9 citations · 27 across the 13 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.AI2025
Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning
Mehrdad Zakershahrak
Reinforcement learning has traditionally focused on a singular objective: learning policies that select actions to maximize reward. We challenge this paradigm by asking: what if we…
cs.CL2025
H-Net++: Hierarchical Dynamic Chunking for Tokenizer-Free Language Modelling in Morphologically-Rich Languages
Mehrdad Zakershahrak, Samira Ghodratnama
Byte-level language models eliminate fragile tokenizers but face computational challenges in morphologically-rich languages (MRLs), where words span many bytes. We propose H-NET++,…