PRPC reformulates CZSL as a five-step bidirectional reasoning process in an MLLM with GRPO-based RL post-training, achieving state-of-the-art on three benchmarks.
Event-centric multi-modal fusion method for dense video captioning.Neural Net- works, 146:120–129,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning
PRPC reformulates CZSL as a five-step bidirectional reasoning process in an MLLM with GRPO-based RL post-training, achieving state-of-the-art on three benchmarks.