Author

Aryan Chowdhury

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation

It is demonstrated that zeroing out a substantial fraction of attention heads prior to inference can significantly suppress verbatim memorisation while preserving, or even improving, language modelling performance on the benchmark used to identify redundant heads.

Aryan Chowdhury, R. Batista-Navarro · 0 citations

#machine learning Preprint Oct 2026

MOSAIC: Addressing Disproportionate Task-Modality Dependencies via Modality-Partitioned Gradient Routing

MOSAIC (MOdality-Separated Architecture with Inter-modal Cross-attention), which preserves unimodal representations while enabling controlled interaction between them, and uses modality-specific losses to route gradients to their corresponding partitions, demonstrates that modality partitioning yields consistent gains...

Aryan Chowdhury, Yi-Zheng Sun, Thomas Carroll et al. · 0 citations