Tian Yu Liu
14 papers · 2012–2025 · 7 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (32)
π§
Keyword Pioneer
ποΈ
Keyword Collector
(68)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(11)
Artificial Intelligence
(7)
Deep Learning
(6)
Application Areas
(6)
Core AI
(5)
Core Methods
(5)
Learning Types Β· Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Architectures
(3)
Optimization & Theory
(3)
Computer Vision
(2)
Natural Language Processing
(2)
Security & Privacy
(2)
Analysis
(2)
Learning Paradigms
(2)
Keywords
depth estimation
(2)
gradient matching
(2)
adversarial perturbation
(2)
data poisoning
(2)
vision transformer
(1)
information retrieval
(1)
contrastive learning
(1)
domain adaptation
(1)
zero-shot learning
(1)
disparity estimation
(1)
self-supervised learning
(1)
data augmentation
(1)
transfer learning
(1)
image captioning
(1)
model unlearning
(1)
domain generalization
(1)
trajectory prediction
(1)
test-time adaptation
(1)
adversarial training
(1)
stochastic gradient descent
(1)
Papers
PICASO: Permutation-Invariant Context Composition with State Space Models
ICLR 2025
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
ECCV 2024
Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding
CVPR 2024
Meaning Representations from Trajectories in Autoregressive Models
ICLR 2024
Sub-token ViT Embedding via Stochastic Resonance Transformers
ICML 2024
Tangent Transformers for Composition,Privacy and Removal
ICLR 2024
Tangent Model Composition for Ensembling and Continual Fine-tuning
ICCV 2023
Train/Test-Time Adaptation With Retrieval
CVPR 2023
Data-Efficient Augmentation for Training Neural Networks
NeurIPS 2022
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack
NeurIPS 2022
Monitored Distillation for Positive Congruent Depth Completion
ECCV 2022
Not All Poisons are Created Equal: Robust Training against Data Poisoning
ICML 2022
Stereoscopic Universal Perturbations Across Different Architectures and Datasets
CVPR 2022
Contextual Sequence Prediction with Application to Control Library Optimization
RSS 2012