3 papers
cs.LG2026
Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
Ashim Dhor, Pin-Yu Chen
Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method t…
cs.AI2026
ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence
Ashim Dhor, Rasel Mondal, Pin-Yu Chen
Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and content-dependent pairwise interaction -- an…
cs.MA2025
Hierarchical Pedagogical Oversight: A Multi-Agent Adversarial Framework for Reliable AI Tutoring
Saisab Sadhu, Ashim Dhor
Large Language Models (LLMs) are increasingly deployed as automated tutors to address educator shortages; however, they often fail at pedagogical reasoning, frequently validating i…