Text-Centric Post-Training for Omni-Modal Reasoning
Improving joint audio-visual reasoning in Omni Large Language Models typically incurs substantial data construction and training costs. Our diagnostics reveal multi-hop reasoning difficulties despite correct answers to all corresponding single-hop questions and suggest partial decoupling in the local optimization of pe...
Zi-Yang Cheng, Yu-Hao Wang, Hong-Cheng Liu et al.
· 0 citations