R3-Streaming uses cascaded control, age-aware memory forgetting, and TB-GRPO reinforcement learning to reach SOTA scores on streaming video benchmarks while cutting visual token usage by 95-96%.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.
citing papers explorer
-
An Efficient Streaming Video Understanding Framework with Agentic Control
R3-Streaming uses cascaded control, age-aware memory forgetting, and TB-GRPO reinforcement learning to reach SOTA scores on streaming video benchmarks while cutting visual token usage by 95-96%.
-
How Adversarial Environments Mislead Agentic AI?
Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.