R. Manmatha

6

Papers

68

Total Citations

Papers (6)

DocFormerv2: Local Features for Document Understanding

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

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

Scaling up Image Segmentation across Data and Tasks

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

On the Scalability of Diffusion-based Text-to-Image Generation