My research aims to advance efficient and scalable AI through algorithmic innovation in efficient modeling and the design of high-performance machine learning systems. I currently focus on training and inference for multimodal content generation, addressing computational and memory bottlenecks to enable high-quality, long-horizon generation in real time.
I earned my Ph.D. at UC Santa Barbara, where I was fortunate to work with Prof. Peng Li (IEEE Fellow). Before UCSB, I completed my M.S. at the University of Michigan, Ann Arbor, where I had the pleasure of working with Prof. David Blaauw and Prof. Dennis Sylvester. I received my B.S. from the University of Electronic Science and Technology of China.
My work received consecutive William J. McCalla Best Paper Award nominations at ICCAD 2024 and 2025. I was awarded the Radhakrishnan Nagarajan Family Fellowship at UC Santa Barbara and won the Second Place at the DAC 2026 Ph.D. Forum.
Research Intern & Student Researcher
Explored Video Sparse Attention for MovieGen-30B, focusing on serving inference acceleration and large-scale sparse distribution matching distillation on hundreds of GPUs.
Advisors: Yuming Du, Zichang Liu, Siyu Yang, Wenchen Wang, Albert Pumarola
Research Intern
Explored Multi-teacher knowledge distillation for multi-modal and multi-task foundation models supporting integrity detection across Facebook, Instagram, and WhatsApp.
I have published in leading conferences and journals in machine learning, computer architecture, and design automation, including ISCA, NeurIPS, AAAI, CVPR, ICCV, ICCAD, TCAD, and JSSC.
Preprint 2026
Long-horizon video generation needs persistent visual memory without the cost of dense attention. First native trainable sparse attention for autoregressive video diffusion to make video generation both faster and better.
Conference on Neural Information Processing Systems (NeurIPS), 2026
Large KV caches limit the scalability of autoregressive image and video generation. First tuning-free KV-cache quantization for visual autoregressive generation, evaluated across nine image and video models.
AAAI Conference on Artificial Intelligence (AAAI), 2026
Different layers and image scales need different cache budgets to preserve generation quality. First adaptive KV-caching framework tailored to multi-scale visual autoregressive transformers.
International Symposium on Computer Architecture (ISCA), 2025
Spiking transformers produce workloads with different activity densities across tokens and time. First heterogeneous HW/SW co-design framework for brain-inspired neuromorphic transformers.
ACM/IEEE International Conference on Computer-Aided Design (ICCAD), 2025
William J. McCalla Best Paper Award Nomination
Mixture-of-experts expands model capacity through conditional computation, creating a need for parallel, distributed hardware. First 3D distributed and parallel accelerator for spiking MoE and multi-head attention.
ACM/IEEE International Conference on Computer-Aided Design (ICCAD), 2024
William J. McCalla Best Paper Award Nomination
Spiking transformers combine attention with binary spike operations, but require dedicated hardware to realize their efficiency. First dedicated 3D accelerator for brain-inspired neuromorphic transformers.
Defended my Ph.D. dissertation, “Co-Architecting Models and Systems for Efficient Perception and Generation,” at UC Santa Barbara.
Received Second Place at the DAC 2026 Ph.D. Forum and a travel grant from ACM SIGDA / IEEE CEDA.
Recognized as an ICML 2026 Gold Reviewer.
Released the Sparse Forcing preprint with Meta Superintelligence Labs.ProjectPaper
Received the Radhakrishnan Nagarajan Family Fellowship at UC Santa Barbara.
Completed my internship and student research role at Meta Superintelligence Labs, working on efficient video generation.
VEGAS was accepted at CVPR 2026 Findings.
AMS-KV and Khan-GCL were accepted at AAAI 2026.
Received a second consecutive William J. McCalla Best Paper Award nomination at ICCAD 2025 for the 3D MoE spiking transformer paper.
Joined Meta in Seattle as a research intern, working on efficient video generation.
The 3D MoE spiking transformer paper was accepted at ICCAD 2025.
The Vmin prediction paper was accepted at ITC 2025.
The spiking vision transformer quantization paper was accepted at ASAP 2025.
Bishop was accepted at ISCA 2025.
SpikeX was accepted as a long paper in TCAD.
Received a William J. McCalla Best Paper Award nomination at ICCAD 2024 for the 3D spiking transformer paper.
Two papers were accepted at ICCAD 2024, on 3D spiking transformers and LLM-guided analog design.
Joined Meta AI as a research intern, working on multimodal, multitask knowledge distillation.
AIMMI was accepted in JSSC.
Selected as a DAC Young Fellow.
Received the ECE Outstanding Teaching Assistant Award at UC Santa Barbara.
Started my Ph.D. at UC Santa Barbara, advised by Prof. Peng Li.
The 10 TOPS/W multimodal SoC paper was accepted at the VLSI Symposium 2022.
A complete list of my publications and preprints.
Preprint, 2026
Work done during internship at Meta Superintelligence Labs.
Conference on Neural Information Processing Systems (NeurIPS), 2026
Extended image and video paper. Earlier version appeared at the ICCV 2025 Binary and Extreme Quantization workshop.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026
Preprint, 2026
Under review at Transactions on Machine Learning Research (TMLR)
ACM/IEEE International Test Conference (ITC), 2026
AAAI Conference on Artificial Intelligence (AAAI), Main Track, January 2026
AAAI Conference on Artificial Intelligence (AAAI), Main Track, 2026
IEEE/CVF International Conference on Computer Vision (ICCV) Workshop on Binary and Extreme Quantization for Computer Vision, 2025
International Symposium on Computer Architecture (ISCA), 2025
ACM/IEEE International Conference on Computer-Aided Design (ICCAD), 2025
William J. McCalla Best Paper Award Nomination
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2025
IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP), 2025
ACM/IEEE International Test Conference (ITC), 2025
ACM/IEEE International Conference on Computer-Aided Design (ICCAD), 2024
William J. McCalla Best Paper Award Nomination
ACM/IEEE International Conference on Computer-Aided Design (ICCAD), 2024
arXiv, 2024
IEEE Journal of Solid-State Circuits (JSSC), 2024
2022 IEEE Symposium on VLSI Technology and Circuits (VLSI-Symposium), 2022
More to come.