Fabio Dias Rollo's picture

123 1205

Fabio Dias Rollo

fabiodr

·

AI & ML interests

Image synthesis, computer vision, physics simulation

Recent Activity

upvoted a paper about 5 hours ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

liked a dataset about 7 hours ago

zjunlp/WorFBench_test

liked a dataset about 7 hours ago

zjunlp/WorFBench_train

View all activity

Organizations

None yet

fabiodr's activity

upvoted a paper about 5 hours ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published 3 days ago • 54

upvoted 2 papers about 7 hours ago

Benchmarking Agentic Workflow Generation

Paper • 2410.07869 • Published Oct 10, 2024 • 26

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data

Paper • 2409.03810 • Published Sep 5, 2024 • 35

upvoted a paper 8 days ago

SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?

Paper • 2502.13233 • Published 10 days ago • 13

upvoted a paper 10 days ago

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Paper • 2502.12115 • Published 11 days ago • 41

upvoted a paper 14 days ago

WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation

Paper • 2502.08047 • Published 16 days ago • 25

upvoted 2 papers 15 days ago

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Paper • 2408.03910 • Published Aug 7, 2024 • 18

CodeRAG-Bench: Can Retrieval Augment Code Generation?

Paper • 2406.14497 • Published Jun 20, 2024 • 2

upvoted a collection 23 days ago

AceCoder

13 items • Updated 16 days ago • 6

upvoted an article 23 days ago

Article

Open-source DeepResearch – Freeing our search agents

25 days ago

• 1.11k

upvoted a paper 25 days ago

Magicoder: Source Code Is All You Need

Paper • 2312.02120 • Published Dec 4, 2023 • 82

upvoted an article 26 days ago

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Jan 23

• 143

upvoted a collection 27 days ago

VisRAG

Parsing-free RAG supported by VLMs • 9 items • Updated Oct 23, 2024 • 3

upvoted 2 papers 27 days ago

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Paper • 2410.10594 • Published Oct 14, 2024 • 26

McEval: Massively Multilingual Code Evaluation

Paper • 2406.07436 • Published Jun 11, 2024 • 40

upvoted an article 28 days ago

Article

How to run Gemini Nano locally in your browser

By

•

Jul 11, 2024

• 44

upvoted a collection 29 days ago

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated 16 days ago • 91

upvoted an article about 1 month ago

Article

We now support VLMs in smolagents!

Jan 24

• 86

upvoted 2 collections about 1 month ago

ColSmolVLM

Pre-trained checkpoints for the ColVision models with a ColSmolVLM backbone. • 2 items • Updated Jan 23 • 1

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated Jan 23 • 31