Keqiang Sun
16 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π§ Keyword Pioneer π Cross-Pollinator (11) π Conference Polyglot (6) π Academic Marathon (6) π Renaissance Researcher (5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(30)
π
Conference Polyglot
(6)
π€
Dynamic Duo
(11)
π§¬
Topic Evolution
π
Century Club
(15)
ποΈ
Keyword Collector
(72)
π₯
Unstoppable
(5)
Conferences
ICCV (5)
ECCV (3)
NIPS (3)
AAAI (2)
ICLR (2)
CVPR (1)
Top co-authors
Keywords
diffusion model
(4)
text-to-image generation
(3)
human preference
(2)
facial landmark detection
(2)
image generation
(2)
self-supervised learning
(1)
preference learning
(1)
motion deblurring
(1)
depth estimation
(1)
image captioning
(1)
multi-modal learning
(1)
conditional generation
(1)
visual question answering
(1)
data-free learning
(1)
model alignment
(1)
preference optimization
(1)
face alignment
(1)
image processing
(1)
preference modeling
(1)
data augmentation
(1)
Papers
Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning
AAAI 2026
InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation
ICLR 2025
HPSv3: Towards Wide-Spectrum Human Preference Score
ICCV 2025
Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection
AAAI 2025
Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models
ICLR 2025
"BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events"
ECCV 2024
Phased Consistency Models
NIPS 2024
Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos
ECCV 2024
Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
ECCV 2024
JourneyDB: A Benchmark for Generative Image Understanding
NIPS 2023
Human Preference Score: Better Aligning Text-to-Image Models with Human Preference
ICCV 2023
NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space
ICCV 2023
Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
NIPS 2022
Inverting Generative Adversarial Renderer for Face Reconstruction
CVPR 2021
FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos
ICCV 2019
Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style Translation
ICCV 2019