Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning
Paper • 2603.16189 • Published • 11
SelimAI
SelimAI
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 30 days ago
Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning liked a model about 1 month ago
InternSVG/InternSVG-8B new activity 2 months ago
microsoft/VibeVoice-ASR:Training loss is too highOrganizations
upvoted a paper 30 days ago
upvoted an article 3 months ago
Article
The Optimal Architecture for Small Language Models
•
120