Guohao Dai

Shanghai Jiao Tong University — China

Computer Science · Physical Sciences

13h-index756citations82works4.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(16), Advanced Memory and Neural Computing(14), Advanced Graph Neural Networks(12), Ferroelectric and Negative Capacitance Devices(11), Advanced Image and Video Retrieval Techniques(9)

Publications82 total

SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs
arXiv (Cornell University)·2025Open Access
SG-Filter: Enhancing Similar Text Retrieval via Hierarchical Summarized-Semantic Index and Adaptive Filtering
2025
CD-LLM: A Heterogeneous Multi-FPGA System for Batched Decoding of 70B+ LLMs using a Compute-Dedicated Architecture
ACM Transactions on Reconfigurable Technology and Systems·2025
Towards Floating Point-Based AI Acceleration: Hybrid PIM with Non-Uniform Data Format and Reduced Multiplications
ACM Transactions on Design Automation of Electronic Systems·2025Open Access
RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation
arXiv (Cornell University)·2025Open Access
Reducing GPU Memory Fragmentation via Spatio-Temporal Planning for Efficient Large-Scale Model Training
arXiv (Cornell University)·2025Open Access
<i>FlashDecoding++Next</i>: High Throughput LLM Inference With Latency and Memory Optimization
IEEE Transactions on Computers·2025
Harnessing Conventional Video Processing Insights for Emerging 3D Video Generation Models: A Comprehensive Attention-aware Way
2025
SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
2025Open Access
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
arXiv (Cornell University)·2025Open Access
semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage
arXiv (Cornell University)·2025Open Access
SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
arXiv (Cornell University)·2025Open Access
DyLGNN: Efficient LM-GNN Fine-Tuning with Dynamic Node Partitioning, Low-Degree Sparsity, and Asynchronous Sub-Batch
2025
TB-STC: Transposable Block-wise N:M Structured Sparse Tensor Core
2025· 2 cited
FlightVGM: Efficient Video Generation Model Inference with Online Sparsification and Hybrid Precision on FPGAs
2025· 9 citedOpen Access
FMC-LLM: Enabling FPGAs for Efficient Batched Decoding of 70B+ LLMs with a Memory-Centric Streaming Architecture
2025· 2 citedOpen Access
DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
arXiv (Cornell University)·2025Open Access
LLSM: LLM-enhanced Logic Synthesis Model with EDA-guided CoT Prompting, Hybrid Embedding and AIG-tailored Acceleration
2025
ViDA: Video Diffusion Transformer Acceleration with Differential Approximation and Adaptive Dataflow
2025
Deploying Diffusion Models with Scheduling Space Search and Memory Overflow Prevention Based on Graph Optimization
2025· 2 cited
page 1 of 5Next →

Frequent Co-authors

Yu Wang(29), Huazhong Yang(21), Zhenhua Zhu(18), Shulin Zeng(15), Hanbo Sun(9), Xuefei Ning(8), Kai Zhong(8), Yu Wang(7), Huazhong Yang(7), Zhongming Yu(7), Guyue Huang(6), J Liu(5), Yuan Xie(5), Xinhao Yang(4), Tianyu Fu(4), Hongyi Wang(4), Hengrui Zhang(4), Yu Wang(4), Ke Hong(4), Haoyu Zhang(4)