Cvpr 2025 Context Aware Multimodal Pretraining

Paper: https://arxiv.org/abs/2411.15099 Authors: Karsten Roth, Zeynep Akata, Dima Damen, Ivana Balažević*, Olivier J. Hénaff* ...

Next in our #CVPR2025 lineup: PromptHMR ✨ Drop a video and watch it blossom into crisp 3D people, even when limbs are ...

We propose LongVALE, the first time-

CVPR 2025

PersonaBooth: Personalized Text-to-Motion Generation (

My part of the

Project Page: https://aim-skku.github.io/QA-TIGER/ Abstract: Audio-Visual Question Answering (AVQA) requires not only ...

Paper: https://arxiv.org/abs/2412.06712 Code: https://github.com/ExplainableML/fomo_in_flux.

Experience

Virtual presentation of our recent work "Towards Zero-Shot Anomaly Detection and Reasoning with

This is the official video of the

We introduce SeqAfford, a

Abstract: Uncertainty Quantification (UQ) is crucial for ensuring the reliability of machine learning models deployed in real-world ...

CVPR 2025

Disentangle-then-Align: Non-Iterative Hybrid

Brief intro of our paper. Feel free to find more in https://arxiv.org/abs/2511.19972.

Visual question answering (VQA) systems face significant challenges when adapting to real-world data shifts, especially in ...