A controlled study on compact video LLMs finds that continuous temporal decoding delivers the strongest accuracy-efficiency trade-off for video temporal grounding across three benchmarks.
Self-chained image-language model for video localization and question answering.Advances in Neural Information Processing Systems, 36:76749–76771
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms
A controlled study on compact video LLMs finds that continuous temporal decoding delivers the strongest accuracy-efficiency trade-off for video temporal grounding across three benchmarks.