AIConfPaper
← Search

Philip Alexander Teare

5 accepted papers

2025

Balancing Act: Diversity and Consistency in Large Language Model Ensembles

Ahmed Abdulaal, Chen Jin, Nina Montaña-Brown, Aryo Pradipta Gema, Daniel C. Castro, Daniel C. Alexander +4
ICLR 2025poster

Ensembling strategies for Large Language Models (LLMs) have demonstrated significant potential in improving performance across various tasks by combining the strengths of individual models. However, identifying the most effective ensembling method remains an open challenge, as neither maximizing out…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations

Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal, Tom Diethe, Philip Alexander Teare, Beatrice Alex +2
EMNLP 2025

Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads within the Transformer architecture, known as retrieval hea

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Diffusion Instruction Tuning

Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Alexander Teare
ICML 2025poster

We introduce *Lavender*, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion. Specifically, Lavender aligns the text-vision attention in the VLM transformer…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation

Zhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy +5
ICML 2025poster

Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning

Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Alexander Teare
ICML 2024poster

Textural Inversion, a prompt learning method, learns a singular text embedding for a new "word" to represent image style and appearance, allowing it to be integrated into natural language sentences to generate novel synthesised images. However, identifying multiple unknown object-level concepts with…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗