Debopam Sanyal — accepted AI-conference papers

2026

DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation

Divyansh Srivastava, Akshay Mehra, Pranav Maneriker, Debopam Sanyal, Vishnu Raj, Vijay Kamarshi +2

CVPR 2026

Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present DPAR, a novel decoder-only autoregressive model that dynami

Cited by 0 Source ↗code ↗Scholar ↗

2026

KLAS: Using Similarity to Stitch Neural Networks for an Improved Accuracy-Efficiency Tradeoff

Debopam Sanyal, Anantharaman S. Iyer, Alind Khare, Trisha Jain, Akshay Jajoo, Myungjin Lee +2

ICLR 2026poster

Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent work demonstrates that stitching pretrained models within a model family enables cost-effective interpolation of the accuracy-efficiency tradeoff space.…

Cited by 0 Source ↗Scholar ↗