Eric Winsor — accepted AI-conference papers

2025

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

Xander Davies, Eric Winsor, Alexandra Souly, Tomek Korbak, Robert Kirk, Christian Schroeder de Witt +1

NeurIPS 2025poster

LLM developers deploy technical mitigations to prevent _fine-tuning misuse attacks_, attacks in which adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks against specific fine-tuning API defences; however, prior attacks t…

Cited by 0 Source ↗Scholar ↗

2025

Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models

Alexandre Variengien, Eric Winsor

ICLR 2025poster

When solving challenging problems, language models (LMs) are able to identify relevant information from long and complicated contexts. To study how LMs solve retrieval tasks in diverse situations, we introduce ORION, a collection of structured retrieval tasks spanning six domains, from text understa…

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

Scatterbrain: Unifying Sparse and Low-rank Attention

Beidi Chen, Tri Dao, Eric Winsor, Zhao Song, Atri Rudra, Christopher Ré

NeurIPS 2021poster

Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is still challenging to balance the trade-off between model quality and efficiency to p…

Cited by 152 Source ↗PDF ↗code ↗Scholar ↗