arXiv subjects

Xihua Wang

Publications and source records attributed to Xihua Wang.

At least 19 recordsLinked to original sources

arXiv2026

FATE: Frame-Level Audio-Visual Temporal Embedding

When a dog opens its mouth and barks, humans naturally recognize what the sound is and when it occurs. Building audio-visual models with this same ability requires representations that capture both semantic and temporal alignment. Current approaches fall short on one side or the other: embedding models match semantic but lose temporal information; synchronization models capture temporal offsets but lack semantic understanding. To bridge this gap, we propose FATE, Frame-level Audio-visual Temporal Embedding. Unlike prior embedding models that pool each modality into a single embedding and discard temporal information, FATE retains frame-level sequences, aligns them on the physical timeline, and computes similarity over strictly aligned frame pairs. Unlike synchronization models that output only an offset prediction, FATE encodes synchronization in a reusable embedding space, trained with a joint objective combining cross-video semantic and within-video temporal contrastive learning to capture both what sounds and when it occurs. Across three tasks, FATE surpasses the strongest baseline on temporal and semantic retrieval by a large margin, matches fully supervised methods on event localization in a zero-shot setting, and achieves the best correlation with human judgments as a generation evaluation metric. The source code can be found at \texttt{https://github.com/guankaisi/FATE}.

cs.MM↗

arXiv2026

Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction

This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text conditions, meanwhile ensuring both modalities are aligned with text. Despite progress in joint audio-video training, two critical challenges still remain unaddressed: (1) a single, shared text caption where the text for video is equal to the text for audio often creates modal interference, confusing the pretrained backbones, and (2) the optimal mechanism for cross-modal feature interaction remains unclear. To address these challenges, we first propose the Hierarchical Visual-Grounded Captioning (HVGC) framework that generates pairs of disentangled captions, a video caption, and an audio caption, eliminating interference at the conditioning stage. Based on HVGC, we further introduce BridgeDiT, a novel dual-tower diffusion transformer, which employs a Dual CrossAttention (DCA) mechanism that acts as a robust ``bridge" to enable a symmetric, bidirectional exchange of information, achieving both semantic and temporal synchronization. Extensive experiments on three benchmark datasets, supported by human evaluations, demonstrate that our method achieves state-of-the-art results on most metrics. Comprehensive ablation studies further validate the effectiveness of our contributions, offering key insights for the future T2SV task. All the codes and checkpoints will be publicly released.

cs.CV↗

arXiv2026

Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts

Audio generation has made significant progress, yet synthesizing unified audio where speech and sounds are naturally composited remains a challenge. Current methods either rely on disjoint pipelines, which fail to capture fine-grained interactions, or require structured inputs and external text rewriting, which limits the flexibility of free-form text prompts. In this paper, we introduce a new task: Free-Form-Text-Prompt-to-Unified-Audio generation, which aims to directly synthesize unified audio containing speech, sound, and their composites from unconstrained natural language. To address this task, we propose PlanAudio, a unified, autoregressive LLM-based framework. First, it simplifies the model architecture by leveraging intrinsic LLM reasoning capability instead of traditional text encoders. Second, it introduces a semantic latent chain-of-thought mechanism, an implicit planning mechanism that bridges high-level semantic understanding and low-level acoustic synthesis. Furthermore, we create PlanAudio-Bench, a specialized benchmark for evaluating composite audio scenarios. We perform evaluations in the scenarios of speech, sound, and their composites. The results demonstrate that PlanAudio generally outperforms the existing pipeline and unified baselines, while staying competitive with models designed for a single scenario. Our analysis further reveals the superiority of semantic latent CoT over other CoT mechanisms and highlights the importance of continuous multi-scenario training curricula.

cs.SD↗

arXiv2026

SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning

Recent advancements in video-audio joint generation have achieved remarkable success in semantic correspondence. However, achieving precise temporal synchronization, which requires fine-grained alignment between audio events and their visual triggers, remains a challenging problem. The post-training method for joint generation is largely dominated by Supervised Fine-Tuning, but the commonly used Mean Squared Error loss provides insufficient penalties for subtle temporal misalignments. Direct Preference Optimization offers an alternative by introducing explicit misaligned counterparts to better improve temporal sensitivity. In this paper we propose a post-training framework SyncDPO, leveraging DPO to improve the temporal sensitivity of V-A joint generation. Conventional DPO pipelines typically depend on costly sampling-and-ranking procedures to construct preference pairs, resulting in substantial computational cost. To improve efficiency, we introduce a suite of on-the-fly rule-based negative construction strategies that distort temporal structures without incurring additional annotation or sampling. We demonstrate that the temporal alignment capability can be effectively reinforced by providing explicit negative supervision through temporally distorted V-A pairs. Accordingly, we implement a curriculum learning strategy that progressively increases the difficulty of negative samples, transitioning from coarse misalignment to subtle inconsistencies. Extensive objective and subjective experiments across four diverse benchmarks, ranging from ambient sound videos to human speech videos, demonstrate that SyncDPO significantly outperforms other methods in improving model's temporal alignment capability. It also demonstrates superior generalization on out-of-distribution benchmark by capturing intrinsic motion-sound dynamics. Demo and code is available in https://syncdpo.github.io/syncdpo/.

cs.CV↗

arXiv2026

Qwen-Image-2.0 Technical Report

We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.

cs.CV↗

arXiv2026

VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning

Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTTS), has traditionally been treated as distinct tasks, leaving the potential for a unified generative framework largely underexplored. In this paper, we bridge this gap with VSSFlow, a unified flow-matching framework that seamlessly solve both problems. To effectively handle multiple input signals within a Diffusion Transformer (DiT) architecture, we propose a disentangled condition aggregation mechanism leveraging distinct intrinsic properties of attention layers: cross-attention for semantic conditions, and self-attention for temporally-intensive conditions. Besides, contrary to the prevailing belief that joint training for the two tasks leads to performance degradation, we demonstrate that VSSFlow maintains superior performance during end-to-end joint learning process. Furthermore, we use a straightforward feature-level data synthesis method, demonstrating that our framework provides a robust foundation that easily adapts to joint sound and speech generation using synthetic data. Extensive experiments on V2S, VisualTTS and joint generation benchmarks show that VSSFlow effectively unifies these tasks and surpasses state-of-the-art domain-specific baselines, underscoring the critical potential of unified generative models. Project page: https://vasflow1.github.io/vasflow/

eess.AS↗

arXiv2026

Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents

The Rust programming language presents a steep learning curve and significant coding challenges, making the automation of issue resolution essential for its broader adoption. Recently, LLM-powered code agents have shown remarkable success in resolving complex software engineering tasks, yet their application to Rust has been limited by the absence of a large-scale, repository-level benchmark. To bridge this gap, we introduce Rust-SWE-bench, a benchmark comprising 500 real-world, repository-level software engineering tasks from 34 diverse and popular Rust repositories. We then perform a comprehensive study on Rust-SWE-bench with four representative agents and four state-of-the-art LLMs to establish a foundational understanding of their capabilities and limitations in the Rust ecosystem. Our extensive study reveals that while ReAct-style agents are promising, i.e., resolving up to 21.2% of issues, they are limited by two primary challenges: comprehending repository-wide code structure and complying with Rust's strict type and trait semantics. We also find that issue reproduction is rather critical for task resolution. Inspired by these findings, we propose RUSTFORGER, a novel agentic approach that integrates an automated test environment setup with a Rust metaprogramming-driven dynamic tracing strategy to facilitate reliable issue reproduction and dynamic analysis. The evaluation shows that RUSTFORGER using Claude-Sonnet-3.7 significantly outperforms all baselines, resolving 28.6% of tasks on Rust-SWE-bench, i.e., a 34.9% improvement over the strongest baseline, and, in aggregate, uniquely solves 46 tasks that no other agent could solve across all adopted advanced LLMs.

cs.SE↗

arXiv2025

VSpeechLM: A Visual Speech Language Model for Visual Text-to-Speech Task

The task of Visual Text-to-Speech (VisualTTS), also known as video dubbing, aims to generate speech synchronized with the lip movements in an input video, in additional to being consistent with the content of input text and cloning the timbre of a reference speech. Existing VisualTTS models typically adopt lightweight architectures and design specialized modules to achieve the above goals respectively, yet the speech quality is not satisfied due to the model capacity and the limited data in VisualTTS. Recently, speech large language models (SpeechLLM) show the robust ability to generate high-quality speech. But few work has been done to well leverage temporal cues from video input in generating lip-synchronized speech. To generate both high-quality and lip-synchronized speech in VisualTTS tasks, we propose a novel Visual Speech Language Model called VSpeechLM based upon a SpeechLLM. To capture the synchronization relationship between text and video, we propose a text-video aligner. It first learns fine-grained alignment between phonemes and lip movements, and then outputs an expanded phoneme sequence containing lip-synchronization cues. Next, our proposed SpeechLLM based decoders take the expanded phoneme sequence as input and learns to generate lip-synchronized speech. Extensive experiments demonstrate that our VSpeechLM significantly outperforms previous VisualTTS methods in terms of overall quality, speaker similarity, and synchronization metrics.

cs.MM↗

arXiv2025

Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies

Existing imitation learning methods decouple perception and action, which overlooks the causal reciprocity between sensory representations and action execution that humans naturally leverage for adaptive behaviors. To bridge this gap, we introduce Action-Guided Diffusion Policy (DP-AG), a unified representation learning that explicitly models a dynamic interplay between perception and action through probabilistic latent dynamics. DP-AG encodes latent observations into a Gaussian posterior via variational inference and evolves them using an action-guided SDE, where the Vector-Jacobian Product (VJP) of the diffusion policy's noise predictions serves as a structured stochastic force driving latent updates. To promote bidirectional learning between perception and action, we introduce a cycle-consistent contrastive loss that organizes the gradient flow of the noise predictor into a coherent perception-action loop, enforcing mutually consistent transitions in both latent updates and action refinements. Theoretically, we derive a variational lower bound for the action-guided SDE, and prove that the contrastive objective enhances continuity in both latent and action trajectories. Empirically, DP-AG significantly outperforms state-of-the-art methods across simulation benchmarks and real-world UR5 manipulation tasks. As a result, our DP-AG offers a promising step toward bridging biological adaptability and artificial policy learning.

cs.RO↗

arXiv2024

LoVA: Long-form Video-to-Audio Generation

Video-to-audio (V2A) generation is important for video editing and post-processing, enabling the creation of semantics-aligned audio for silent video. However, most existing methods focus on generating short-form audio for short video segment (less than 10 seconds), while giving little attention to the scenario of long-form video inputs. For current UNet-based diffusion V2A models, an inevitable problem when handling long-form audio generation is the inconsistencies within the final concatenated audio. In this paper, we first highlight the importance of long-form V2A problem. Besides, we propose LoVA, a novel model for Long-form Video-to-Audio generation. Based on the Diffusion Transformer (DiT) architecture, LoVA proves to be more effective at generating long-form audio compared to existing autoregressive models and UNet-based diffusion models. Extensive objective and subjective experiments demonstrate that LoVA achieves comparable performance on 10-second V2A benchmark and outperforms all other baselines on a benchmark with long-form video input.

cs.SD↗

arXiv2024

Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization

Audiovisual Automatic Speech Recognition (AV-ASR) aims to improve speech recognition accuracy by leveraging visual signals. It is particularly challenging in unconstrained real-world scenarios across various domains due to noisy acoustic environments, spontaneous speech, and the uncertain use of visual information. Most previous works fine-tune audio-only ASR models on audiovisual datasets, optimizing them for conventional ASR objectives. However, they often neglect visual features and common errors in unconstrained video scenarios. In this paper, we propose using a preference optimization strategy to improve speech recognition accuracy for real-world videos. First, we create preference data via simulating common errors that occurred in AV-ASR from two focals: manipulating the audio or vision input and rewriting the output transcript. Second, we propose BPO-AVASR, a Bifocal Preference Optimization method to improve AV-ASR models by leveraging both input-side and output-side preference. Extensive experiments demonstrate that our approach significantly improves speech recognition accuracy across various domains, outperforming previous state-of-the-art models on real-world video speech recognition.

eess.AS↗

arXiv2024

Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer

Multi-person interactive motion generation, a critical yet under-explored domain in computer character animation, poses significant challenges such as intricate modeling of inter-human interactions beyond individual motions and generating two motions with huge differences from one text condition. Current research often employs separate module branches for individual motions, leading to a loss of interaction information and increased computational demands. To address these challenges, we propose a novel, unified approach that models multi-person motions and their interactions within a single latent space. Our approach streamlines the process by treating interactive motions as an integrated data point, utilizing a Variational AutoEncoder (VAE) for compression into a unified latent space, and performing a diffusion process within this space, guided by the natural language conditions. Experimental results demonstrate our method's superiority over existing approaches in generation quality, performing text condition in particular when motions have significant asymmetry, and accelerating the generation efficiency while preserving high quality.

cs.CV↗

arXiv2024

SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition

Recent advancements in language models have significantly enhanced performance in multiple speech-related tasks. Existing speech language models typically utilize task-dependent prompt tokens to unify various speech tasks in a single model. However, this design omits the intrinsic connections between different speech tasks, which can potentially boost the performance of each task. In this work, we propose a novel decoder-only speech language model, SpeechComposer, that can unify common speech tasks by composing a fixed set of prompt tokens. Built upon four primary tasks -- speech synthesis, speech recognition, speech language modeling, and text language modeling -- SpeechComposer can easily extend to more speech tasks via compositions of well-designed prompt tokens, like voice conversion and speech enhancement. The unification of prompt tokens also makes it possible for knowledge sharing among different speech tasks in a more structured manner. Experimental results demonstrate that our proposed SpeechComposer can improve the performance of both primary tasks and composite tasks, showing the effectiveness of the shared prompt tokens. Remarkably, the unified decoder-only model achieves a comparable and even better performance than the baselines which are expert models designed for single tasks.

cs.CL↗

arXiv2023

TeViS:Translating Text Synopses to Video Storyboards

A video storyboard is a roadmap for video creation which consists of shot-by-shot images to visualize key plots in a text synopsis. Creating video storyboards, however, remains challenging which not only requires cross-modal association between high-level texts and images but also demands long-term reasoning to make transitions smooth across shots. In this paper, we propose a new task called Text synopsis to Video Storyboard (TeViS) which aims to retrieve an ordered sequence of images as the video storyboard to visualize the text synopsis. We construct a MovieNet-TeViS dataset based on the public MovieNet dataset. It contains 10K text synopses each paired with keyframes manually selected from corresponding movies by considering both relevance and cinematic coherence. To benchmark the task, we present strong CLIP-based baselines and a novel VQ-Trans. VQ-Trans first encodes text synopsis and images into a joint embedding space and uses vector quantization (VQ) to improve the visual representation. Then, it auto-regressively generates a sequence of visual features for retrieval and ordering. Experimental results demonstrate that VQ-Trans significantly outperforms prior methods and the CLIP-based baselines. Nevertheless, there is still a large gap compared to human performance suggesting room for promising future work. The code and data are available at: \url{https://ruc-aimind.github.io/projects/TeViS/}

cs.CV↗

arXiv2022

Surface microlenses for much more efficient photodegradation in water treatment

The global need for clean water requires sustainable technology for purifying contaminated water. Highly efficient solar-driven photodegradation is a sustainable strategy for wastewater treatment. In this work, we demonstrate that the photodegradation efficiency of micropollutants in water can be improved by ~2-24 times by leveraging polymeric microlenses (MLs). These microlenses (MLs) are fabricated from the in-situ polymerization of surface nanodroplets. We found that photodegradation efficiency (η) in water correlates approximately linearly with the sum of the intensity from all focal points of MLs, although no difference in the photodegradation pathway is detected from the chemical analysis of the byproducts. With the same overall power over a given surface area, η is doubled by using ordered arrays, compared to heterogeneous MLs on an unpatterned substrate. Higher η from ML arrays may be attributed to a coupled effect from the focal points on the same plane that creates high local concentrations of active species to further speed up the rate of photodegradation. As a proof-of-concept for ML-enhanced water treatment, MLs were formed on the inner wall of glass bottles that were used as containers for water to be treated. Three representative micropollutants (norfloxacin, sulfadiazine, and sulfamethoxazole) in the bottles functionalized by MLs were photodegraded by 30% to 170% faster than in normal bottles. Our findings suggest that the ML-enhanced photodegradation may lead to a highly efficient solar water purification approach without a large solar collector size. Such an approach may be particularly suitable for portable transparent bottles in remote regions.

physics.chem-ph↗

arXiv2014

Field Effect Transistor Nanosensor for Breast Cancer Diagnostics

Silicon nanochannel field effect transistor (FET) biosensors are one of the most promising technologies in the development of highly sensitive and label-free analyte detection for cancer diagnostics. With their exceptional electrical properties and small dimensions, silicon nanochannels are ideally suited for extraordinarily high sensitivity. In fact, the high surface-to-volume ratios of these systems make single molecule detection possible. Further, FET biosensors offer the benefits of high speed, low cost, and high yield manufacturing, without sacrificing the sensitivity typical for traditional optical methods in diagnostics. Top down manufacturing methods leverage advantages in Complementary Metal Oxide Semiconductor (CMOS) technologies, making richly multiplexed sensor arrays a reality. Here, we discuss the fabrication and use of silicon nanochannel FET devices as biosensors for breast cancer diagnosis and monitoring.

q-bio.QM↗

arXiv2008

Surface modified silicon nanochannel for urea sensing

Silicon nanowires have been surface functionalized with the enzyme urease for biosensor applications to detect and quantify urea concentration. The device is nanofabricated from a silicon on insulator (SOI) wafer with a top down lithography approach. The differential conductance of silicon nanowires can be tuned for optimum performance using the source drain bias voltage, and is sensitive to urea at low concentration. The experimental results show a linear relationship between surface potential change and urea concentration in the range of 0.1 to 0.68 mM. The sensitivity of our devices shows high reproducibility with time and different measurement conditions. The nanowire urea biosensor offers the possibility of high quality, reusable enzyme sensor array integration with silicon based circuits.

physics.bio-ph↗

arXiv2008

Channel-Width Dependent Enhancement in Nanoscale Field Effect Transistor

We report the observation of channel-width dependent enhancement in nanoscale field effect transistors containing lithographically-patterned silicon nanowires as the conduction channel. These devices behave as conventional metal-oxide-semiconductor field-effect transistors in reverse source drain bias. Reduction of nanowire width below 200 nm leads to dramatic change in the threshold voltage. Due to increased surface-to-volume ratio, these devices show higher transconductance per unit width at smaller width. Our devices with nanoscale channel width demonstrate extreme sensitivity to surface field profile, and therefore can be used as logic elements in computation and as ultrasensitive sensors of surface-charge in chemical and biological species.

cond-mat.other↗