arxiv:2504.13161
Pavlo Molchanov PRO
pmolchanov
AI & ML interests
Efficiency in Multi-Modal LLMs
Recent Activity
authored
a paper
8 days ago
PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation
authored
a paper
8 days ago
EoRA: Training-free Compensation for Compressed LLM with Eigenspace
Low-Rank Approximation
authored
a paper
8 days ago
Hymba: A Hybrid-head Architecture for Small Language Models
Organizations
Papers
27
models
0
None public yet
datasets
0
None public yet