Tom Joy
5 papers · 2021–2024 · 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
(20)
🐣
Hot Topic Early Bird
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Models
(3)
Computer Vision
(1)
Natural Language Processing
(1)
Analysis
(1)
Architectures
(1)
Core Methods
(1)
Domain-Specific
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Keywords
variational autoencoder
(2)
uncertainty quantification
(1)
object detection
(1)
direct preference optimization
(1)
preference alignment
(1)
preference optimization
(1)
multimodal learning
(1)
autonomous driving
(1)
confidence calibration
(1)
conditional generation
(1)
shared representation
(1)
latent representation
(1)
out-of-distribution detection
(1)
mechanistic interpretability
(1)
safety fine-tuning
(1)
domain shift
(1)
temperature scaling
(1)
adversarial input
(1)
mlp weight transformation
(1)
jailbreak defense
(1)
Papers
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
NeurIPS 2024
Sample-Dependent Adaptive Temperature Scaling for Improved Calibration
AAAI 2023
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
CVPR 2023
Learning Multimodal VAEs through Mutual Supervision
ICLR 2022
Capturing Label Characteristics in VAEs
ICLR 2021