Fabio Rollo's picture

Fabio Rollo

fabiodr

·

AI & ML interests

LLMs, Computer Vision, Physics Simulation, Image synthesis

Recent Activity

liked a Space about 5 hours ago

gemma-challenge/gemma-interactions-view

liked a model 2 days ago

baidu/Unlimited-OCR

liked a Space 2 days ago

akhaliq/Unlimited-OCR

View all activity

Organizations

None yet

upvoted 2 articles 3 days ago

Article

Party is over: regularizing ColBERT models to fix efficient ANN methods

lightonai

•

10 days ago

• 23

Article

DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models

lightonai

•

Apr 21

• 42

upvoted a collection 4 days ago

Tmax

Data and models associated with "Tmax: A simple recipe for terminal agents". paper: https://arxiv.org/abs/2606.23321 • 23 items • Updated 4 days ago • 12

upvoted a collection 25 days ago

Cosmos3

Omnimodal World Models for Physical AI • 16 items • Updated about 22 hours ago • 132

upvoted a collection 30 days ago

Bonsai Image

6 items • Updated 22 days ago • 87

upvoted a collection about 2 months ago

XTR Replicability

All the models used in experiments from "A Replicability Study of XTR" • 16 items • Updated May 5 • 7

upvoted a collection 3 months ago

Gemma 4

88 items • Updated 23 days ago • 146

upvoted 2 articles 3 months ago

Article

Falcon Perception

tiiuae

•

Apr 1

• 68

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 909

upvoted 2 collections 3 months ago

TranslateGemma

3 items • Updated Mar 12 • 245

Gemma 4

15 items • Updated 16 days ago • 992

upvoted a paper 3 months ago

MJ1: Multimodal Judgment via Grounded Verification

Paper • 2603.07990 • Published Mar 9 • 1

upvoted 3 articles 3 months ago

Article

TRL v1.0: Post-Training Library Built to Move with the Field

+2

qgallouedec, stevhliu, pcuenq, sergiopaniego

•

Mar 31

• 57

Article

Training and Finetuning Reranker Models with Sentence Transformers

tomaarsen

•

Mar 26, 2025

• 195

Article

Transformers.js v4: Now Available on NPM!

Xenova, nico-martin

•

Feb 9

• 96

upvoted a collection 3 months ago

Transformers.js V4 demos

A collection of demos built with Transformers.js V4 • 24 items • Updated Apr 16 • 65

upvoted a paper 3 months ago

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

Paper • 2603.20105 • Published Mar 20 • 37

upvoted 3 collections 3 months ago

CodeScout

RL-trained code search agents (1.7B, 4B, 14B) that outperform 2–18× larger models using only a Unix terminal. 📄 arxiv.org/abs/2603.17829 • 12 items • Updated Mar 19 • 8

PyLate 🐕

State-of-the-art late interaction models trained using PyLate • 7 items • Updated 2 days ago • 6

ColBERT-Zero 🐶

First large-scale fully pre-trained ColBERT model using only public data, outperforming GTE-ModernColBERT and GTE-ModernBERT • 10 items • Updated 2 days ago • 23