Lichen Bai
5 papers · 2025–2026 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
⭐
Rising Star
(5)
Top co-authors
Research topics
Keywords
diffusion model
(3)
image generation
(2)
text-to-image synthesis
(1)
preference optimization
(1)
text-to-image generation
(1)
supervised fine-tuning
(1)
training acceleration
(1)
human preference
(1)
semantic prior
(1)
reward filtering
(1)
gradient dynamics
(1)
context compression
(1)
representation similarity
(1)
large language model
(1)
neural network
(1)
frozen language model
(1)
noise prompt learning
(1)
golden noise
(1)
noise perturbation
(1)
gradient coherence
(1)
Papers
Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective
CVPR 2026
CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
CVPR 2026
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
ACL 2026
Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers
AAAI 2025
Golden Noise for Diffusion Models: A Learning Framework
ICCV 2025