8 papers
Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction
Boran Wen, Ye Lu, Sirui Wang +7
Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless an…
Schrödinger Bridge Mamba for One-Step Speech Enhancement
Jing Yang, Sirui Wang, Chao Wu +2
We present Schrödinger Bridge Mamba (SBM), a novel model for efficient speech enhancement by integrating the Schrödinger Bridge (SB) training paradigm and the Mamba architecture.…
Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation
Sirui Wang, Andong Chen, Tiejun Zhao
Emotional text-to-speech (E-TTS) is central to creating natural and trustworthy human-computer interaction. Existing systems typically rely on sentence-level control through predef…
Growing Through Experience: Scaling Episodic Grounding in Language Models
Chunhui Zhang, Sirui, Wang +3
Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approa…
Enhancing LLMs via High-Knowledge Data Selection
Feiyu Duan, Xuemiao Zhang, Sirui Wang +4
The performance of Large Language Models (LLMs) is intrinsically linked to the quality of its training data. Although several studies have proposed methods for high-quality data se…
FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
Xuemiao Zhang, Feiyu Duan, Liangyu Xu +5
Large language models (LLMs) have significantly advanced human language understanding and generation, with pretraining data quality and organization being crucial to their performa…