On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
Paper
•
2501.04377
•
Published
•
14
Zhenmei Shi
Zhenmei
AI & ML interests
None yet
Organizations
authored
a
paper
about 1 year ago
authored
5
papers
over 1 year ago
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
Paper
•
2402.15017
•
Published
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
Paper
•
2406.14852
•
Published
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
Paper
•
2408.13233
•
Published
•
23
Toward Infinite-Long Prefix in Transformer
Paper
•
2406.14036
•
Published
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
Paper
•
2409.17422
•
Published
•
25