collaborators

27 papers

cs.AR2026

A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation

Zihan Liu, Jingwen Leng, Yangjie Zhou +12

Modern GPUs increasingly integrate Tensor Cores into the execution pipeline. Although aggregate tensor throughput continues to grow, aided by an operand supply that has evolved fro…

cs.AR2026

Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference

Zheng Liu, Zeyu Guo, Zihan Liu +9

Vision-language-action (VLA) models have emerged as a key component in embodied AI. Among existing approaches, diffusion-based VLA models achieve superior motion quality and genera…

cs.AR2026

DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization

Minnan Pei, Gang Li, Zeyu Zhu +7

3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time novel view synthesis, yet existing 3DGS accelerators suffer from poor architectural scalability: incre…

cs.AR2026

DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction

Chi Zhang, Jieru Zhao, Yu Feng +3

Diffusion Transformers (DiTs) have been widely used in many tasks, including image synthesis, video generation, and content editing. However, their multi-iteration inference proces…

cs.AR2026

Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations

Wenxuan Miao, Haosong Liu, Weiming Hu +9

Kaleido introduces a hardware‑software co‑design that speeds up video diffusion transformers by reusing channel‑wise spatiotemporal information in the latent space, achieving large…

cs.DC2026

GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design

Yitong Ding, Jiawei Huang, Renyang Guan +7

The paper introduces GPU‑Tile‑Sim, a tile‑centric GPU simulation framework that models LLM kernels using warp‑level tile graphs to capture dependency and overlap, achieving low err…