Retrieval and Reasoning to jointly retrieves and reasons over both factual and counterfactual evidence. Experiments across four long-horizon EHR prediction tasks show that EHR-RAG consistently outperforms the strongest LLM-based baselines, achieving an average Macro-F1 improvement of 10.76%. Overall, our work highlights the potential of retrieval-augmented LLMs to advance clinical prediction on structured EHR data in practice. △ Less

Submitted 29 January, 2026; originally announced January 2026.

QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding

Authors: Linhan Cao, Wei Sun, Weixia Zhang, Xiangyang Zhu, Kaiwei Zhang, Jun Jia, Dandan Zhu, Guangtao Zhai, Xiongkuo Min

Abstract: Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spatiotemporal perception} and \textit{auxiliary contextual information}. Current approaches rely on supervised fine-tuning or reinforcement learning on curated instruction datasets, which involve labor-intensive annotation… ▽ More Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spatiotemporal perception} and \textit{auxiliary contextual information}. Current approaches rely on supervised fine-tuning or reinforcement learning on curated instruction datasets, which involve labor-intensive annotation and are prone to dataset-specific biases. To address these challenges, we propose \textbf{QualiRAG}, a \textit{training-free} \textbf{R}etrieval-\textbf{A}ugmented \textbf{G}eneration \textbf{(RAG)} framework that systematically leverages the latent perceptual knowledge of large multimodal models (LMMs) for visual quality perception. Unlike conventional RAG that retrieves from static corpora, QualiRAG dynamically generates auxiliary knowledge by decomposing questions into structured requests and constructing four complementary knowledge sources: \textit{visual metadata}, \textit{subject localization}, \textit{global quality summaries}, and \textit{local quality descriptions}, followed by relevance-aware retrieval for evidence-grounded reasoning. Extensive experiments show that QualiRAG achieves substantial improvements over open-source general-purpose LMMs and VQA-finetuned LMMs on visual quality understanding tasks, and delivers competitive performance on visual quality comparison tasks, demonstrating robust quality assessment capabilities without any task-specific training. The code will be publicly available at https://github.com/clh124/QualiRAG. △ Less

Submitted 26 January, 2026; originally announced January 2026.

Preventing the Collapse of Peer Review Requires Verification-First AI

Authors: Lei You, Lele Cao, Iryna Gurevych

Abstract: This paper argues that AI-assisted peer review should be verification-first rather than review-mimicking. We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth, as the right objective for review tools. We formalize two forces that drive a phase transition toward proxy-sovereign evaluation: verification pressure, when claims outpace verification capacity, and signal… ▽ More This paper argues that AI-assisted peer review should be verification-first rather than review-mimicking. We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth, as the right objective for review tools. We formalize two forces that drive a phase transition toward proxy-sovereign evaluation: verification pressure, when claims outpace verification capacity, and signal shrinkage, when real improvements become hard to separate from noise. In a minimal model that mixes occasional high-fidelity checks with frequent proxy judgment, we derive an explicit coupling law and an incentive-collapse condition under which rational effort shifts from truth-seeking to proxy optimization, even when current decisions still appear reliable. These results motivate actions for tool builders and program chairs: deploy AI as an adversarial auditor that generates auditable verification artifacts and expands effective verification bandwidth, rather than as a score predictor that amplifies claim inflation. △ Less

Submitted 12 February, 2026; v1 submitted 23 January, 2026; originally announced January 2026.

LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting

Authors: Yuhan Chen, Wenxuan Yu, Guofa Li, Yijun Xu, Ying Fang, Yicui Shi, Long Cao, Wenbo Chu, Keqiang Li

Abstract: 2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios. However, existing low-light enhancement algorithms operate predominantly within the pixel domain. Processing 2DGS-compressed images necessitates a cumbersome decompression-enhancement-recompression pipeline, which compro… ▽ More 2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios. However, existing low-light enhancement algorithms operate predominantly within the pixel domain. Processing 2DGS-compressed images necessitates a cumbersome decompression-enhancement-recompression pipeline, which compromises efficiency and introduces secondary degradation. To address these limitations, we propose LL-GaussianImage, the first zero-shot unsupervised framework designed for low-light enhancement directly within the 2DGS compressed representation domain. Three primary advantages are offered by this framework. First, a semantic-guided Mixture-of-Experts enhancement framework is designed. Dynamic adaptive transformations are applied to the sparse attribute space of 2DGS using rendered images as guidance to enable compression-as-enhancement without full decompression to a pixel grid. Second, a multi-objective collaborative loss function system is established to strictly constrain smoothness and fidelity during enhancement, suppressing artifacts while improving visual quality. Third, a two-stage optimization process is utilized to achieve reconstruction-as-enhancement. The accuracy of the base representation is ensured through single-scale reconstruction and network robustness is enhanced. High-quality enhancement of low-light images is achieved while high compression ratios are maintained. The feasibility and superiority of the paradigm for direct processing within the compressed representation domain are validated through experimental results. △ Less

Submitted 22 January, 2026; originally announced January 2026.

Online identification of nonlinear time-varying systems with uncertain information

Authors: He Ren, Gaowei Yan, Hang Liu, Lifeng Cao, Zhijun Zhao, Gang Dang

Abstract: Digital twins (DTs), serving as the core enablers for real-time monitoring and predictive maintenance of complex cyber-physical systems, impose critical requirements on their virtual models: high predictive accuracy, strong interpretability, and online adaptive capability. However, existing techniques struggle to meet these demands simultaneously: Bayesian methods excel in uncertainty quantificati… ▽ More Digital twins (DTs), serving as the core enablers for real-time monitoring and predictive maintenance of complex cyber-physical systems, impose critical requirements on their virtual models: high predictive accuracy, strong interpretability, and online adaptive capability. However, existing techniques struggle to meet these demands simultaneously: Bayesian methods excel in uncertainty quantification but lack model interpretability, while interpretable symbolic identification methods (e.g., SINDy) are constrained by their offline, batch-processing nature, which make real-time updates challenging. To bridge this semantic and computational gap, this paper proposes a novel Bayesian Regression-based Symbolic Learning (BRSL) framework. The framework formulates online symbolic discovery as a unified probabilistic state-space model. By incorporating sparse horseshoe priors, model selection is transformed into a Bayesian inference task, enabling simultaneous system identification and uncertainty quantification. Furthermore, we derive an online recursive algorithm with a forgetting factor and establish precise recursive conditions that guarantee the well-posedness of the posterior distribution. These conditions also function as real-time monitors for data utility, enhancing algorithmic robustness. Additionally, a rigorous convergence analysis is provided, demonstrating the convergence of parameter estimates under persistent excitation conditions. Case studies validate the effectiveness of the proposed framework in achieving interpretable, probabilistic prediction and online learning. △ Less

Submitted 15 January, 2026; originally announced January 2026.

HGATSolver: A Heterogeneous Graph Attention Solver for Fluid-Structure Interaction

Authors: Qin-Yi Zhang, Hong Wang, Siyao Liu, Haichuan Lin, Linying Cao, Xiao-Hu Zhou, Chen Chen, Shuangyi Wang, Zeng-Guang Hou

Abstract: Fluid-structure interaction (FSI) systems involve distinct physical domains, fluid and solid, governed by different partial differential equations and coupled at a dynamic interface. While learning-based solvers offer a promising alternative to costly numerical simulations, existing methods struggle to capture the heterogeneous dynamics of FSI within a unified framework. This challenge is further… ▽ More Fluid-structure interaction (FSI) systems involve distinct physical domains, fluid and solid, governed by different partial differential equations and coupled at a dynamic interface. While learning-based solvers offer a promising alternative to costly numerical simulations, existing methods struggle to capture the heterogeneous dynamics of FSI within a unified framework. This challenge is further exacerbated by inconsistencies in response across domains due to interface coupling and by disparities in learning difficulty across fluid and solid regions, leading to instability during prediction. To address these challenges, we propose the Heterogeneous Graph Attention Solver (HGATSolver). HGATSolver encodes the system as a heterogeneous graph, embedding physical structure directly into the model via distinct node and edge types for fluid, solid, and interface regions. This enables specialized message-passing mechanisms tailored to each physical domain. To stabilize explicit time stepping, we introduce a novel physics-conditioned gating mechanism that serves as a learnable, adaptive relaxation factor. Furthermore, an Inter-domain Gradient-Balancing Loss dynamically balances the optimization objectives across domains based on predictive uncertainty. Extensive experiments on two constructed FSI benchmarks and a public dataset demonstrate that HGATSolver achieves state-of-the-art performance, establishing an effective framework for surrogate modeling of coupled multi-physics systems. △ Less

Submitted 14 January, 2026; originally announced January 2026.

Journal ref: Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1534-1542 (2026)

MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

Authors: Changli Wu, Haodong Wang, Jiayi Ji, Yutian Yao, Chunsai Du, Jihua Kang, Yanwei Fu, Liujuan Cao

Abstract: Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints. We introduce Multi-view 3D Referring Expression Segmentation (MV-3DRES), where the model must recover scene structure and segment the referred object directly fr… ▽ More Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints. We introduce Multi-view 3D Referring Expression Segmentation (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images. Traditional two-stage pipelines, which first reconstruct a point cloud and then perform segmentation, often yield low-quality geometry, produce coarse or degraded target regions, and run slowly. We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning through a dual-branch design. Training in this setting exposes a critical optimization barrier, termed Foreground Gradient Dilution (FGD), where sparse 3D signals lead to weak supervision. To resolve this, we introduce Per-view No-target Suppression Optimization (PVSO), which provides stronger and more balanced gradients across views, enabling stable and efficient learning. To support consistent evaluation, we build MVRefer, a benchmark that defines standardized settings and metrics for MV-3DRES. Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives. The code is available at https://mvggt.github.io/. △ Less

Submitted 31 March, 2026; v1 submitted 11 January, 2026; originally announced January 2026.

Comments: Accepted to CVPR 2026; Project Website: https://mvggt.github.io/

TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL

Authors: Lang Cao, Hui Ruan, Yongqian Li, Peng Chao, Wu Ning, Haonan Song, Renhong Chen, Yitong Li

Abstract: Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large language models on complex reasoning tasks. However, standard GRPO treats each rollout trajectory as an independent flat sequence and assigns a single sequence-level advantage to all tokens, which leads to sample inefficiency and a length bias toward verbo… ▽ More Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large language models on complex reasoning tasks. However, standard GRPO treats each rollout trajectory as an independent flat sequence and assigns a single sequence-level advantage to all tokens, which leads to sample inefficiency and a length bias toward verbose, redundant chains of thought without improving logical depth. We introduce TreeAdv (Tree-Structured Advantage Redistribution for Group-Based RL), which makes the tree structure of group rollouts explicit for both exploration and advantage assignment. Specifically, TreeAdv builds a group of trees (a forest) based on an entropy-driven sampling method where each tree branches at high-uncertainty decisions while sharing low-uncertainty tokens across rollouts. Then, TreeAdv aggregates token-level advantages for internal tree segments by redistributing the advantages of complete rollouts (all leaf nodes), and TreeAdv can easily apply to group-based objectives such as GRPO or GSPO. Across 10 math reasoning benchmarks, TreeAdv consistently outperforms GRPO and GSPO, while using substantially fewer generated tokens under identical supervision, data, and decoding budgets. △ Less

Submitted 9 April, 2026; v1 submitted 7 January, 2026; originally announced January 2026.

Deep versus Broad Technology Search and the Timing of Innovation Impact

Authors: Likun Cao, James Evans

Abstract: This study offers a new perspective on the depth-versus-breadth debate in innovation strategy, by modeling inventive search within dynamic collective knowledge systems, and underscoring the importance of timing for technological impact. Using frontier machine learning to project patent citation networks in hyperbolic space, we analyze 4.9 million U.S. patents to examine how search strategies give… ▽ More This study offers a new perspective on the depth-versus-breadth debate in innovation strategy, by modeling inventive search within dynamic collective knowledge systems, and underscoring the importance of timing for technological impact. Using frontier machine learning to project patent citation networks in hyperbolic space, we analyze 4.9 million U.S. patents to examine how search strategies give rise to distinct temporal patterns in impact accumulation. We find that inventions based on deep search, which relies on a specialized understanding of complex recombination structures, drive higher short-term impact through early adoption within specialized communities, but face diminishing returns as innovations become "locked-in" with limited diffusion potential. Conversely, when inventions are grounded in broad search that spans disparate domains, they encounter initial resistance but achieve wider diffusion and greater long-term impact by reaching cognitively diverse audiences. Individual inventions require both depth and breadth for stable impact. Organizations can strategically balance approaches across multiple inventions: using depth to build reliable technological infrastructure while pursuing breadth to expand applications. We advance innovation theory by demonstrating how deep and broad search strategies distinctly shape the timing and trajectory of technological impact, and how individual inventors and organizations can leverage these mechanisms to balance exploitation and exploration. △ Less

Submitted 30 December, 2025; originally announced January 2026.

Comments: 47 pages, 8 figures, 3 tables

Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting

Authors: Kai Ye, Xiaotong You, Jianghang Lin, Jiayi Ji, Pingyang Dai, Liujuan Cao

Abstract: Reasoning Segmentation requires models to interpret complex, context-dependent linguistic queries to achieve pixel-level localization. Current dominant approaches rely heavily on Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). However, SFT suffers from catastrophic forgetting and domain dependency, while RL is often hindered by training instability and rigid reliance on predefined rew… ▽ More Reasoning Segmentation requires models to interpret complex, context-dependent linguistic queries to achieve pixel-level localization. Current dominant approaches rely heavily on Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). However, SFT suffers from catastrophic forgetting and domain dependency, while RL is often hindered by training instability and rigid reliance on predefined reward functions. Although recent training-free methods circumvent these training burdens, they are fundamentally limited by a static inference paradigm. These methods typically rely on a single-pass "generate-then-segment" chain, which suffers from insufficient reasoning depth and lacks the capability to self-correct linguistic hallucinations or spatial misinterpretations. In this paper, we challenge these limitations and propose EVOL-SAM3, a novel zero-shot framework that reformulates reasoning segmentation as an inference-time evolutionary search process. Instead of relying on a fixed prompt, EVOL-SAM3 maintains a population of prompt hypotheses and iteratively refines them through a "Generate-Evaluate-Evolve" loop. We introduce a Visual Arena to assess prompt fitness via reference-free pairwise tournaments, and a Semantic Mutation operator to inject diversity and correct semantic errors. Furthermore, a Heterogeneous Arena module integrates geometric priors with semantic reasoning to ensure robust final selection. Extensive experiments demonstrate that EVOL-SAM3 not only substantially outperforms static baselines but also significantly surpasses fully supervised state-of-the-art methods on the challenging ReasonSeg benchmark in a zero-shot setting. The code is available at https://github.com/AHideoKuzeA/Evol-SAM3. △ Less

Submitted 31 December, 2025; originally announced December 2025.

Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education

Authors: Hung-Fu Chang, MohammadShokrolah Shirazi, Lizhou Cao, Supannika Koolmanojwong Mobasser

Abstract: Recent advances in large language models (LLMs) have introduced new paradigms in software development, including vibe coding, AI-assisted coding, and agentic coding, fundamentally reshaping how software is designed, implemented, and maintained. Prior research has primarily examined AI-based coding at the individual level or in educational settings, leaving industrial practitioners' perspectives un… ▽ More Recent advances in large language models (LLMs) have introduced new paradigms in software development, including vibe coding, AI-assisted coding, and agentic coding, fundamentally reshaping how software is designed, implemented, and maintained. Prior research has primarily examined AI-based coding at the individual level or in educational settings, leaving industrial practitioners' perspectives underexplored. This paper addresses this gap by investigating how LLM coding tools are used in professional practice, the associated concerns and risks, and the resulting transformations in development workflows, with particular attention to implications for computing education. We conducted a qualitative analysis of 57 curated YouTube videos published between late 2024 and 2025, capturing reflections and experiences shared by practitioners. Following a filtering and quality assessment process, the selected sources were analyzed to compare LLM-based and traditional programming, identify emerging risks, and characterize evolving workflows. Our findings reveal definitions of AI-based coding practices, notable productivity gains, and lowered barriers to entry. Practitioners also report a shift in development bottlenecks toward code review and concerns regarding code quality, maintainability, security vulnerabilities, ethical issues, erosion of foundational problem-solving skills, and insufficient preparation of entry-level engineers. Building on these insights, we discuss implications for computer science and software engineering education and argue for curricular shifts toward problem-solving, architectural thinking, code review, and early project-based learning that integrates LLM tools. This study offers an industry-grounded perspective on AI-based coding and provides guidance for aligning educational practices with rapidly evolving professional realities. △ Less

Submitted 29 December, 2025; originally announced December 2025.

Comments: 21 pages, 5 figures

ACM Class: D.2; K.6.3; K.3.2

RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure

Authors: Wei Gao, Yuheng Zhao, Tianyuan Wu, Shaopan Xiong, Weixun Wang, Dakai An, Lunxi Cao, Dilxat Muhtar, Zichen Liu, Haizhou Zhao, Ju Huang, Siran Yang, Yongbin Li, Wenbo Su, Jiamang Wang, Lin Qu, Bo Zheng, Wei Wang

Abstract: Agentic Reinforcement Learning (RL) enables Large Language Models (LLMs) to perform autonomous decision-making and long-term planning. Unlike standard LLM post-training, agentic RL workloads are highly heterogeneous, combining compute-intensive prefill phases, bandwidth-bound decoding, and stateful, CPU-heavy environment simulations. We argue that efficient agentic RL training requires disaggregat… ▽ More Agentic Reinforcement Learning (RL) enables Large Language Models (LLMs) to perform autonomous decision-making and long-term planning. Unlike standard LLM post-training, agentic RL workloads are highly heterogeneous, combining compute-intensive prefill phases, bandwidth-bound decoding, and stateful, CPU-heavy environment simulations. We argue that efficient agentic RL training requires disaggregated infrastructure to leverage specialized, best-fit hardware. However, naive disaggregation introduces substantial synchronization overhead and resource underutilization due to the complex dependencies between stages. We present RollArc, a distributed system designed to maximize throughput for multi-task agentic RL on disaggregated infrastructure. RollArc is built on three core principles: (1) hardware-affinity workload mapping, which routes compute-bound and bandwidth-bound tasks to bestfit GPU devices, (2) fine-grained asynchrony, which manages execution at the trajectory level to mitigate resource bubbles, and (3) statefulness-aware computation, which offloads stateless components (e.g., reward models) to serverless infrastructure for elastic scaling. Our results demonstrate that RollArc effectively improves training throughput and achieves 1.35-2.05\(\times\) end-to-end training time reduction compared to monolithic and synchronous baselines. We also evaluate RollArc by training a hundreds-of-billions-parameter MoE model for Qoder product on an Alibaba cluster with more than 3,000 GPUs, further demonstrating RollArc scalability and robustness. The code is available at https://github.com/alibaba/ROLL. △ Less

Submitted 27 December, 2025; originally announced December 2025.

Comments: 17 pages, 17 figures

A Lightweight Coordinate-Conditioned Diffusion Approach for 6G C-V2X Radio Environment Maps

Authors: Liu Cao, Zhaoyu Liu, Dongyu Wei, Yuan Yang, Yukun Pan, Lyutianyang Zhang

Abstract: Transmitter vehicles that broadcast 6G Cellular Vehicle-to-Everything (C-V2X)-based messages, e.g., Basic Safety Messages (BSMs), are prone to be impacted by PHY issues due to the lack of dynamic high-fidelity Radio Environment Map (REM) with dynamic location variation. This paper explores a lightweight diffusion-based generative approach, the Coordinate-Conditioned Denoising Diffusion Probabilist… ▽ More Transmitter vehicles that broadcast 6G Cellular Vehicle-to-Everything (C-V2X)-based messages, e.g., Basic Safety Messages (BSMs), are prone to be impacted by PHY issues due to the lack of dynamic high-fidelity Radio Environment Map (REM) with dynamic location variation. This paper explores a lightweight diffusion-based generative approach, the Coordinate-Conditioned Denoising Diffusion Probabilistic Model (CCDDPM), that leverages the signal intensity-based 6G V2X Radio Environment Map (REM) from limited historical transmitter vehicles in a specific region, to predict the REMs for a transmitter vehicle with arbitrary coordinates across the same region. The transmitter vehicle coordinate is encoded as a smooth Gaussian prior and fused with the Gaussian noise through a lightweight two-channel conditional U-Net architecture. We demonstrate that the predicted REM closely matches the statistics and structure of ground-truth REM while exhibiting the improved stability and over other widely applied generative AI approaches. The resulting predictor enables rapid and scenario-consistent REM with arbitrary transmitter coordinates, which thereby supports more efficient 6G C-V2X communications where transmitter vehicles are less likely to suffer from the PHY issues. △ Less

Submitted 30 December, 2025; v1 submitted 27 December, 2025; originally announced December 2025.

Comments: 5 pages,5 figures