2 13 10

Xindi Wu

xindiw

https://xindiwu.github.io/

cindy_x_wu

AI & ML interests

None yet

Recent Activity

authored a paper about 4 hours ago

Ego4D: Around the World in 3,000 Hours of Egocentric Video

authored a paper about 4 hours ago

Language Models as Science Tutors

authored a paper about 4 hours ago

ICONS: Influence Consensus for Vision-Language Data Selection

View all activity

Organizations

authored 7 papers about 4 hours ago

Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification

Paper • 2510.24078 • Published Oct 28, 2025 • 3

Reinforced Fast Weights with Next-Sequence Prediction

Paper • 2602.16704 • Published 2 days ago • 9

upvoted a paper about 16 hours ago

Learning Personalized Agents from Human Feedback

Paper • 2602.16173 • Published 2 days ago • 6

upvoted a paper about 19 hours ago

Reinforced Fast Weights with Next-Sequence Prediction

Paper • 2602.16704 • Published 2 days ago • 9

submitted a paper to Daily Papers about 19 hours ago

Reinforced Fast Weights with Next-Sequence Prediction

Paper • 2602.16704 • Published 2 days ago • 9

reacted to lorraine2's post with ❤️ about 1 month ago

Post

1496

📽️ New NVIDIA paper: Motion Attribution for Video Generation 📽️

We propose MOTIVE, a method for taking query video clips and identifying which training data will improve or degrade performance after finetuning, enabling sophisticated data curation and beyond!

🔎 Project Page: https://research.nvidia.com/labs/sil/projects/MOTIVE/
📖 Full Paper: https://arxiv.org/abs/2601.08828

Check out more work from the NVIDIA Spatial Intelligence Lab here: https://research.nvidia.com/labs/sil/

This project was led by the great work of Xindi(Cindy) Wu, along with Despoina Paschalidou, Jun Gao, Antonio Torralba, Laura Leal-Taixé, Olga Russakovsky, and Sanja Fidler.