Audio-Visual Dataset KU-AGI/commonvoice_dualcodec_pretokenize Updated Jul 16 • 13 KU-AGI/gigaspeech_dualcodec_pretokenize Updated Jul 16 • 14 KU-AGI/mls_dualcodec_pretokenize Updated Jul 16 • 14 KU-AGI/LibriSpeech_dualcodec_pretokenize Updated Jul 16 • 13
Slot-MLLM (ICML ver) KU-AGI/SlotTok Updated Mar 9 • 3 KU-AGI/Slot-MLLM-7B-instruct-ICML 7B • Updated Mar 10 • 5 KU-AGI/Slot-MLLM-14B-instruct-ICML 15B • Updated Mar 10 • 10
OSPO Object-centric Self-improving Preference Optimization for T2I KU-AGI/OSPO-Janus-Pro-7B-iter1 7B • Updated Apr 15 • 3 KU-AGI/OSPO-Janus-Pro-7B-iter2 7B • Updated Apr 15 • 5 KU-AGI/OSPO-Janus-Pro-1B-iter1 2B • Updated Apr 15 • 3 KU-AGI/OSPO-Janus-Pro-7B-iter2-data Viewer • Updated Sep 19, 2025 • 6.91k • 43
🔥 FiRe FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation Paper • 2604.13491 • Published May 26 • 1 KU-AGI/FiRe-SFT Text-to-Image • 7B • Updated 5 days ago • 26 KU-AGI/FiRe-300Step Text-to-Image • Updated 5 days ago • 17 KU-AGI/FiRe-2500Step Text-to-Image • 7B • Updated 5 days ago • 20
FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation Paper • 2604.13491 • Published May 26 • 1
Mol-LLM Collection of model, data used in the paper "Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization". KU-AGI/Mol-LLM 8B • Updated Dec 18, 2025 KU-AGI/Mol-LLM-wo-graph 8B • Updated Dec 18, 2025 KU-AGI/Mol-LLM-trainset Viewer • Updated Dec 18, 2025 • 3.31M • 18 • 1 KU-AGI/Mol-LLM-testset Viewer • Updated Dec 18, 2025 • 55.5k • 18 • 1
Audio-Visual Dataset KU-AGI/commonvoice_dualcodec_pretokenize Updated Jul 16 • 13 KU-AGI/gigaspeech_dualcodec_pretokenize Updated Jul 16 • 14 KU-AGI/mls_dualcodec_pretokenize Updated Jul 16 • 14 KU-AGI/LibriSpeech_dualcodec_pretokenize Updated Jul 16 • 13
🔥 FiRe FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation Paper • 2604.13491 • Published May 26 • 1 KU-AGI/FiRe-SFT Text-to-Image • 7B • Updated 5 days ago • 26 KU-AGI/FiRe-300Step Text-to-Image • Updated 5 days ago • 17 KU-AGI/FiRe-2500Step Text-to-Image • 7B • Updated 5 days ago • 20
FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation Paper • 2604.13491 • Published May 26 • 1
Slot-MLLM (ICML ver) KU-AGI/SlotTok Updated Mar 9 • 3 KU-AGI/Slot-MLLM-7B-instruct-ICML 7B • Updated Mar 10 • 5 KU-AGI/Slot-MLLM-14B-instruct-ICML 15B • Updated Mar 10 • 10
Mol-LLM Collection of model, data used in the paper "Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization". KU-AGI/Mol-LLM 8B • Updated Dec 18, 2025 KU-AGI/Mol-LLM-wo-graph 8B • Updated Dec 18, 2025 KU-AGI/Mol-LLM-trainset Viewer • Updated Dec 18, 2025 • 3.31M • 18 • 1 KU-AGI/Mol-LLM-testset Viewer • Updated Dec 18, 2025 • 55.5k • 18 • 1
OSPO Object-centric Self-improving Preference Optimization for T2I KU-AGI/OSPO-Janus-Pro-7B-iter1 7B • Updated Apr 15 • 3 KU-AGI/OSPO-Janus-Pro-7B-iter2 7B • Updated Apr 15 • 5 KU-AGI/OSPO-Janus-Pro-1B-iter1 2B • Updated Apr 15 • 3 KU-AGI/OSPO-Janus-Pro-7B-iter2-data Viewer • Updated Sep 19, 2025 • 6.91k • 43
