arXiv subjects

Senhua Zhu

Publications and source records attributed to Senhua Zhu.

8 recordsLinked to original sources

arXiv2026

GLAM: Training a latent world model over global spatiotemporal memory for active exploration and navigation

Active exploration and semantic navigation require an embodied agent to build memory from partial observations, predict how the evolution of observed spatial memory may support future motion, and convert that prediction into actionable plans. We present GLAM, a goal-conditioned latent world model trained over global spatiotemporal memory, and GLAM NAV, the complete navigation system built around it. Given historical map tokens, a navigation goal, and the current robot pose, GLAM jointly predicts future map representations and robot-centric waypoint latents, allowing future spatial context and navigation intent to be inferred in a shared representation space. The model follows a JEPA-like latent prediction paradigm, operates directly on map-level latent tokens rather than RGB reconstruction, and uses a pretrained waypoint encoder-decoder to supervise and decode navigation plans within GLAM NAV. Training data are collected by replaying ObjectNav expert trajectories in Habitat over HM3D v0.2 scene assets and slicing them into multi-timescale prediction samples. On a controlled HM3D-ObjectNav subset reproduction setting, GLAM NAV improves over a reproduced BSC-Nav baseline in both success rate and success weighted by path length.

cs.RO↗

arXiv2026

PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies

Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not explicitly required to describe how the scene evolves over multiple time scales, and deployment trajectories of unequal quality are often reused without separating useful dynamics from undesirable behavior. We introduce \method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement. \method first retains a local fixed-offset JEPA objective and adds trajectory-relative multi-horizon transition alignment at 25%, 50%, 75%, and 100% of the remaining episode. These training-only targets require the current policy representation to preserve both local physical changes and longer-range task progress, without supplying explicit future tokens to the action head. \method then trains an independent distributional value critic on cumulative deployment trajectories, computes action-chunk-aligned $N$-step advantages, and converts them into positive, negative, or null text conditions for a flow-matching actor. Thus, every valid trajectory can teach what physically happened, while the actor is deployed only under the condition associated with relatively better actions. The multi-horizon predictor and critic are removed from online execution, preserving direct action generation from the current observation, language instruction, and proprioception. \redclaim{Across the three simulation benchmarks, \method achieves the strongest overall performance while preserving the direct actor's online execution path.}

cs.RO↗

arXiv2025

Nearly invariant subspaces and kernels of Toeplitz operators on the Hardy space over the bidisk

In this paper, the analysis of nearly invariant subspaces and kernels of Toeplitz operators on the Hardy space over the bidisk is developed. Firstly, we transcribe Chalendar, Chevrot and Partington's result to vector-valued Hardy space $H^{2}_{\ma{H}}(\mathbb{D})$ when $\ma{H}$ is an infinite dimensional separable complex Hilbert space. Secondly, we explore the definition of nearly invariant subspaces on Hardy space over the bidisk, and apply it to characterize kernels of Toeplitz operators. Finally, we define the nearly invariant subspaces for commutative isometric tuples, which allows us to show that the kernel of general Toeplitz operators is also nearly invariant.

math.FA↗

arXiv2025

A class of linear operators on Bergman spaces

We study the boundedness of the linear operator $S$ on $L^{p}_{a}(dA_α)$ $(0<p<\infty)$. In particular, we obtain a sufficient and necessary condition for the compactness of the linear operator $S$ on $L^{p}_{a}(dA_α)$ $(1<p<\infty)$. Our results weaken the assumptions of earlier results of J. Miao and D. Zheng in a certain sense.

math.FA↗

arXiv2025

Which hyponormal block Toeplitz operators are either normal or analytic?

In this paper, we continue Curto-Hwang-Lee's work to study the connection between hyponormality and subnormality for block Toeplitz operators acting on the vector-valued Hardy space of the unit circle. Curto-Hwang-Lee's work focuses primarily on hyponormality and subnormality of block Toeplitz operators with rational symbols. By studying the greatest common divisor of matrix-valued inner functions and the ``weak" commutativity of matrix-valued inner functions, we extended Curto-Hwang-Lee's result to block Toeplitz operators with symbols of bounded type. More precisely, we proved that if $Ψ,Ψ^{\ast}$ are matrix-valued functions of bounded type and the inner part of $Ψ$ of Douglas-Shapiro-Shields factorization is a scalar inner function, then every hyponormal Toeplitz operator $T_Ψ$ whose square is also hyponormal must be either normal or analytic.

math.FA↗

arXiv2025

Lifelong 3D Mapping Framework for Hand-held & Robot-mounted LiDAR Mapping Systems

We propose a lifelong 3D mapping framework that is modular, cloud-native by design and more importantly, works for both hand-held and robot-mounted 3D LiDAR mapping systems. Our proposed framework comprises of dynamic point removal, multi-session map alignment, map change detection and map version control. First, our sensor-setup agnostic dynamic point removal algorithm works seamlessly with both hand-held and robot-mounted setups to produce clean static 3D maps. Second, the multi-session map alignment aligns these clean static maps automatically, without manual parameter fine-tuning, into a single reference frame, using a two stage approach based on feature descriptor matching and fine registration. Third, our novel map change detection identifies positive and negative changes between two aligned maps. Finally, the map version control maintains a single base map that represents the current state of the environment, and stores the detected positive and negative changes, and boundary information. Our unique map version control system can reconstruct any of the previous clean session maps and allows users to query changes between any two random mapping sessions, all without storing any input raw session maps, making it very unique. Extensive experiments are performed using hand-held commercial LiDAR mapping devices and open-source robot-mounted LiDAR SLAM algorithms to evaluate each module and the whole 3D lifelong mapping framework.

cs.RO↗

arXiv2022

Intrinsic Bias Identification on Medical Image Datasets

Machine learning based medical image analysis highly depends on datasets. Biases in the dataset can be learned by the model and degrade the generalizability of the applications. There are studies on debiased models. However, scientists and practitioners are difficult to identify implicit biases in the datasets, which causes lack of reliable unbias test datasets to valid models. To tackle this issue, we first define the data intrinsic bias attribute, and then propose a novel bias identification framework for medical image datasets. The framework contains two major components, KlotskiNet and Bias Discriminant Direction Analysis(bdda), where KlostkiNet is to build the mapping which makes backgrounds to distinguish positive and negative samples and bdda provides a theoretical solution on determining bias attributes. Experimental results on three datasets show the effectiveness of the bias attributes discovered by the framework.

cs.CV↗

arXiv2021

DuCN: Dual-children Network for Medical Diagnosis and Similar Case Recommendation towards COVID-19

Early detection of the coronavirus disease 2019 (COVID-19) helps to treat patients timely and increase the cure rate, thus further suppressing the spread of the disease. In this study, we propose a novel deep learning based detection and similar case recommendation network to help control the epidemic. Our proposed network contains two stages: the first one is a lung region segmentation step and is used to exclude irrelevant factors, and the second is a detection and recommendation stage. Under this framework, in the second stage, we develop a dual-children network (DuCN) based on a pre-trained ResNet-18 to simultaneously realize the disease diagnosis and similar case recommendation. Besides, we employ triplet loss and intrapulmonary distance maps to assist the detection, which helps incorporate tiny differences between two images and is conducive to improving the diagnostic accuracy. For each confirmed COVID-19 case, we give similar cases to provide radiologists with diagnosis and treatment references. We conduct experiments on a large publicly available dataset (CC-CCII) and compare the proposed model with state-of-the-art COVID-19 detection methods. The results show that our proposed model achieves a promising clinical performance.

eess.IV↗