Davi Ferreira

davifs's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 14 days ago

Running

Featured

451

HF Realtime Voice

🎙

451

Voice chat over WebSocket against a HF speech-to-speech

upvoted 3 papers 20 days ago

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Paper • 2606.28733 • Published 26 days ago • 148

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 24 days ago • 112

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published about 1 month ago • 31

upvoted a paper 21 days ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 27 days ago • 111

liked 2 models about 1 month ago

empero-ai/Qwable-9B-Claude-Fable-5-GGUF

Image-Text-to-Text • 9B • Updated Jun 19 • 49.7k • 70

empero-ai/Qwable-9B-Claude-Fable-5

Text Generation • 9B • Updated Jun 19 • 7.95k • • 106

liked a dataset about 1 month ago

Glint-Research/Fable-5-traces

Traces • Updated 23 days ago • 4.67k • 67.5k • 655

upvoted a paper about 1 month ago

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published Jun 17 • 141

liked 2 datasets about 1 month ago

openbmb/UltraData-SFT-2605

Viewer • Updated May 28 • 12.2M • 21.9k • 372

stanford-vision-lab/gpic

Updated Jun 4 • 73.6k • 146

liked 3 models about 1 month ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 1.73M • 2.77k

google/gemma-4-12B

Any-to-Any • 12B • Updated 7 days ago • 294k • 670

bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated 13 days ago • 333k • 664

upvoted a paper about 2 months ago

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Paper • 2605.31264 • Published May 29 • 124

upvoted 2 papers 3 months ago

KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance

Paper • 2604.12627 • Published Apr 14 • 102

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Paper • 2604.09497 • Published Apr 10 • 29

liked a model 3 months ago

meta-llama/Llama-3.2-3B

Text Generation • 3B • Updated Oct 24, 2024 • 564k • • 871

upvoted a paper 3 months ago

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Paper • 2604.04323 • Published Apr 6 • 41

liked a model 4 months ago

facebook/tribev2

Updated Mar 27 • 46.9k • 655