arXiv subjects

Junhui Zhang

Publications and source records attributed to Junhui Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we propose a unified guidance framework that enhances generation efficiency and robustness through two complementary strategies. On the data front, we introduce Data-guidance via heterogeneous augmentation, encouraging the model to disentangle linguistic content from acoustic residue. In parallel, we propose an enhanced Model-guidance mechanism that synergizes trajectory rectification with a novel intrinsic guidance objective. This approach distills conditional knowledge into network weights and straightens inference trajectory path, thereby eliminating Classifier-Free Guidance (CFG) overhead. Experiments demonstrate that our framework accelerates inference by nearly three times while effectively improving speaker similarity compared to state-of-the-art baselines.

cs.SD↗

arXiv2026

Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions

While recent text-to-speech (TTS) models achieve high naturalness, controlling fine-grained expression via natural-language instructions remains challenging. We introduce Poly- InstructTTS, which learns expressive speech from open-ended instructions using in-the-wild audiovisual data. We build a scalable multi-modal pipeline to construct a 1,000-hour instruction-annotated corpus covering 1,000+ fine-grained emotions and styles. The framework uses a prompt-free GPT with attribute-based thinking tokens, followed by a flow-matching module that injects timbre from a reference audio. We also present a speaker fine-tuning procedure to transfer instruction control to specific speakers while preserving persona. We further extend InstructTTSEval with broader tasks. Experiments show that Poly-InstructTTS delivers strong performance in instruction adherence and expressiveness. Audio demos and the expanded testset are available on our project page.

cs.CL↗

arXiv2026

Multi-Timescale Primal Dual Hybrid Gradient with Application to Distributed Optimization

We propose two variants of the Primal Dual Hybrid Gradient (PDHG) algorithm for saddle point problems with block decomposable duals, hereafter called Multi-Timescale PDHG (MT-PDHG) and its accelerated variant (AMT-PDHG). Through novel mixtures of Bregman divergence and multi-timescale extrapolations, our MT-PDHG and AMT-PDHG converge under arbitrary updating rates for different dual blocks while remaining fully deterministic and robust to extreme delays in dual updates. We further apply our (A)MT-PDHG, augmented with the gradient sliding techniques introduced in Lan et al. (2020), Lan (2016), to distributed optimization. The flexibility in choosing different updating rates for different blocks allows a more refined control over the communication rounds between different pairs of agents, thereby improving the efficiencies in settings with heterogeneity in local objectives and communication costs. Moreover, with careful choices of penalty levels, our algorithms show linear and thus optimal dependency on function similarities, a measure of how similar the gradients of local objectives are. This provides a positive answer to the open question whether such dependency is achievable for non-smooth objectives (Arjevani and Shamir 2015).

math.OC↗

arXiv2026

Efficient Online Mirror Descent Stochastic Approximation for Multi-Stage Stochastic Programming

We study the unconstrained and the minimax saddle point variants of the convex multi-stage stochastic programming problem, where consecutive decisions are coupled through the objective functions, rather than through the constraints. We approach the problems from the infinite-dimensional policy perspective, but consider an online setting where only the policies corresponding to the actual realization of the underlying stochastic process is needed. This leads to a trackable formulation, where the dimension of the output is linear in the number of stages $T$. We propose hypothetical Mirror Descent Stochastic Approximation (MDSA) for the infinite dimensional policies using stochastic conditional gradients. By taking advantage of the decomposability of the updates across stages and realizations of the underlying stochastic process, we show that the proposed MDSA algorithms admit efficient online implementation, which achieves overall gradient complexity linear in $T$, improving exponentially over all existing algorithms.

math.OC↗

arXiv2025

Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning

Modern robot navigation systems encounter difficulties in diverse and complex indoor environments. Traditional approaches rely on multiple modules with small models or rule-based systems and thus lack adaptability to new environments. To address this, we developed Astra, a comprehensive dual-model architecture, Astra-Global and Astra-Local, for mobile robot navigation. Astra-Global, a multimodal LLM, processes vision and language inputs to perform self and goal localization using a hybrid topological-semantic graph as the global map, and outperforms traditional visual place recognition methods. Astra-Local, a multitask network, handles local path planning and odometry estimation. Its 4D spatial-temporal encoder, trained through self-supervised learning, generates robust 4D features for downstream tasks. The planning head utilizes flow matching and a novel masked ESDF loss to minimize collision risks for generating local trajectories, and the odometry head integrates multi-sensor inputs via a transformer encoder to predict the relative pose of the robot. Deployed on real in-house mobile robots, Astra achieves high end-to-end mission success rate across diverse indoor environments.

cs.RO↗

arXiv2025

PARF-Net: integrating pixel-wise adaptive receptive fields into hybrid Transformer-CNN network for medical image segmentation

Convolutional neural networks (CNNs) excel in local feature extraction while Transformers are superior in processing global semantic information. By leveraging the strengths of both, hybrid Transformer-CNN networks have become the major architectures in medical image segmentation tasks. However, existing hybrid methods still suffer deficient learning of local semantic features due to the fixed receptive fields of convolutions, and also fall short in effectively integrating local and long-range dependencies. To address these issues, we develop a new method PARF-Net to integrate convolutions of Pixel-wise Adaptive Receptive Fields (Conv-PARF) into hybrid Network for medical image segmentation. The Conv-PARF is introduced to cope with inter-pixel semantic differences and dynamically adjust convolutional receptive fields for each pixel, thus providing distinguishable features to disentangle the lesions with varying shapes and scales from the background. The features derived from the Conv-PARF layers are further processed using hybrid Transformer-CNN blocks under a lightweight manner, to effectively capture local and long-range dependencies, thus boosting the segmentation performance. By assessing PARF-Net on four widely used medical image datasets including MoNuSeg, GlaS, DSB2018 and multi-organ Synapse, we showcase the advantages of our method over the state-of-the-arts. For instance, PARF-Net achieves 84.27% mean Dice on the Synapse dataset, surpassing existing methods by a large margin.

cs.CV↗

arXiv2024

Safety-Critical Control with Offline-Online Neural Network Inference

This paper presents a safety-critical control framework for an ego agent moving among other agents. The approach infers the dynamics of the other agents, and incorporates the inferred quantities into the design of control barrier function (CBF)-based controllers for the ego agent. The inference method combines offline and online learning with radial basis function neural networks (RBFNNs). The RBFNNs are initially trained offline using collected datasets. To enhance the generalization of the RBFNNs, the weights are then updated online with new observations, without requiring persistent excitation conditions in order to enhance the applicability of the method. Additionally, we employ adaptive conformal prediction to quantify the estimation error of the RBFNNs for the other agents' dynamics, generating prediction sets to cover the true value with high probability. Finally, we formulate a CBF-based controller for the ego agent to guarantee safety with the desired confidence level by accounting for the prediction sets of other agents' dynamics in the sampled-data CBF conditions. Simulation results are provided to demonstrate the effectiveness of the proposed method.

eess.SY↗

arXiv2024

Stable Acceleration of a LHe-Free Nb3Sn demo SRF e-linac Based on Conduction Cooling

The design, construction, and commissioning of a conduction-cooled Nb3Sn demonstration superconducting radio frequency (SRF) electron accelerator at the Institute of Modern Physics of the Chinese Academy of Sciences (IMP, CAS) will be presented. In the context of engineering application planning for Nb3Sn thin-film SRF cavities within the CiADS project, a 650MHz 5-cell elliptical cavity was coated using the vapor diffusion method for electron beam acceleration. Through high-precision collaborative control of 10 GM cryocooler, slow cooldown of the cavity crossing 18K is achieved accompanied by obviously characteristic magnetic flux expulsion. The horizontal test results of the liquid helium-free (LHe-free) cryomodule show that the cavity can operate steadily at Epk=6.02MV/m in continuous wave (CW) mode, and at Epk=14.90MV/m in 40% duty cycle pulse mode. The beam acceleration experiment indicates that the maximum average current of the electron beam in the macropulse after acceleration exceeds 200mA, with a maximum energy gain of 4.6MeV. The results provide a principle validation for the engineering application of Nb3Sn thin-film SRF cavities, highlighting the promising industrial application prospects of a small-scale compact Nb3Sn SRF accelerator driven by commercial cryocoolers.

physics.acc-ph↗

arXiv2024

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety

The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs, many of these focus primarily on capabilities, usually overlooking potential alignment and safety issues. To address this gap, we introduce OpenEval, an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. For capability assessment, we include 12 benchmark datasets to evaluate Chinese LLMs from 4 sub-dimensions: NLP tasks, disciplinary knowledge, commonsense reasoning and mathematical reasoning. For alignment assessment, OpenEval contains 7 datasets that examines the bias, offensiveness and illegalness in the outputs yielded by Chinese LLMs. To evaluate safety, especially anticipated risks (e.g., power-seeking, self-awareness) of advanced LLMs, we include 6 datasets. In addition to these benchmarks, we have implemented a phased public evaluation and benchmark update strategy to ensure that OpenEval is in line with the development of Chinese LLMs or even able to provide cutting-edge benchmark datasets to guide the development of Chinese LLMs. In our first public evaluation, we have tested a range of Chinese LLMs, spanning from 7B to 72B parameters, including both open-source and proprietary models. Evaluation results indicate that while Chinese LLMs have shown impressive performance in certain tasks, more attention should be directed towards broader aspects such as commonsense reasoning, alignment, and safety.

cs.CL↗

arXiv2023

Secretary Problems with Random Number of Candidates: How Prior Distributional Information Helps

We study variants of the secretary problem, where $N$, the number of candidates, is a random variable, and the decision maker wants to maximize the probability of success -- picking the largest number among the $N$ candidates -- using only the relative ranks of the candidates revealed so far. We consider three forms of prior information about $\mathbf p$, the probability distribution of $N$. In the full information setting, we assume $\mathbf p$ to be fully known. In that case, we show that single-threshold type of strategies can achieve $1/e$-approximation to the maximum probability of success among all possible strategies. In the upper bound setting, we assume that $N\leq \overline{n}$ (or $\mathbb E[N]\leq \barμ$), where $\bar{n}$ (or $\barμ$) is known. In that case, we show that randomization over single-threshold type of strategies can achieve the optimal worst case probability of success of $\frac{1}{\log(\bar{n})}$ (or $\frac{1}{\log(\barμ)}$) asymptotically. Surprisingly, there is a single-threshold strategy (depending on $\overline{n}$) that can succeed with probability $2/e^2$ for all but an exponentially small fraction of distributions supported on $[\bar{n}]$. In the sampling setting, we assume that we have access to $m$ samples $N^{(1)},\ldots,N^{(m)}\sim_{iid} \mathbf p$. In that case, we show that if $N\leq T$ with probability at least $1-O(ε)$ for some $T\in \mathbb N$, $m\gtrsim \frac{1}{ε^2}\max(\log(\frac{1}ε),ε\log(\frac{\log(T)}ε))$ is enough to learn a strategy that is at least $ε$-suboptimal, and we provide a lower bound of $Ω(\frac{1}{ε^2})$, showing that the sampling algorithm is optimal when $ε=O(\frac{1}{\log\log(T)})$.

cs.DS↗

arXiv2023

Memory-Constrained Algorithms for Convex Optimization via Recursive Cutting-Planes

We propose a family of recursive cutting-plane algorithms to solve feasibility problems with constrained memory, which can also be used for first-order convex optimization. Precisely, in order to find a point within a ball of radius $ε$ with a separation oracle in dimension $d$ -- or to minimize $1$-Lipschitz convex functions to accuracy $ε$ over the unit ball -- our algorithms use $\mathcal O(\frac{d^2}{p}\ln \frac{1}ε)$ bits of memory, and make $\mathcal O((C\frac{d}{p}\ln \frac{1}ε)^p)$ oracle calls, for some universal constant $C \geq 1$. The family is parametrized by $p\in[d]$ and provides an oracle-complexity/memory trade-off in the sub-polynomial regime $\ln\frac{1}ε\gg\ln d$. While several works gave lower-bound trade-offs (impossibility results) -- we explicit here their dependence with $\ln\frac{1}ε$, showing that these also hold in any sub-polynomial regime -- to the best of our knowledge this is the first class of algorithms that provides a positive trade-off between gradient descent and cutting-plane methods in any regime with $ε\leq 1/\sqrt d$. The algorithms divide the $d$ variables into $p$ blocks and optimize over blocks sequentially, with approximate separation vectors constructed using a variant of Vaidya's method. In the regime $ε\leq d^{-Ω(d)}$, our algorithm with $p=d$ achieves the information-theoretic optimal memory usage and improves the oracle-complexity of gradient descent.

math.OC↗

arXiv2023

Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal

We give query complexity lower bounds for convex optimization and the related feasibility problem. We show that quadratic memory is necessary to achieve the optimal oracle complexity for first-order convex optimization. In particular, this shows that center-of-mass cutting-planes algorithms in dimension $d$ which use $\tilde O(d^2)$ memory and $\tilde O(d)$ queries are Pareto-optimal for both convex optimization and the feasibility problem, up to logarithmic factors. Precisely, we prove that to minimize $1$-Lipschitz convex functions over the unit ball to $1/d^4$ accuracy, any deterministic first-order algorithms using at most $d^{2-δ}$ bits of memory must make $\tildeΩ(d^{1+δ/3})$ queries, for any $δ\in[0,1]$. For the feasibility problem, in which an algorithm only has access to a separation oracle, we show a stronger trade-off: for at most $d^{2-δ}$ memory, the number of queries required is $\tildeΩ(d^{1+δ})$. This resolves a COLT 2019 open problem of Woodworth and Srebro.

cs.LG↗

arXiv2022

A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation

Chinese dialects are different variations of Chinese and can be considered as different languages in the same language family with Mandarin. Though they all use Chinese characters, the pronunciations, grammar and idioms can vary significantly, and even local speakers may find it hard to input correct written forms of dialect. Besides, using Mandarin text as text-to-speech inputs would generate speech with poor naturalness. In this paper, we propose a novel Chinese dialect TTS frontend with a translation module, which converts Mandarin text into dialectic expressions to improve the intelligibility and naturalness of synthesized speech. A non-autoregressive neural machine translation model with various tricks is proposed for the translation task. It is the first known work to incorporate translation with TTS frontend. Experiments on Cantonese show the proposed model improves 2.56 BLEU and TTS improves 0.27 MOS with Mandarin inputs.

cs.CL↗

arXiv2022

Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features

Speech-to-speech translation directly translates a speech utterance to another between different languages, and has great potential in tasks such as simultaneous interpretation. State-of-art models usually contains an auxiliary module for phoneme sequences prediction, and this requires textual annotation of the training dataset. We propose a direct speech-to-speech translation model which can be trained without any textual annotation or content information. Instead of introducing an auxiliary phoneme prediction task in the model, we propose to use bottleneck features as intermediate training objectives for our model to ensure the translation performance of the system. Experiments on Mandarin-Cantonese speech translation demonstrate the feasibility of the proposed approach and the performance can match a cascaded system with respect of translation and synthesis qualities.

cs.CL↗

arXiv2022

Sparse and Safe Frequency Regulation for Inverter Intensive Microgrids

This paper developed a novel control approach for the sparse and safe frequency regulation for inverter intensive microgrids (MGs). In the scenario, the inverters and external grids are expected to reach a synchronized desired frequency under regulations. To this end, the active power set-point acting as a control from a high-level controller is designed while considering two important performance metrics "sparsity" and "safety", which are to reduce the information exchange between controllers and ensure that the frequency keeps in safety regions during the whole operation process. Our proposed control design framework allows the sparse linear feedback controller (SLFC) to be unified with a family of conditions for safe control using control barrier functions. A quadratic programming (QP) problem is then constructed, and the real-time control policy is obtained by solving the QP problem. Importantly, we also found that the real-time control for each inverter depends on the cross-layer communication network topology which is the union of the one between controllers from SLFC and the one determined by the power flow network. Furthermore, our approach has been validated through extensive numerical simulations.

eess.SY↗

arXiv2021

Principal Component Pursuit for Pattern Identification in Environmental Mixtures

Environmental health researchers often aim to identify sources/behaviors that give rise to potentially harmful exposures. We adapted principal component pursuit (PCP)-a robust technique for dimensionality reduction in computer vision and signal processing-to identify patterns in environmental mixtures. PCP decomposes the exposure mixture into a low-rank matrix containing consistent exposure patterns across pollutants and a sparse matrix isolating unique exposure events. We adapted PCP to accommodate non-negative and missing data, and values below a given limit of detection (LOD). We simulated data to represent environmental mixtures of two sizes with increasing proportions <LOD and three noise structures. We compared PCP-LOD to principal component analysis (PCA) to evaluate performance. We next applied PCP-LOD to a mixture of 21 persistent organic pollutants (POPs) measured in 1,000 U.S. adults from the 2001-2002 National Health and Nutrition Examination Survey. We applied singular value decomposition to the estimated low-rank matrix to characterize the patterns. PCP-LOD recovered the true number of patterns through cross-validation for all simulations; based on an a priori specified criterion, PCA recovered the true number of patterns in 32% of simulations. PCP-LOD achieved lower relative predictive error than PCA for all simulated datasets with up to 50% of the data <LOD. When 75% of values were <LOD, PCP-LOD outperformed PCA only when noise was low. In the POP mixture, PCP-LOD identified a rank-three underlying structure and separated 6% of values as unique events. One pattern represented comprehensive exposure to all POPs. The other patterns grouped chemicals based on known structure and toxicity. PCP-LOD serves as a useful tool to express multi-dimensional exposures as consistent patterns that, if found to be related to adverse health, are amenable to targeted interventions.

stat.AP↗

arXiv2021

Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery

We propose a new framework -- Square Root Principal Component Pursuit -- for low-rank matrix recovery from observations corrupted with noise and outliers. Inspired by the square root Lasso, this new formulation does not require prior knowledge of the noise level. We show that a single, universal choice of the regularization parameter suffices to achieve reconstruction error proportional to the (a priori unknown) noise level. In comparison, previous formulations such as stable PCP rely on noise-dependent parameters to achieve similar performance, and are therefore challenging to deploy in applications where the noise level is unknown. We validate the effectiveness of our new method through experiments on simulated and real datasets. Our simulations corroborate the claim that a universal choice of the regularization parameter yields near optimal performance across a range of noise levels, indicating that the proposed method outperforms the (somewhat loose) bound proved here.

cs.LG↗

arXiv2021

Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech

In expressive speech synthesis, there are high requirements for emotion interpretation. However, it is time-consuming to acquire emotional audio corpus for arbitrary speakers due to their deduction ability. In response to this problem, this paper proposes a cross-speaker emotion transfer method that can realize the transfer of emotions from source speaker to target speaker. A set of emotion tokens is firstly defined to represent various categories of emotions. They are trained to be highly correlated with corresponding emotions for controllable synthesis by cross-entropy loss and semi-supervised training strategy. Meanwhile, to eliminate the down-gradation to the timbre similarity from cross-speaker emotion transfer, speaker condition layer normalization is implemented to model speaker characteristics. Experimental results show that the proposed method outperforms the multi-reference based baseline in terms of timbre similarity, stability and emotion perceive evaluations.

eess.AS↗