arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 631 records · Page 35Linked to original sources

arXiv2025

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations

High-throughput 3D quantitative phase imaging (QPI) in flow cytometry enables label-free, volumetric characterization of individual cells by reconstructing their refractive index (RI) distributions from multiple viewing angles during flow through microfluidic channels. However, current imaging methods assume that cells undergo uniform, single-axis rotation, which require their poses to be known at each frame. This assumption restricts applicability to near-spherical cells and prevents accurate imaging of irregularly shaped cells with complex rotations. As a result, only a subset of the cellular population can be analyzed, limiting the ability of flow-based assays to perform robust statistical analysis. We introduce OmniFHT, a pose-free 3D RI reconstruction framework that leverages the Fourier diffraction theorem and implicit neural representations (INRs) for high-throughput flow cytometry tomographic imaging. By jointly optimizing each cell's unknown rotational trajectory and volumetric structure under weak scattering assumptions, OmniFHT supports arbitrary cell geometries and multi-axis rotations. Its continuous representation also allows accurate reconstruction from sparsely sampled projections and restricted angular coverage, producing high-fidelity results with as few as 10 views or only 120 degrees of angular range. OmniFHT enables, for the first time, in situ, high-throughput tomographic imaging of entire flowing cell populations, providing a scalable and unbiased solution for label-free morphometric analysis in flow cytometry platforms.

cs.CV↗

arXiv2025

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

Recent advancements in large language models (LLMs) have revolutionized natural language processing through their remarkable capabilities in understanding and executing diverse tasks. While supervised fine-tuning, particularly in Retrieval-Augmented Generation (RAG) scenarios, effectively enhances task-specific performance, it often leads to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. Existing solutions either require access to general instruction data or face limitations in preserving the model's original distribution. To overcome these limitations, we propose SelfAug, a self-distribution alignment method that aligns input sequence logits to preserve the model's semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. Extensive experiments demonstrate that SelfAug achieves a superior balance between downstream learning and general capability retention. Our comprehensive empirical analysis reveals a direct correlation between distribution shifts and the severity of catastrophic forgetting in RAG scenarios, highlighting how the absence of RAG capabilities in general instruction tuning leads to significant distribution shifts during fine-tuning. Our findings not only advance the understanding of catastrophic forgetting in RAG contexts but also provide a practical solution applicable across diverse fine-tuning scenarios. Our code is publicly available at https://github.com/USTC-StarTeam/SelfAug.

cs.CL↗

arXiv2025

S2M2ECG: Spatio-temporal bi-directional State Space Model Enabled Multi-branch Mamba for ECG

As one of the most effective methods for cardiovascular disease (CVD) diagnosis, multi-lead Electrocardiogram (ECG) signals present a characteristic multi-sensor information fusion challenge that has been continuously researched in deep learning domains. Despite the numerous algorithms proposed with different DL architectures, maintaining a balance among performance, computational complexity, and multi-source ECG feature fusion remains challenging. Recently, state space models (SSMs), particularly Mamba, have demonstrated remarkable effectiveness across various fields. Their inherent design for high-efficiency computation and linear complexity makes them particularly suitable for low-dimensional data like ECGs. This work proposes S2M2ECG, an SSM architecture featuring three-level fusion mechanisms: (1) Spatio-temporal bi-directional SSMs with segment tokenization for low-level signal fusion, (2) Intra-lead temporal information fusion with bi-directional scanning to enhance recognition accuracy in both forward and backward directions, (3) Cross-lead feature interaction modules for spatial information fusion. To fully leverage the ECG-specific multi-lead mechanisms inherent in ECG signals, a multi-branch design and lead fusion modules are incorporated, enabling individual analysis of each lead while ensuring seamless integration with others. Experimental results reveal that S2M2ECG achieves superior performance in the rhythmic, morphological, and clinical scenarios. Moreover, its lightweight architecture ensures it has nearly the fewest parameters among existing models, making it highly suitable for efficient inference and convenient deployment. Collectively, S2M2ECG offers a promising alternative that strikes an excellent balance among performance, computational complexity, and ECG-specific characteristics, paving the way for high-performance, lightweight computations in CVD diagnosis.

eess.SP↗

arXiv2025

AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation

Leveraging the autonomous decision-making capabilities of large language models (LLMs) has demonstrated superior performance in reasoning tasks. However, despite the success of iterative or agentic retrieval-augmented generation (RAG) techniques, these methods are often constrained to a single solution space when confronted with complex problems. In this paper, we propose a novel thinking pattern in RAG that integrates autonomous strategic planning with efficient reasoning actions, significantly activating intrinsic reasoning capabilities and expanding the solution space of specific tasks via Monte Carlo Tree Search (MCTS), which we refer to as AirRAG. Specifically, our approach designs five fundamental reasoning actions, which are expanded to a broad tree-based reasoning space using MCTS. The approach also incorporates self-consistency verification to explore potential reasoning paths and inference scaling law. Additionally, computationally optimal strategies are employed to allocate more inference resources to key actions, thereby enhancing overall performance. Experimental results demonstrate the effectiveness of AirRAG, showing significant performance gains on complex question-answering datasets. Furthermore, AirRAG is flexible and lightweight, making it easy to integrate with other advanced technologies and models.

cs.AI↗

arXiv2025

SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction

Monocular texture 3D human reconstruction aims to create a complete 3D digital avatar from just a single front-view human RGB image. However, the geometric ambiguity inherent in a single 2D image and the scarcity of 3D human training data are the main obstacles limiting progress in this field. To address these issues, current methods employ prior geometric estimation networks to derive various human geometric forms, such as the SMPL model and normal maps. However, they struggle to integrate these modalities effectively, leading to view inconsistencies, such as facial distortions. To this end, we propose a two-process 3D human reconstruction framework, SAT, which seamlessly learns various prior geometries in a unified manner and reconstructs high-quality textured 3D avatars as the final output. To further facilitate geometry learning, we introduce a Supervisor Feature Regularization module. By employing a multi-view network with the same structure to provide intermediate features as training supervision, these varied geometric priors can be better fused. To tackle data scarcity and further improve reconstruction quality, we also propose an Online Animation Augmentation module. By building a one-feed-forward animation network, we augment a massive number of samples from the original 3D human data online for model training. Extensive experiments on two benchmarks show the superiority of our approach compared to state-of-the-art methods.

cs.CV↗

arXiv2025

CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks

Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various in-game tasks. However, for complex tasks requiring lengthy sequences of actions, single-agent approaches often face challenges related to inefficiency and limited fault tolerance. Despite these issues, research on multi-agent collaboration remains scarce. In this paper, we propose CausalMACE, a holistic causality planning framework designed to enhance multi-agent systems, in which we incorporate causality to manage dependencies among subtasks. Technically, our proposed framework introduces two modules: an overarching task graph for global task planning and a causality-based module for dependency management, where inherent rules are adopted to perform causal intervention. Experimental results demonstrate our approach achieves state-of-the-art performance in multi-agent cooperative tasks of Minecraft.

cs.AI↗

arXiv2025

Multimodal Guided Surface Lattice Resonances in Index-Discontinuous Environments

Surface lattice resonances (SLRs) in metasurfaces have become a transformative platform for subwavelength optical devices, leveraging their high quality (Q)-factors, pronounced local field enhancement, and extensive long-range interactions. However, current high-Q SLR implementations are fundamentally limited by their dependence on homogeneous dielectric environments. This restriction significantly hinders their applicability in emerging fields such as molecular sensing, where operation in heterogeneous dielectric media (e.g., interfaces with an aqueous or air cladding) is often indispensable. To overcome this limitation, we introduce guided surface lattice resonances (gSLRs) by integrating nanoparticle arrays within slab waveguides. This configuration facilitates efficient coupling between scattered light and Bloch modes, thereby enabling high-Q multimodal resonances even in index-discontinuous environments. Experimental validation under incoherent illumination demonstrates a Q-factor of 1489 in an index-mismatched surrounding. Furthermore, the coupling strength and resonance intensity of these multimodal gSLRs can be continuously modulated by adjusting the vertical displacement of the nanoparticle arrays within the slab layers. To augment the sensitivity to local dielectric variations, we investigate gSLRs in metasurfaces integrated with metallic substrates, demonstrating suitability for biomolecule detection. A mathematical sensing model, incorporating biochemical reaction kinetics and optical responses, is established by representing adsorbed molecules as a uniform dielectric layer and validated through bovine serum albumin (BSA) sensing experiments. This work not only advances the fundamental understanding of resonance engineering in complex media but also facilitates the development of ultrathin, ultra-compact nano-optical and optoelectronic devices.

physics.optics↗

arXiv2025

Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs

The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages, especially when integrating cultural knowledge, remains a significant challenge. To better assess this issue, we introduce two new benchmarks: KnowRecall and VisRecall, which evaluate cross-lingual consistency in MLLMs. KnowRecall is a visual question answering benchmark designed to measure factual knowledge consistency in 15 languages, focusing on cultural and historical questions about global landmarks. VisRecall assesses visual memory consistency by asking models to describe landmark appearances in 9 languages without access to images. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, still struggle to achieve cross-lingual consistency. This underscores the need for more robust approaches that produce truly multilingual and culturally aware models.

cs.CL↗

arXiv2025

Lossless Token Sequence Compression via Meta-Tokens

Existing work on prompt compression for Large Language Models (LLM) focuses on lossy methods that try to maximize the retention of semantic information that is relevant to downstream tasks while significantly reducing the sequence length. In this paper, we introduce a task-agnostic lossless compression technique similar to LZ77 that makes it possible to reduce the input token sequence length on average by 27\% and 18\% for the two evaluation tasks explored here. Given that we use transformer-based LLMs, this equates to 47\% and 33\% less encoding computation, respectively, due to the quadratic nature of attention. The token sequence transformation is trivial to reverse and highlights that no semantic information is lost in the process. We evaluate our proposed approach on two tasks that require strict preservation of semantics/syntax and demonstrate that existing lossy compression methods perform poorly in this setting. We find that our lossless compression technique produces only a small gap in performance compared to using the uncompressed input and posit that larger models and an expanded computing budget would likely erase the gap entirely.

cs.CL↗

arXiv2025

D$^2$-LIO: Enhanced Optimization for LiDAR-IMU Odometry Considering Directional Degeneracy

LiDAR-inertial odometry (LIO) plays a vital role in achieving accurate localization and mapping, especially in complex environments. However, the presence of LiDAR feature degeneracy poses a major challenge to reliable state estimation. To overcome this issue, we propose an enhanced LIO framework that integrates adaptive outlier-tolerant correspondence with a scan-to-submap registration strategy. The core contribution lies in an adaptive outlier removal threshold, which dynamically adjusts based on point-to-sensor distance and the motion amplitude of platform. This mechanism improves the robustness of feature matching in varying conditions. Moreover, we introduce a flexible scan-to-submap registration method that leverages IMU data to refine pose estimation, particularly in degenerate geometric configurations. To further enhance localization accuracy, we design a novel weighting matrix that fuses IMU preintegration covariance with a degeneration metric derived from the scan-to-submap process. Extensive experiments conducted in both indoor and outdoor environments-characterized by sparse or degenerate features-demonstrate that our method consistently outperforms state-of-the-art approaches in terms of both robustness and accuracy.

cs.RO↗

arXiv2025

Equinox: Holistic Fair Scheduling in Serving Large Language Models

We address the limitations of current LLM serving with a dual-counter framework separating user and operator perspectives. The User Fairness Counter measures quality of service via weighted tokens and latency; the Resource Fairness Counter measures operational efficiency through throughput and GPU utilization. Since these metrics are only available post-execution, creating a scheduling paradox, we introduce a deterministic Mixture of Prediction Experts (MoPE) framework to predict user-perceived latency, output tokens, throughput, and GPU utilization. These predictions enable calculation of a unified Holistic Fairness score that balances both counters through tunable parameters for proactive fairness-aware scheduling. We implement this in Equinox, an open-source system with other optimizations like adaptive batching, and stall-free scheduling. Evaluations on production traces (ShareGPT, LMSYS) and synthetic workloads demonstrate Equinox achieves up to $1.3\times$ higher throughput, 60\% lower time-to-first-token latency, and 13\% higher fairness versus VTC while maintaining 94\% GPU utilization, proving fairness under bounded discrepancy across heterogeneous platforms.

cs.DC↗

arXiv2025

Dynamic reinsurance design with heterogeneous beliefs under the mean-variance framework

This paper investigates the dynamic reinsurance design problem under the mean-variance criterion, incorporating heterogeneous beliefs between the insurer and the reinsurer, and introducing an incentive compatibility constraint to address moral hazard. The insurer's surplus process is modeled using the classical Cramér-Lundberg risk model, with the option to invest in a risk-free asset. To solve the extended Hamilton-Jacobi-Bellman (HJB) system, we apply the partitioned domain optimization technique, transforming the infinite-dimensional optimization problem into a finite-dimensional one determined by several key parameters. The resulting optimal reinsurance contracts are more complex than the standard proportional and excess-of-loss contracts commonly studied in the mean-variance literature with homogeneous beliefs. By further assuming specific forms of belief heterogeneity, we derive the parametric solutions and obtain a clear optimal equilibrium solution. Finally, we compare our results with models where the insurer and reinsurer share identical beliefs or where the incentive compatibility constraint is relaxed. Numerical examples are provided to illustrate the impact of belief heterogeneity on optimal reinsurance strategies.

math.OC↗

arXiv2025

Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer Models

Transformer models have demonstrated exceptional performance and have become indispensable in computer vision (CV) and natural language processing (NLP) tasks. However, recent studies reveal that transformers are susceptible to backdoor attacks. Prior backdoor attack methods typically rely on retraining with clean data or altering the model architecture, both of which can be resource-intensive and intrusive. In this paper, we propose Head-wise Pruning and Malicious Injection (HPMI), a novel retraining-free backdoor attack on transformers that does not alter the model's architecture. Our approach requires only a small subset of the original data and basic knowledge of the model architecture, eliminating the need for retraining the target transformer. Technically, HPMI works by pruning the least important head and injecting a pre-trained malicious head to establish the backdoor. We provide a rigorous theoretical justification demonstrating that the implanted backdoor resists detection and removal by state-of-the-art defense techniques, under reasonable assumptions. Experimental evaluations across multiple datasets further validate the effectiveness of HPMI, showing that it 1) incurs negligible clean accuracy loss, 2) achieves at least 99.55% attack success rate, and 3) bypasses four advanced defense mechanisms. Additionally, relative to state-of-the-art retraining-dependent attacks, HPMI achieves greater concealment and robustness against diverse defense strategies, while maintaining minimal impact on clean accuracy.

cs.LG↗

arXiv2025

AtomDiffuser: Time-Aware Degradation Modeling for Drift and Beam Damage in STEM Imaging

Scanning transmission electron microscopy (STEM) plays a critical role in modern materials science, enabling direct imaging of atomic structures and their evolution under external interferences. However, interpreting time-resolved STEM data remains challenging due to two entangled degradation effects: spatial drift caused by mechanical and thermal instabilities, and beam-induced signal loss resulting from radiation damage. These factors distort both geometry and intensity in complex, temporally correlated ways, making it difficult for existing methods to explicitly separate their effects or model material dynamics at atomic resolution. In this work, we present AtomDiffuser, a time-aware degradation modeling framework that disentangles sample drift and radiometric attenuation by predicting an affine transformation and a spatially varying decay map between any two STEM frames. Unlike traditional denoising or registration pipelines, our method leverages degradation as a physically heuristic, temporally conditioned process, enabling interpretable structural evolutions across time. Trained on synthetic degradation processes, AtomDiffuser also generalizes well to real-world cryo-STEM data. It further supports high-resolution degradation inference and drift alignment, offering tools for visualizing and quantifying degradation patterns that correlate with radiation-induced atomic instabilities.

cs.CV↗

arXiv2025

FuXi-β: Towards a Lightweight and Fast Large-Scale Generative Recommendation Model

Scaling laws for autoregressive generative recommenders reveal potential for larger, more versatile systems but mean greater latency and training costs. To accelerate training and inference, we investigated the recent generative recommendation models HSTU and FuXi-$α$, identifying two efficiency bottlenecks: the indexing operations in relative temporal attention bias and the computation of the query-key attention map. Additionally, we observed that relative attention bias in self-attention mechanisms can also serve as attention maps. Previous works like Synthesizer have shown that alternative forms of attention maps can achieve similar performance, naturally raising the question of whether some attention maps are redundant. Through empirical experiments, we discovered that using the query-key attention map might degrade the model's performance in recommendation tasks. To address these bottlenecks, we propose a new framework applicable to Transformer-like recommendation models. On one hand, we introduce Functional Relative Attention Bias, which avoids the time-consuming operations of the original relative attention bias, thereby accelerating the process. On the other hand, we remove the query-key attention map from the original self-attention layer and design a new Attention-Free Token Mixer module. Furthermore, by applying this framework to FuXi-$α$, we introduce a new model, FuXi-$β$. Experiments across multiple datasets demonstrate that FuXi-$β$ outperforms previous state-of-the-art models and achieves significant acceleration compared to FuXi-$α$, while also adhering to the scaling law. Notably, FuXi-$β$ shows an improvement of 27% to 47% in the NDCG@10 metric on large-scale industrial datasets compared to FuXi-$α$. Our code is available in a public repository: https://github.com/USTC-StarTeam/FuXi-beta

cs.IR↗

arXiv2025

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control

Over the years, reinforcement learning has emerged as a popular approach to develop signal control and vehicle platooning strategies either independently or in a hierarchical way. However, jointly controlling both in real-time to alleviate traffic congestion presents new challenges, such as the inherent physical and behavioral heterogeneity between signal control and platooning, as well as coordination between them. This paper proposes an innovative solution to tackle these challenges based on heterogeneous graph multi-agent reinforcement learning and traffic theories. Our approach involves: 1) designing platoon and signal control as distinct reinforcement learning agents with their own set of observations, actions, and reward functions to optimize traffic flow; 2) designing coordination by incorporating graph neural networks within multi-agent reinforcement learning to facilitate seamless information exchange among agents on a regional scale; 3) applying alternating optimization for training, allowing agents to update their own policies and adapt to other agents' policies. We evaluate our approach through SUMO simulations, which show convergent results in terms of both travel time and fuel consumption, and superior performance compared to other adaptive signal control methods.

cs.LG↗

arXiv2025

A Multi-scale Perimeter Control and Route Guidance System for Large-scale Road Networks

Perimeter control and route guidance are effective ways to reduce traffic congestion and improve traffic efficiency by controlling the spatial and temporal traffic distribution on the network. This paper presents a multi-scale joint perimeter control and route guidance (MSJC) framework for controlling traffic in large-scale networks. The network is first partitioned into several subnetworks (regions) with traffic in each region governed by its macroscopic fundamental diagram (MFD), which forms the macroscale network (upper level). Each subnetwork, comprised of actual road links and signalized intersections, forms the microscale network (lower level). At the upper level, a joint perimeter control and route guidance model solves the region-based inflow rate and hyper-path flows to control the accumulation of each region and thus maximize the throughput of each region. At the lower level, a perimeter control strategy integrated with a backpressure policy determines the optimal signal phases of the intersections at the regional boundary. At the same time, a route choice model for vehicles is constructed to meet hyper-path flows and ensure the intra-region homogeneity of traffic density. The case study results demonstrate that the proposed MSJC outperforms other benchmarks in regulating regional accumulation, thereby improving throughput.

math.OC↗

arXiv2025

GRB 240825A: Early Reverse Shock and Its Physical Implications

Early multiwavelength observations offer crucial insights into the nature of the relativistic jets responsible for gamma-ray bursts and their interaction with the surrounding medium.We present data of GRB 240825A from 17 space- and ground-based telescopes/instruments, covering wavelengths from NIR/optical to X-ray and GeV, and spanning from the prompt emission to the afterglow phase triggered by Swift and Fermi. The early afterglow observations were carried out by SVOM/C-GFT, and spectroscopic observations of the afterglow by GTC, VLT, and TNG determined the redshift of the burst ($z = 0.659$) later.A comprehensive analysis of the prompt emission spectrum observed by Swift-BAT and Fermi-GBM/LAT reveals a rare and significant high-energy cutoff at ~76 MeV. Assuming this cutoff is due to $γγ$ absorption allows us to place an upper limit on the initial Lorentz factor, $Γ_0 < 245$. The optical/NIR and GeV afterglow light curves be described by the standard external shock model, with early-time emission dominated by a reverse shock (RS) and a subsequent transition to forward shock (FS) emission. Our afterglow modelling yields a consistent estimate of the initial Lorentz factor ($Γ_{\rm 0} \sim 234$). Furthermore, the RS-to-FS magnetic field ratio ($\mathcal{R}_B \sim 302$) indicates that the reverse shock region is significantly more magnetized than the FS region. An isotropic-equivalent kinetic energy of $E_{\text{k,iso}} = 5.25 \times 10^{54}$ erg is derived, and the corresponding $γ$-ray radiation efficiency is estimated to be $η_γ$ = 3.1%. On the other hand, the standard afterglow model can not reproduce the X-ray light curve of GRB 240825A, calling for improved models to characterize all multiwavelength data.

astro-ph.HE↗