arXiv subjects

Hongbin Sun

Publications and source records attributed to Hongbin Sun.

At least 19 recordsLinked to original sources

arXiv2026

Determination of acoustic nonlinearity parameters using thermal modulation of ultrasonic waves

This study presents a test method and its theoretical framework to determine the acoustic nonlinearity parameters ($\alpha,\beta,\delta$) of material using thermal modulation of ultrasonic waves. Temperature change induced thermal strain excites the nonlinear response of the material and modulates the ultrasonic wave propagating in it. Experimental results showed a strong correlation between the relative wave velocity change and the temperature change. With a quadratic polynomial model, the acoustic nonlinearity parameters were obtained from the polynomial coefficients by curve fitting the experimental curves. Their effects on thermal-induced velocity change were discussed. The parameters $\alpha,\beta,\delta$ govern the hysteretic gap, average slope, and curvature of the correlation curve, respectively. The proposed theory was validated on aluminum, steel, intact and damaged concrete samples. The obtained nonlinear parameters show reasonable agreements with values reported in the literature. Compared to other nonlinear acoustic methods using vibration or acoustic excitation, the thermal modulation method generates more uniform, slow changing, and larger strain field in the test sample. Employing thermal effect as the driving force for nonlinearity instead of an undesired influencing factor, this method can measure the absolute values of $\alpha,\beta,\delta$ with good accuracy using a simple ultrasonic test setup.

physics.app-ph↗

arXiv2026

Two aspects of graph 3-manifold groups

We prove that fundamental groups of graph 3-manifolds are virtually poly-free and lie in the family Lex. As a consequence, we prove that all finitely generated 3-manifold groups also have these two properties. The first property is a purely group-theoretical concept, and the second is related to the left-exactness property of bounded cohomology of groups. Both properties are proved by constructing sequences of covers of graph 3-manifolds.

math.GT↗

arXiv2026

CORE Planner: Contextual-memory Oriented Reinforcement-learning in Unknown Environments for Robot Navigation

Autonomous navigation in unknown environments requires a robot to efficiently reach a predefined goal while exploring without prior maps. Although progress has been made in this area, most existing works still rely on traditional planning methods with hand-crafted rules, while learning-based methods often suffer from limited environmental memory and challenges in simulation-to-real (sim-to-real) transfer. To overcome these limitations, we propose a Contextual-memory Oriented Reinforcement-learning (CORE) planner for robot navigation in unknown environments. The proposed CORE planner effectively combines the core advantages of traditional and learning-based methods. Specifically, our method uses a sparse visibility graph for structured environment representation, reducing the computational overhead of dense grid maps, and employs a Transformer network to achieve a holistic environmental understanding, thereby significantly improving navigation efficiency. Moreover, we introduce a visibility graph-based graph sparsification method and a contextual memory mechanism, which alleviates local optima and enhances computational performance in large-scale scenes. Finally, our approach achieves zero-shot sim-to-real transfer after training solely on image-based environments, requiring no fine-tuning. Experimental results show that CORE Planner consistently outperforms state-of-the-art methods, including the traditional FAR Planner and all learning-based baselines, across representative environments, reducing travel distance by 13\% over traditional FAR Planner and by up to 48\% relative to learning-based baselines, with larger gains observed in more complex environments. In real-world scenarios, CORE successfully navigates without human intervention, showcasing zero-shot sim-to-real transfer. Code is available at https://github.com/BBD00/core_planner.

cs.RO↗

arXiv2026

Real-Time Neural Distributed Energy Resources Dispatch with Feasibility Guarantees

The growing penetration of renewable energy necessitates high-frequency real-time scheduling. While neural network-based surrogates enable computationally efficient scheduling, strictly enforcing nonconvex power flow constraints without external solvers remains a fundamental challenge. To bridge this gap, this letter proposes a solver-free neural dispatch framework with rigorous feasibility guarantees. A convex inner approximation of the DistFlow model is first derived via the convex envelope theorem. Building upon this approximation, a robust optimization-based affine policy is formulated to yield a theoretically certified interior-point mapping rule, which is then embedded within a bisection-based projection scheme to efficiently recover feasibility for infeasible NN outputs without any external solver. Experimental results demonstrate that the proposed method restores feasibility on the order of $10^{-3}$ s while maintaining near-optimal performance.

eess.SY↗

arXiv2026

Flexible exponents of non-geometric 3-manifolds

A classical question in quantitative topology is to bound the mapping degree $\operatorname{deg}(f)$ in terms of its Lipchitz constant $\text{Lip}(f)$. For a closed, orientable, Riemannian manifold $M$, the flexible exponent $\alpha(M)$ is the infimum of $\alpha\geqslant 0$ such that $|\text{deg}(f)|\leqslant C\cdot (\text{Lip}(f))^\alpha$ holds for any Lipschitz map $f:M\to M$. For a geometric 3-manifold $M$ in the sense of Thurston, $\alpha(M)$ is determined in \cite{DLWWW}. In this paper, we determine $\alpha(M)$ for non-geometric 3-manifolds.

math.GT↗

arXiv2026

WAT: Online Video Understanding Needs Watching Before Thinking

Multimodal Large Language Models (MLLMs) have shown strong capabilities in image understanding, motivating recent efforts to extend them to video reasoning. However, existing Video LLMs struggle in online streaming scenarios, where long temporal context must be preserved under strict memory constraints. We propose WAT (Watching Before Thinking), a two-stage framework for online video reasoning. WAT separates processing into a query-independent watching stage and a query-triggered thinking stage. The watching stage builds a hierarchical memory system with a Short-Term Memory (STM) that buffers recent frames and a fixed-capacity Long-Term Memory (LTM) that maintains a diverse summary of historical content using a redundancy-aware eviction policy. In the thinking stage, a context-aware retrieval mechanism combines the query with the current STM context to retrieve relevant historical frames from the LTM for cross-temporal reasoning. To support training for online video tasks, we introduce WAT-85K, a dataset containing streaming-style annotations emphasizing real-time perception, backward tracing, and forecasting. Experiments show that WAT achieves state-of-the-art performance on online video benchmarks, including 77.7% accuracy on StreamingBench and 55.2% on OVO-Bench, outperforming existing open-source online Video LLMs while operating at real-time frame rates.

cs.CV↗

arXiv2026

Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization

Post-Training Quantization (PTQ) has emerged as an effective technique for alleviating the substantial computational and memory overheads of Vision-Language Models (VLMs) by compressing both weights and activations without retraining the full model. Existing PTQ methods primarily rely on static identification and global compensation of sensitive or outlier channels, yet they often overlook the distributional differences of these important channels across inputs, leading to unsatisfactory quantization. In this work, we observe that the distributions and occurrence frequencies of important channels vary significantly both across modalities and among tokens, even within the same modality. Accordingly, we propose \textbf{Quant Experts (QE)}, a token-aware adaptive error compensation with mixture-of-experts for VLMs quantization. QE divides the important channels into token-independent and token-dependent groups. For the former, a shared expert is designed for most tokens to compensate for global quantization error using a low-rank adapter. For the latter, routed experts including multiple routed low-rank adapters are elaborated to compensate for local quantization error related to specific tokens. Extensive experiments demonstrate that QE consistently enhances task accuracy across various quantization settings and model scales, ranging from 2B to 70B parameters, while maintaining performance comparable to full-precision models.

cs.CV↗

arXiv2025

Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation

Embodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to support goal-directed behavior can improve long-horizon planning performance. However, they overlook visual frontier boundaries, which fundamentally dictate future trajectories and observations, and fall short of inferring the relationship between partial visual observations and navigation goals. In this paper, we propose Semantic Cognition Over Potential-based Exploration (SCOPE), a zero-shot framework that explicitly leverages frontier information to drive potential-based exploration, enabling more informed and goal-relevant decisions. SCOPE estimates exploration potential with a Vision-Language Model and organizes it into a spatio-temporal potential graph, capturing boundary dynamics to support long-horizon planning. In addition, SCOPE incorporates a self-reconsideration mechanism that revisits and refines prior decisions, enhancing reliability and reducing overconfident errors. Experimental results on two diverse embodied navigation tasks show that SCOPE outperforms state-of-the-art baselines by 4.6\% in accuracy. Further analysis demonstrates that its core components lead to improved calibration, stronger generalization, and higher decision quality.

cs.RO↗

arXiv2025

SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA

Accurate 24-hour solar irradiance forecasting is essential for the safe and economic operation of solar photovoltaic systems. Traditional numerical weather prediction (NWP) models represent the state-of-the-art in forecasting performance but rely on computationally costly data assimilation and solving complicated partial differential equations (PDEs) that simulate atmospheric physics. Here, we introduce SolarSeer, an end-to-end large artificial intelligence (AI) model for solar irradiance forecasting across the Contiguous United States (CONUS). SolarSeer is designed to directly map the historical satellite observations to future forecasts, eliminating the computational overhead of data assimilation and PDEs solving. This efficiency allows SolarSeer to operate over 1,500 times faster than traditional NWP, generating 24-hour cloud cover and solar irradiance forecasts for the CONUS at 5-kilometer resolution in under 3 seconds. Compared with the state-of-the-art NWP in the CONUS, i.e., High-Resolution Rapid Refresh (HRRR), SolarSeer significantly reduces the root mean squared error of solar irradiance forecasting by 27.28% in reanalysis data and 15.35% across 1,800 stations. SolarSeer also effectively captures solar irradiance fluctuations and significantly enhances the first-order irradiance difference forecasting accuracy. SolarSeer's ultrafast, accurate 24-hour solar irradiance forecasts provide strong support for the transition to sustainable, net-zero energy systems.

cs.LG↗

arXiv2025

Maps between circle bundles: Fiber-preserving, Finiteness and Realization of mapping degree sets

Let $E_i$ be an oriented circle bundle over a closed oriented aspherical $n$-manifold $M_i$ with Euler class $e_i\in H^2(M_i;\mathbb{Z})$, $i=1,2$. We prove the following: (i) If every finite-index subgroup of $\pi_1(M_2)$ has trivial center, then any non-zero degree map from $E_1$ to $E_2$ is homotopic to a fiber-preserving map. (ii) The mapping degree set of fiber-preserving maps from $E_1$ to $E_2$ is given by $$\{0\} \cup\{k\cdot \mathrm{deg}(f) \ | \, k\ne 0, \ f\colon M_1\to M_2 \, \text{with} \, \mathrm{deg}(f)\ne 0 \ \text{such that}\, f^\#(e_2)=ke_1\},$$ where $f^\# \colon H^2(M_2;\mathbb{Z})\to H^2(M_1;\mathbb{Z})$ is the induced homomorphism. As applications of (i) and (ii), we obtain the following results with respect to the finiteness and the realization problems for mapping degree sets: ($\mathcal F$) The mapping degree set $D(E_1, E_2)$ is finite if $M_2$ is hyperbolic and $e_2$ is not torsion. ($\mathcal R$) For any finite set $A$ of integers containing $0$ and each $n>2$, $A$ is the mapping degree set $D(M,N)$ for some closed oriented $n$-manifolds $M$ and $N$. Items (i) and ($\mathcal F$) extend in all dimensions $\geq 3$ the previously known $3$-dimensional case (i.e., for maps between circle bundles over hyperbolic surfaces). Item ($\mathcal R$) gives a complete answer to the realization problem for finite sets (containing $0$) in any dimension, establishing in particular the previously unknown cases in dimensions $n= 4, 5$.

math.GT↗

arXiv2025

From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation

Autoregressive (AR) image generators offer a language-model-friendly approach to image generation by predicting discrete image tokens in a causal sequence. However, unlike diffusion models, AR models lack a mechanism to refine previous predictions, limiting their generation quality. In this paper, we introduce TensorAR, a new AR paradigm that reformulates image generation from next-token prediction to next-tensor prediction. By generating overlapping windows of image patches (tensors) in a sliding fashion, TensorAR enables iterative refinement of previously generated content. To prevent information leakage during training, we propose a discrete tensor noising scheme, which perturbs input tokens via codebook-indexed noise. TensorAR is implemented as a plug-and-play module compatible with existing AR models. Extensive experiments on LlamaGEN, Open-MAGVIT2, and RAR demonstrate that TensorAR significantly improves the generation performance of autoregressive models.

cs.CV↗

arXiv2025

On virtual chirality of 3-manifolds

We prove that if a prime 3-manifold M is not finitely covered by the 3-sphere or a product manifold, then M is virtually chiral, i.e. it has a finite cover that does not admit an orientation reversing self-homeomorphism. In general if a 3-manifold contains a virtually chiral prime summand, then it is virtually chiral.

math.GT↗

arXiv2025

Risk Assessment and Vulnerability Identification of Energy-Transportation Infrastructure Systems to Extreme Weather

The interaction between extreme weather events and interdependent critical infrastructure systems involves complex spatiotemporal dynamics. Multi-type emergency decisions within energy-transportation infrastructures significantly influence system performance throughout the extreme weather process. A comprehensive assessment of these factors faces challenges in model complexity, heterogeneous differences between energy and transportation systems, and cross-sector privacy. This paper proposes a risk assessment framework that integrates the heterogeneous energy and transportation systems in the form of a unified network flow model, which enables full accommodation of multiple types of energy-transportation emergency decisions while capturing the compound spatiotemporal impacts of extreme weather on both systems simultaneously. Based on this framework, a targeted method for identifying system vulnerabilities is further developed. This method employs neural network surrogates to achieve privacy protection and accelerated identification while maintaining consideration of system interdependencies. Numerical experiments demonstrate that the proposed framework and method can reveal the risk levels faced by urban infrastructure systems, identify vulnerabilities that should be prioritized for reinforcement, and strike a balance between accuracy and speed.

eess.SY↗

arXiv2024

Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms

We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.

cs.LG↗

arXiv2024

Bidding and Dispatch Strategies with Flexibility Quantification and Pricing for Electric Vehicle Aggregator in Joint Energy-Regulation Market

Managing and unlocking the flexibility hidden in electric vehicles (EVs) has emerged as a critical yet challenging task towards low-carbon power and energy systems. This paper focuses on the online bidding and dispatch strategies for an EV aggregator (EVA) in a joint energy-regulation market, considering EVs' flexibility contributions and compensations. A method for quantifying EV flexibility as a tradable commodity is proposed, allowing the EVA to set flexibility prices based on bid-in supply curves. An EVA bidding model in the joint market incorporate flexibility procurement is formulated. The stochastic model predictive control technique is employed to solve the bidding problem online and address the uncertainties from the electricity markets and the EVs. A power dispatch protocol that ensures a profitable and feasible allocation based on EV flexibility contribution is proposed. An affine mapping control strategy can be derived based on parametric linear programming, enables online indexing of optimal solutions given the regulation signals to avoid repeatedly solving the problem. Numerical experiments show the effectiveness of the proposed scheme, and the solution methodology can be applied in real-time.

eess.SY↗

arXiv2024

Energy Internet: A Standardization-Based Blueprint Design

The decarbonization of power and energy systems faces a bottleneck: The enormous number of user-side resources cannot be properly managed and operated by centralized system operators, who used to send dispatch instructions only to a few large power plants. To break through, we need not only new devices and algorithms, but structural reforms of our energy systems. Taking the Internet as a paradigm, a practicable design of the Energy Internet is presented based on the principle of standardization. A combination of stylized data and energy delivery, referred to as a Block of Energy Exchange (BEE), is designed as the media to be communicated, which is parsed by the Energy Internet Card. Each Energy Internet Card is assigned a unique MAC address, defining a participant of the Energy Internet, whose standardized profile will be automatically updated according to BEE transfers without the intervention of any centralized operator. The structure of Energy Internet and protocols thereof to support the transfer of BEE are presented. System operators will become Energy Internet Service Providers, who operate the energy system by flow control and dispatching centralized resources, which is decoupled from users' behaviors in the Energy Internet. Example shows that the Energy Internet can not only reduce carbon emissions via interactions between peers, but also promotes energy democracy and dwindles the gap in energy equity.

eess.SY↗

arXiv2024

Latent Feature and Attention Dual Erasure Attack against Multi-View Diffusion Models for 3D Assets Protection

Multi-View Diffusion Models (MVDMs) enable remarkable improvements in the field of 3D geometric reconstruction, but the issue regarding intellectual property has received increasing attention due to unauthorized imitation. Recently, some works have utilized adversarial attacks to protect copyright. However, all these works focus on single-image generation tasks which only need to consider the inner feature of images. Previous methods are inefficient in attacking MVDMs because they lack the consideration of disrupting the geometric and visual consistency among the generated multi-view images. This paper is the first to address the intellectual property infringement issue arising from MVDMs. Accordingly, we propose a novel latent feature and attention dual erasure attack to disrupt the distribution of latent feature and the consistency across the generated images from multi-view and multi-domain simultaneously. The experiments conducted on SOTA MVDMs indicate that our approach achieves superior performances in terms of attack effectiveness, transferability, and robustness against defense methods. Therefore, this paper provides an efficient solution to protect 3D assets from MVDMs-based 3D geometry reconstruction.

cs.CV↗

arXiv2024

Residual Deep Reinforcement Learning for Inverter-based Volt-Var Control

A residual deep reinforcement learning (RDRL) approach is proposed by integrating DRL with model-based optimization for inverter-based volt-var control in active distribution networks when the accurate power flow model is unknown. RDRL learns a residual action with a reduced residual action space, based on the action of the model-based approach with an approximate model. RDRL inherits the control capability of the approximate-model-based optimization and enhances the policy optimization capability by residual policy learning. Additionally, it improves the approximation accuracy of the critic and reduces the search difficulties of the actor by reducing residual action space. To address the issues of "too small" or "too large" residual action space of RDRL and further improve the optimization performance, we extend RDRL to a boosting RDRL approach. It selects a much smaller residual action space and learns a residual policy by using the policy of RDRL as a base policy. Simulations demonstrate that RDRL and boosting RDRL improve the optimization performance considerably throughout the learning stage and verify their rationales point-by-point, including 1) inheriting the capability of the approximate model-based optimization, 2) residual policy learning, and 3) learning in a reduced action space.

eess.SY↗