Jiajun Li
12 papers · 2024–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (25) ποΈ Keyword Collector (64)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Deep Learning
(8)
Computer Vision
(7)
Machine Learning
(6)
Models
(6)
Artificial Intelligence
(5)
Core AI
(5)
Generation
(5)
Application Areas
(4)
Optimization & Theory Β· Machine Learning
(3)
Optimization & Theory Β· Deep Learning
(3)
Computer Science
(2)
Applications
(2)
Architectures
(2)
Processing
(2)
Mathematics & Optimization
(1)
Keywords
diffusion model
(5)
image generation
(3)
generative model
(2)
preference learning
(2)
text-to-image diffusion
(2)
backdoor defense
(1)
image synthesis
(1)
model robustness
(1)
knowledge distillation
(1)
text-to-image synthesis
(1)
text classification
(1)
human-in-the-loop learning
(1)
flow matching
(1)
neural network optimization
(1)
low-resource language
(1)
attention mechanism
(1)
preference modeling
(1)
model alignment
(1)
image restoration
(1)
adversarial learning
(1)
Papers
SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
AAAI 2026
Where, What, Why: Toward Explainable 3D-GS Watermarking
CVPR 2026
Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
ICCV 2025
Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction
AAAI 2025
Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
IJCNLP 2025
LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
ICCV 2025
NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation
ICCV 2025
ProReflow: Progressive Reflow with Decomposed Velocity
CVPR 2025
Single Image Rolling Shutter Removal with Diffusion Models
AAAI 2025
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
NeurIPS 2024
RecDiffusion: Rectangling for Image Stitching with Diffusion Models
CVPR 2024
SAFETY-J: Evaluating Safety with Critique
EMNLP 2024