arXiv subjects

Yuyue Wang

Publications and source records attributed to Yuyue Wang.

12 recordsLinked to original sources

arXiv2026

Programming In-Storage Computing with Located, Stateful Dataflow

In-storage computing (ISC) reduces host--storage data movement by executing computation inside computational storage devices (CSDs). For multi-stage applications, realizing these benefits requires coordinating data placement, I/O--compute overlap, and device-resident state across the workflow, yet existing interfaces lack a unified abstraction for these decisions. We present Epic, an NVMe-based ISC stack that provides this abstraction by capturing data residency and lifetime in the program: location types declare logical residency, dataflow derives lifetimes for intermediate values and operation state within an invocation, and a keep primitive extends selected state across invocations. These semantics expose the complete offloaded workflow as a located, stateful dataflow. A storage-aware compiler transforms this workflow, performs movement-aware logical mapping and fusion, and exposes I/O--compute overlap; a runtime completes the plan using execution-time information, asynchronously binding work to physical resources and managing device-resident state. Across 12 file-scanning, database, and machine learning workloads, Epic is 1.6$\times$ faster on average than the strongest of five prior ISC systems, while achieving 4.2$\times$ speedup on average and up to 16.1$\times$ over the corresponding host baselines, and reducing application-side code by up to 14$\times$ in our implementations.

cs.AR↗

arXiv2026

Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans

Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and whether post-training changes this default behavior. We apply repetition priming (Shiffrin and Schneider, 1977) to 15 models across five model families (1.5B-14B parameters) in two tasks, semantic categorization and cloze completion, with matched human experiments using identical stimuli. We find that base models exhibit automatic processing: they show immediate facilitation that remains stable across lags, partially survives context removal, and correlates with attention to prior occurrences. Instruct models exhibit controlled processing: their facilitation decays with lag, collapses without expected context, and reverses to interference at larger scales. Within the Qwen 2.5 family, this dissociation increases monotonically with model scale, suggesting that post-training progressively alters repetition processing. Humans show a hybrid profile, with lag-sensitive facilitation resembling instruct models but without interference, suggesting that neither model type fully captures human cognition. Our findings reveal a qualitative shift in how language models process repeated information after post-training and provide mechanistic evidence for the divergence between model behaviors.

cs.CL↗

arXiv2026

AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

Multimodal Large Language Models have achieved remarkable progress in short-form audio-video understanding, yet long-form audio-video comprehension remains challenged by limited context windows and severe information redundancy. To address these bottlenecks, we propose AVOC, a framework for long-form audio-video understanding in Omni-modal Large Language Models. AVOC introduces a learnable token compression module between the modality encoders and the LLM backbone. We reframe multimodal token compression as a top-$K$ retrieval problem: given a fixed context budget, the module must retrieve a compact subset of tokens that best supports answering the user query. We draw inspiration from three classical Information Retrieval criteria for selecting informative units from a large candidate pool: relevance, importance, and diversity. AVOC instantiates each criterion as a tailored mechanism for audio-video understanding, and integrates them into a unified retrieval-style compression pipeline. Experiments show that AVOC achieves state-of-the-art performance on long-form audio-video benchmarks, surpassing the second-best model by 4.9 and 5.5 points in average accuracy on OmniVideoBench and LVOmniBench, respectively. Moreover, AVOC maintains robust performance on Audio-Video Needle-in-a-Haystack task at durations up to one hour.

cs.CL↗

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

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↗

arXiv2025

ChronusOmni: Improving Time Awareness of Omni Large Language Models

Time awareness is a fundamental ability of omni large language models, especially for understanding long videos and answering complex questions. Previous approaches mainly target vision-language scenarios and focus on the explicit temporal grounding questions, such as identifying when a visual event occurs or determining what event happens at aspecific time. However, they often make insufficient use of the audio modality, and overlook implicit temporal grounding across modalities--for example, identifying what is visually present when a character speaks, or determining what is said when a visual event occurs--despite such cross-modal temporal relations being prevalent in real-world scenarios. In this paper, we propose ChronusOmni, an omni large language model designed to enhance temporal awareness for both explicit and implicit audiovisual temporal grounding. First, we interleave text-based timestamp tokens with visual and audio representations at each time unit, enabling unified temporal modeling across modalities. Second, to enforce correct temporal ordering and strengthen fine-grained temporal reasoning, we incorporate reinforcement learning with specially designed reward functions. Moreover, we construct ChronusAV, a temporally-accurate, modality-complete, and cross-modal-aligned dataset to support the training and evaluation on audiovisual temporal grounding task. Experimental results demonstrate that ChronusOmni achieves state-of-the-art performance on ChronusAV with more than 30% improvement and top results on most metrics upon other temporal grounding benchmarks. This highlights the strong temporal awareness of our model across modalities, while preserving general video and audio understanding capabilities.

cs.CL↗

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↗

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

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

ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios

Text to Speech (TTS) models can generate natural and high-quality speech, but it is not expressive enough when synthesizing speech with dramatic expressiveness, such as stand-up comedies. Considering comedians have diverse personal speech styles, including personal prosody, rhythm, and fillers, it requires real-world datasets and strong speech style modeling capabilities, which brings challenges. In this paper, we construct a new dataset and develop ComedicSpeech, a TTS system tailored for the stand-up comedy synthesis in low-resource scenarios. First, we extract prosody representation by the prosody encoder and condition it to the TTS model in a flexible way. Second, we enhance the personal rhythm modeling by a conditional duration predictor. Third, we model the personal fillers by introducing comedian-related special tokens. Experiments show that ComedicSpeech achieves better expressiveness than baselines with only ten-minute training data for each comedian. The audio samples are available at https://xh621.github.io/stand-up-comedy-demo/

cs.SD↗

arXiv2021

TENET: A Framework for Modeling Tensor Dataflow Based on Relation-centric Notation

Accelerating tensor applications on spatial architectures provides high performance and energy-efficiency, but requires accurate performance models for evaluating various dataflow alternatives. Such modeling relies on the notation of tensor dataflow and the formulation of performance metrics. Recent proposed compute-centric and data-centric notations describe the dataflow using imperative directives. However, these two notations are less expressive and thus lead to limited optimization opportunities and inaccurate performance models. In this paper, we propose a framework TENET that models hardware dataflow of tensor applications. We start by introducing a relation-centric notation, which formally describes the hardware dataflow for tensor computation. The relation-centric notation specifies the hardware dataflow, PE interconnection, and data assignment in a uniform manner using relations. The relation-centric notation is more expressive than the compute-centric and data-centric notations by using more sophisticated affine transformations. Another advantage of relation-centric notation is that it inherently supports accurate metrics estimation, including data reuse, bandwidth, latency, and energy. TENET computes each performance metric by counting the relations using integer set structures and operators. Overall, TENET achieves 37.4\% and 51.4\% latency reduction for CONV and GEMM kernels compared with the state-of-the-art data-centric notation by identifying more sophisticated hardware dataflows.

cs.AR↗