SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
Gptscore: Evaluate as you desire
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM safety judges flip verdicts on equivalent policy rewrites up to 9.1% of the time and cannot distinguish meaningful from meaningless changes, requiring new invariance-based reliability metrics.
citing papers explorer
-
SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
-
Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges
LLM safety judges flip verdicts on equivalent policy rewrites up to 9.1% of the time and cannot distinguish meaningful from meaningless changes, requiring new invariance-based reliability metrics.