Alon Ragoler(@alon_rag):multimodal LLMs are great but they have some key limitations preventing them from accomplishing general audio tasks, including some as basic as speaker-change detection!

Alon Ragoler

@alon_rag

Seattle, Berkeley '29-ish, research @DecagonAI

加入 May 2023

91 正在關注 94 粉絲

Alon Ragoler@alon_rag

2026.08.28 02:25

multimodal LLMs are great but they have some key limitations preventing them from accomplishing general audio tasks, including some as basic as speaker-change detection!

轉發到社區

熱門用戶

4.2M 粉絲

1.9M 粉絲

26.4M 粉絲

569.1K 粉絲

181.5K 粉絲

34.1K 粉絲

256.8K 粉絲

464.6K 粉絲

16.8M 粉絲

547.4K 粉絲

100.9K 粉絲

3.4M 粉絲

348.8K 粉絲

0 粉絲

10.5M 粉絲