Co-occurring keywords · papers mentioning both
disentangled spatial temporal representation
(1)
action-scene hallucination
(1)
decoder-only transformer models
(1)
multi pass-progressive inference
(1)
single pass-progressive inference
(1)
sub-sequence level attributions
(1)
video large language model
(1)
spatial-temporal representation
(1)
masked attention
(1)
intermediate prediction
(1)
Papers
MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
CVPR 2025
Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
ICML 2024