Guoqi Li

Autoregressive Image Generation with Randomized Parallel Decoding

Scaling Linear Attention Capacity with Sparse State Expansion

Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence Modeling

Adaptive Hopfield Network: Rethinking Similarities in Associative Memory

SMixer: Rethinking Efficient-Training and Event-Driven SNNs

PLA: The Optimal Path from Softmax Attention to Linear Models via KV Cache Compression

An Efficient Framework for Length Extension via Dynamically Growing Positional Embedding and Correlation-Aware Routing Attention

DIME: Tackling Density Imbalance for High-Performance and Low-Latency Event-Based Object Detection

SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding

Parallel Training in Spiking Neural Networks

Spike-driven Large Language Model

Exploring Reprensentation Invariance in Finetuning

EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Edge Language Models

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

MI-TRQR: Mutual Information-Based Temporal Redundancy Quantification and Reduction for Energy-Efficient Spiking Neural Networks

MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition

Adaptive Continual Learning Through Proactive Detection of Transfer and Interference