Shengyi Qian
12 papers · 2019–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🐝 Cross-Pollinator (8) 🌍 Conference Polyglot (5) 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6)
🌍
Conference Polyglot
(5)
🏃
Academic Marathon
(6)
🐝
Cross-Pollinator
(8)
🧬
Topic Evolution
💎
Century Club
(12)
🗃️
Keyword Collector
(73)
🔥
Unstoppable
(7)
Conferences
CVPR (6)
ICCV (3)
ECCV (1)
EMNLP (1)
NIPS (1)
Top co-authors
Keywords
3d vision
(2)
large language model
(2)
benchmark evaluation
(2)
domain adaptation
(2)
3d reconstruction
(2)
surface normal estimation
(1)
multimodal learning
(1)
pose estimation
(1)
self-supervised learning
(1)
dataset creation
(1)
domain generalization
(1)
depth estimation
(1)
object detection
(1)
video understanding
(1)
policy learning
(1)
scene understanding
(1)
3d scene understanding
(1)
visual grounding
(1)
embodied ai
(1)
robotic manipulation
(1)
Papers
3D-MVP: 3D Multiview Pretraining for Manipulation
CVPR 2025
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
EMNLP 2025
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
CVPR 2025
Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning
CVPR 2025
Multi-Object Hallucination in Vision Language Models
NIPS 2024
Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation
ICCV 2023
Understanding 3D Object Interaction from a Single Image
ICCV 2023
Understanding 3D Object Articulation in Internet Videos
CVPR 2022
Planar Surface Reconstruction From Sparse Views
ICCV 2021
OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
CVPR 2020
Associative3D: Volumetric Reconstruction from Sparse Views
ECCV 2020
Learning Single-Image Depth From Videos Using Quality Assessment Networks
CVPR 2019