EFlow separates temporal grounding from logical reasoning via two CoT stages and adds confidence-aware reflection, trained via SFT and RL on custom trajectory data, yielding gains on five video benchmarks.
Title resolution pending
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
-
EFlow: Learning Evidence Flow for Long-Video Reasoning with Adaptive Reflection
EFlow separates temporal grounding from logical reasoning via two CoT stages and adds confidence-aware reflection, trained via SFT and RL on custom trajectory data, yielding gains on five video benchmarks.