LyraV uses FDTC and SToP for per-frame incremental decoding to reach 98.29% video synchrony at 3.89 FPS while preserving general understanding.
Streamready: Learning what to answer and when in long streaming videos,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
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 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
-
Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding
LyraV uses FDTC and SToP for per-frame incremental decoding to reach 98.29% video synchrony at 3.89 FPS while preserving general understanding.
-
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.