Barry-John Theobald
15 papers · 2019–2026 · 9 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 Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (37) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird
π
Renaissance Researcher
(5)
β
The Questioner
(3)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(84)
Top co-authors
Research topics
Artificial Intelligence
(11)
Machine Learning
(10)
Core AI
(9)
Learning Types Β· Machine Learning
(8)
Core Methods
(5)
Deep Learning
(4)
Natural Language Processing
(4)
Speech & Audio
(4)
Resources & Methods
(4)
Reinforcement Learning
(3)
Learning Paradigms
(3)
Learning Types Β· Deep Learning
(3)
Methods
(3)
Analysis
(2)
Application Areas
(2)
Keywords
self-supervised learning
(4)
speaker verification
(2)
large language model
(2)
policy learning
(2)
preference-based reinforcement learning
(2)
source localization
(2)
spatial audio
(2)
few-shot learning
(1)
sample efficiency
(1)
representation learning
(1)
direct preference optimization
(1)
data augmentation
(1)
test-time adaptation
(1)
reinforcement learning
(1)
out-of-distribution generalization
(1)
embedding space
(1)
language model alignment
(1)
speaker embedding
(1)
coreference resolution
(1)
entropy minimization
(1)
Papers
DSO: Direct Steering Optimization for Bias Mitigation
CVPR 2026
Aligning LLMs by Predicting Preferences from User Writing Samples
ICML 2025
Bias after Prompting: Persistent Discrimination in Large Language Models
EMNLP 2025
Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
ICML 2025
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
ICML 2025
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
ACL 2025
Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? Itβs Complicated
AAAI 2024
Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
Interspeech 2024
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
Interspeech 2024
Learning Spatially-Aware Language and Audio Embeddings
NeurIPS 2024
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
EMNLP 2024
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
WACV 2024
Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards
CoRL 2023
Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
Interspeech 2023
Mirroring to Build Trust in Digital Assistants
Interspeech 2019