KU-AGI

Popular repositories Loading

1. Slot-MLLM Slot-MLLM Public

   Official implementation of "Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM"

   Python 5

2. OSPO OSPO Public

   [CVPR2026] Official implementation of "OSPO: Object-centric Self-improving Preference Optimization for Text-to-Image Generation"

   Python 2

3. FiRe FiRe Public

   [NeurIPS 2026] Official implementation of Fire: Enhanced Text-to-Image Generation by Fine-grained Multimodal Reasoning

   Python 2

4. Q-SPT Q-SPT Public

   Official implementation of "Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization"

   Python 2

5. Mol-LLM-submission Mol-LLM-submission Public

   This repository provide necessary code, model, and test dataset to reproduce results in the paper "Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization".

   Python 1

6. SG-PVR SG-PVR Public

   [EMNLP2026] Official implementation of "Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding"

   Python 1