21 citations · 22 across the 14 of their papers we have counts for
15 papers
Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
Chunyu Qi, Zhuoran Song, Jian Weng +6
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hin…
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…
A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference
Zhuoran Song, Haozhe Jiang, Chunyu Qi +4
Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment. Existing accelerators,…
Accelerating 3D Gaussian Splatting using Tensor Cores
Sheng Li, Yang Sui, Yue Wu +4
3D Gaussian Splatting (3DGS) has become a leading technique for real-time neural rendering and 3D scene reconstruction, but its rendering cost remains too high for many latency-sen…
Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems
Chen Zhang, Qijun Zhang, Zhuoshan Zhou +10
Tensor parallelism (TP) in large-scale LLM inference and training introduces frequent collective operations that dominate inter-GPU communication. While in-switch computing, exempl…
DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs
Zeyu Zhu, Gang Li, Peisong Wang +5
Mixture of Experts (MoE) architectures significantly enhance the capacity of LLMs without proportional increases in computation, but at the cost of a vast parameter size. Offloadin…
AGS: Accelerating 3D Gaussian Splatting SLAM via CODEC-Assisted Frame Covisibility Detection
Houshu He, Naifeng Jing, Li Jiang +2
Simultaneous Localization and Mapping (SLAM) is a critical task that enables autonomous vehicles to construct maps and localize themselves in unknown environments. Recent breakthro…
ASDR: Exploiting Adaptive Sampling and Data Reuse for CIM-based Instant Neural Rendering
Fangxin Liu, Haomin Li, Bowen Zhu +4
Neural Radiance Fields (NeRF) offer significant promise for generating photorealistic images and videos. However, existing mainstream neural rendering models often fall short in me…
GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processing
Minnan Pei, Gang Li, Junwen Si +6
3D Gaussian Splatting (3DGS) has emerged as a leading neural rendering technique for high-fidelity view synthesis, prompting the development of dedicated 3DGS accelerators for reso…
Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance
Zhican Wang, Guanghui He, Lingjun Gao +6
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, combining high-quality reconstruction with efficient rendering. It has been widely adopte…
Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
Dan Peng, Zhihui Fu, Zewen Ye +2
Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attentio…
DNN Training Acceleration via Exploring GPGPU Friendly Sparsity
Zhuoran Song, Yihong Xu, Han Li +3
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the…
CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction
Zhuoran Song, Yihong Xu, Zhezhi He +3
Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobil…
Invocation-driven Neural Approximate Computing with a Multiclass-Classifier and Multiple Approximators
Haiyue Song, Chengwen Xu, Qiang Xu +4
Neural approximate computing gains enormous energy-efficiency at the cost of tolerable quality-loss. A neural approximator can map the input data to output while a classifier deter…
Approximate Random Dropout
Zhuoran Song, Ru Wang, Dongyu Ru +5
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the…