arXiv subjects

Bo Hu

Publications and source records attributed to Bo Hu.

At least 37 records · Page 2Linked to original sources

arXiv2026

SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads

Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale models often suffer from prohibitive computational costs, while lightweight alternatives typically compromise on holistic facial representations and temporal stability. In this paper, we propose SoulX-FlashHead, a unified 1.3B-parameter framework designed for real-time, infinite-length, and high-fidelity streaming video generation. To address the instability of audio features in streaming scenarios, we introduce Streaming-Aware Spatiotemporal Pre-training equipped with a Temporal Audio Context Cache mechanism, which ensures robust feature extraction from short audio fragments. Furthermore, to mitigate the error accumulation and identity drift inherent in long-sequence autoregressive generation, we propose Oracle-Guided Bidirectional Distillation, leveraging ground-truth motion priors to provide precise physical guidance. We also present VividHead, a large-scale, high-quality dataset containing 782 hours of strictly aligned footage to support robust training. Extensive experiments demonstrate that SoulX-FlashHead achieves state-of-the-art performance on HDTF and VFHQ benchmarks. Notably, our Lite variant achieves an inference speed of 96 FPS on a single NVIDIA RTX 4090, facilitating ultra-fast interaction without sacrificing visual coherence.

cs.CV↗

arXiv2026

A Multi-agent Framework for Physical Laws Discovery

Discovering explicit physical laws has traditionally depended on human intuition and domain expertise. Recent advances in artificial intelligence, particularly large language models (LLMs), offer a new route to accelerate this process by automating key steps from hypothesis generation to interpretable model construction. Here we develop an LLM-based multi-agent framework for physical-law discovery that integrates literature-guided variable selection, hypothesis formulation, symbolic regression, formula derivation, and mechanistic explanation. We validate the framework on three representative materials problems: the glass-forming ability (GFA) of metallic glasses, the Vickers hardness of compounds, and the Young's modulus of multi-component alloys. Using physically and chemically meaningful descriptors as inputs, the discovered formulas achieve strong agreement with reference data, with correlation coefficients up to 0.94 (GFA), 0.86 (hardness), and 0.94 (Young's modulus), while remaining compact and interpretable. Beyond fitting, the Young's modulus formula generalizes to quaternary and quinary alloys, improving prediction accuracy by up to 78.8% relative to the classical rule of mixtures. By integrating cross-disciplinary knowledge, reflection mechanisms, and expert-like reasoning ability into symbolic regression, our AI-centric framework offers a robust and extensible platform for automated physical laws discovery, demonstrating that AI can increasingly serve as an essential role in modern scientific research by thinking and acting like field experts.

cond-mat.mtrl-sci↗

arXiv2025

MatTools: Benchmarking Large Language Models for Materials Science Tools

Large language models (LLMs) are increasingly applied to materials science questions, including literature comprehension, property prediction, materials discovery and alloy design. At the same time, a wide range of physics-based computational approaches have been developed in which materials properties can be calculated. Here, we propose a benchmark application to evaluate the proficiency of LLMs to answer materials science questions through the generation and safe execution of codes based on such physics-based computational materials science packages. MatTools is built on two complementary components: a materials simulation tool question-answer (QA) benchmark and a real-world tool-usage benchmark. We designed an automated methodology to efficiently collect real-world materials science tool-use examples. The QA benchmark, derived from the pymatgen (Python Materials Genomics) codebase and documentation, comprises 69,225 QA pairs that assess the ability of an LLM to understand materials science tools. The real-world benchmark contains 49 tasks (138 subtasks) requiring the generation of functional Python code for materials property calculations. Our evaluation of diverse LLMs yields three key insights: (1)Generalists outshine specialists;(2)AI knows AI; and (3)Simpler is better. MatTools provides a standardized framework for assessing and improving LLM capabilities for materials science tool applications, facilitating the development of more effective AI systems for materials science and general scientific research.

cond-mat.mtrl-sci↗

arXiv2025

Contrastive Entropy Bounds for Density and Conditional Density Decomposition

This paper studies the interpretability of neural network features from a Bayesian Gaussian view, where optimizing a cost is reaching a probabilistic bound; learning a model approximates a density that makes the bound tight and the cost optimal, often with a Gaussian mixture density. The two examples are Mixture Density Networks (MDNs) using the bound for the marginal and autoencoders using the conditional bound. It is a known result, not only for autoencoders, that minimizing the error between inputs and outputs maximizes the dependence between inputs and the middle. We use Hilbert space and decomposition to address cases where a multiple-output network produces multiple centers defining a Gaussian mixture. Our first finding is that an autoencoder's objective is equivalent to maximizing the trace of a Gaussian operator, the sum of eigenvalues under bases orthonormal w.r.t. the data and model distributions. This suggests that, when a one-to-one correspondence as needed in autoencoders is unnecessary, we can instead maximize the nuclear norm of this operator, the sum of singular values, to maximize overall rank rather than trace. Thus the trace of a Gaussian operator can be used to train autoencoders, and its nuclear norm can be used as divergence to train MDNs. Our second test uses inner products and norms in a Hilbert space to define bounds and costs. Such bounds often have an extra norm compared to KL-based bounds, which increases sample diversity and prevents the trivial solution where a multiple-output network produces the same constant, at the cost of requiring a sample batch to estimate and optimize. We propose an encoder-mixture-decoder architecture whose decoder is multiple-output, producing multiple centers per sample, potentially tightening the bound. Assuming the data are small-variance Gaussian mixtures, this upper bound can be tracked and analyzed quantitatively.

cs.LG↗

arXiv2025

DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Model

Text-to-SQL tasks have gained attractive improvements since the release of ChatGPT. Among them, agent-based frameworks have been widely used in this field. However, the impact of data-centric strategies on text-to-SQL tasks has rarely been explored. In this paper, we systemically design a fully automated data-centric pipeline for text-to-SQL tasks, including \emph{adaptive data repair}, which can automatically find and fix errors in the training dataset; and \emph{error data augmentation}, where we specifically diffuse and enhance erroneous data predicted by the initially trained models. Meanwhile, we propose a Multi-Model collaboration training schema, aiming to train multiple models with different augmented data, enabling them to possess distinct capabilities and work together to complement each other, because it has been found that the capability of a single fine-tuned model is very limited. Furthermore, we utilize an ensemble strategy to integrate the capabilities of multiple models to solve a multiple-choice question, aiming to further improve the accuracy of text-to-SQL tasks. The experiment results and ablation study have demonstrated the effectiveness of data-centric pipeline and Multi-Model(MM) interactive iterative strategies, achieving first place in lightweight text-to-SQL models (within 70B).

cs.CL↗

arXiv2025

A Family of Kernelized Matrix Costs for Multiple-Output Mixture Neural Networks

Pairwise distance-based costs are crucial for self-supervised and contrastive feature learning. Mixture Density Networks (MDNs) are a widely used approach for generative models and density approximation, using neural networks to produce multiple centers that define a Gaussian mixture. By combining MDNs with contrastive costs, this paper proposes data density approximation using four types of kernelized matrix costs in the Hilbert space: the scalar cost, the vector-matrix cost, the matrix-matrix cost (the trace of Schur complement), and the SVD cost (the nuclear norm), for learning multiple centers required to define a mixture density.

cs.LG↗

arXiv2025

A Modular and Scalable Simulator for Connected-UAVs Communication in 5G Networks

Cellular-connected UAV systems have enabled a wide range of low-altitude aerial services. However, these systems still face many challenges, such as frequent handovers and the inefficiency of traditional transport protocols. To better study these issues, we develop a modular and scalable simulation platform specifically designed for UAVs communication leveraging the research ecology in wireless communication of MATLAB. The platform supports flexible 5G NR node deployment, customizable UAVs mobility models, and multi-network-interface extensions. It also supports multiple transport protocols including TCP, UDP, QUIC, etc., allowing to investigate how different transport protocols affect UAVs communication performance. In addition, the platform includes a handover management module, enabling the evaluation of both traditional and learning-based handover strategies. Our platform can serve as a testbed for the development and evaluation of advanced transmission strategies in cellular-connected UAV systems.

cs.NI↗

arXiv2025

Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT

Non-contrast computed tomography (NCCT) is essential for rapid stroke diagnosis but is limited by low image contrast and signal to noise ratio. We address this challenge by leveraging DINOv3, a state-of-the-art self-supervised vision transformer, to generate powerful feature representations for a comprehensive set of stroke analysis tasks. Our evaluation encompasses infarct and hemorrhage segmentation, anomaly classification (normal vs. stroke and normal vs. infarct vs. hemorrhage), hemorrhage subtype classification (EDH, SDH, SAH, IPH, IVH), and dichotomized ASPECTS classification (<=6 vs. >6) on multiple public and private datasets. This study establishes strong benchmarks for these tasks and demonstrates the potential of advanced self-supervised models to improve automated stroke diagnosis from NCCT, providing a clear analysis of both the advantages and current constraints of the approach. The code is available at https://github.com/Zzz0251/DINOv3-stroke.

cs.CV↗

arXiv2025

TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback

Learning large-scale pre-trained models on broad-ranging data and then transfer to a wide range of target tasks has become the de facto paradigm in many machine learning (ML) communities. Such big models are not only strong performers in practice but also offer a promising way to break out of the task-specific modeling restrictions, thereby enabling task-agnostic and unified ML systems. However, such a popular paradigm is mainly unexplored by the recommender systems (RS) community. A critical issue is that standard recommendation models are primarily built on categorical identity features. That is, the users and the interacted items are represented by their unique IDs, which are generally not shareable across different systems or platforms. To pursue the transferable recommendations, we propose studying pre-trained RS models in a novel scenario where a user's interaction feedback involves a mixture-of-modality (MoM) items, e.g., text and images. We then present TransRec, a very simple modification made on the popular ID-based RS framework. TransRec learns directly from the raw features of the MoM items in an end-to-end training manner and thus enables effective transfer learning under various scenarios without relying on overlapped users or items. We empirically study the transferring ability of TransRec across four different real-world recommendation settings. Besides, we look at its effects by scaling source and target data size. Our results suggest that learning neural recommendation models from MoM feedback provides a promising way to realize universal RS.

cs.IR↗

arXiv2025

On Sampling of Multiple Correlated Stochastic Signals

Multiple stochastic signals possess inherent statistical correlations, yet conventional sampling methods that process each channel independently result in data redundancy. To leverage this correlation for efficient sampling, we model correlated channels as a linear combination of a smaller set of uncorrelated, wide-sense stationary latent sources. We establish a theoretical lower bound on the total sampling density for zero mean-square error reconstruction, proving it equals the ratio of the joint spectral bandwidth of latent sources to the number of correlated signal channels. We then develop a constructive multi-band sampling scheme that attains this bound. The proposed method operates via spectral partitioning of the latent sources, followed by spatio-temporal sampling and interpolation. Experiments on synthetic and real datasets confirm that our scheme achieves near-lossless reconstruction precisely at the theoretical sampling density, validating its efficiency.

eess.SP↗

arXiv2025

VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results

This paper presents an overview of the VQualA 2025 Challenge on Engagement Prediction for Short Videos, held in conjunction with ICCV 2025. The challenge focuses on understanding and modeling the popularity of user-generated content (UGC) short videos on social media platforms. To support this goal, the challenge uses a new short-form UGC dataset featuring engagement metrics derived from real-world user interactions. This objective of the Challenge is to promote robust modeling strategies that capture the complex factors influencing user engagement. Participants explored a variety of multi-modal features, including visual content, audio, and metadata provided by creators. The challenge attracted 97 participants and received 15 valid test submissions, contributing significantly to progress in short-form UGC video engagement prediction.

cs.CV↗

arXiv2025

Sampling Theory of Jointly Bandlimited Time-vertex Graph Signals

Time-vertex graph signal (TVGS) models describe time-varying data with irregular structures. The bandlimitedness in the joint time-vertex Fourier spectral domain reflects smoothness in both temporal and graph topology. In this paper, we study the critical sampling of three types of TVGS including continuous-time signals, infinite-length sequences, and finite-length sequences in the time domain for each vertex on the graph. For a jointly bandlimited TVGS, we prove a lower bound on sampling density or sampling ratio, which depends on the measure of the spectral support in the joint time-vertex Fourier spectral domain. We also provide a lower bound on the sampling density or sampling ratio of each vertex on sampling sets for perfect recovery. To demonstrate that critical sampling is achievable, we propose the sampling and reconstruction procedures for the different types of TVGS. Finally, we show how the proposed sampling schemes can be applied to numerical as well as real datasets.

eess.SP↗

arXiv2025

Subset Random Sampling and Reconstruction of Finite Time-Vertex Graph Signals

Finite time-vertex graph signals (FTVGS) provide an efficient representation for capturing spatio-temporal correlations across multiple data sources on irregular structures. Although sampling and reconstruction of FTVGS with known spectral support have been extensively studied, the case of unknown spectral support requires further investigation. Existing random sampling methods may extract samples from any vertex at any time, but such strategies are not friendly in practice, where sampling is typically limited to a subset of vertices and moments. To address this requirement, we propose a subset random sampling scheme for FTVGS. Specifically, we first randomly select a subset of rows and columns to form a submatrix, followed by random sampling within that submatrix. In theory, we provide sufficient conditions for reconstructing the original FTVGS with high probability. Additionally, we introduce a reconstruction framework incorporating low-rank, sparsity, and smoothness priors (LSSP), and verify the feasibility of the reconstruction and the effectiveness of the framework through experiments.

eess.SP↗

arXiv2025

Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience

Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure transfer mechanisms. Unlike humans who seamlessly apply learned patterns across data modalities, LLMs struggle to infer implicit relationships embedded in tabular formats, especially in the absence of explicit structural guidance. To bridge this cognitive gap, we introduce Contrastive Retrieval-Augmented Generation on Experience (CoRE), a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning (ICL) to simulate human-like knowledge transfer. Experiments on Text-to-SQL and TableQA show CoRE significantly improves performance, achieving average gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks. Our Monte Carlo Tree Search (MCTS)-generated Experience Memory expands training data 8-9x, enhancing diversity and domain coverage. This training-free and continual method propels LLMs toward structured knowledge expertise.

cs.CL↗

arXiv2025

Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding

Human intelligence requires correctness and robustness, with the former being foundational for the latter. In video understanding, correctness ensures the accurate interpretation of visual content, and robustness maintains consistent performance in challenging conditions. Despite advances in video large language models (video LLMs), existing benchmarks inadequately reflect the gap between these models and human intelligence in maintaining correctness and robustness in video interpretation. We introduce the Video Thinking Test (Video-TT), to assess if video LLMs can interpret real-world videos as effectively as humans. Video-TT reflects genuine gaps in understanding complex visual narratives, and evaluates robustness against natural adversarial questions. Video-TT comprises 1,000 YouTube Shorts videos, each with one open-ended question and four adversarial questions that probe visual and narrative complexity. Our evaluation shows a significant gap between video LLMs and human performance.

cs.CV↗

arXiv2025

Diagnostic Imaging for Damage Detection in Plates Based on Topological Acoustic (TA) Sensing Technique

Traditional structural damage detection methods in aerospace applications face challenges in accuracy and sensitivity, often necessitating multiple sensors to evaluate various measurement paths between the reference and defective states. However, the recently developed topological acoustic (TA) sensing technique can capture shifts in the geometric phase of an acoustic field, enabling the detection of even minor perturbations in the supporting medium. In this study, a diagnostic imaging method for damage detection in plate structures based on the TA sensing technique is presented. The method extracts the geometric phase shift index (GPS-I) from the Lamb wave response signals to indicate the location of the damage. Using Abaqus/CAE, a finite element model of the plate was established to simulate the Lamb wave response signals, which were then used to validate the feasibility of the proposed method. The results indicate that this technique enables rapid and precise identification of damage and its location within the plate structure, requiring response signals from only a few points on the damaged plate, and it is reference-free.

physics.app-ph↗

arXiv2025

NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

cs.CV↗

arXiv2025

Analysis of Distributional Dynamics for Repeated Cross-Sectional and Intra-Period Observations

This paper introduces a novel approach to investigate the dynamics of state distributions, which accommodate both cross-sectional distributions of repeated panels and intra-period distributions of a time series observed at high frequency. In our approach, densities of the state distributions are regarded as functional elements in a Hilbert space, and are assumed to follow a functional autoregressive model. We propose an estimator for the autoregressive operator, establish its consistency, and provide tools and asymptotics to analyze the forecast of state density and the moment dynamics of state distributions. We apply our methodology to study the time series of distributions of the GBP/USD exchange rate intra-month returns and the time series of cross-sectional distributions of the NYSE stocks monthly returns. Finally, we conduct simulations to evaluate the density forecasts based on our model.

econ.EM↗