arXiv subjects

Hao Yang

Publications and source records attributed to Hao Yang.

At least 127 records · Page 7Linked to original sources

arXiv2025

Handwriting Imagery EEG Classification based on Convolutional Neural Networks

Handwriting imagery has emerged as a promising paradigm for brain-computer interfaces (BCIs) aimed at translating brain activity into text output. Compared with invasively recorded electroencephalography (EEG), non-invasive recording offers a more practical and feasible approach to capturing brain signals for BCI. This study explores the limit of decoding non-invasive EEG associated with handwriting imagery into English letters using deep neural networks. To this end, five participants were instructed to imagine writing the 26 English letters with their EEG being recorded from the scalp. A measurement of EEG similarity across letters was conducted to investigate letter-specific patterns in the dataset. Subsequently, four convolutional neural network (CNN) models were trained for EEG classification. Descriptively, the EEG data clearly exhibited letter-specific patterns serving as a proof-of-concept for EEG-to-text translation. Under the chance level of accuracy at 3.85%, the CNN classifiers trained on each participant reached the highest limit of around 20%. This study marks the first attempt to decode non-invasive EEG associated with handwriting imagery. Although the achieved accuracy is not sufficient for a usable brain-to-text BCI, the model's performance is noteworthy in revealing the potential for translating non-invasively recorded brain signals into text outputs and establishing a baseline for future research.

eess.SP↗

arXiv2025

Fabrication and Characterization of the Moiré surface state on a topological insulator

A Moire superlattice on the topological insulator surface is predicted to exhibit many novel properties but has not been experimentally realized. Here, we developed a two-step growth method to successfully fabricate a topological insulator Sb2Te3 thin film with a Moire superlattice, which is generated by a twist of the topmost layer via molecular beam epitaxy. The established Moire topological surface state is characterized by scanning tunneling microscopy and spectroscopy. By application of a magnetic field, new features in Landau levels arise on the Moire region compared to the pristine surface of Sb2Te3, which makes the system a promising platform for pursuing next-generation electronics. Notably, the growth method, which circumvents contamination and the induced interface defects in the manual fabrication method, can be widely applied to other van der Waals materials for fabricating Moire superlattices.

cond-mat.mtrl-sci↗

arXiv2025

Why Not Transform Chat Large Language Models to Non-English?

The scarcity of non-English data limits the development of non-English large language models (LLMs). Transforming English-centric LLMs to non-English has been identified as an effective and resource-efficient method. Previous works start from base LLMs and perform knowledge distillation (KD) with data generated by stronger LLMs, e.g. GPT-4. Compared to base LLMs, chat LLMs are further optimized for advanced abilities, e.g. multi-turn conversation and human preference alignment, and thus more powerful in both helpfulness and safety. However, transforming a chat LLM involves two critical issues: (1) How can we effectively transfer advanced abilities without their supervised data? (2) How can we prevent the original knowledge from catastrophic forgetting during transformation? We target these issues by introducing a simple framework called TransLLM. For the first issue, TransLLM divides the transfer problem into some common sub-tasks with the translation chain-of-thought, which uses the translation as the bridge between English and non-English step-by-step. We further enhance the performance of sub-tasks with publicly available data. For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters. In the experiments, we transform the LLaMA-2-chat-7B to the Thai language. Our method, using only single-turn data, outperforms strong baselines and ChatGPT on multi-turn benchmark MT-bench. Furthermore, our method, without safety data, rejects more harmful queries of safety benchmark AdvBench than both ChatGPT and GPT-4. Code is available at https://github.com/hy5468/TransLLM.

cs.CL↗

arXiv2025

Weak irreducibility of stochastic delay differential equation driven by pure jump noise

In this paper, we study the weak irreducibility of stochastic delay differential equations(SDDEs) driven by pure jump noise. The main contribution of this paper is to provide a concise proof of weak irreducibility, releasing condition (A1-3) in Assumption 2.1 from the literature \cite{WYZZ1}. As an application, we derive the weak irreducibility of SDDEs with weakly dissipative coefficients. An important novelty of this paper is to allow the driving noises to be degenerate. This closes the gap of the irreducibility of SDDEs driven by pure jump noise.

math.PR↗

arXiv2025

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors

Chain-of-Thought reasoning has emerged as a pivotal methodology for enhancing model inference capabilities. Despite growing interest in Chain-of-Thought reasoning, its underlying mechanisms remain unclear. This paper explores the working mechanisms of Chain-of-Thought reasoning from the perspective of the dual relationship between in-context learning and pretrained priors. We first conduct a fine-grained lexical-level analysis of rationales to examine the model's reasoning behavior. Then, by incrementally introducing noisy exemplars, we examine how the model balances pretrained priors against erroneous in-context information. Finally, we investigate whether prompt engineering can induce slow thinking in large language models. Our extensive experiments reveal three key findings: (1) The model not only quickly learns the reasoning structure at the lexical level but also grasps deeper logical reasoning patterns, yet it heavily relies on pretrained priors. (2) Providing sufficient exemplars shifts the model's decision-making from pretrained priors to in-context signals, while misleading prompts introduce instability. (3) Long Chain-of-Thought prompting can induce the model to generate longer reasoning chains, thereby improving its performance on downstream tasks.

cs.CL↗

arXiv2025

PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification

Domain Generalization (DG) has been recently explored to enhance the generalizability of Point Cloud Classification (PCC) models toward unseen domains. Prior works are based on convolutional networks, Transformer or Mamba architectures, either suffering from limited receptive fields or high computational cost, or insufficient long-range dependency modeling. RWKV, as an emerging architecture, possesses superior linear complexity, global receptive fields, and long-range dependency. In this paper, we present the first work that studies the generalizability of RWKV models in DG PCC. We find that directly applying RWKV to DG PCC encounters two significant challenges: RWKV's fixed direction token shift methods, like Q-Shift, introduce spatial distortions when applied to unstructured point clouds, weakening local geometric modeling and reducing robustness. In addition, the Bi-WKV attention in RWKV amplifies slight cross-domain differences in key distributions through exponential weighting, leading to attention shifts and degraded generalization. To this end, we propose PointDGRWKV, the first RWKV-based framework tailored for DG PCC. It introduces two key modules to enhance spatial modeling and cross-domain robustness, while maintaining RWKV's linear efficiency. In particular, we present Adaptive Geometric Token Shift to model local neighborhood structures to improve geometric context awareness. In addition, Cross-Domain key feature Distribution Alignment is designed to mitigate attention drift by aligning key feature distributions across domains. Extensive experiments on multiple benchmarks demonstrate that PointDGRWKV achieves state-of-the-art performance on DG PCC.

cs.CV↗

arXiv2025

Waver: Wave Your Way to Lifelike Video Generation

We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.

cs.CV↗

arXiv2025

VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results

Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.

cs.CV↗

arXiv2025

Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment

Current Omnidirectional Image Quality Assessment (OIQA) methods struggle to evaluate locally non-uniform distortions due to inadequate modeling of spatial variations in quality and ineffective feature representation capturing both local details and global context. To address this, we propose a graph neural network-based OIQA framework that explicitly models structural relationships between viewports to enhance perception of spatial distortion non-uniformity. Our approach employs Fibonacci sphere sampling to generate viewports with well-structured topology, representing each as a graph node. Multi-stage feature extraction networks then derive high-dimensional node representation. To holistically capture spatial dependencies, we integrate a Graph Attention Network (GAT) modeling fine-grained local distortion variations among adjacent viewports, and a graph transformer capturing long-range quality interactions across distant regions. Extensive experiments on two large-scale OIQA databases with complex spatial distortions demonstrate that our method significantly outperforms existing approaches, confirming its effectiveness and strong generalization capability.

cs.CV↗

arXiv2025

ZeroStereo: Zero-shot Stereo Matching from Single Images

State-of-the-art supervised stereo matching methods have achieved remarkable performance on various benchmarks. However, their generalization to real-world scenarios remains challenging due to the scarcity of annotated real-world stereo data. In this paper, we propose ZeroStereo, a novel stereo image generation pipeline for zero-shot stereo matching. Our approach synthesizes high-quality right images from arbitrary single images by leveraging pseudo disparities generated by a monocular depth estimation model. Unlike previous methods that address occluded regions by filling missing areas with neighboring pixels or random backgrounds, we fine-tune a diffusion inpainting model to recover missing details while preserving semantic structure. Additionally, we propose Training-Free Confidence Generation, which mitigates the impact of unreliable pseudo labels without additional training, and Adaptive Disparity Selection, which ensures a diverse and realistic disparity distribution while preventing excessive occlusion and foreground distortion. Experiments demonstrate that models trained with our pipeline achieve state-of-the-art zero-shot generalization across multiple datasets with only a dataset volume comparable to Scene Flow. Code: https://github.com/Windsrain/ZeroStereo.

cs.CV↗

arXiv2025

Basic Reading Distillation

Large language models (LLMs) have demonstrated remarkable abilities in various natural language processing areas, but they demand high computation resources which limits their deployment in real-world. Distillation is one technique to solve this problem through either knowledge distillation or task distillation. Both distillation approaches train small models to imitate specific features of LLMs, but they all neglect basic reading education for small models on generic texts that are \emph{unrelated} to downstream tasks. In this paper, we propose basic reading distillation (BRD) which educates a small model to imitate LLMs basic reading behaviors, such as named entity recognition, question raising and answering, on each sentence. After such basic education, we apply the small model on various tasks including language inference benchmarks and BIG-bench tasks. It shows that the small model can outperform or perform comparable to over 20x bigger LLMs. Analysis reveals that BRD effectively influences the probability distribution of the small model, and has orthogonality to either knowledge distillation or task distillation.

cs.CL↗

arXiv2025

Met$^2$Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems

The increasing frequency of extreme weather events due to global climate change urges accurate weather prediction. Recently, great advances have been made by the \textbf{end-to-end methods}, thanks to deep learning techniques, but they face limitations of \textit{representation inconsistency} in multivariable integration and struggle to effectively capture the dependency between variables, which is required in complex weather systems. Treating different variables as distinct modalities and applying a \textbf{two-stage training approach} from multimodal models can partially alleviate this issue, but due to the inconformity in training tasks between the two stages, the results are often suboptimal. To address these challenges, we propose an implicit two-stage training method, configuring separate encoders and decoders for each variable. In detailed, in the first stage, the Translator is frozen while the Encoders and Decoders learn a shared latent space, in the second stage, the Encoders and Decoders are frozen, and the Translator captures inter-variable interactions for prediction. Besides, by introducing a self-attention mechanism for multivariable fusion in the latent space, the performance achieves further improvements. Empirically, extensive experiments show the state-of-the-art performance of our method. Specifically, it reduces the MSE for near-surface air temperature and relative humidity predictions by 28.82\% and 23.39\%, respectively. The source code is available at https://github.com/ShremG/Met2Net.

cs.LG↗

arXiv2025

SpecDis: Value added distance catalogue for 4 million stars from DESI Year-1 data

We present the SpecDis value added stellar distance catalog accompanying DESI DR1. SpecDis trains a feed-forward Neural Network (NN) with Gaia parallaxes and gets the distance estimates. To build up unbiased training sample, we do not apply selections on parallax error or signal-to-noise (S/N) of the stellar spectra, and instead we incorporate parallax error into the loss function. Moreover, we employ Principal Component Analysis (PCA) to reduce the noise and dimensionality of stellar spectra. Validated by independent external samples of member stars with precise distances from globular clusters (GCs), dwarf galaxies, stellar streams, combined with blue horizontal branch (BHB) stars, we demonstrate that our distance measurements show no significant bias up to 100kpc, and are much more precise than Gaia parallax beyond 7kpc. The median distance uncertainties are 23%, 19%, 11% and 7% for S/N $<$ 20, 20 $\leq$ S/N$<$ 60, 60 $\leq$ S/N $<$ 100 and S/N $\geq$ 100. Selecting stars with $\log g<3.8$ and distance uncertainties smaller than 25%, we have more than 74,000 giant candidates within 50kpc to the Galactic center and 1,500 candidates beyond this distance. Additionally, we develop a Gaussian mixture model to identify unresolvable equal-mass binaries by modeling the discrepancy between the NN-predicted and the geometric absolute magnitudes from Gaia parallaxes and identify 120,000 equal-mass binary candidates. Our final catalog provides distances and distance uncertainties for $>$ 4 million stars, offering a valuable resource for Galactic astronomy.

astro-ph.GA↗

arXiv2025

Function-to-Style Guidance of LLMs for Code Translation

Large language models (LLMs) have made significant strides in code translation tasks. However, ensuring both the correctness and readability of translated code remains a challenge, limiting their effective adoption in real-world software development. In this work, we propose F2STrans, a function-to-style guiding paradigm designed to progressively improve the performance of LLMs in code translation. Our approach comprises two key stages: (1) Functional learning, which optimizes translation correctness using high-quality source-target code pairs mined from online programming platforms, and (2) Style learning, which improves translation readability by incorporating both positive and negative style examples. Additionally, we introduce a novel code translation benchmark that includes up-to-date source code, extensive test cases, and manually annotated ground-truth translations, enabling comprehensive functional and stylistic evaluations. Experiments on both our new benchmark and existing datasets demonstrate that our approach significantly improves code translation performance. Notably, our approach enables Qwen-1.5B to outperform prompt-enhanced Qwen-32B and GPT-4 on average across 20 diverse code translation scenarios.

cs.AI↗

arXiv2025

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing. Although existing methods can guide generation beyond text prompts, the challenge of effectively combining multiple conditional inputs while maintaining consistency with all of them remains unsolved. To address this, we introduce UniCombine, a DiT-based multi-conditional controllable generative framework capable of handling any combination of conditions, including but not limited to text prompts, spatial maps, and subject images. Specifically, we introduce a novel Conditional MMDiT Attention mechanism and incorporate a trainable LoRA module to build both the training-free and training-based versions. Additionally, we propose a new pipeline to construct SubjectSpatial200K, the first dataset designed for multi-conditional generative tasks covering both the subject-driven and spatially-aligned conditions. Extensive experimental results on multi-conditional generation demonstrate the outstanding universality and powerful capability of our approach with state-of-the-art performance.

cs.CV↗

arXiv2025

Force-IMU Fusion-Based Sensing Acupuncture Needle and Quantitative Analysis System for Acupuncture Manipulations

Acupuncture, one of the key therapeutic methods in Traditional Chinese Medicine (TCM), has been widely adopted in various clinical fields. Quantitative research on acupuncture manipulation parameters is critical to achieve standardized techniques. However, quantitative mechanical detection of acupuncture parameters remains limited. This study establishes a kinematic and dynamic model of acupuncture, identifying key parameters such as lifting-thrusting force, acceleration, velocity, displacement, as well as twirling-rotating angular velocity and angle. To measure these critical parameters, we propose a quantitative system comprising a sensing needle equipped with a force sensor and an inertial measurement unit (IMU), as well as an external camera module to capture image information. By fusing visual and IMU data, we accurately identify the stationary or motion states of the needle, enabling segmented computation of lifting-thrusting velocity and displacement. The experimental results demonstrate that the sensing needle achieves comprehensive detection with high precision, featuring a nonlinearity error of 0.45% in force measurement and an RMSE of 1.2 mm in displacement. The extracted parameters provide an objective description of the operational characteristics and motion patterns of the four basic acupuncture manipulations. These findings provide valuable tools and methods for research in acupuncture standardization.

eess.SY↗

arXiv2025

Echoes and quasi-normal modes of perturbations around Schwarzchild traversable wormholes

We investigate the waveforms and quasi-normal modes around Schwarzschild traversable wormholes under different field perturbations, including the scalar field, the electromagnetic (vector) field, and the axial gravitational (tensor) field perturbations. Our results indicate that under the influence of the matter at the throat of the wormhole, a Dirac $δ$-function distribution of matter appears in the effective potentials of the scalar and axial gravitational perturbations and it affects the propagation of these two types of perturbations in spacetime. However, the matter at the throat has no influence on the propagation of electromagnetic perturbations. Furthermore, we quantify the impact of throat matter on both the perturbation waveforms and quasi-normal modes for all three field types. Through comparative studies between Schwarzschild traversable wormholes and Schwarzschild black holes, we identify two distinct features. Firstly, the perturbation waveforms exhibit echoes and damping oscillations around wormholes, whereas they solely display damping oscillations around black holes. Secondly, the difference between the adjacent peaks varies with the mass parameter and the throat radial coordinate in the waveform around Schwarzschild traversable wormholes, while a constant peak spacing occurs, which is determined solely by mass, in the waveform around Schwarzschild black holes. Based on these findings, we propose a framework to estimate the mass parameter and throat radial coordinate of Schwarzschild traversable wormholes through waveforms and quasi-normal modes. Our analyses provide a more profound comprehension of the inherent characteristics of Schwarzschild traversable wormholes.

gr-qc↗

arXiv2025

BERT4Traj: Transformer Based Trajectory Reconstruction for Sparse Mobility Data

Understanding human mobility is essential for applications in public health, transportation, and urban planning. However, mobility data often suffers from sparsity due to limitations in data collection methods, such as infrequent GPS sampling or call detail record (CDR) data that only capture locations during communication events. To address this challenge, we propose BERT4Traj, a transformer based model that reconstructs complete mobility trajectories by predicting hidden visits in sparse movement sequences. Inspired by BERT's masked language modeling objective and self_attention mechanisms, BERT4Traj leverages spatial embeddings, temporal embeddings, and contextual background features such as demographics and anchor points. We evaluate BERT4Traj on real world CDR and GPS datasets collected in Kampala, Uganda, demonstrating that our approach significantly outperforms traditional models such as Markov Chains, KNN, RNNs, and LSTMs. Our results show that BERT4Traj effectively reconstructs detailed and continuous mobility trajectories, enhancing insights into human movement patterns.

cs.LG↗