fabiodr (Fabio Dias Rollo)

upvoted a paper about 3 hours ago

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Paper • 2411.04905 • Published 3 days ago • 82

upvoted a paper 3 days ago

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Paper • 2410.02089 • Published Oct 2 • 10

upvoted a paper 11 days ago

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation

Paper • 2404.13026 • Published Apr 19 • 23

upvoted a paper 15 days ago

AutoTrain: No-code training for state-of-the-art models

Paper • 2410.15735 • Published 20 days ago • 55

upvoted 2 articles 18 days ago

Article

Transformers.js v3: WebGPU support, new models & tasks, and more…

19 days ago

• 58

Article

Deploying Speech-to-Speech on Hugging Face

19 days ago

• 33

upvoted a paper 18 days ago

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17 • 106

upvoted an article 19 days ago

Article

Virtual Try-On using IP-Adapter Inpainting

By

•

Jun 4

• 26

upvoted a paper 22 days ago

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25 • 73

upvoted a paper 24 days ago

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Paper • 2408.06195 • Published Aug 12 • 61

upvoted a collection 25 days ago

Gemma-APS Release

Collection

Gemma models for text-to-propositions segmentation. The models are distilled from fine-tuned Gemini Pro model applied to multi-domain synthetic data. • 3 items • Updated 26 days ago • 19

upvoted a paper 25 days ago

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Paper • 2410.08815 • Published 30 days ago • 41

upvoted an article 30 days ago

Article

Welcome, Gradio 5

Oct 9

• 66

upvoted a paper about 1 month ago

CoTracker: It is Better to Track Together

Paper • 2307.07635 • Published Jul 14, 2023 • 17

upvoted a collection about 1 month ago

Emu3

Collection

5 items • Updated 16 days ago • 64

upvoted a paper about 1 month ago

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

Paper • 2409.18042 • Published Sep 26 • 36

upvoted a paper about 2 months ago

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

Paper • 2409.14393 • Published Sep 22 • 7

upvoted an article about 2 months ago

Article

Document Similarity Search with ColPali

By

•

Sep 21

• 46

upvoted a collection about 2 months ago

Qwen2.5-Coder

Collection

Code-specific model series based on Qwen2.5 • 22 items • Updated 1 day ago • 92

upvoted a paper about 2 months ago

Imagine yourself: Tuning-Free Personalized Image Generation

Paper • 2409.13346 • Published Sep 20 • 67

Fabio Dias Rollo

AI & ML interests

Organizations

fabiodr's activity

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation

AutoTrain: No-code training for state-of-the-art models

Transformers.js v3: WebGPU support, new models & tasks, and more…

Deploying Speech-to-Speech on Hugging Face

OmniGen: Unified Image Generation

Virtual Try-On using IP-Adapter Inpainting

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Gemma-APS Release

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Welcome, Gradio 5

CoTracker: It is Better to Track Together

Emu3

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

Document Similarity Search with ColPali

Qwen2.5-Coder

Imagine yourself: Tuning-Free Personalized Image Generation