Zhenglun Kong

机构：Harvard University · ORCID：0000-0002-8120-4456

发表论文 62 篇 · 总被引 1374 次 · h-index 19

代表论文

• Pruning Foundation Models for High Accuracy without Retraining (2024 · Conference on Empirical Methods in Natural Language Processing · 被引 30)
• Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment (2024 · AAAI Conference on Artificial Intelligence · 被引 26)
• Squat: Quant Small Language Models on the Edge (2024 · 2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD) · 被引 21)
• Search for Efficient Large Language Models (2024 · Neural Information Processing Systems · 被引 20)
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory (2025 · arXiv.org · 被引 16)
• RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation (2025 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 被引 16)