arXiv subjects

He Wang

Publications and source records attributed to He Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Learned Single-Pass Multitasking Perceptual Graphics for Immersive Displays

Emerging immersive display technologies efficiently utilize resources with perceptual graphics methods such as foveated rendering and denoising. Running multiple perceptual graphics methods challenges devices with limited power and computational resources. We propose a computationally-lightweight learned multitasking perceptual graphics model. Given RGB images and text-prompts, our model performs text-described perceptual tasks in a single inference step. Simply daisy-chaining multiple models or training dedicated models can lead to model management issues and exhaust computational resources. In contrast, our flexible method unlocks consistent high quality perceptual effects with reasonable compute, supporting various permutations at varied intensities using adjectives in text prompts (e.g. mildly, lightly). Text-guidance provides ease of use for dynamic requirements such as creative processes. To train our model, we propose a dataset containing source and perceptually enhanced images with corresponding text prompts. We evaluate our model on desktop and embedded platforms and validate perceptual quality through a user study.

cs.CV↗

arXiv2025

ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark

Automatic Speech Recognition (ASR) has been extensively investigated, yet prior benchmarks have largely focused on assessing the acoustic robustness of ASR models, leaving evaluations of their linguistic capabilities relatively underexplored. This largely stems from the limited parameter sizes and training corpora of conventional ASR models, leaving them with insufficient world knowledge, which is crucial for accurately recognizing named entities across diverse domains. For instance, drug and treatment names in medicine or specialized technical terms in engineering. Recent breakthroughs in Large Language Models (LLMs) and corresponding Large Audio Language Models (LALMs) have markedly enhanced the visibility of advanced context modeling and general artificial intelligence capabilities. Leveraging LLMs, we envision a unified system capable of robust speech recognition across diverse real-world domains, yet existing benchmarks are inadequate for evaluating this objective. To address this gap, we propose ContextASR-Bench: a comprehensive, large-scale benchmark designed to assess the linguistic competence of ASR systems using corpora that feature numerous named entities across multiple domains. It encompasses up to 40,000 data entries with more than 300,000 named entities across over 10 domains. Beyond the audio and its transcription, each sample provides the domain it belongs to and a list of named entities it contains, which are referred to as the context. Based on this, we introduce three evaluation modes to assess how effectively models can exploit such context to improve ASR accuracy. Extensive evaluation on ContextASR-Bench highlights that LALMs outperform conventional ASR models by a large margin thanks to the strong world knowledge and context modeling of LLMs, yet there remains ample room for further improvement. The dataset and evaluation code have been released.

eess.AS↗

arXiv2025

DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation

Nonprehensile manipulation is crucial for handling objects that are too thin, large, or otherwise ungraspable in unstructured environments. While conventional planning-based approaches struggle with complex contact modeling, learning-based methods have recently emerged as a promising alternative. However, existing learning-based approaches face two major limitations: they heavily rely on multi-view cameras and precise pose tracking, and they fail to generalize across varying physical conditions, such as changes in object mass and table friction. To address these challenges, we propose the Dynamics-Adaptive World Action Model (DyWA), a novel framework that enhances action learning by jointly predicting future states while adapting to dynamics variations based on historical trajectories. By unifying the modeling of geometry, state, physics, and robot actions, DyWA enables more robust policy learning under partial observability. Compared to baselines, our method improves the success rate by 31.5% using only single-view point cloud observations in the simulation. Furthermore, DyWA achieves an average success rate of 68% in real-world experiments, demonstrating its ability to generalize across diverse object geometries, adapt to varying table friction, and robustness in challenging scenarios such as half-filled water bottles and slippery surfaces.

cs.RO↗

arXiv2025

Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge

Deep learning models have achieved state-of-the-art performance in automated Cardiac Magnetic Resonance (CMR) analysis. However, the efficacy of these models is highly dependent on the availability of high-quality, artifact-free images. In clinical practice, CMR acquisitions are frequently degraded by respiratory motion, yet the robustness of deep learning models against such artifacts remains an underexplored problem. To promote research in this domain, we organized the MICCAI CMRxMotion challenge. We curated and publicly released a dataset of 320 CMR cine series from 40 healthy volunteers who performed specific breathing protocols to induce a controlled spectrum of motion artifacts. The challenge comprised two tasks: 1) automated image quality assessment to classify images based on motion severity, and 2) robust myocardial segmentation in the presence of motion artifacts. A total of 22 algorithms were submitted and evaluated on the two designated tasks. This paper presents a comprehensive overview of the challenge design and dataset, reports the evaluation results for the top-performing methods, and further investigates the impact of motion artifacts on five clinically relevant biomarkers. All resources and code are publicly available at: https://github.com/CMRxMotion

eess.IV↗

arXiv2025

Binding energy of $^{3}_Λ\rm{H}$ and $^{4}_Λ\rm{H}$ via image analyses of nuclear emulsions using deep-learning

Subatomic systems are pivotal for understanding fundamental baryonic interactions, as they provide direct access to quark-level degrees of freedom. In particular, introducing a strange quark adds "strangeness" as a new dimension, offering a powerful tool for exploring nuclear forces. The hypertriton, the lightest three-body hypernuclear system, provides an ideal testing ground for investigating baryonic interactions and quark behavior involving up, down, and strange quarks. However, experimental measurements of its lifetime and binding energy, key indicators of baryonic interactions, show significant deviations in results obtained from energetic collisions of heavy-ion beams. Identifying alternative pathways for precisely measuring the hypertriton's binding energy and lifetime is thus crucial for advancing experimental and theoretical nuclear physics. Here, we present an experimental study on the binding energies of $^3_Λ\mathrm{H}$ (hypertriton) and $^4_Λ\mathrm{H}$, performed through the analysis of photographic nuclear emulsions using modern techniques. By incorporating deep-learning methods, we uncovered systematic uncertainties in conventional nuclear emulsion analyses and established a refined calibration protocol for determining binding energies accurately. Our results are independent of those obtained from heavy-ion collision experiments, offering a complementary measurement and opening new avenues for investigating few-body hypernuclei interactions.

nucl-ex↗

arXiv2025

On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation

The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. We present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN and experimentally, we conducted extensive evaluations on diverse datasets.

cs.LG↗

arXiv2025

X-Intelligence 3.0: Training and Evaluating Reasoning LLM for Semiconductor Display

Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry.

cs.CL↗

arXiv2025

Recent Advances in Simulation-based Inference for Gravitational Wave Data Analysis

The detection of gravitational waves by the LIGO-Virgo-KAGRA collaboration has ushered in a new era of observational astronomy, emphasizing the need for rapid and detailed parameter estimation and population-level analyses. Traditional Bayesian inference methods, particularly Markov chain Monte Carlo, face significant computational challenges when dealing with the high-dimensional parameter spaces and complex noise characteristics inherent in gravitational wave data. This review examines the emerging role of simulation-based inference methods in gravitational wave astronomy, with a focus on approaches that leverage machine-learning techniques such as normalizing flows and neural posterior estimation. We provide a comprehensive overview of the theoretical foundations underlying various simulation-based inference methods, including neural posterior estimation, neural ratio estimation, neural likelihood estimation, flow matching, and consistency models. We explore the applications of these methods across diverse gravitational wave data processing scenarios, from single-source parameter estimation and overlapping signal analysis to testing general relativity and conducting population studies. Although these techniques demonstrate speed improvements over traditional methods in controlled studies, their model-dependent nature and sensitivity to prior assumptions are barriers to their widespread adoption. Their accuracy, which is similar to that of conventional methods, requires further validation across broader parameter spaces and noise conditions.

gr-qc↗

arXiv2025

The Anisotropy of Thermal Activation Energy of 2H-NbS$_2$

We investigate the anisotropic flux dynamics in 2H-NbS$_2$ single crystals through temperature-dependent resistance measurements under in-plane ($H \parallel ab$ plane) and out-of-plane ($H \perp ab$ plane) magnetic fields. Analysis of thermally activated flux flow (TAFF) resistance in the superconducting mixed state reveals stark contrasts in thermal activation energy ($U_0$) scaling and field dependence. For $H \perp ab$, $U_0(0.1 \mathrm{T}) = (1228.76 \pm 53.64)$ K follows the Arrhenius relation with a power-law field decay ($U_0\propto H^{-α}$). In contrast, under $H \parallel ab$, $U_0(0.5 \mathrm{T}) = (7205.58 \pm 619.65)$ K aligns with the modified TAFF theory, where the scaling exponent $q = 2$ potentially reflects two-dimensional vortex behavior in the TAFF region, and the field dependence of $U_0$ follows parabolic relation $H^γ\left[1 - \frac{H}{H^{*}}\right]^2$. These results establish 2H-NbS$_2$ as a model system for probing the anisotropy of flux dynamics in layered superconductors.

cond-mat.supr-con↗

arXiv2025

Investigation on high-order planar Hall effect in trigonal PtBi$_2$

The trigonal PtBi$_2$ (t-PtBi$_2$) as a Weyl semimetal possessing triply degenerate points in its electronic bands near the Fermi level endows it with rich electronic properties. Previous studies have already measured the planar Hall effect (PHE) and in-plane anisotropic magnetoresistance (AMR) of t-PtBi$_2$. We noticed that their experimental results exhibited high-order features in both the PHE and AMR, yet these features were not systematically investigated. In our work, we conducted more systematic measurements and analyses of the PHE and AMR in t-PtBi$_2$. Both PHE and AMR show high-order features under low temperatures and strong magnetic fields, and these features share a similar temperature and magnetic field dependence with the turn-on behavior of resistance and temperature curves, indicating a common physical origin for them. We further summarize the critical conditions for the emergence of high-order PHE in t-PtBi$_2$, which will help to understand the origin of high-order features. In addition, we performed computational simulations on the AMR of t-PtBi$_2$, and the results were consistent with the experiments, indicating the high-order features are the result of the combined contribution of the Fermi surface anisotropy and the scaling behavior of magnetoresistance. Our findings will contribute to a deeper understanding of the origins of high-order features in non-magnetic topological materials.

cond-mat.mtrl-sci↗

arXiv2025

Search for exotic gravitational wave signals beyond general relativity using deep learning

The direct detection of gravitational waves by LIGO has confirmed general relativity (GR) and sparked rapid growth in gravitational wave (GW) astronomy. However, subtle post-Newtonian (PN) deviations observed during the analysis of high signal-to-noise ratio events from the observational runs suggest that standard waveform templates, which assume strict adherence to GR, might overlook signals from alternative theories of gravity. Incorporating these exotic signals into traditional search algorithms is computationally infeasible due to the vast template space required. This paper introduces a proof-of-principle deep learning framework for detecting exotic GW signals, leveraging neural networks trained on GR-based templates. Through their generalization ability, neural networks learn intricate features from the data, enabling the detection of signals that deviate from GR. We present the first study evaluating the capability of deep learning to detect beyond-GR signals, including a variety of PN orders. Our model achieves rapid and accurate identification of exotic GW signals across different luminosity distances, with performance comparable to GR-based detections. In particular, applying the model to the GW150914 event demonstrates excellent performance, highlighting the potential of AI-driven methods for detecting previously overlooked signals beyond GR. This work paves the way for new discoveries in gravitational wave astronomy, enabling the detection of signals that might escape traditional search pipelines.

gr-qc↗

arXiv2025

PIP-Net: Pedestrian Intention Prediction in the Wild

Accurate pedestrian intention prediction (PIP) by Autonomous Vehicles (AVs) is one of the current research challenges in this field. In this article, we introduce PIP-Net, a novel framework designed to predict pedestrian crossing intentions by AVs in real-world urban scenarios. We offer two variants of PIP-Net designed for different camera mounts and setups. Leveraging both kinematic data and spatial features from the driving scene, the proposed model employs a recurrent and temporal attention-based solution, outperforming state-of-the-art performance. To enhance the visual representation of road users and their proximity to the ego vehicle, we introduce a categorical depth feature map, combined with a local motion flow feature, providing rich insights into the scene dynamics. Additionally, we explore the impact of expanding the camera's field of view, from one to three cameras surrounding the ego vehicle, leading to an enhancement in the model's contextual perception. Depending on the traffic scenario and road environment, the model excels in predicting pedestrian crossing intentions up to 4 seconds in advance, which is a breakthrough in current research studies in pedestrian intention prediction. Finally, for the first time, we present the Urban-PIP dataset, a customised pedestrian intention prediction dataset, with multi-camera annotations in real-world automated driving scenarios.

cs.CV↗

arXiv2025

Pedestrian Intention Prediction via Vision-Language Foundation Models

Prediction of pedestrian crossing intention is a critical function in autonomous vehicles. Conventional vision-based methods of crossing intention prediction often struggle with generalizability, context understanding, and causal reasoning. This study explores the potential of vision-language foundation models (VLFMs) for predicting pedestrian crossing intentions by integrating multimodal data through hierarchical prompt templates. The methodology incorporates contextual information, including visual frames, physical cues observations, and ego-vehicle dynamics, into systematically refined prompts to guide VLFMs effectively in intention prediction. Experiments were conducted on three common datasets-JAAD, PIE, and FU-PIP. Results demonstrate that incorporating vehicle speed, its variations over time, and time-conscious prompts significantly enhances the prediction accuracy up to 19.8%. Additionally, optimised prompts generated via an automatic prompt engineering framework yielded 12.5% further accuracy gains. These findings highlight the superior performance of VLFMs compared to conventional vision-based models, offering enhanced generalisation and contextual understanding for autonomous driving applications.

cs.CV↗

arXiv2025

RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments

For the task of hanging clothes, learning how to insert a hanger into a garment is a crucial step, but has rarely been explored in robotics. In this work, we address the problem of inserting a hanger into various unseen garments that are initially laid flat on a table. This task is challenging due to its long-horizon nature, the high degrees of freedom of the garments and the lack of data. To simplify the learning process, we first propose breaking the task into several subtasks. Then, we formulate each subtask as a policy learning problem and propose a low-dimensional action parameterization. To overcome the challenge of limited data, we build our own simulator and create 144 synthetic clothing assets to effectively collect high-quality training data. Our approach uses single-view depth images and object masks as input, which mitigates the Sim2Real appearance gap and achieves high generalization capabilities for new garments. Extensive experiments in both simulation and reality validate our proposed method. By training on various garments in the simulator, our method achieves a 75\% success rate with 8 different unseen garments in the real world.

cs.RO↗

arXiv2025

A Kalman-smoother based data imputation strategy to data gaps in spaceborne gravitational wave detectors

Massive black hole binaries (MBHBs) and other sources within the frequency band of spaceborne gravitational wave observatories like the Laser Interferometer Space Antenna (LISA), Taiji and Tianqin pose unique challenges, as gaps and glitches during the years-long observation lead to both loss of information and spectral leakage. We propose a novel data imputation strategy based on Kalman filter and smoother to mitigate gap-induced biases in parameter estimation. Applied to a scenario where traditional windowing and smoothing technique introduce significant biases, our method mitigates the biases and demonstrates lower computational cost compared to existing data augmentation techniques such as noise inpainting. This framework presents a new gap treatment approach that balances robustness and efficiency for space-based gravitational wave data analysis.

astro-ph.IM↗

arXiv2025

DexVLG: Dexterous Vision-Language-Grasp Model at Scale

As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large models for human-like dexterous hands. In this paper, we introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions using single-view RGBD input. To accomplish this, we generate a dataset of 170 million dexterous grasp poses mapped to semantic parts across 174,000 objects in simulation, paired with detailed part-level captions. This large-scale dataset, named DexGraspNet 3.0, is used to train a VLM and flow-matching-based pose head capable of producing instruction-aligned grasp poses for tabletop objects. To assess DexVLG's performance, we create benchmarks in physics-based simulations and conduct real-world experiments. Extensive testing demonstrates DexVLG's strong zero-shot generalization capabilities-achieving over 76% zero-shot execution success rate and state-of-the-art part-grasp accuracy in simulation-and successful part-aligned grasps on physical objects in real-world scenarios.

cs.CV↗

arXiv2025

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding

Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with flow matching (FM) struggle with streaming capabilities due to their reliance on a global receptive field. Additionally, directly implementing token-by-token streaming speech generation often results in degraded audio quality. To address these challenges, we propose StreamFlow, a novel neural architecture that facilitates streaming flow matching with diffusion transformers (DiT). To mitigate the long-sequence extrapolation issues arising from lengthy historical dependencies, we design a local block-wise receptive field strategy. Specifically, the sequence is first segmented into blocks, and we introduce block-wise attention masks that enable the current block to receive information from the previous or subsequent block. These attention masks are combined hierarchically across different DiT-blocks to regulate the receptive field of DiTs. Both subjective and objective experimental results demonstrate that our approach achieves performance comparable to non-streaming methods while surpassing other streaming methods in terms of speech quality, all the while effectively managing inference time during long-sequence generation. Furthermore, our method achieves a notable first-packet latency of only 180 ms.\footnote{Speech samples: https://dukguo.github.io/StreamFlow/}

cs.SD↗

arXiv2025

Moderating the Generalization of Score-based Generative Model

Score-based Generative Models (SGMs) have demonstrated remarkable generalization abilities, e.g. generating unseen, but natural data. However, the greater the generalization power, the more likely the unintended generalization, and the more dangerous the abuse. Research on moderated generalization in SGMs remains limited. To fill this gap, we first examine the current 'gold standard' in Machine Unlearning (MU), i.e., re-training the model after removing the undesirable training data, and find it does not work in SGMs. Further analysis of score functions reveals that the MU 'gold standard' does not alter the original score function, which explains its ineffectiveness. Based on this insight, we propose the first Moderated Score-based Generative Model (MSGM), which introduces a novel score adjustment strategy that redirects the score function away from undesirable data during the continuous-time stochastic differential equation process. Extensive experimental results demonstrate that MSGM significantly reduces the likelihood of generating undesirable content while preserving high visual quality for normal image generation. Albeit designed for SGMs, MSGM is a general and flexible MU framework that is compatible with diverse diffusion architectures (SGM and DDPM) and training strategies (re-training and fine-tuning), and enables zero-shot transfer of the pre-trained models to downstream tasks, e.g. image inpainting and reconstruction. The code will be shared upon acceptance.

cs.LG↗