Normalized Low-Rank Adaptation
Paper • 2608.31036 • Published • 47
zheng zhan
zz8585
·
AI & ML interests
Model compression
Continual (Lifelong) learning
Recent Activity
authored a paper about 7 hours ago
Normalized Low-Rank Adaptation authored a paper about 7 hours ago
Full-bandwidth transformer authored a paper about 7 hours ago
LightCache: Memory-Efficient, Training-Free Acceleration for Video
GenerationOrganizations
None yet
authored 14
papers about 7 hours ago
Full-bandwidth transformer
Paper • 2608.08888 • Published • 23
LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
Paper • 2510.05367 • Published • 7
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
Paper • 2507.06607 • Published • 10
Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
Paper • 2505.23844 • Published • 4
Rethinking Token Reduction for State Space Models
Paper • 2410.14725 • Published
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Paper • 2411.01171 • Published
E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
Paper • 2401.06127 • Published
Search for Efficient Large Language Models
Paper • 2409.17372 • Published
Exploring Token Pruning in Vision State Space Models
Paper • 2409.18962 • Published
DiffClass: Diffusion-Based Class Incremental Learning
Paper • 2403.05016 • Published
Efficient Training with Denoised Neural Weights
Paper • 2407.11966 • Published • 9
SparCL: Sparse Continual Learning on the Edge
Paper • 2209.09476 • Published • 2
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Paper • 2305.00380 • Published
upvoted 2
papers 1 day ago
liked a
dataset about 2 months ago
liked a
model about 2 months ago
liked 2
datasets 2 months ago