作者位次 #7/9ICLR 2026Poster· Reinforcement Learning / Everything Else
Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
Jiajun Fan · Roger Ren · Jingyuan Li · Rahul Pandey · Prashanth Gurunath Shivakumar · Ivan Bulyko · Ankur Gandhe · Ge Liu · Yile Gu