arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 145 records · Page 8Linked to original sources

arXiv2026

ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding

Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to entity confusion, error propagation, and hallucinated answers. We propose ViSAGE, a multimodal agentic memory framework that constructs self-correcting, entity-centric memories. Specifically, ViSAGE anchors entity identity via cross-modal binding over long temporal ranges. It then applies bidirectional memory refinement to propagate delayed identity evidence, retroactively unifying historical records and improving future reasoning. We also introduce multi-agent cross-verification to assess retrieved evidence under an identity-evidence alignment onstraint, enabling abstention instead of unsupported answers when evidence is missing. Extensive results demonstrate that ViSAGE consistently outperforms the strongest baseline, achieving 5.9% higher accuracy.

cs.AI↗

arXiv2026

MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents

Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized responses, and knowledge reuse. However, existing LLM memory systems typically adopt a coarse-grained (utility-agnostic) manner that treats heterogeneous user-LLM interaction records uniformly, leading to redundant and low-impact records persisting in the memory repository. To address this challenge, we present MemLens, a value-aware memory management system that takes memory records as first-class data objects. MemLens provides an end-to-end interactive analytics dashboard that exposes the complete memory lifecycle, including Shapley-style memory evaluation, value-aware storage, and memory-assisted response. Through a study-copilot application, the system enables users to inspect memory values, visualize hierarchical memory structures, and compare various memory management strategies in terms of response quality, retrieval latency, and token consumption. Therefore, our MemLens can serve as an efficient, interpretable, and personalized long-term memory management system for LLM-based agents.

cs.DB↗

arXiv2026

ISAC-Enabled On-Demand UAV Charging for Wireless Rechargeable Sensor Networks

Unmanned aerial vehicles (UAVs) equipped with wireless power transfer (WPT) extend the lifetime of wireless rechargeable sensor networks (WRSNs) by delivering energy on demand. This article presents an integrated sensing and communication (ISAC)-enabled on-demand UAV charging framework coordinated by a central base station. A prioritized charging queue captures node urgency and service cost through residual energy, traffic load, estimated UAV travel time, and flight-direction alignment. This bidirectional coupling ensures that scheduling decisions shape the UAV trajectory, while updated mobility estimates from ISAC dynamically reorder the queue. ISAC-assisted estimation of UAV distance, speed, and position updates travel-time predictions under mobility uncertainty. A time-allocated partial charging policy distributes limited hover time across queued nodes according to criticality. Simulations show gains in energy usage efficiency, travel distance, and charging delay compared with representative baselines. We discuss deployment considerations, including computational overhead, scalability, and parameter selection, to aid practitioners evaluating the framework for IoT scenarios.

cs.NI↗

arXiv2026

TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs

Unmanned aerial vehicles (UAVs) have emerged as a key enabler of next-generation Internet of Things (IoT) ecosystems, offering flexible aerial relaying to extend connectivity across dynamic vehicular ad hoc networks (VANETs) in smart city environments. However, conventional centralized approaches for UAV trajectory planning require continuous global network state aggregation, making them impractical under bandwidth and energy constraints typical of dense urban deployments. In this article, we present TRUAV, a distributed multi-agent reinforcement learning framework based on independent tabular Q-learning for joint UAV trajectory planning and routing enhancement in UAV-aided VANETs. Each UAV is equipped with a local Q-learning agent that operates purely on locally observable information, including vehicle density, packet queue states, and neighbor UAV positions, thereby eliminating the need for global state exchange. A potential-game-inspired reward design encourages spatial diversity and routing-aware UAV positioning among interacting agents while accounting for energy consumption. Numerical simulations over a large urban area with 200 mobile vehicles show that the proposed TRUAV framework achieves network coverage and packet delivery ratios comparable to centralized deep reinforcement learning methods, while also improving relay delay and energy efficiency. Finally, we discuss emerging challenges and future research directions for distributed multi-agent UAV-assisted IoT systems.

cs.NI↗

arXiv2026

PIML-OFEM: A New Large-Scale Structural Analysis Method Based on Problem-Independent Machine Learning and Overlapping Finite Element Technique

High-resolution analysis and design of large-scale heterogeneous structures require accurate reduced-order models and efficient online computation. Existing multiscale methods must repeatedly construct local basis functions for different material distributions, whereas substructure-based problem-independent machine learning (PIML) methods can be limited by prescribed boundary displacement interpolation. We propose PIML-OFEM, an overlapping finite element method accelerated by problem-independent machine learning. Each substructure retains only its corner-node degrees of freedom. Oversampled numerical basis functions are constructed by solving local elasticity problems on extended domains and restricting the solutions to the target substructure, eliminating prescribed displacement interpolation on its boundary. Independently constructed local bases are blended through a partition-of-unity overlapping formulation to obtain a globally continuous displacement field. A U-Net learns the mapping from local Young's modulus distributions to numerical basis functions, replacing repeated online local solves and allowing the model to be reused across load cases and global boundary conditions. Numerical examples show close agreement with fine-scale finite element results in displacement and elemental strain energy. PIML-OFEM reduces online computational cost relative to direct finite element analysis and improves accuracy over PIML substructure models based on linear boundary interpolation. In topology optimization, the method supports stable high-resolution iterations with small filter radii and preserves fine-scale features, including local patterns resembling rank-2 microstructures. The framework provides an efficient physics-data approach for large-scale heterogeneous structural analysis and high-resolution topology optimization.

math.NA↗

arXiv2026

MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentation

Medical image segmentation models require both high accuracy and lightweight design to accommodate real-world medical applications. The deployment of these models on resource-limited medical platforms remains a significant challenge due to their high computational and parameter requirements. Existing pruning methods for model compression mostly overlook the intrinsic connections and similarity between the internal structures of complex deep neural networks. As a result, compressed models may not effectively retain the basic features of the pretrained network. To solve this problem, we propose a hierarchical clustering compression method for medical image segmentation models (MIS-HCC). This approach employs hierarchical clustering to partition channels and fuse their parameters efficiently. Specifically, it leverages the Wasserstein distance to represent similarity of channels within layers of pre-trained network, forming a similarity matrix that guides the clustering process. Channels within each cluster are then fused to produce a compressed network. Experimental results on three medical image datasets application demonstrate that MIS-HCC outperforms the state-of-the-art methods in both accuracy and compression efficiency, offering an effective solution for deploying medical image segmentation models on resource-limited medical platforms.

cs.CV↗

arXiv2026

Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection

Domain-incremental object detection (DIOD) requires models to continually adapt to new domains while preserving prior knowledge. Recently, parameter-efficient fine-tuning offers a promising avenue, wherein a pre-trained model is frozen and a small number of learnable parameters are injected for downstream tasks. However, these methods risk overwriting critical past knowledge, triggering inter-domain interference and performance degradation. To address this challenge, we propose Orthogonal Knowledge Refreshing (OKR), a simple yet effective framework for DIOD. OKR incrementally constructs independent domain-specific subspaces via dedicated low-rank branches for each domain, which are seamlessly fused for a holistic decision, enabling conflict-free capacity expansion without domain selection during inference. To minimize knowledge interference during fusion, we present a gradient-based orthogonal refreshing strategy that projects gradient updates of new domains onto the orthogonal complement of the fused historical subspace, supporting continual adaptation without forgetting. Moreover, to mitigate semantic fragmentation across domains, we enforce topology-aware consistency, aligning the semantic structures of old and new domains. Extensive experiments validate the superiority of OKR, outperforming the best exemplar-free method by significant margins of +5.6% and +6.5% mAP on the Pascal VOC and BDD100K series, respectively.

cs.CV↗

arXiv2026

Handwritten and Printed Text Segmentation via Region-Aware Human-Writing Descriptor Engineering

With the increasing demand for reusing paper documents in educational and office settings, accurate segmentation of handwritten and printed text has become a crucial step in document digitization. Although numerous deep learning models have been developed for this task, their high computational cost limits deployment on resource-constrained edge devices. To address this challenge, we present a lightweight framework optimized for efficient performance on devices with severely limited computational capacity. Our approach begins with the Sentence-level Connected Component Segmentation algorithm, aimed at extracting coherent sentence-level segments from document images. We then design a novel Region-aware Handwriting Descriptor (RHD) to capture the intrinsic variability of human handwriting at the sentence level. A simple conventional classifier can then be seamlessly integrated with our designed descriptor, demonstrating strong classification performance for distinguishing handwritten and printed sentence-level text images, highlighting that the proposed descriptor is agnostic to the choice of classifier. Extensive experiments are performed on our self-constructed Multilingual High-Quality Annotated Dataset for Handwritten and Printed Text Segmentation (MAD-HPTS) and a public benchmark PHD-AS, and the experimental results demonstrate that the proposed framework outperforms current state-of-the-art methods in both accuracy and computational efficiency. On MAD-HPTS, our method sacrifices only 1.4% accuracy compared to the leading deep neural network baseline, yet achieves more than 8 times speedup in inference, making it well-suited for lightweight deployment.

cs.CV↗

arXiv2026

Video-HOCA: A Diagnostic Benchmark for Physical Anomaly Reasoning in Video-LLMs

We introduce Video-HOCA, a diagnostic benchmark for physical anomaly reasoning in videos. Video-HOCA uses an Ontological-Causal taxonomy to distinguish violations of an entity's own properties or capabilities from violations of physical relations among entities and the environment. It contains more than 1,400 generated and real-world videos and 3,470 question-answer pairs, with human verification of labels and reference answers. The benchmark evaluates four levels of reasoning: plausibility checking, anomaly attribution, fine-grained recognition, and open-ended physical explanation. Across 20 Instruct-mode Video-LLMs, we find that recognition outpaces explanation: Task I scores cluster at 75-88, while Task II macro-F1 stays mostly below 50. We also find that the Ontological-Causal gap depends on the task and model configuration, and that Thinking-mode gains are not explained by sampling or output budget alone. Annotation agreement, Task-IV human-judge and judge-judge checks, alternative metrics, and temporal/decoding controls validate the evaluation pipeline and bound the claims supported by the benchmark.

cs.CV↗

arXiv2026

Ai2-Kit: Streamlining AI-Accelerated Ab Initio Workflows for Complex Chemical Systems

Molecular simulations of complex chemical systems, such as catalysis, electrochemistry, and energy storage, often need to capture the interplay of effects such as electronic structure, finite-temperature fluctuations, and electric-field response. Such complexity is difficult to address with traditional ab initio calculations, which are limited by the time and length scales they can reach. AI-accelerated ab initio (AI2) methods use machine learning potentials trained on first-principles data to replace expensive electronic-structure calculations, extending ab initio accuracy to these regimes, but their routine application requires reliable workflows that connect first-principles calculations, model training, molecular dynamics, enhanced sampling, trajectory analysis, and HPC orchestration. Here we present ai2-kit, a software toolkit for developing accessible, reproducible, and extensible AI2 workflows. ai2-kit provides high-semantic-density command-line interfaces and Python APIs for structure and dataset conversion, batch task generation, active-learning screening, job orchestration, and workflow recovery. We demonstrate ai2-kit in four representative applications: active-learning-based machine learning potential construction, free-energy perturbation for redox and acid-base processes, electrochemical machine learning potentials for electrified interfaces, and spectroscopies from machine learning molecular dynamics. ai2-kit also provides AI-agent skills that help users adapt these use cases into customized workflows for their own chemical systems and computational software stacks. Together, ai2-kit helps turn AI2 methods from bespoke computational protocols into reusable and extensible workflows for complex chemical systems, from model construction to property prediction.

physics.chem-ph↗

arXiv2026

A Collocated Boris Integrator in Flux Coordinates: Balancing Accuracy, Conservation, Cost and Robustness

When the guiding-center description fails and the full gyromotion must be resolved for energetic particles in complex configurations like stellarators, charged-particle integrators must be formulated directly in the curvilinear flux coordinates. The Boris algorithm, which adopts a staggered scheme in Cartesian coordinates, is phase-space-volume-preserving and second-order accurate; but a direct port to flux coordinates degrades the position update to first order, because the evolving basis vectors of the curvilinear frame make the starting-point metric deviate from the ideal midpoint metric. We construct a collocated, midpoint-predicted Boris algorithm in flux coordinates, restoring second-order accuracy at the cost of one additional field evaluation per step. In reactor-scale stellarator magnetic fields, the scheme recovers second-order convergence in every coordinate component, retains near-machine-precision energy conservation and a bounded magnetic moment, and demonstrates greater orbit robustness than Staggered Boris and RK4 at coarse time steps.

physics.plasm-ph↗

arXiv2026

TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling

Global Station Weather Forecasting (GSWF) is pivotal for localized and extreme weather prediction over key regions. Despite efforts to exploit look-back windows, existing methods show limited accuracy gains and struggle with extreme events and error accumulation. These limitations stem from overreliance on short-term patterns, which are insufficient to capture chaotic weather dynamics, especially under partial observations. To address this problem, we propose a novel Triaxial State Space Model (TSSM) with a history-enhanced Temporal-VariableHistorical paradigm, which incorporates period-aligned historical weather data to compensate for long-term, large-scale periodic, and full-window weather patterns beyond the temporal lookback window. Specifically, TSSM stacks historical samples into period-aligned batches, where forecasting is causally supported by historical and current observations. Temporal, variable, and historical scanning are designed to capture axial temporal dependencies, variable correlations, and historical evolution. This structure is hierarchically shared to model seasonal to extreme events while alleviating misalignment across historical patterns. TSSM achieves SOTA performance on Weather-5K, the largest station weather dataset to date, with 10% and 61% gains in accuracy and extreme event metrics, and obtains 95% best or second-best results on human-involved datasets. Its advantages are more pronounced in long-horizon and iterative forecasting, reaching a 37.5% gain at 240h and up to 103.5% under a 48h times 5 iterative setting. Moreover, TSSM retains > 90% performance under up to 80% missing observations, compared with < 43% for baselines, demonstrating robustness and practical potential for reliable GSWF in global in-situ observation networks.

cs.LG↗

arXiv2026

Multiwavelength Analysis of Six Luminous Fast Blue Optical Transients

We present multiwavelength observations and analysis of six luminous fast blue optical transients (LFBOTs) discovered in Zwicky Transient Facility (ZTF) survey data. We identified these LFBOTs from their fast light-curve evolution ($t_{1/2}\leq 12 $d), blue colors at peak brightness ($g-r\leq-0.5 $mag), a visible host galaxy, high optical luminosity ($M_g<-20$), and an X-ray or radio detection. With the exception of AT2024aehp (ZTF24abygbss), these transients exhibit peaks in their $10\,$GHz radio light curves at $t_{\text{rest}} \approx 50-100$ d, with peak radio luminosities ranging from $10^{38}-10^{40}$ erg s$^{-1}$. Modeling the radio emission as synchrotron radiation indicates a fast ($v=0.1-0.3c$) shock in a dense ($n_e\approx10^{3}-10^{4}$ cm$^{-3}$) medium. The X-ray emission varies by $\approx2$ orders of magnitude in luminosity ($10^{42}-10^{44}$ erg s$^{-1}$) at $t_{\text{rest}}\sim20 $d. Analysis of the host-galaxy photometry and spectroscopy for each transient shows that they are predominantly nonnuclear (a few kpc offset) with star-forming host galaxies of stellar masses $10^{9}-10^{11} ,M_\odot$. Unlike all other LFBOTs to date, AT2024aehp exhibited a luminous ($M<-19 $mag) plateau in the optical light curve; spectra during this plateau phase showed a featureless blue continuum. The $6-15$ GHz radio emission of AT2024aehp brightened by over an order of magnitude from $t_{\text{rest}} \approx70 $d to $t_{\mathrm{rest}} \approx130 $d. The mostly consistent radio behavior between optically selected LFBOTs implies a similar circumburst medium, leading us to prefer a progenitor scenario in which mass is lost in a consistent way shortly prior to the terminal event, such as a massive star merging with a compact object.

astro-ph.HE↗

arXiv2026

SAM-MT: Real-Time Interactive Multi-Target Video Segmentation

Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each individual object, resulting in reduced frame rates (FPS) with unbounded latency as target count increases. Built upon Segment Anything 2 (SAM2), we propose SAM-MT, which addresses this by transforming the model into an interactive framework for real-time Multi-Target video segmentation. SAM-MT uses explicit queries to represent different individual targets, in parallel with a shared representation for global context. It employs decoupled masked attention to keep individual identities distinct from cross-target interference, and sparse memory for stable temporal evolution, along with specialized strategies for occlusion handling and overlap prevention. SAM-MT successfully decouples latency from the number of targets, achieving real-time speed on par with single-target baselines (>36 FPS for 10 targets) while maintaining SAM2's robust video segmentation performance.

cs.CV↗

arXiv2026

Visualizing modified spin-wave wavefronts near magnetic defects and domains using nitrogen-vacancy centers

Direct, real-space imaging of spin-wave propagation and wavefronts in magnetic materials is crucial for advancing both fundamental understanding of spin dynamics and the development of functional devices. This, however, remains a significant challenge, especially in materials with complex magnetic characteristics at the nanoscale. Here, we employ scanning nitrogen-vacancy center spectroscopy to achieve visualization of spin waves in two archetypical magnetic films: yttrium-iron-garnet and lanthanum strontium manganese oxide. We reveal a wavelength-dependent spin-wave filtering effect near point-like magnetic scatterers and a modified spin wavefront in antiferromagnetically coupled stripe domains. The spin-wave characteristics are explained using micromagnetic simulations and analytical calculations. These findings point to possible fine control of spin-wave propagation near complex magnetic structures and extend the scope of spin-wave imaging based on nitrogen-vacancy centers beyond uniform magnets.

cond-mat.mes-hall↗

arXiv2026

UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods

The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges beyond raw interconnect bandwidth. While these systems provide unified global address spaces and high-bandwidth fabrics, their full potential for sparse MoE communication is hindered by three fundamental bottlenecks: (1) Strict execution serialization imposed by coarse-grained Bulk Synchronous Parallel (BSP) orchestration of interdependent communication phases; (2) Prohibitive synchronization overhead that fails to scale alongside high interconnect bandwidth; and (3) Severe load imbalance resulting from distance-agnostic scheduling of irregular token traffic. To eliminate these bottlenecks, we introduce UBEP (Unified-Bus Expert Parallelism), a production-ready communication library that rethinks MoE's All-to-All primitives for modern superpod architectures. Through large scale experiments, UBEP reduces All-to-All latency by up to 52.4% and MoE inference Time Per Output Token (TPOT) by up to 11.1%.

cs.DC↗

arXiv2026

PAGE: Towards Practical Human-level Gaze Target Estimation

Gaze target estimation, the task of predicting where a person is looking in a scene, is crucial to understanding human attention and intent. It is a challenging task that combines high-level understanding of global scene semantics and precise spatial reasoning using human appearance (e.g. pose, eye orientation). As a result, human-level performance remains elusive for existing models, limiting their practical application. To this end, we propose PaGE (Practical Gaze Estimator), a gaze estimation model that explicitly models the complex interaction between scene and head features. Using a PaGE model with a large ViT-H+ backbone as the teacher, we further distill student models with lighter backbones on a much larger and more diverse unlabeled dataset. The architectural improvements and novel training recipe allow PaGE to achieve state-of-the-art performance on several gaze estimation tasks, outperforming humans in 7 out of 9 metrics while reducing the human-AI gap by at least 60% in the remaining 2. The distilled student models retain most of the teacher's performance while being lightweight enough for practical deployment on robots and consumer devices. The code and model checkpoints are available at our project page.

cs.CV↗

arXiv2026

HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration

Current vision-language-action (VLA) benchmarks primarily evaluate isolated manipulation skills while leaving human-robot interaction structure largely unmodeled. However, real-world collaboration fundamentally requires coordination under shared agency, including intent understanding, temporal synchronization, protocol adherence, and safe interaction in dynamic environments. To address this gap, we introduce HRIBench, a diagnostic benchmark for intent-aware human-robot collaboration based on executable interaction scenarios. HRIBench represents collaborative tasks as structured scenario scripts that explicitly model agent roles, temporal dependencies, coordination constraints, and human behavior distributions. Building on this abstraction, HRIBench defines three representative interaction roles: Instructor, Collaborator, and Intruder, covering intent communication, joint coordination, and robustness under human intervention. The benchmark contains 13 role-conditioned tasks with over 650 evaluation episodes generated from diverse interaction trajectories and scene variations. Beyond binary task success, HRIBench introduces interpretable interaction-centric metrics spanning synchronization, responsiveness, protocol compliance, and safety. We evaluate adapted policies based on GR00T, pi0.5, and ACT under a unified protocol. Results show that current foundation robot policies struggle substantially in collaborative settings despite strong manipulation ability, revealing major limitations in temporal coordination and intent-aware behavior. Fine-tuning on HRIBench consistently improves collaborative performance. In a real-world adaptation study, simulation data generated by HRIBench improves GR00T N1.5's physical-task success rate from 0.10 to 0.43, demonstrating the benchmark's value for advancing interaction-centric robot learning.

cs.RO↗