Dongyue Lu

PhD student, National University of Singapore

4 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras

#2311 Spotlight · Lingdong Kong, Dongyue Lu, Alan Liang, Rong Li, Yuhao Dong, Tianshuai Hu, Lai Xing Ng, Wei Tsang Ooi, Benoit R Cottereau

Talk2Event is a new benchmark for attribute-aware visual grounding from event cameras.

3EED: Ground Everything Everywhere in 3D

#4603 · Rong Li, Yuhao Dong, Tianshuai Hu, Alan Liang, Youquan Liu, Dongyue Lu, Liang Pan, Lingdong Kong, Junwei Liang, Ziwei Liu

We present 3EED, the first large-scale benchmark for 3D visual grounding across vehicles, drones, and quadrupeds, with over 134K 3D objects and 25K human-verified expressions in diverse outdoor scenes.

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies

#5016 · Dongyue Lu, Lingdong Kong, Gim Hee Lee, Camille Simon Chane, Wei Tsang Ooi

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

#4308 · Dekai Zhu, Yixuan Hu, Youquan Liu, Dongyue Lu, Lingdong Kong, Slobodan Ilic

Spiral is a new type of LiDAR generation model that enables semantic awareness and progressive diffusion.