SceneGraphVLM generates dynamic scene graphs from video using compact VLMs, TOON serialization, and hallucination-aware RL to improve precision and achieve one-second latency.
Compile scene graphs with reinforcement learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
A 241M multi-task student trained with suffix identity, VAR loss, and a decoupled Q2L head matches or beats most VLMs and safety APIs on grounded sensitive scene graphs at 7.6× lower latency.
OracleAnalyser applies post-training and a new Stable Focal Preference Optimization algorithm to a 3B MLLM for oracle bone script analysis, releasing datasets and a benchmark where the small model outperforms larger ones.
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.
-
SenBen: Sensitive Scene Graphs for Explainable Content Moderation
A 241M multi-task student trained with suffix identity, VAR loss, and a decoupled Q2L head matches or beats most VLMs and safety APIs on grounded sensitive scene graphs at 7.6× lower latency.
-
OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training
OracleAnalyser applies post-training and a new Stable Focal Preference Optimization algorithm to a 3B MLLM for oracle bone script analysis, releasing datasets and a benchmark where the small model outperforms larger ones.