Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation
Paper
• 2603.04971 • Published
• 3
Yichen
YichenLLM
·
AI & ML interests
None yet
Recent Activity
authored
a paper
2 days ago
NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time authored
a paper
2 days ago
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion Organizations
None yet
upvoted a paper 1 day ago
authored 4 papers 2 days ago
NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
Paper
• 2408.03675 • Published
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
Paper
• 2406.06567 • Published
Mixture of Hidden-Dimensions Transformer
Paper
• 2412.05644 • Published
• 1
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
Paper
• 2502.13842 • Published
upvoted a paper 2 days ago
upvoted a paper about 1 month ago