MLLMs know event timing during prefill via sparse Temporal Grounding Heads but lose it in autoregressive decoding; restricting visual context to the high-attention interval at inference time improves VTG performance on three benchmarks.
Tempo-r0: A video-mllm for temporal video grounding through efficient temporal sensing reinforcement learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it