arXiv subjects

Qi Wang

Publications and source records attributed to Qi Wang.

At least 163 records · Page 9Linked to original sources

arXiv2026

Fed-PISA: Federated Voice Cloning via Personalized Identity-Style Adaptation

Voice cloning for Text-to-Speech (TTS) aims to generate expressive and personalized speech from text using limited data from a target speaker. Federated Learning (FL) offers a collaborative and privacy-preserving framework for this task, but existing approaches suffer from high communication costs and tend to suppress stylistic heterogeneity, resulting in insufficient personalization. To address these issues, we propose Fed-PISA, which stands for Federated Personalized Identity-Style Adaptation. To minimize communication costs, Fed-PISA introduces a disentangled Low-Rank Adaptation (LoRA) mechanism: the speaker's timbre is retained locally through a private ID-LoRA, while only a lightweight style-LoRA is transmitted to the server, thereby minimizing parameter exchange. To harness heterogeneity, our aggregation method, inspired by collaborative filtering, is introduced to create custom models for each client by learning from stylistically similar peers. Experiments show that Fed-PISA improves style expressivity, naturalness, and speaker similarity, outperforming standard federated baselines with minimal communication costs.

cs.SD↗

arXiv2026

SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild

High-quality AI-powered video dubbing demands precise audio-lip synchronization, high-fidelity visual generation, and faithful preservation of identity and background. Most existing methods rely on a mask-based training strategy, where the mouth region is masked in talking-head videos, and the model learns to synthesize lip movements from corrupted inputs and target audios. While this facilitates lip-sync accuracy, it disrupts spatiotemporal context, impairing performance on dynamic facial motions and causing instability in facial structure and background consistency. To overcome this limitation, we propose SyncAnyone, a novel two-stage learning framework that achieves accurate motion modeling and high visual fidelity simultaneously. In Stage 1, we train a diffusion-based video transformer for masked mouth inpainting, leveraging its strong spatiotemporal modeling to generate accurate, audio-driven lip movements. However, due to input corruption, minor artifacts may arise in the surrounding facial regions and the background. In Stage 2, we develop a mask-free tuning pipeline to address mask-induced artifacts. Specifically, on the basis of the Stage 1 model, we develop a data generation pipeline that creates pseudo-paired training samples by synthesizing lip-synced videos from the source video and random sampled audio. We further tune the stage 2 model on this synthetic data, achieving precise lip editing and better background consistency. Extensive experiments show that our method achieves state-of-the-art results in visual quality, temporal coherence, and identity preservation under in-the wild lip-syncing scenarios.

cs.CV↗

arXiv2026

DiMo: Discrete Diffusion Modeling for Motion Generation and Understanding

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike GPT-style autoregressive approaches that tokenize motion and decode sequentially, DiMo performs iterative masked token refinement, unifying Text-to-Motion (T2M), Motion-to-Text (M2T), and text-free Motion-to-Motion (M2M) within a single model. This decoding paradigm naturally enables a quality-latency trade-off at inference via the number of refinement steps. We further improve motion token fidelity with residual vector quantization (RVQ) and enhance alignment and controllability with Group Relative Policy Optimization (GRPO). Experiments on HumanML3D and KIT-ML show strong motion quality and competitive bidirectional understanding under a unified framework. In addition, we demonstrate model ability in text-free motion completion, text-guided motion prediction and motion caption correction without architectural change. Additional qualitative results are available on our project page: https://animotionlab.github.io/DiMo/.

cs.CV↗

arXiv2026

NECromancer: Breathing Life into Skeletons via BVH Animation

Motion tokenization is a key component of generalizable motion models, yet most existing approaches are restricted to species-specific skeletons, limiting their applicability across diverse morphologies. We propose NECromancer (NEC), a universal motion tokenizer that operates directly on arbitrary BVH skeletons. NEC consists of three components: (1) an Ontology-aware Skeletal Graph Encoder (OwO) that encodes structural priors from BVH files, including joint semantics, rest-pose offsets, and skeletal topology, into skeletal embeddings; (2) a Topology-Agnostic Tokenizer (TAT) that compresses motion sequences into a universal, topology-invariant discrete representation; and (3) the Unified BVH Universe (UvU), a large-scale dataset aggregating BVH motions across heterogeneous skeletons. Experiments show that NEC achieves high-fidelity reconstruction under substantial compression and effectively disentangles motion from skeletal structure. The resulting token space supports cross-species motion transfer, composition, denoising, generation with token-based models, and text-motion retrieval, establishing a unified framework for motion analysis and synthesis across diverse morphologies. Demo page: https://animotionlab.github.io/NECromancer/

cs.CV↗

arXiv2026

Nanoscale spin-wave frequency-selective limiter for 5G technology

Power limiters are essential devices in modern radio frequency (RF) communications systems to protect highly sensitive input channels from large incoming signals. Nowadays-used semiconductor limiters suffer from high electronic noise and switching delays when approaching the GHz range, which is crucial for the modern generation of 5G communication technologies aiming to operate at the EU 5G high band (24.25-27.5 GHz). The proposed solution is to use ferrite-based Frequency Selective Limiters (FSLs), which maintain their efficiency at high GHz frequencies, although they have only been studied at the macroscale so far. In this study, we demonstrate a proof of concept of nanoscale FSLs. The devices are based on spin-wave transmission affected by four-magnon scattering phenomena in a 97-nm-thin Yttrium Iron Garnet (YIG) film. Spin waves were excited and detected using coplanar waveguide (CPW) transducers of the smallest feature size of 250 nm. The FSLs are tested in the frequency range up to 25 GHz, and the key parameters are extracted (power threshold, power limiting level, insertion losses, bandwidth) for different spin-wave modes and transducer lengths. An analytical theory has been formulated to describe the fundamental physical processes, and a numerical model has been developed to quantitatively describe the insertion losses and power characteristics of the FSLs. Additionally, the perspective of the spin-wave devices is discussed, including the possibility of simultaneously integrating three devices into one: a frequency-selective limiter, an RF filter, and a delay line, allowing for more efficient use of space and energy.

cond-mat.other↗

arXiv2026

Beyond Retraining: Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision-Language Models

Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test image's class label is drawn from a predefined label set and lack a reliable mechanism to reject samples from emerging unknown classes when only unlabeled data are available. To address this gap, open-set domain adaptation methods retrain models to push potential unknowns away from known clusters. Yet, some unknown samples remain stably anchored to specific known classes in the VLM feature space due to semantic relevance, which is termed as Semantic Affinity Anchoring (SAA). Forcibly repelling these samples unavoidably distorts the native geometry of VLMs and degrades performance. Meanwhile, existing score-based unknown detectors use simplistic thresholds and suffer from threshold sensitivity, resulting in sub-optimal performance. To address aforementioned issues, we propose VLM-OpenXpert, which comprises two training-free, plug-and-play inference modules. SUFF performs SVD on high-confidence unknowns to extract a low-rank "unknown subspace". Each sample's projection onto this subspace is weighted and softly removed from its feature, suppressing unknown components while preserving semantics. BGAT corrects score skewness via a Box-Cox transform, then fits a bimodal Gaussian mixture to adaptively estimate the optimal threshold balancing known-class recognition and unknown-class rejection. Experiments on 9 benchmarks and three backbones (CLIP, SigLIP, ALIGN) under source-free OSDA settings show that our training-free pipeline matches or outperforms retraining-heavy state-of-the-art methods, establishing a powerful lightweight inference calibration paradigm for open-set VLM deployment.

cs.CV↗

arXiv2026

Stimulated Magnonic Frequency Combs

Magnonic frequency combs, characterized by a series of discrete frequency lines, have emerged as a promising frontier in magnon spintronics, with potential applications in advanced information processing and sensing technologies. Although the three-magnon scattering process is widely recognized as a fundamental mechanism for generating these combs, its experimental realization has remained challenging due to the high threshold power and strict conservation of momentum and energy. In this work, we propose a novel mechanism for the stimulated generation of magnonic frequency combs that overcomes these limitations. Our approach offers precise and efficient control over key comb properties, including spacing between spectral lines and the number of lines, marking a significant advancement in the field. We substantiate this mechanism through a robust combination of theoretical modeling, micromagnetic simulations, and experimental validation. This study not only demonstrates the feasibility of our method but also opens new pathways for integrating magnonic frequency combs into practical spintronic devices.

cond-mat.mes-hall↗

arXiv2026

Text-Pass Filter: An Efficient Scene Text Detector

To pursue an efficient text assembling process, existing methods detect texts via the shrink-mask expansion strategy. However, the shrinking operation loses the visual features of text margins and confuses the foreground and background difference, which brings intrinsic limitations to recognize text features. We follow this issue and design Text-Pass Filter (TPF) for arbitrary-shaped text detection. It segments the whole text directly, which avoids the intrinsic limitations. It is noteworthy that different from previous whole text region-based methods, TPF can separate adhesive texts naturally without complex decoding or post-processing processes, which makes it possible for real-time text detection. Concretely, we find that the band-pass filter allows through components in a specified band of frequencies, called its passband but blocks components with frequencies above or below this band. It provides a natural idea for extracting whole texts separately. By simulating the band-pass filter, TPF constructs a unique feature-filter pair for each text. In the inference stage, every filter extracts the corresponding matched text by passing its pass-feature and blocking other features. Meanwhile, considering the large aspect ratio problem of ribbon-like texts makes it hard to recognize texts wholly, a Reinforcement Ensemble Unit (REU) is designed to enhance the feature consistency of the same text and to enlarge the filter's recognition field to help recognize whole texts. Furthermore, a Foreground Prior Unit (FPU) is introduced to encourage TPF to discriminate the difference between the foreground and background, which improves the feature-filter pair quality. Experiments demonstrate the effectiveness of REU and FPU while showing the TPF's superiority.

cs.CV↗

arXiv2026

Pressure-induced superconductivity in topological insulator Ge2Bi2Te5 and the evolution with Mn doping

Introducing superconductivity (SC) or magnetism into topological insulators (TIs) can give rise to novel quantum states and exotic physical phenomena. Here, we report a high-pressure transport study on the TI Ge2Bi2Te5 and its Mn-doped counterparts. The application of pressure induces a SC in Ge2Bi2Te5, which shows a dome-shape phase diagram with the maximum Tc of 7.6 K at 23 GPa. Doping Mn into Ge2Bi2Te5 introduces an antiferromagnetic order at ambient pressure and strongly weakens the pressure-induced SC, demonstrating that magnetism and SC compete in this material system. Present study provides a new platform for investigating the interplay among band topology, magnetism, and SC.

cond-mat.supr-con↗

arXiv2026

Unveiling pressurized bulk superconductivity in a trilayer nickelate Pr4Ni3O10 single crystal

The recent discovery of superconductivity in pressurized Ruddlesden-Popper (RP) nickelates has provided new perspectives on the mechanism of high-temperature superconductivity. Up to now, most experiments concentrated on the lanthanum-related RP phase, so the discovery of new superconducting RP nickelates is highly desirable to reveal their generality. Here we report that high-quality Pr4Ni3O10 single crystal is grown with an optical floating zone furnace under high oxygen pressure. High-pressure transport measurements show that the superconducting state arises above 10 GPa, and the maximum Tc reaches 39 K without saturation, significantly exceeding the value of 25-30 K of La4Ni3O10. Ultrasensitive d.c. magnetic susceptibility measurements under high pressure indicate bulk superconductivity with appreciable superconducting volume fractions. By performing in situ high-pressure synchrotron X-ray diffraction measurements at 16 K, a structural transition is found from monoclinic to tetragonal. Unlike La4Ni3O10, the electronic structure of the high-pressure phase of Pr4Ni3O10 from density functional theory exhibits a dramatic metallization of the sigma-bonding band consisting of three dz2 orbitals and van Hove singularity of coupled bands of dx2-y2 orbitals near the Fermi level, similar to the bilayer nickelate La3Ni2O7. These findings reveal some generic features of both crystal and electronic structures for high-temperature superconductivity in nickelates and multi-layer cuprates.

cond-mat.supr-con↗

arXiv2026

Spin-density-wave transition in monolayer-trilayer La3Ni2O7 single crystals

The recent discovery of high-temperature superconductivity in pressurized Ruddlesden-Popper nickelates stimulated intense research into their correlated electron physics. Establishing the diversity of ground states across different Ruddlesden-Popper phases is crucial for elucidating the superconducting mechanisms in these nickelates. Motivated by the recent report of superconductivity in hybrid 1212-type La5Ni3O11, we synthesized and investigated the long-range-ordered hybrid 1313-type La3Ni2O7. In contrast to its bilayer counterpart, the 1313-type La3Ni2O7 exhibits characteristic semiconducting behavior at ambient pressure, displaying a distinct anomaly at 170 K. This behavior is consistently evidenced by measurements of both magnetic susceptibility and specific heat. Nuclear magnetic resonance spectroscopy unambiguously indicates a spin-density-wave transition occurring at 170 K. High-pressure electrical transport measurements demonstrate the induction of metallization under pressure, yet reveal no discernible traces of superconductivity up to 65 GPa. Our findings establish hybrid 1313-type La3Ni2O7 as a new member of the Ruddlesden-Popper nickelate family exhibiting a distinct spin-density-wave transition, and offers a new platform for investigating the interplay among crystal structure, electronic orders, and superconductivity in hybrid nickelates.

cond-mat.supr-con↗

arXiv2026

Weakly anisotropic superconductivity of Pr4Ni3O10 single crystals

Since the discovery of high-temperature superconductivity, studying the upper critical field and its anisotropy has been crucial for understanding superconducting mechanism and guiding applications. Here we perform in situ high-pressure angular-dependent electrical transport measurements on Pr4Ni3O10 single crystals using a custom diamond anvil cell (DAC) rotator and confirming its anisotropic superconductivity. The anisotropy parameter is approximately 1.6, decreasing with increasing temperature and approaches 1 near Tc. Comparing effective mass anisotropy and inter-block distance in cuprates and iron-based superconductors (FeSCs) reveals that Pr4Ni3O10 single crystals superconductors are consistent with a two-band model, where intralayer quantum confinement within the unit cell induces interlayer coherence, thereby leading to three-dimensional (3D) superconductivity. This study not only establishes the existence of anisotropic superconductivity in bulk Ruddlesden-Popper nickelates, but also provide critical insight into the role of dimensionality in high-temperature superconductivity.

cond-mat.supr-con↗

arXiv2026

Coexistence of stripe order and superconductivity in NaAlSi

Here, we report a scanning tunneling microscopy study on an s-wave superconductor NaAlSi, revealing the coexistence of stripe order and superconductivity. This stripe order manifests as a unidirectional spatial charge modulation with a commensurate period of four times the lattice constant. This modulation undergoes a phase shift in the differential conductance maps under opposite bias voltages, while its period remains approximately constant over an energy range of $\pm$50 meV. These features suggest that this stripe is likely a static charge order. Furthermore, we find that the stripe order imposes a periodic modulation on the intensity of the superconducting coherence peaks. This work provides new perspectives on the intricate interplay between stripe order and s-wave superconductivity.

cond-mat.supr-con↗

arXiv2026

Projected Stochastic Momentum Methods for Nonlinear Equality-Constrained Optimization for Machine Learning

Two algorithms are proposed, analyzed, and tested for solving continuous optimization problems with nonlinear equality constraints. Each is an extension of a stochastic momentum-based method from the unconstrained setting to the setting of a stochastic Newton-SQP-type algorithm for solving equality-constrained problems. One is an extension of the heavy-ball method and the other is an extension of the Adam optimization method. Convergence guarantees for the algorithms for the constrained setting are provided that are on par with state-of-the-art guarantees for their unconstrained counterparts. A critical feature of each extension is that the momentum terms are implemented with projected gradient estimates, rather than with the gradient estimates themselves. The significant practical effect of this choice is seen in an extensive set of numerical experiments on solving informed supervised machine learning problems. These experiments also show benefits of employing a constrained approach to supervised machine learning rather than a typical regularization-based approach.

math.OC↗

arXiv2026

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?

Recent advances have witnessed the effectiveness of reinforcement learning (RL) finetuning in enhancing the reasoning capabilities of large language models (LLMs). The optimization process often requires numerous iterations to achieve satisfactory performance, resulting in high computational costs due to the need for frequent prompt evaluations under intensive LLM interactions and repeated policy updates. Appropriate online prompt selection methods reduce iteration steps by prioritizing informative prompts during training, while the pipeline's reliance on exhaustive prompt evaluation and subset selection for optimization still incurs substantial computational overhead due to frequent LLM inference calls. Distinguished from these direct evaluate-then-select schemes, this work investigates iterative approximate evaluation for arbitrary prompts and introduces Model Predictive Prompt Selection (MoPPS), a Bayesian risk-predictive framework that online estimates prompt difficulty without requiring costly LLM interactions. Technically, MoPPS models each prompt's success rate as a latent variable, performs streaming Bayesian inference, and employs posterior sampling in a constructed multi-armed bandit machine, enabling sample efficient and adaptive prompt selection. Extensive experiments across mathematics, planning, and vision-based geometry tasks show that MoPPS reliably predicts prompt difficulty and accelerates training with significantly reduced LLM rollouts. Our code is available at https://github.com/thu-rllab/MoPPS.

cs.AI↗

arXiv2026

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing

The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retrieval synthesis stage--where agents must digest massive amounts of context and consolidate fragmented evidence into coherent, long-form reports--remains under-evaluated due to the subjectivity of open-ended writing. To bridge this gap, we introduce DeepSynth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities. We leverage high-quality survey papers as gold standards, reverse-engineering research requests and constructing "Oracle Contexts" from their bibliographies to isolate synthesis from retrieval noise. We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization), transforming subjective judgment into verifiable metrics. Experiments across 96 tasks reveal that synthesizing information from hundreds of references remains a significant challenge. Our results demonstrate that agentic plan-and-write workflows significantly outperform single-turn generation, effectively reducing hallucinations and improving adherence to complex structural constraints.

cs.CL↗

arXiv2026

Integrated magnonic chip using cascaded logic

The transistor transformed not only electronics but everyday life, and the integrated circuit - now simply the "chip" - made computation scalable and ubiquitous. Magnonics has long promised a parallel path to low-energy information processing by using spin waves instead of charge. Progress, however, has been limited by two fundamental obstacles: intrinsic attenuation of spin waves and the requirement for precisely normalised output intensity and input phase to ensure reliable logic operation - conditions that are difficult to maintain in large-scale circuits owing to inevitable imperfections. Here, we report an integrated magnonic circuit that overcomes both limitations through engineered nonlinearity in nanoscale yttrium iron garnet waveguides. Nonlinear self-adjustment of the spin wave phase renders logic operation insensitive to the relative phases of the inputs, while a deeply nonlinear, threshold-activated self-normalised excitation restores and standardises the output intensity. Using space-resolved micro-focused Brillouin light scattering, we demonstrate reconfigurable AND, OR and three-input majority gates and realise deterministic cascading across sequential stages, establishing a scalable on-chip logic primitive. The architecture operates with gigahertz frequencies, supports dynamic threshold control for functional reconfiguration, and is compatible with scalable integration, making it attractive for adaptive and neuromorphic computing. By resolving phase-independent operation and signal restoration at the level of device physics, this work advances magnonics from isolated proof-of-concept devices towards integrated magnonic chips that can complement advanced CMOS in energy-constrained computing tasks.

cond-mat.mtrl-sci↗

arXiv2026

AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs

Visual abductive reasoning (VAR) is a challenging task that requires AI systems to infer the most likely explanation for incomplete visual observations. While recent MLLMs develop strong general-purpose multimodal reasoning capabilities, they fall short in abductive inference, as compared to human beings. To bridge this gap, we draw inspiration from the interplay between verbal and pictorial abduction in human cognition, and propose to strengthen abduction of MLLMs by mimicking such dual-mode behavior. Concretely, we introduce AbductiveMLLM comprising of two synergistic components: REASONER and IMAGINER. The REASONER operates in the verbal domain. It first explores a broad space of possible explanations using a blind LLM and then prunes visually incongruent hypotheses based on cross-modal causal alignment. The remaining hypotheses are introduced into the MLLM as targeted priors, steering its reasoning toward causally coherent explanations. The IMAGINER, on the other hand, further guides MLLMs by emulating human-like pictorial thinking. It conditions a text-to-image diffusion model on both the input video and the REASONER's output embeddings to "imagine" plausible visual scenes that correspond to verbal explanation, thereby enriching MLLMs' contextual grounding. The two components are trained jointly in an end-to-end manner. Experiments on standard VAR benchmarks show that AbductiveMLLM achieves state-of-the-art performance, consistently outperforming traditional solutions and advanced MLLMs.

cs.CV↗