Aviral Agrawal

3D multimodal future with the fusion of 3D representation and Vision Language Models

← Back to Members
Aviral Agrawal, former master student at CMU Momentum Lab

Aviral Agrawal

3D multimodal future with the fusion of 3D representation and Vision Language Models

Publications

Method and electronic device for compressing a video using ai-based in loop filter

A Singh, A AGRAWAL, RN GADDE, Y Piao, M Park, K CHOI

arXiv preprint · 2026

Materialfusion: Enhancing inverse rendering with material diffusion priors

Y Litman, O Patashnik, K Deng, A Agrawal, R Zawar, F De la Torre, ...

2025 International Conference on 3D Vision (3DV), 802-812

Method and system for content-based scaling for artificial intelligence based inloop filters

A Agrawal, A Singh, RN Gadde, Y Piao, M Park, C Kwangpyo

US Patent US20250175623A1

Method, and electronic device for processing a video

P GANGULY, A AGRAWAL, A Singh, RN GADDE, Y Piao, M Park, K CHOI

US Patent App. 19/237,865, 2025

KOROL: Learning Visualizable Object Feature with Koopman Operator Rollout for Manipulation

H Chen, A Abuduweili, A Agrawal, Y Han, H Ravichandar, C Liu, ...

CoRL 2024

Clear-Splatting: Learning Residual Gaussian Splats for Transparent Object Manipulation

A Agrawal, R Roy, BP Duisterhof, KB Hekkadka, H Chen, J Ichnowski

ICRA 2024 Workshop

Listen then see: Video alignment with speaker attention

A Agrawal, CMS Lezcano, IB Heredia-Marin, PS Sethi

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Method and system for reducing complexity of a processing pipeline using feature-augmented training

A Agrawal, RN Gadde, A Singh, Y Piao, M Park, C Kwangpyo

AU Patent AU2023227722A1, 2024

System and method for training artificial intelligence models for in-loop filters

A Singh, A AGRAWAL, RN Gadde, HK BHAT, Y Piao, M Park, K CHOI

US Patent US20230362367A1

On the (In) Feasibility of Attribute Inference Attacks on Machine Learning Models

BZ Hao Zhao, A Agrawal, C Coburn, H Jameel Asghar, R Bhaskar, ...

arXiv:2103.07101 · 2021

Diffusion Models for Counterfactual Generation

A Agrawal, R Zawar

arXiv preprint