Yuehao Liu
4 papers · 2025–2026 · 3 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
Top co-authors
Research topics
Keywords
continual learning
(1)
catastrophic forgetting
(1)
abstraction refinement
(1)
formal verification
(1)
diffusion model
(1)
neural network verification
(1)
multimodal large language model
(1)
classifier-free guidance
(1)
image fidelity
(1)
neuron similarity
(1)
counterexample-guided refinement
(1)
network size reduction
(1)
two-stage fine-tuning
(1)
unconditional generation
(1)
gradient orthogonalization
(1)
plasticity stability balance
(1)
token swapping
(1)
self-swap guidance
(1)
Papers
Guiding a Diffusion Model by Swapping Its Tokens
CVPR 2026
Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models
CVPR 2026
Cross-Architecture Distillation Made Simple with Redundancy Suppression
ICCV 2025
Neuron Similarity-Based Neural Network Verification via Abstraction and Refinement
IJCAI 2025