← Search

Petra Poklukar

8 accepted papers

2025

Gatekeeper: Improving Model Cascades Through Confidence Tuning

NeurIPS 2025poster

Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these challenges, local smaller models are often deployed alongside larger models, relying on routing and deferral mechanisms to o…

Cited by 0SourceScholar
2024

BRAVE: Broadening the visual encoding of vision-language models

ECCV 2024oral

"Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders, e.…

2022

Augment-Connect-Explore: a Paradigm for Visual Action Planning with Data Scarcity

IROS 2022poster

Visual action planning particularly excels in applications where the state of the system cannot be computed explicitly, such as manipulation of deformable objects, as it enables planning directly from raw images. Even though the field has been significantly accelerated by deep learning techniques, a…

Cited by 4SourceScholar
2022

Delaunay Component Analysis for Evaluation of Data Representations

ICLR 2022poster

Advanced representation learning techniques require reliable and general evaluation methods. Recently, several algorithms based on the common idea of geometric and topological analysis of a manifold approximated from the learned data representations have been proposed. In this work, we introduce Del…

2022

Geometric Multimodal Contrastive Representation Learning

ICML 2022spotlight

Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels. To address it, we present a novel Geometric Multimodal Contrastive (GMC) repre…

2021

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

IROS 2021poster

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challe…

Cited by 34SourceScholar
2021

GeomCA: Geometric Evaluation of Data Representations

ICML 2021spotlight

Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological prop…

2020

Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation

IROS 2020poster

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects. Planning is performed in a low-dimensional latent state space that embeds images. We define and implement a Latent Space Roadmap (LSR) which…

Cited by 70SourcecodeScholar