Barry-John Theobald
14 papers · 2019–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Academic Marathon (6) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (8) π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(32)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
β‘
Prolific Year
(6)
π
Trend Setter
β
The Questioner
(3)
π
Century Club
(14)
ποΈ
Keyword Collector
(61)
Conferences
INTERSPEECH (4)
ICML (3)
EMNLP (2)
AAAI (1)
ACL (1)
CORL (1)
NIPS (1)
WACV (1)
Top co-authors
Keywords
self-supervised learning
(4)
preference-based reinforcement learning
(2)
source localization
(2)
policy learning
(2)
spatial audio
(2)
speaker verification
(2)
entropy minimization
(1)
few-shot learning
(1)
representation learning
(1)
direct preference optimization
(1)
data augmentation
(1)
test-time adaptation
(1)
sample efficiency
(1)
language model alignment
(1)
speaker recognition
(1)
speaker embedding
(1)
out-of-distribution generalization
(1)
embedding space
(1)
cross-lingual alignment
(1)
contrastive learning
(1)
Papers
Bias after Prompting: Persistent Discrimination in Large Language Models
EMNLP 2025
Aligning LLMs by Predicting Preferences from User Writing Samples
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
Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
ICML 2025
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
WACV 2024
Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? Itβs Complicated
AAAI 2024
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
EMNLP 2024
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
INTERSPEECH 2024
Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
INTERSPEECH 2024
Learning Spatially-Aware Language and Audio Embeddings
NIPS 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