Alper Canberk — accepted AI-conference papers

2025

AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation

Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin, Ivan Skorokhodov, Alper Canberk, Kwot Sin Lee +2

ICCV 2025poster

We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional in…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Differentiable Robot Rendering

Ruoshi Liu, Alper Canberk, Shuran Song, Carl Vondrick

CoRL 2024poster

Vision foundation models trained on massive amounts of visual data have shown unprecedented reasoning and planning skills in open-world settings. A key challenge in applying them to robotic tasks is the modality gap between visual data and action data. We introduce differentiable robot rendering, a…

Cited by 6 Source ↗Scholar ↗

2023

Cloth Funnels: Canonicalized-Alignment for Multi-Purpose Garment Manipulation

Alper Canberk, Cheng Chi, Huy Ha, Benjamin Burchfiel, Eric Cousineau, Siyuan Feng +1

ICRA 2023poster

Automating garment manipulation is challenging due to extremely high variability in object configurations. To reduce this intrinsic variation, we introduce the task of “canonicalized-alignment” that simplifies downstream applications by reducing the possible garment configurations. This task can be…

Cited by 46 Source ↗Scholar ↗

2021

Learning Human Objectives from Sequences of Physical Corrections

Mengxi Li, Alper Canberk, Dylan P. Losey, Dorsa Sadigh

ICRA 2021poster

When personal, assistive, and interactive robots make mistakes, humans naturally and intuitively correct those mistakes through physical interaction. In simple situations, one correction is sufficient to convey what the human wants. But when humans are working with multiple robots or the robot is pe…

Cited by 44 Source ↗Scholar ↗