Hugging Face's logo
William Suffill's picture
1 7 51

William Suffill

wsuff
shtefcs's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to merterbak's post with 👀 2 days ago
Qwen 3 can launch very soon. 👀 https://github.com/ggml-org/llama.cpp/pull/12828
reacted to MikeDoes's post with 🔥 12 days ago
🚀 We are quite excited to announce the Ai4Privacy Python library! 🎉 pip install ai4privacy to anonymize short english text with OpenPII Masking 500k labels 📊 Day 5/7 of PII Masking 1M announcements complete! ⏰
reacted to m-ric's post with ❤️ 12 days ago
🚀 DeepSeek R1 moment has come for GUI agents: Rule-based Reinforcement Learning gives better results than SFT with 500x smaller datasets! Traditionally (by which I mean "in the last few months"), GUI agents have been trained with supervised fine-tuning (SFT). This meant, collecting huge datasets of screen captures from people using computers, and using these to fine-tune your model. 📚 👉 But last week, a new paper introduced UI-R1, applying DeepSeek's R1-style rule-based reinforcement learning (RL) specifically to GUI action prediction tasks. This is big news: with RL, maybe we could build good agents without the need for huge datasets. UI-R1 uses a unified reward function that evaluates multiple responses from models, optimizing via policy algorithms like Group Relative Policy Optimization (GRPO). Specifically, the reward function assesses: 🎯 Action type accuracy: Does the predicted action match the ground truth? 📍 Coordinate accuracy (specifically for clicks): Is the predicted click within the correct bounding box? 📑 Output format: Does the model clearly articulate both its reasoning and final action? Using just 136 carefully selected mobile tasks—compared to 76,000 tasks for larger models like OS-Atlas—UI-R1 shows significant efficiency and improved performance: 📈 Boosted action prediction accuracy from 76% to 89% on AndroidControl. 🌐 Outperformed larger, SFT-trained models (e.g., OS-Atlas-7B), demonstrating superior results with vastly fewer data points (136 tasks vs. 76K). 🔍 Enhanced adaptability and generalization, excelling even in out-of-domain scenarios. The paper tests this RL-based method only in low-level GUI tasks. Could it generalize to more complex interactions? 🧐 Read the full paper here 👉 https://huggingface.co/papers/2503.21620
View all activity

Organizations

None yet

wsuff's activity

liked a model 24 days ago
liked a model about 1 month ago
liked a model about 2 months ago
liked 5 models 3 months ago
liked 2 models 4 months ago
liked a model 5 months ago
liked a model 6 months ago
liked a Space 7 months ago
liked 2 models 7 months ago
liked 3 models 8 months ago
liked a Space 8 months ago
liked a model 8 months ago