Yunyang Xiong
19 papers · 2017–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
๐ Renaissance Researcher (5) ๐ Interdisciplinary Bridge ๐ Conference Polyglot (6) ๐ Academic Marathon (8) ๐บ๏ธ Taxonomy Completionist (36)
๐ฃ
Hot Topic Early Bird
๐
Conference Polyglot
(6)
๐
Academic Marathon
(8)
โก
Prolific Year
(5)
๐
Century Club
(19)
๐๏ธ
Keyword Collector
(89)
โ
The Questioner
๐ฅ
Unstoppable
(5)
Conferences
CVPR (8)
ICCV (4)
ICML (4)
AAAI (1)
ACL (1)
NIPS (1)
Top co-authors
Keywords
neural architecture search
(3)
vision transformer
(3)
model compression
(2)
segment anything model
(2)
video segmentation
(1)
object detection
(1)
semantic segmentation
(1)
efficient computing
(1)
knowledge distillation
(1)
machine translation
(1)
data augmentation
(1)
multimodal learning
(1)
convergence analysis
(1)
point cloud
(1)
efficient inference
(1)
attention mechanism
(1)
3d vision
(1)
flow matching
(1)
point cloud generation
(1)
image segmentation
(1)
Papers
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
ICCV 2025
EdgeTAM: On-Device Track Anything Model
CVPR 2025
Agent-as-a-Judge: Evaluate Agents with Agents
ICML 2025
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
ICML 2025
Efficient Track Anything
ICCV 2025
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
CVPR 2024
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
ACL 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
ICML 2024
Self-Positioning Point-Based Transformer for Point Cloud Understanding
CVPR 2023
Fast Point Cloud Generation With Straight Flows
CVPR 2023
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
CVPR 2023
SageMix: Saliency-Guided Mixup for Point Clouds
NIPS 2022
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
ICML 2021
Nystrรถmformer: A Nystrรถm-based Algorithm for Approximating Self-Attention
AAAI 2021
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
CVPR 2021
Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
ICCV 2019
Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains
ICCV 2019
Mixed Effects Neural Networks (MeNets) With Applications to Gaze Estimation
CVPR 2019
Filter Flow Made Practical: Massively Parallel and Lock-Free
CVPR 2017