Fabio Rollo's picture

227 1573

Fabio Rollo

fabiodr

·

AI & ML interests

LLMs, Computer Vision, Physics Simulation, Image synthesis

Recent Activity

liked a model 8 days ago

nvidia/canary-1b-v2

liked a Space 8 days ago

ekwek/Soprano-TTS

liked a model 8 days ago

ekwek/Soprano-80M

View all activity

Organizations

None yet

upvoted a collection 8 days ago

Parakeet

Nvidia's ASR models, now in MLX! • 10 items • Updated Aug 16, 2025 • 9

upvoted 3 articles 12 days ago

Article

Towards Open Evolutionary Agents

Aug 4, 2025

•

21

Article

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

Nov 3, 2025

•

53

Article

System Prompt Learning: Teaching LLMs to Learn Problem-Solving Strategies from Experience

Jun 2, 2025

•

23

upvoted an article about 1 month ago

Article

We Got Claude to Fine-Tune an Open Source LLM

Dec 4, 2025

•

558

upvoted a paper about 1 month ago

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published Nov 25, 2025 • 117

upvoted an article about 1 month ago

Article

Streaming datasets: 100x More Efficient

+3

Oct 27, 2025

•

77

upvoted a paper about 1 month ago

Prompt-MII: Meta-Learning Instruction Induction for LLMs

Paper • 2510.16932 • Published Oct 19, 2025 • 7

upvoted a collection about 2 months ago

EmbeddingGemma

3 items • Updated Sep 11, 2025 • 105

upvoted 2 articles about 2 months ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

Oct 23, 2025

•

62

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

Nov 5, 2025

•

57

upvoted a collection about 2 months ago

Tarka Embed V1

Efficient DFKD embeddings for language understanding • 5 items • Updated 19 days ago • 6

upvoted an article about 2 months ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15, 2025

•

222

upvoted a collection about 2 months ago

POTION

These are the flagship POTION models. Load them and use them with model2vec (https://github.com/MinishLab/model2vec) or sentence-transformers • 6 items • Updated Nov 13, 2025 • 14

upvoted a paper about 2 months ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29, 2025 • 36

upvoted 2 collections about 2 months ago

V-JEPA 2

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 181

Meta CLIP 1

Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 7 items • Updated Nov 24, 2025 • 21

upvoted 3 papers about 2 months ago

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models

Paper • 2502.09604 • Published Feb 13, 2025 • 37

Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine

Paper • 2510.21614 • Published Oct 24, 2025 • 22

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents

Paper • 2507.04009 • Published Jul 5, 2025 • 51