Article
Did GPT 5.2 make a breakthrough discovery in theoretical physics?
•
56
Quentin Gallouédec PRO
qgallouedec
AI & ML interests
None yet
Recent Activity
updated
a dataset about 2 hours ago
hf-doc-build/doc-build-dev reacted
to
sergiopaniego's
post with 🚀 about 4 hours ago
What happens when you make an LLM drive a car where physics are real and actions can't be undone?
I ported CARLA, the autonomous driving simulator, to OpenEnv and added training support via TRL + Hugging Face Spaces.
The model interacts with the simulator through tool calls (observe, brake, change lane) and learns from a reward signal.
In 50 training steps, Qwen 0.6B learns to swerve and brake to avoid pedestrians in emergency situations.
The project supports text and vision (VLMs can see through a camera sensor), open-world driving with traffic, and multiple driving scenarios.
This builds on the carla-env project by sinatras, which originally placed LLMs inside CARLA for evaluation. We extended it with vision, new scenarios, rubric-based rewards, and made it trainable end-to-end.
Blog: https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl/
CARLA env in OpenEnv: https://github.com/meta-pytorch/OpenEnv/tree/main/envs/carla_env
Training script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla.py updated
a Space 1 day ago
qgallouedec/trackio-dev Organizations
upvoted 2 articles 3 days ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
•
465
upvoted a paper 6 days ago
upvoted a paper 11 days ago
upvoted an article 13 days ago
Article
Scaling OpenEnv: From Free Usage to Thousands of Concurrent Environments
•
11
upvoted 2 articles 17 days ago
Article
Transformers.js v4 Preview: Now Available on NPM!
•
72
Article
Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face
•
105
upvoted 3 papers 20 days ago
Rethinking the Trust Region in LLM Reinforcement Learning
Paper
• 2602.04879 • Published
• 35
Defeating the Training-Inference Mismatch via FP16
Paper
• 2510.26788 • Published
• 31
Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR
Paper
• 2602.05261 • Published
• 49
upvoted an article 27 days ago
Article
Preference Tuning LLMs with Direct Preference Optimization Methods
- +3
•
79
upvoted a collection 29 days ago
upvoted an article about 1 month ago
Article
Transformers v5: Simple model definitions powering the AI ecosystem
- +2
•
302
upvoted 4 papers about 1 month ago
Your Group-Relative Advantage Is Biased
Paper
• 2601.08521 • Published
• 155
Learn Your Reference Model for Real Good Alignment
Paper
• 2404.09656 • Published
• 90
Nash Learning from Human Feedback
Paper
• 2312.00886 • Published
• 18
Language Models are Few-Shot Learners
Paper
• 2005.14165 • Published
• 19
upvoted an article about 1 month ago
Article
Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models
•
109
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago