Article
The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU
Weyaxi
• • 26
Abidoye Aanuoluwapo
Aanuoluwapo65
AI & ML interests
Computer vision and multimodal learning
Recent Activity
liked a model about 8 hours ago
PrimeIntellect/INTELLECT-3 upvoted an article 7 days ago
The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU upvoted an article 7 days ago
One sandbox per rollout, or how labs run RL for agents in 2026Organizations
upvoted 2
articles 7 days ago
Article
One sandbox per rollout, or how labs run RL for agents in 2026
sergiopaniego
• • 12 upvoted a paper 14 days ago
upvoted a paper 15 days ago
upvoted 2
articles 15 days ago
Article
What is MoE 2.0? Update Your Knowledge about Mixture-of-experts
Kseniase
• • 11 Article
Comprehensive Guide to Reinforcement Learning in Modern AI
ProCreations
• • 4 upvoted 2
articles 18 days ago
Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 151 Article
Transformers now runs llama.cpp quants
- +1
marcsun13, ArthurZ, lysandre
• • 118 upvoted 3
papers 18 days ago
CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
Paper • 2601.06352 • Published • 7
InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
Paper • 2609.31394 • Published • 31
AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs
Paper • 2609.31590 • Published • 13
upvoted 3
papers 21 days ago
AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation
Paper • 2609.29816 • Published • 12
Rufus-Air: An Open LLM Post-Training Recipe
Paper • 2609.29421 • Published • 44
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Paper • 2609.29845 • Published • 105
upvoted a changelog 21 days ago
Hugging Face Changelog
Live resource usage on Jobs
• 210
upvoted 5
papers 21 days ago
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
Paper • 2609.28923 • Published • 11
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Paper • 2609.28416 • Published • 44
Training Object Permanence in World Models
Paper • 2609.28654 • Published • 181
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
Paper • 2609.29892 • Published • 34
World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
Paper • 2609.29964 • Published • 15