Lune

Profiles2022-2025

Ting Cao

Microsoft Research

11Papers
0Last author
41Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers11

  1. T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on EdgeAuthor 3 of 7EuroSys 2025 · 30 citations
  2. LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning AcceleratorAuthor 6 of 9HPCA 2025 · 7 citations
  3. Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert InferenceAuthor 6 of 7ISCA 2024 · 48 citations
  4. FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge DevicesAuthor 4 of 5MobiCom 2024 · 40 citations
  5. PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-OptimizationAuthor 5 of 8ASPLOS 2024 · 27 citations
  6. BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-DistillationAuthor 5 of 7ACL 2024 · 16 citations
  7. VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language ModelsAuthor 7 of 9EMNLP 2024 · 10 citations
  8. AFPQ: Asymmetric Floating Point Quantization for LLMsAuthor 5 of 6ACL Findings 2024 · 6 citations
  9. LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table LookupAuthor 3 of 14MobiCom 2023 · 29 citations
  10. Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer InferenceAuthor 9 of 24KDD 2023 · 12 citations
  11. Romou: rapidly generate high-performance tensor kernels for mobile GPUsAuthor 2 of 7MobiCom 2022 · 13 citations
Dusk over the sea between two cliffs drawn in fine vertical lines