Kai Qiu
9 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (6) π Academic Marathon (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (18) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
AAAI (2)
CVPR (2)
ICCV (2)
ECCV (1)
ICLR (1)
WACV (1)
Top co-authors
Keywords
diffusion model
(3)
text-to-video generation
(2)
video generation
(2)
image generation
(1)
video restoration
(1)
human pose estimation
(1)
variational autoencoder
(1)
spatiotemporal modeling
(1)
density map
(1)
multimodal reasoning
(1)
dynamic graph
(1)
latent space
(1)
stable diffusion
(1)
image inpainting
(1)
density estimation
(1)
motion dynamics
(1)
graph convolutional network
(1)
crowd counting
(1)
efficient training
(1)
reinforcement learning
(1)
Papers
MageBench: Bridging Large Multimodal Models to Agents
WACV 2026
HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
AAAI 2026
REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents
ICCV 2025
ImageFolder: Autoregressive Image Generation with Folded Tokens
ICLR 2025
HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion
CVPR 2025
R^2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
ECCV 2024
MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
CVPR 2024
DGCN: Dynamic Graph Convolutional Network for Efficient Multi-Person Pose Estimation
AAAI 2020
Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting
ICCV 2019