pith. sign in

Huihong Shi

Identifiers

  • name variant Huihong Shi 0.60 · backfill

Papers (17)

  1. AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design cs.AR · 2025 · author #2
  2. M$^2$-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization cs.AR · 2024 · author #2
  3. NASH: Neural Architecture and Accelerator Search for Multiplication-Reduced Hybrid Models cs.LG · 2024 · author #2
  4. Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration cs.LG · 2024 · author #4
  5. ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization cs.LG · 2024 · author #5
  6. P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer cs.AI · 2024 · author #1
  7. Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer cs.CV · 2024 · author #1
  8. An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT cs.AR · 2024 · author #2
  9. A Computationally Efficient Neural Video Compression Accelerator Based on a Sparse CNN-Transformer Hybrid Network eess.IV · 2023 · author #3
  10. S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-Resolution cs.CV · 2023 · author #3
  11. ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer cs.LG · 2023 · author #2
  12. Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction cs.AR · 2023 · author #8
  13. ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention cs.CV · 2022 · author #3
  14. NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks cs.AR · 2022 · author #1
  15. ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design cs.LG · 2022 · author #3
  16. ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks cs.LG · 2022 · author #3
  17. Max-Affine Spline Insights Into Deep Network Pruning cs.LG · 2021 · author #5

Mentions

  • 2505.03745 #2 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2304.12467 #8 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2210.09573 #3 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2205.08119 #3 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2101.02338 #5 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2406.05981 #5 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2410.09113 #2 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2405.03882 #1 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2409.04829 #2 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2306.06446 #2 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2406.15765 #4 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2405.19915 #1 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2403.20230 #2 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2312.10716 #3 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2308.08142 #3 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2210.13361 #1 · arxiv_oai · confidence 0.70 Huihong Shi
  • 2211.05109 #3 · arxiv_oai · confidence 0.70 Huihong Shi

Frequent Coauthors