Research

cool research stuff

  1. Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs SFT Finetuned Models

    Antyabha Rahman, Akshaj Gurugubelli, Omar Ankit, Kevin Zhu, Aishwarya Balwani

    Investigating how reinforcement learning and supervised fine-tuning shape internal representations for mathematical reasoning.

    AAAI 2026 Workshop on XAI4Science, 2026OpenReviewarXiv