Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with
TurnWise improves streaming video understanding by assigning turn-level credit and balancing decision weights in group relative policy optimization.
Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Turns Matter: Advancing Streaming Video RL via Turn-Level Credit was first seen on Hugging Face · Daily papers on Nov 5, 2026. Since then it has appeared in 19 checks on 2 different days. Its best position was #1 of 30, reached on Nov 5, 11:28 UTC. It dropped off the list after Nov 6, 19:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 6, 19:28 UTC, after 2 days of trending.
#1 on Hugging Face · Daily papers, on Nov 5, 11:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 5, 2026 and has been on the list on 2 days (19 checks) since.