2 papers
cs.LG2026
dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
Arnav Shah, Junzhe Li, Parsa Idehpour +7
Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff in their input representation. Standard fixed-vocabulary tokenizers fragment biol…
cs.CL2025
Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation
Nikita Mounier, Parsa Idehpour
A key challenge for iterative text generation is enabling models to efficiently identify and correct their own errors. We propose Review, Remask, Refine (R3), a relatively simple y…