4 papers
FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
Zhuokun Chen, Jianfei Cai, Bohan Zhuang
Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency v…
R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
Zhuokun Chen, Zeren Chen, Jiahao He +4
Chain-of-thought (CoT) enhances the problem-solving ability of large language models (LLMs) but incurs substantial inference cost due to long autoregressive trajectories. Existing…
Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis
Zhuokun Chen, Jugang Fan, Zhuowei Yu +2
Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and…
Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion
Zhuokun Chen, Jinwu Hu, Zeshuai Deng +3
Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs…