Publications & Contributions

Preprints

H. Sun, L.W. Chang, W. Bao, S. Zheng, N. Zheng, X. Liu, H. Dong, Y. Chi, B. Chen, ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference, 2024.

T. Efimov, H. Dong, M. Shah, J. Simmons, S. Donegan, Y. Chi, Leveraging Multimodal Diffusion Models to Accelerate Imaging with Side Information, 2024.

Journals

H. Dong, S. Donegan, M. Shah, Y. Chi, A Lightweight Transformer for Faster and Robust EBSD Data Collection, Scientific Reports, 2024.
- Oral presentation at the Machine Learning for Scientific Imaging Conference at Electronic Imaging, 2024.
- Poster presentation at the Joint Workshop at the Intersection of Materials Science and Machine Learning, 2023.

H. Dong, T. Tong, C. Ma, Y. Chi, Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent, Information and Inference: A Journal of the IMA, 2023.
- Contributed talk at SIAM Conference on Mathematics of Data Science, 2022.

Conferences

H. Dong, B. Chen, Y. Chi, Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation, Conference on Language Modeling (COLM), 2024.
- Oral presentation at ICML Workshop on Efficient Systems for Foundation Models, 2024.

H. Dong, X. Yang, Z. Zhang, Z. Wang, Y. Chi, B. Chen, Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference, International Conference on Machine Learning (ICML), 2024.

H. Dong, M. Shah, S. Donegan, Y. Chi, Deep Unfolded Tensor Robust PCA with Self-supervised Learning, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
- Also presented at the Third Workshop on Seeking Low‑Dimensionality in Deep Neural Networks, 2023.

T. Cabannes, J. Li, F. Wu, H. Dong, A. Bayen, Learning Optimal Traffic Routing Behaviors using Markovian Framework in Microscopic Simulation, TRB 99th Annual Meeting, 2020.

Workshops

H. Dong, T. Johnson, M. Cho, E. Soroush, Towards Low-bit Communication for Tensor Parallel LLM Inference, NeurIPS Workshop on Efficient Natural Language and Speech Processing IV, 2024.

H. Dong, B. Chen, Y. Chi, Towards Structured Sparsity in Transformers for Efficient Inference, ICML Workshop on Efficient Systems for Foundation Models, 2023.