Tweet fijado
Just landed in San Diego to present "Head Pursuit: Probing Attention Specialization in Multimodal Transformers", our spotlight paper @NeurIPSConf!
Don't miss poster #1013 on Wednesday, Dec 3 at 11AM.
[1/6]
English
Lorenzo Basile
14 posts
Lorenzo Basile
@lorebasile
Postdoc @AreaSciencePark
Trieste, Italy Se unió Haziran 2020
282 Siguiendo43 Seguidores
Lorenzo Basile retuiteado
Steering generative models with LinEAS is:
– parameter-efficient
– fine-grained
– data-efficient
– robust across models and modalities
Come check it out at #NeurIPS2025!
🗓️ Dec 5 • 4:30–7:30 PM PST
📍 Exhibit Hall C,D,E #3604
Pau Rodríguez@prlz77
🚀 Excited to share LinEAS, our new activation steering method accepted at NeurIPS 2025! It approximates optimal transport maps e2e to precisely guide 🧭 activations achieving finer control 🎚️ with ✨ less than 32 ✨ prompts! 💻github.com/apple/ml-lineas 📄arxiv.org/abs/2503.10679
English
Lorenzo Basile retuiteado
Come find us at
NeurIPS Poster Session 6 #1114 4PM - 7PM
to hear how multimodal models develope localized image-text communication in their internal representations.
#NeurIPS2025
@alexserra1998 @francescortu @lorebasile @DiegoDoimo
Alessandro Pietro Serra@aleserra1998
Excited to present "The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models" at #NeurIPS2025 and #EurIPS2025! 📍NeurIPS: Poster Session 6 #1114 (Fri Dec 5 4pm-7pm) 📍EurIPS: Poster Session D3 #88 (Wed Dec 3 10:30am-12:30pm) 🧵👇
English
Amazing collaboration with @ValeMaiorca, @DiegoDoimo, @FrancescoLocat8 and @albecazzaniga.
📘 Paper: arxiv.org/abs/2510.21518
💻 Code: github.com/lorenzobasile/…
@AreaSciencePark @SapienzaRoma @ISTAustria
[6/6]
English
🌈 Property enhancement/inhibition
We can control image captioning with head-level interventions.
Rescaling heads specialized on colors or sentiments we can promote or remove related words, without finetuning.
[5/6]
English
Just landed in San Diego to present "Head Pursuit: Probing Attention Specialization in Multimodal Transformers", our spotlight paper @NeurIPSConf!
Don't miss poster #1013 on Wednesday, Dec 3 at 11AM.
[1/6]
English
Lorenzo Basile retuiteado
🤖Seminar Series
Next week, Giorgos Nikolaou and Tommaso Mencattini (@EPFL) will present "Language Models are Injective and Hence Invertible". @GiorgosNik02 @tommaso_mncttn
📅Nov 27, 11 CET (Online)
👉Register to attend: bit.ly/4ieKRYq
English
Lorenzo Basile retuiteado
Excited to share that 2/2 papers from our Lab (LADE) were accepted to #NeurIPS2025 (one spotlight 🎉)
Great work from all the students and collaborators involved!
@AreaSciencePark @aleserra1998 @lorebasile @francescortu @lucrevaleriani @DiegoDoimo @ansuin @FrancescoLocat8
English
Lorenzo Basile retuiteado
Thrilled to announce that our paper is accepted at #NeurIPS 2025!! See you in San Diego! 🇺🇸
francesco ortu@francescortu
🚨🚨 Excited to share our latest paper, now on @arxiv! 🖼️ We studied how unified VLMs, trained to generate both text and images (e.g., @MetaAI's Chameleon), exchange information between modalities, comparing them to standard VLMs. Deep dive:👇
English
Lorenzo Basile retuiteado
Lorenzo Basile retuiteado
I just landed in Vancouver to present @NeurIPSConf the findings of our new work!
Few-shot learning and fine-tuning change the hidden layers of LLMs in a dramatically different way, even when they perform equally well on multiple-choice question-answering tasks.
🧵1/6
English
Lorenzo Basile retuiteado
✨ Meet #ResiDual, a novel perspective on the alignment of multimodal latent spaces!
Think of it as a spectral "panning for gold" along the residual stream. It improves text-image alignment by simply amplifying task-related directions! 🌌🔍
arxiv.org/abs/2411.00246
[1/6]
English