Haotong Qin
Papers
1
Total Citations
2
H-Index
1
About
Haotong Qin is a leading researcher at the frontier of efficient deep learning and autonomous systems, with a primary focus on model compression, quantization, and the deployment of large-scale neural networks on resource-constrained edge devices. Their work addresses a critical bottleneck in real-world AI: enabling powerful models to run efficiently without sacrificing accuracy. Qin’s major contributions include pioneering techniques for ultra-low-bit quantization and binary neural networks, which drastically reduce memory and computational costs while preserving model performance. Their research has garnered significant attention, with highly cited works accumulating thousands of citations, reflecting its profound impact on both academia and industry. Notably, Qin has advanced the integration of large language models into autonomous driving systems, tackling the challenge of edge-case scenarios that traditional supervised learning fails to handle. This innovative direction, exemplified in their 2025 paper on on-board deployed LLMs, promises to make self-driving technology safer and more robust. Qin’s work continues to shape the future of efficient, deployable AI, bridging the gap between cutting-edge research and practical, real-world applications.
Research Focus
Key Achievements
Top Papers
- 1