TON Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models. kolerk/TON-3B-AITZ Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 1 kolerk/TON-3B-CLEVR Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 3 kolerk/TON-3B-Math Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 4 kolerk/TON-7B-Math Image-Text-to-Text • 8B • Updated Jul 14, 2025 • 6
TON Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models. kolerk/TON-3B-AITZ Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 1 kolerk/TON-3B-CLEVR Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 3 kolerk/TON-3B-Math Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 4 kolerk/TON-7B-Math Image-Text-to-Text • 8B • Updated Jul 14, 2025 • 6
