Srikar Appalaraju

7

Papers

83

Total Citations

1

Affiliations

Affiliations

Amazon

Papers (7)

DocFormerv2: Local Features for Document Understanding

Enhancing Vision-Language Pre-training with Rich Supervisions

VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding

No Head Left Behind – Multi-Head Alignment Distillation for Transformers

Scalable Enumeration of Trap Spaces in Boolean Networks via Answer Set Programming

LaTr: Layout-Aware Transformer for Scene-Text VQA

DocFormer: End-to-End Transformer for Document Understanding