IPIBench evaluates MLLMs on interactive proactive intelligence in streaming videos, identifies unstable triggering and poor coordination, and proposes the training-free IPI-Agent framework to improve performance across settings.
Streamready: Learning what to answer and when in long streaming videos.arXiv preprint arXiv:2603.08620, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
StreamOV proposes evidence-guided long-short term memory and a hidden-state-driven trigger for efficient online audio-visual reasoning in streaming videos, along with the SOVBench benchmark for multi-turn evaluation.
citing papers explorer
-
IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
IPIBench evaluates MLLMs on interactive proactive intelligence in streaming videos, identifies unstable triggering and poor coordination, and proposes the training-free IPI-Agent framework to improve performance across settings.
-
StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
StreamOV proposes evidence-guided long-short term memory and a hidden-state-driven trigger for efficient online audio-visual reasoning in streaming videos, along with the SOVBench benchmark for multi-turn evaluation.