← Search

Boglarka Ecsedi

2 accepted papers

2025

Model merging with SVD to tie the Knots

ICLR 2025poster

Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks without retraining. Yet, this success does not transfer well when merging LoRA finetuned models. We study this phenomenon…

2024

AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images

ICLR 2024poster

Synthetic data (Sim) drawn from simulators have emerged as a popular alternativefor training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world applicationscan be challenging due to appearance disparities. A commonl…

Cited by 0SourcePDFScholar