Harsh Kohli

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Architecture Design (Transformers, SSMs, MoE) (1)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Srinivasan Parthasarathy (1)Huan Sun (1)Yuekun Yao (1)

Papers (1)

Apr 9, 2026

Harsh Kohli +32w ago·also Ohio State

Loop, Think,&Generalize: Implicit Reasoning in Recurrent-Depth Transformers

Recurrent-depth transformers don't just memorize facts, they learn to *reason* with them, unlocking systematic generalization and depth extrapolation that eludes standard transformers.

Harsh Kohli, Srinivasan Parthasarathy, Huan Sun +1

Architecture Design (Transformers, SSMs, MoE)Reasoning & Chain-of-Thought

Search

Harsh Kohli

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)