Muhammad Ferjad Naeem
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
PARCEL introduces a novel visual tokenization architecture that combines spatial pooling anchors with conditioned elastic queries, efficiently reducing the computational cost of large Vision-Language Models without sacrificing performance.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIcs.CLRecentMay 28, 2026
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
Selim Kuzucu, Alessio Tonioni, Vasile Lup, Bernt Schiele +2 more
PARCEL introduces a novel visual tokenization architecture that combines spatial pooling anchors with conditioned elastic queries, efficiently reducing the computational cost of large Vision-Language…
View →