4 papers
WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
Chiheng Lou, Sheng Qi, Rui Kang +5
Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems impr…
Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation
Haojie Zhang, Zhihao Liang, Ruibo Fu +5
Long-duration talking video synthesis faces enduring challenges in achieving high video quality, portrait consistency, temporal coherence, and computational efficiency. As video le…
JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation
Bingyang Kelvin Liu, Ziyu Patrick Chen, David P. Woodruff
Current autoregressive language models couple high-level reasoning and low-level token generation into a single sequential process, making the reasoning trajectory vulnerable to co…
A Separable Self-attention Inspired by the State Space Model for Computer Vision
Juntao Zhang, Shaogeng Liu, Kun Bian +5
Mamba is an efficient State Space Model (SSM) with linear computational complexity. Although SSMs are not suitable for handling non-causal data, Vision Mamba (ViM) methods still de…