Picture for Barry-John Theobald

Barry-John Theobald

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models

Add code
Feb 21, 2025
Viaarxiv icon

Analyze the Neurons, not the Embeddings: Understanding When and Where LLM Representations Align with Humans

Add code
Feb 20, 2025
Viaarxiv icon

Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models

Add code
Dec 04, 2024
Viaarxiv icon

PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories

Add code
Oct 08, 2024
Viaarxiv icon

Learning Spatially-Aware Language and Audio Embedding

Add code
Sep 17, 2024
Figure 1 for Learning Spatially-Aware Language and Audio Embedding
Figure 2 for Learning Spatially-Aware Language and Audio Embedding
Figure 3 for Learning Spatially-Aware Language and Audio Embedding
Figure 4 for Learning Spatially-Aware Language and Audio Embedding
Viaarxiv icon

Towards Automatic Assessment of Self-Supervised Speech Models using Rank

Add code
Sep 16, 2024
Viaarxiv icon

Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models

Add code
Sep 16, 2024
Figure 1 for Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models
Figure 2 for Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models
Figure 3 for Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models
Figure 4 for Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models
Viaarxiv icon

Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels

Add code
Sep 16, 2024
Viaarxiv icon

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization

Add code
Sep 05, 2024
Figure 1 for On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Figure 2 for On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Figure 3 for On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Figure 4 for On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Viaarxiv icon

Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards

Add code
Feb 28, 2024
Viaarxiv icon