arXiv subjects

Hui Wang

Publications and source records attributed to Hui Wang.

At least 181 records · Page 10Linked to original sources

arXiv2025

Role of two-body dissipation on the mean-field dynamics validity

The role of two-body dissipation in nuclear reactions at energies of several times Coulomb barrier remains unclear but is crucial for understanding the mechanisms of deep-inelastic reactions. In this letter, we report a systematic analysis of two-body dissipation effects on the validity of mean-field dynamics, enabled by the TDHF-QRx approach, which incorporates the collision term via the relaxation-time approximation rather than full collision calculations. For deep-inelastic reactions, the contact time between nuclei is found to increase, resulting in changes to the reaction process and fragment properties such as scattering angles and total kinetic energy. These changes become important with the increase of reaction energy and decrease of impact parameter. We identify the range of reaction condition where two-body dissipation becomes significant, providing valuable insights for the applicability of mean-field dynamics approaches. The limitations of model, particularly those arising from the incomplete conservation of the locality of two-body dissipation within the quantum framework, are also discussed.

nucl-th↗

arXiv2025

Interleaved Speech-Text Language Models for Simple Streaming Text-to-Speech Synthesis

This paper introduces Interleaved Speech-Text Language Model (IST-LM) for zero-shot streaming Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on interleaved sequences of text and speech tokens with a fixed ratio, eliminating the need for additional efforts like forced alignment or complex designs. The ratio of text chunk size to speech chunk size is crucial for the performance of IST-LM. To explore this, we conducted a comprehensive series of statistical analyses on the training data and performed correlation analysis with the final performance, uncovering several key factors: 1) the distance between speech tokens and their corresponding text tokens, 2) the number of future text tokens accessible to each speech token, and 3) the frequency of speech tokens precedes their corresponding text tokens. Experimental results demonstrate how to achieve an optimal streaming TTS system with a limited performance gap compared to its non-streaming counterpart. IST-LM is conceptually simple and empirically powerful, enabling streaming TTS with minimal overhead while largely preserving performance, and offering broad potential for integration with real-time text streams from large language models.

eess.AS↗

arXiv2025

TMA-Adaptive FP8 Grouped GEMM: Eliminating Padding Requirements in Low-Precision Training and Inference on Hopper

Current FP8 grouped GEMM implementations require padding each group to a fixed alignment (e.g., 128), incurring memory and computational overhead. We propose \textit{TMA-Adaptive FP8 Grouped GEMM}, which eliminates padding by dynamically adapting to variable group dimensions via (1) a TMA descriptor pool with $\log_2(block_M)$ preconfigured descriptors to handle all residual row cases through dynamic runtime selection and dual-phase load-store operations, achieving comprehensive coverage with minimal overhead, and (2) TMA-alignment-aware management to satisfy 16-byte global memory alignment and 128-byte shared memory alignment. Experiments demonstrate 1.7\% to 20.4\% speed up with up to 23.8\% memory reduction compared to padding operation plus state-of-the-art FP8 grouped GEMM, while maintaining full numerical equivalence for valid data. The source code is publicly available at an anonymous repository: https://github.com/sukoncon/TMA-Adaptive-FP8-Grouped-GEMM.

cs.AR↗

arXiv2025

Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis

Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregressive (NAR) models lack temporal modeling and typically require complex designs. In this paper, we introduce a novel pseudo-autoregressive (PAR) codec language modeling approach that unifies AR and NAR modeling. Combining explicit temporal modeling from AR with parallel generation from NAR, PAR generates dynamic-length spans at fixed time steps. Building on PAR, we propose PALLE, a two-stage TTS system that leverages PAR for initial generation followed by NAR refinement. In the first stage, PAR progressively generates speech tokens along the time dimension, with each step predicting all positions in parallel but only retaining the left-most span. In the second stage, low-confidence tokens are iteratively refined in parallel, leveraging the global contextual information. Experiments demonstrate that PALLE, trained on LibriTTS, outperforms state-of-the-art systems trained on large-scale data, including F5-TTS, E2-TTS, and MaskGCT, on the LibriSpeech test-clean set in terms of speech quality, speaker similarity, and intelligibility, while achieving up to ten times faster inference speed. Audio samples are available at https://microsoft.com/research/project/vall-e-x/palle.

eess.AS↗

arXiv2025

Hybrid Hypergraph Networks for Multimodal Sequence Data Classification

Modeling temporal multimodal data poses significant challenges in classification tasks, particularly in capturing long-range temporal dependencies and intricate cross-modal interactions. Audiovisual data, as a representative example, is inherently characterized by strict temporal order and diverse modalities. Effectively leveraging the temporal structure is essential for understanding both intra-modal dynamics and inter-modal correlations. However, most existing approaches treat each modality independently and rely on shallow fusion strategies, which overlook temporal dependencies and hinder the model's ability to represent complex structural relationships. To address the limitation, we propose the hybrid hypergraph network (HHN), a novel framework that models temporal multimodal data via a segmentation-first, graph-later strategy. HHN splits sequences into timestamped segments as nodes in a heterogeneous graph. Intra-modal structures are captured via hyperedges guided by a maximum entropy difference criterion, enhancing node heterogeneity and structural discrimination, followed by hypergraph convolution to extract high-order dependencies. Inter-modal links are established through temporal alignment and graph attention for semantic fusion. HHN achieves state-of-the-art (SOTA) results on four multimodal datasets, demonstrating its effectiveness in complex classification tasks.

cs.LG↗

arXiv2025

Detecting the most probable transition phenomenon of a nutrient-phytoplankton-zooplankton system

The population biology model holds a significant position within ecosystems. Introducing stochastic perturbations into the model can more accurately depict real biological processes. In this paper, we primarily investigate the most probable transition phenomenon in a three-dimensional nutrient-phytoplankton-zooplankton (NPZ) plankton model. With appropriate parameter values, the system coexists with a stable equilibrium point and a stable limit cycle. Under noise perturbations, transitions occur between these two steady states. Based on the Onsager-Machlup action functional and the neural shooting method, we have studied the most probable transition time, the most probable transition pathway and the most probable transition probability of the NPZ system. The transition between these metastable states plays a crucial role in stochastic ecosystems, providing guidance for a better understanding of complex biological processes.

q-bio.PE↗

arXiv2025

Generative Latent Kernel Modeling for Blind Motion Deblurring

Deep prior-based approaches have demonstrated remarkable success in blind motion deblurring (BMD) recently. These methods, however, are often limited by the high non-convexity of the underlying optimization process in BMD, which leads to extreme sensitivity to the initial blur kernel. To address this issue, we propose a novel framework for BMD that leverages a deep generative model to encode the kernel prior and induce a better initialization for the blur kernel. Specifically, we pre-train a kernel generator based on a generative adversarial network (GAN) to aptly characterize the kernel's prior distribution, as well as a kernel initializer to provide a well-informed and high-quality starting point for kernel estimation. By combining these two components, we constrain the BMD solution within a compact latent kernel manifold, thus alleviating the aforementioned sensitivity for kernel initialization. Notably, the kernel generator and initializer are designed to be easily integrated with existing BMD methods in a plug-and-play manner, enhancing their overall performance. Furthermore, we extend our approach to tackle blind non-uniform motion deblurring without the need for additional priors, achieving state-of-the-art performance on challenging benchmark datasets. The source code is available at https://github.com/dch0319/GLKM-Deblur.

cs.CV↗

arXiv2025

SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam

Adam has proven remarkable successful in training deep neural networks, but the mechanisms underlying its empirical successes and limitations remain underexplored. In this study, we demonstrate that the effectiveness of Adam stems largely from its similarity to SignSGD in robustly handling large gradient fluctuations, yet it is also vulnerable to destabilizing loss spikes due to its uncontrolled update scaling. To enhance the advantage of Adam and mitigate its limitation, we propose SignSoftSGD (S3), a novel optimizer with three key innovations. \emph{First}, S3 generalizes the sign-like update by employing a flexible $p$-th order momentum ($p \geq 1$) in the denominator, departing from the conventional second-order momentum (variance) preconditioning. This design enables enhanced performance while achieving stable training even with aggressive learning rates. \emph{Second}, S3 minimizes the occurrences of loss spikes through unified exponential moving average coefficients for numerator and denominator momenta, which inherently bound updates to $[-1, 1]$ and simplify hyperparameter tuning. \emph{Third}, S3 incorporates an equivalent Nesterov's accelerated gradient(NAG) module, accelerating convergence without memory overhead. Theoretically, we prove that S3 achieves the optimal convergence rate of $O\left(\frac{1}{T^{\sfrac{1}{4}}}\right)$ for general nonconvex stochastic optimization under weak assumptions. Extensive experiments across a range of vision and language tasks show that \textsf{\small S3} not only converges more rapidly and improves performance but also rarely experiences loss spikes, even with a \textbf{$\bm{10 \times}$} larger learning rate. In fact, S3 delivers performance comparable to or better than AdamW with \textbf{$2 \times$} the training steps, establishing its efficacy in both efficiency and final task performance.

cs.LG↗

arXiv2025

Simple Convergence Proof of Adam From a Sign-like Descent Perspective

Adam is widely recognized as one of the most effective optimizers for training deep neural networks (DNNs). Despite its remarkable empirical success, its theoretical convergence analysis remains unsatisfactory. Existing works predominantly interpret Adam as a preconditioned stochastic gradient descent with momentum (SGDM), formulated as $\bm{x}_{t+1} = \bm{x}_t - \frac{γ_t}{{\sqrt{\bm{v}_t}+ε}} \circ \bm{m}_t$. This perspective necessitates strong assumptions and intricate techniques, resulting in lengthy and opaque convergence proofs that are difficult to verify and extend. In contrast, we propose a novel interpretation by treating Adam as a sign-like optimizer, expressed as $\bm{x}_{t+1} = \bm{x}_t - γ_t \frac{|\bm{m}_t|}{{\sqrt{\bm{v}_t}+ε}} \circ {\rm Sign}(\bm{m}_t)$. This reformulation significantly simplifies the convergence analysis. For the first time, with some mild conditions, we prove that Adam achieves the optimal rate of ${\cal O}(\frac{1}{T^{\sfrac{1}{4}}})$ rather than the previous ${\cal O} \left(\frac{\ln T}{T^{\sfrac{1}{4}}}\right)$ under weak assumptions of the generalized $p$-affine variance and $(L_0, L_1, q)$-smoothness, without dependence on the model dimensionality or the numerical stability parameter $ε$. Additionally, our theoretical analysis provides new insights into the role of momentum as a key factor ensuring convergence and offers practical guidelines for tuning learning rates in Adam, further bridging the gap between theory and practice.

cs.LG↗

arXiv2025

EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations

In recent years, emotion recognition plays a critical role in applications such as human-computer interaction, mental health monitoring, and sentiment analysis. While datasets for emotion analysis in languages such as English have proliferated, there remains a pressing need for high-quality, comprehensive datasets tailored to the unique linguistic, cultural, and multimodal characteristics of Chinese. In this work, we propose \textbf{EmotionTalk}, an interactive Chinese multimodal emotion dataset with rich annotations. This dataset provides multimodal information from 19 actors participating in dyadic conversational settings, incorporating acoustic, visual, and textual modalities. It includes 23.6 hours of speech (19,250 utterances), annotations for 7 utterance-level emotion categories (happy, surprise, sad, disgust, anger, fear, and neutral), 5-dimensional sentiment labels (negative, weakly negative, neutral, weakly positive, and positive) and 4-dimensional speech captions (speaker, speaking style, emotion and overall). The dataset is well-suited for research on unimodal and multimodal emotion recognition, missing modality challenges, and speech captioning tasks. To our knowledge, it represents the first high-quality and versatile Chinese dialogue multimodal emotion dataset, which is a valuable contribution to research on cross-cultural emotion analysis and recognition. Additionally, we conduct experiments on EmotionTalk to demonstrate the effectiveness and quality of the dataset. It will be open-source and freely available for all academic purposes. The dataset and codes will be made available at: https://github.com/NKU-HLT/EmotionTalk.

cs.MM↗

arXiv2025

Enhanced Image Recognition Using Gaussian Boson Sampling

Gaussian boson sampling (GBS) has emerged as a promising quantum computing paradigm, demonstrating its potential in various applications. However, most existing works focus on theoretical aspects or simple tasks, with limited exploration of its capabilities in solving real-world practical problems. In this work, we propose a novel GBS-based image recognition scheme inspired by extreme learning machine (ELM) to enhance the performance of perceptron and implement it using our latest GBS device, Jiuzhang. Our approach utilizes an 8176-mode temporal-spatial hybrid encoding photonic processor, achieving approximately 2200 average photon clicks in the quantum computational advantage regime. We apply this scheme to classify images from the MNIST and Fashion-MNIST datasets, achieving a testing accuracy of 95.86% on MNIST and 85.95% on Fashion-MNIST. These results surpass those of classical method SVC with linear kernel and previous physical ELM-based experiments. Additionally, we explore the influence of three hyperparameters and the efficiency of GBS in our experiments. This work not only demonstrates the potential of GBS in real-world machine learning applications but also aims to inspire further advancements in powerful machine learning schemes utilizing GBS technology.

quant-ph↗

arXiv2025

Planning of Heuristics: Strategic Planning on Large Language Models with Monte Carlo Tree Search for Automating Heuristic Optimization

Heuristics have achieved great success in solving combinatorial optimization problems~(COPs). However, heuristics designed by humans require too much domain knowledge and testing time. Since Large Language Models~(LLMs) possess strong capabilities to understand and generate content with a knowledge base that covers various domains, they offer potential ways to automatically optimize heuristics. To this end, we propose Planning of Heuristics~(PoH), an optimization method that integrates LLM self-reflection with Monte Carlo Tree Search, a well-known planning algorithm. PoH iteratively refines generated heuristics by evaluating their performance and providing improvement suggestions. Our method enables to iteratively evaluate the generated heuristics~(states) and improve them based on the improvement suggestions~(actions) and evaluation results~(rewards), by effectively simulating future states to search for paths with higher rewards. In this paper, we apply PoH to solve the Traveling Salesman Problem and the Flow Shop Scheduling Problem. The experimental results show that PoH outperforms hand-crafted heuristics and other Automatic Heuristic Design methods based on LLMs, and achieves the state-of-the-art performance in automating heuristic optimization with LLMs to solve tested COPs, especially with large sizes.

cs.AI↗

arXiv2025

StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling

Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming TTS paradigms often rely on multi-stage pipelines and discrete representations, leading to increased computational cost and suboptimal system performance. In this work, we propose StreamMel, a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms. By interleaving text tokens with acoustic frames, StreamMel enables low-latency, autoregressive synthesis while preserving high speaker similarity and naturalness. Experiments on LibriSpeech demonstrate that StreamMel outperforms existing streaming TTS baselines in both quality and latency. It even achieves performance comparable to offline systems while supporting efficient real-time generation, showcasing broad prospects for integration with real-time speech large language models. Audio samples are available at: https://aka.ms/StreamMel.

cs.SD↗

arXiv2025

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference

With the growing deployment of pre-trained models like Transformers on cloud platforms, privacy concerns about model parameters and inference data are intensifying. Existing Privacy-Preserving Transformer Inference (PPTI) frameworks face the "impossible trinity" of balancing privacy, efficiency, and performance: Secure Multi-Party Computation (SMPC)-based approaches ensure strong privacy but suffer from high computational overhead and performance losses; Conversely, permutation-based methods achieve near-plaintext efficiency and accuracy but compromise privacy by exposing sensitive model parameters and intermediate results. Bridging this gap with a single approach presents substantial challenges, motivating the introduction of CENTAUR, a groundbreaking PPTI framework that seamlessly integrates random permutations and SMPC to address the "impossible trinity". By designing efficient PPTI algorithms tailored to the structural properties of Transformer models, CENTAUR achieves an unprecedented balance among privacy, efficiency, and performance. Our experiments demonstrate CENTAUR's ability to resist diverse data reconstruction attacks, achieve plaintext-level inference accuracy, and boost inference speed by 5.0-30.4 times, unlocking new possibilities for secure and efficient AI deployment.

cs.LG↗

arXiv2025

SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC

With the growing use of Transformer models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investment plans and bank account details. Secure Multi-Party Computing (SMPC) emerges as a promising solution to protect the privacy of inference data and model parameters. However, the application of SMPC in Privacy-Preserving Inference (PPI) for Transformer models often leads to considerable slowdowns or declines in performance. This is largely due to the multitude of nonlinear operations in the Transformer architecture, which are not well-suited to SMPC and difficult to circumvent or optimize effectively. To address this concern, we introduce a comprehensive PPI framework called SecFormer to achieve fast and accurate PPI for Transformer models. We successfully eliminate the high-cost exponential and maximum operations in PPI without sacrificing model performance and develop a suite of efficient SMPC protocols by employing suitable numerical computation methods to boost other complex nonlinear functions in PPI, including GeLU, LayerNorm, and a redesigned Softmax. Our extensive experiments reveal that SecFormer outperforms MPCFormer in performance, showing improvements of $3.4\%$ and $24.7\%$ for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, respectively. In terms of efficiency, SecFormer is 3.57 and 3.58 times faster than PUMA for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, demonstrating its effectiveness and speed.

cs.LG↗

arXiv2025

UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities

Entity Set Expansion (ESE) aims to identify new entities belonging to the same semantic class as the given set of seed entities. Traditional methods solely relied on positive seed entities to represent the target fine-grained semantic class, rendering them tough to represent ultra-fine-grained semantic classes. Specifically, merely relying on positive seed entities leads to two inherent shortcomings: (i) Ambiguity among ultra-fine-grained semantic classes. (ii) Inability to define ``unwanted'' semantics. Hence, previous ESE methods struggle to address the ultra-fine-grained ESE (Ultra-ESE) task. To solve this issue, we first introduce negative seed entities in the inputs, which jointly describe the ultra-fine-grained semantic class with positive seed entities. Negative seed entities eliminate the semantic ambiguity by providing a contrast between positive and negative attributes. Meanwhile, it provides a straightforward way to express ``unwanted''. To assess model performance in Ultra-ESE and facilitate further research, we also constructed UltraWiki, the first large-scale dataset tailored for Ultra-ESE. UltraWiki encompasses 50,973 entities and 394,097 sentences, alongside 236 ultra-fine-grained semantic classes, where each class is represented with 3-5 positive and negative seed entities. Moreover, a retrieval-based framework RetExpan and a generation-based framework GenExpan are proposed to provide powerful baselines for Ultra-ESE. Additionally, we devised two strategies to enhance models' comprehension of ultra-fine-grained entities' semantics: contrastive learning and chain-of-thought reasoning. Extensive experiments confirm the effectiveness of our proposed strategies and also reveal that there remains a large space for improvement in Ultra-ESE.

cs.CL↗

arXiv2025

Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling

Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces high processing latency. To address this issue, we propose SMLLE, a streaming framework for generating high-quality speech frame-by-frame. SMLLE employs a Transducer to convert text into semantic tokens in real time while simultaneously obtaining duration alignment information. The combined outputs are then fed into a fully autoregressive (AR) streaming model to reconstruct mel-spectrograms. To further stabilize the generation process, we design a Delete < Bos > Mechanism that allows the AR model to access future text introducing as minimal delay as possible. Experimental results suggest that the SMLLE outperforms current streaming TTS methods and achieves comparable performance over sentence-level TTS systems. Samples are available on shy-98.github.io/SMLLE_demo_page/.

cs.LG↗

arXiv2025

A Selberg-type zero-density result for twisted $\rm GL_2$ $L$-functions and its application

Let $f$ be a fixed holomorphic primitive cusp form of even weight $k$, level $r$ and trivial nebentypus $χ_r$. Let $q$ be an odd prime with $(q,r)=1$ and let $χ$ be a primitive Dirichlet character modulus $q$ with $χ\neqχ_r$. In this paper, we prove an unconditional Selberg-type zero-density estimate for the family of twisted $L$-functions $L(s, f \otimes χ)$ in the critical strip. As an application, we establish an asymptotic formula for the even moments of the argument function $S(t, f \otimes χ)=π^{-1}\arg L(1/2+ıt, f\otimesχ)$ and prove a central limit theorem for its distribution over $χ$ of modulus $q$.

math.NT↗