Junlong Tong

Untangling the mess of "streaming LLMs," this paper delivers a clear taxonomy that distinguishes between streaming generation, streaming inputs, and interactive architectures.

LVLMs can reason about video streams *much* faster and better by thinking concurrently with the incoming data, not in batches.

LLMs actually *do* improve time series forecasting, especially for cross-domain generalization, overturning prior doubts with a massive 8-billion observation study.