Alessio Devoto
banner
alessiodevoto.bsky.social
Alessio Devoto
@alessiodevoto.bsky.social
PhD in ML/AI | Researching Efficient ML/AI (vision & language) 🍀 & Interpretability | @SapienzaRoma @EdinburghNLP | https://alessiodevoto.github.io/ | ex @NVIDIA
Reposted by Alessio Devoto
💡 We compare prompting (zero and multi-shot + explanations) and inference-time interventions (ActAdd, REFT and SAEs).

Following SpARE (@yuzhaouoe.bsky.social @alessiodevoto.bsky.social), we propose ✨ contrastive SAE steering ✨ with mutual info to personalize literary MT by tuning latent features 4/
May 23, 2025 at 12:23 PM
A Geometric Framework for Understanding Memorization in Generative Models : arxiv.org/abs/2411.00113
February 5, 2025 at 4:11 PM
The super weight in LLMs: arxiv.org/abs/2411.07191
Massive Activations in LLMs: arxiv.org/abs/2402.17762
February 4, 2025 at 5:55 PM
Semantic Hub Hypothesis: arxiv.org/abs/2411.04986
Do Llamas Work in English: arxiv.org/abs/2402.10588
December 22, 2024 at 5:57 PM
December 19, 2024 at 4:34 PM