Fabio Rollo's picture

Fabio Rollo

fabiodr

·

AI & ML interests

LLMs, Computer Vision, Physics Simulation, Image synthesis

Recent Activity

liked a model 5 days ago

TheCluster/YOLOv11-CoreML

liked a dataset 6 days ago

Tevatron/AgentIR-data

liked a model 6 days ago

lightonai/Agent-ModernColBERT

View all activity

Organizations

None yet

upvoted a collection 11 days ago

XTR Replicability

All the models used in experiments from "A Replicability Study of XTR" • 16 items • Updated 13 days ago • 6

upvoted a collection about 1 month ago

Gemma 4

64 items • Updated Apr 2 • 125

upvoted an article about 1 month ago

Article

Falcon Perception

tiiuae

•

Apr 1

• 67

upvoted an article about 2 months ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

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

•

Apr 2

• 895

upvoted 2 collections about 2 months ago

TranslateGemma

3 items • Updated Mar 12 • 238

Gemma 4

12 items • Updated 13 days ago • 820

upvoted a paper about 2 months ago

MJ1: Multimodal Judgment via Grounded Verification

Paper • 2603.07990 • Published Mar 9 • 1

upvoted 3 articles about 2 months ago

Article

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

+2

qgallouedec, stevhliu, pcuenq, sergiopaniego

•

Mar 31

• 51

Article

Training and Finetuning Reranker Models with Sentence Transformers

tomaarsen

•

Mar 26, 2025

• 194

Article

Transformers.js v4: Now Available on NPM!

Xenova, nico-martin

•

Feb 9

• 95

upvoted a collection about 2 months ago

Transformers.js V4 demos

A collection of demos built with Transformers.js V4 • 24 items • Updated Apr 16 • 58

upvoted a paper about 2 months ago

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

Paper • 2603.20105 • Published Mar 20 • 37

upvoted a collection about 2 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

upvoted 5 collections 2 months ago

PyLate 🐕

State-of-the-art late interaction models trained using PyLate • 7 items • Updated 6 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 Apr 7 • 22

👁️ LFM2.5-VL

13 items • Updated Apr 8 • 39

💧 LFM2.5

Collection of post-trained and base LFM2.5 models. • 30 items • Updated Apr 8 • 137

LateOn-Code 💻

State-of-the-art late interaction code retrieval models • 6 items • Updated Apr 7 • 20

upvoted an article 2 months ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

lightonai

•

Feb 12

• 56

upvoted an article 3 months ago

Article

ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models?

lightonai

•

Feb 19

• 21