Question-in-the-Loop: Interleaved Query Tokens as Visual Summarizers for Video LLMs
Extending vision-language models (VLMs) to long-form video understanding is bottlenecked by the massive volume of visual tokens that incur quadratic prefill cost in the LLM decoder. Existing compression methods either discard tokens before the question is known (query-agnostic) or passively observe post-hoc attention p...