Zhili Liu
15 papers · 2020–2025 · 8 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (41) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π₯ Mega-Team Β· Squad
π€
Dynamic Duo
(10)
ποΈ
Keyword Collector
(75)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Deep Learning
(12)
Machine Learning
(9)
Artificial Intelligence
(6)
Learning Types Β· Deep Learning
(6)
Application Areas
(5)
Core AI
(5)
Models
(5)
Computer Vision
(4)
Learning Types Β· Machine Learning
(4)
Architectures
(3)
Techniques
(3)
Natural Language Processing
(2)
Learning Paradigms
(2)
Resources & Methods
(2)
Analysis
(1)
Keywords
self-supervised learning
(4)
diffusion model
(3)
representation learning
(2)
mixture of expert
(2)
domain adaptation
(2)
contrastive learning
(2)
vision-language model
(2)
multimodal learning
(2)
transfer learning
(2)
masked autoencoder
(2)
model compression
(2)
speech synthesis
(1)
knowledge distillation
(1)
speech processing
(1)
weakly supervised learning
(1)
visual perception
(1)
visual representation
(1)
model robustness
(1)
image reconstruction
(1)
data visualization
(1)
Papers
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
EMNLP 2025
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
CVPR 2025
Image-level Memorization Detection via Inversion-based Inference Perturbation
ICLR 2025
Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment
ACL 2025
TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models
WACV 2025
"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation"
ECCV 2024
Implicit Concept Removal of Diffusion Models
ECCV 2024
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
CVPR 2024
ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
ACL 2024
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning
ICCV 2023
Mixed Autoencoder for Self-Supervised Visual Representation Learning
CVPR 2023
Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
ICLR 2023
Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
ICLR 2023
Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing
AAAI 2022
EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement
AAAI 2020