← Search

Denis A Gudovskiy

2 accepted papers

2025

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

ICML 2025poster

In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods learn a network to prune redundant visual tokens and require additional training d…

2024

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

ICML 2024poster

Uncertainty estimation is crucial for deep learning models to detect out-of-distribution (OOD) inputs. However, the naive deep learning classifiers produce uncalibrated uncertainty for OOD data. Improving the uncertainty estimation typically requires external data for OOD-aware training or considera…

Cited by 0SourcePDFScholar