Lune

Profiles2023-2026ORCID 0000-0002-8994-431X

Guoqi Li

Institute of Automation, Chinese Academy of Sciences

19Papers
15Last author
28Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers19

  1. Head-in-Head in Linear AttentionAuthor 5 of 5ICML 2026 · 48 citations
  2. Autoregressive Image Generation with Randomized Parallel DecodingAuthor 3 of 4ICLR 2026 · 19 citations
  3. Adaptive Hopfield Network: Rethinking Similarities in Associative MemoryAuthor 6 of 6ICLR 2026 · 1 citation
  4. SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World UnderstandingAuthor 9 of 9ICML 2026 · 1 citation
  5. EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language ModelsAuthor 8 of 9ACL 2026
  6. Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence ModelingAuthor 10 of 10ICLR 2026
  7. SMixer: Rethinking Efficient-Training and Event-Driven SNNsAuthor 9 of 9ICLR 2026
  8. MMDEND: Dendrite-Inspired Multi-Branch Multi-Compartment Parallel Spiking Neuron for Sequence ModelingAuthor 9 of 9ACL 2025 · 4 citations
  9. MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary DecompositionAuthor 6 of 6ICML 2025
  10. SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based SpikingAuthor 9 of 10ICLR 2025
  11. SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) ComplexityAuthor 6 of 7ICML 2025
  12. Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic ChipsAuthor 8 of 8ICLR 2024 · 154 citations
  13. SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking MechanismsAuthor 9 of 9ICML 2024 · 34 citations
  14. High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory and O(1) Inference CostAuthor 9 of 9ICML 2024 · 24 citations
  15. MetaLA: Unified Optimal Linear Approximation to Softmax Attention MapAuthor 10 of 10NeurIPS 2024 · 22 citations
  16. RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing CodingAuthor 7 of 7ACM MM 2024 · 5 citations
  17. SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural NetworkAuthor 7 of 7ACL 2024
  18. Spike-driven TransformerAuthor 7 of 7NeurIPS 2023 · 368 citations
  19. Inherent Redundancy in Spiking Neural NetworksAuthor 7 of 7ICCV 2023 · 30 citations
Dusk over the sea between two cliffs drawn in fine vertical lines