5 papers
SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
Jialiang Kang, Han Shu, Wenshuo Li +2
Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy nature of visual generation yie…
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement
Qianhan Feng, Wenshuo Li, Tong Lin +1
Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile…
Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation
Xuan Du, Qiangyu Yan, Wenshuo Li +4
The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, ta…
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
Zhaoyuan Ding, Yijing Yang, Han Shu +1
Segment Anything Model 2 (SAM 2) serves as a core foundation model in the field of video segmentation. Building upon the original SAM model, it introduces a memory bank mechanism a…
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
Jialiang Kang, Han Shu, Wenshuo Li +2
Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexp…