Co-occurring keywords · papers mentioning both
multi-passage reading comprehension
(1)
dynamic self-attention
(1)
cross-passage information
(1)
gated token selection
(1)
region-level understanding
(1)
video region comprehension
(1)
token mark
(1)
long-range dependencies
(1)
referring expression comprehension
(1)
multimodal large language model
(1)
Papers
LongAttn: Selecting Long-context Training Data via Token-level Attention
ACL 2025
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
CVPR 2025
Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension
ACL 2019