Nanjing University's VideoJev Answers Video Questions 129x Faster Without Decoding

A new family of video models skips autoregressive text generation to score time spans and answer options directly, hitting over 100x QA speedups.

Source

AlphaSignal

Published

Oct 13, 2026, 4:00 PM

Author

AlphaSignal Newsroom

Read

1 min read

A new family of video models skips autoregressive text generation to score time spans and answer options directly, hitting over 100x QA speedups.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Next reads