Tianyu Ding, Ph.D.
Scholar

Tianyu Ding, Ph.D.

Google Scholar ID: Qi7zTOcAAAAJ
Principal Researcher, Microsoft | Johns Hopkins University
Efficient MLEfficient AIGenerative AIComputer Vision
Citations & Impact
All-time
Citations
1,302
 
H-index
15
 
i10-index
20
 
Publications
20
 
Co-authors
44
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning, ACL 2025
  • DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs, ICML 2025 (Oral, top 1%)
  • ONNXPruner: ONNX-Based General Model Pruning Adapter, TPAMI 2025
  • Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration, CVPR 2025
  • Automated Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression, CVPR 2025
  • OFER: Occluded Face Expression Reconstruction, CVPR 2025
  • 3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities, TCSVT 2025
  • StructSR: Refuse Spurious Details in Real-World Image Super-Resolution, AAAI 2025
  • CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering, ECCV 2024
  • Safe and Robust Subgame Exploitation in Imperfect Information Games, ICML 2024
Research Experience
  • Principal Researcher in Applied Sciences Group at Microsoft.
Background
  • Currently a Principal Researcher in Applied Sciences Group at Microsoft. Focused on improving efficiency in machine learning and artificial intelligence, especially in areas like computer vision and generative models.
Miscellany
  • Appreciates Anyverse Anonymous Feedback from anyone on anything. Feel free to ping me!