1 citations · 1 across the 3 of their papers we have counts for
3 papers
CORE: Context-Robust Remasking for Diffusion Language Models
Kevin Zhai, Sabbir Mollah, Zhenyi Wang +1
Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions l…
The Telephone Game: Evaluating Semantic Drift in Unified Models
Sabbir Mollah, Rohit Gupta, Sirnam Swetha +3
Unified models (UMs) combine visual understanding (I2T) and generation (T2I) in a single framework. We focus on T2I and I2T, where cross-consistency---what a model understands, it…
LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting Recognition
Md. Ismail Hossain, Mohammed Rakib, Sabbir Mollah +2
Word-level handwritten optical character recognition (OCR) remains a challenge for morphologically rich languages like Bangla. The complexity arises from the existence of a large n…