8 papers
FreeBalance: Pre-Routing Online Moe Load Balancing via Residual Workload Prediction
Pengfei Chen, Yize Wu, Shouxu Kuang +2
Load imbalance poses a major bottleneck to the efficiency of expert parallelism in distributed inference of Mixture-of-Experts (MoE) models. The most heavily loaded rank stalls glo…
EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference
Yize Wu, Ke Gao, Ling Li +1
Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models. As routing distributions are typically skewed across e…
Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understanding
Yuheng Jiang, Yiwen Cai, Zihao Wang +5
Volumetric video seeks to model dynamic scenes as temporally coherent 4D representations. While recent Gaussian-based approaches achieve impressive rendering fidelity, they primari…
Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation
Yize Wu, Ke Gao, Ling Li +1
Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient method for fine-tuning Large Langauge Models. It updates the weight matrix as , where is the ori…
Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos
Yuheng Jiang, Chengcheng Guo, Yize Wu +9
Volumetric video is emerging as a key medium for digitizing the dynamic physical world, creating the virtual environments with six degrees of freedom to deliver immersive user expe…
BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video
Yu Hong, Yize Wu, Zhehao Shen +5
Volumetric video enables immersive experiences by capturing dynamic 3D scenes, enabling diverse applications for virtual reality, education, and telepresence. However, traditional…
EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
Yize Wu, Ke Gao, Ling Li +1
Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which…
Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos
Yuheng Jiang, Zhehao Shen, Yu Hong +5
Volumetric video represents a transformative advancement in visual media, enabling users to freely navigate immersive virtual experiences and narrowing the gap between digital and…