collaborators

8 papers

cs.LG2026

MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning

Javier Lopez-Piqueres, Pranav Deshpande, Archan Ray +3

We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers. MetaTT enables flexible and parameter-efficient model adaptation by using a si…

cs.LG2026

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

Jamie Heredge, Mattia J. Villani, Pranav Deshpande +2

Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, a…

cs.AI2026

Entropy Distribution as a Fingerprint for Hallucinations in Generative Models

Mattia J. Villani, Pranav Deshpande, Akshay Seshadri +2

Large Language Models (LLMs) often generate factually incorrect outputs, commonly termed hallucinations, that undermine trust and limit deployment in high-stakes settings. Existing…

cs.LG2026

Anytime Training with Schedule-Free Spectral Optimization

Anuj Apte, Pranav Deshpande, Niraj Kumar +2

Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Sch…

cs.HC2026

Designing Digital Humans with Ambient Intelligence

Mengyu Chen, Pranav Deshpande, Runqing Yang +4

Digital humans are lifelike virtual agents capable of natural conversation and are increasingly deployed in domains like retail and finance. However, most current digital humans op…

cs.LG2025

A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values

Tyler Chen, Akshay Seshadri, Mattia J. Villani +7

Shapley values have emerged as a critical tool for explaining which features impact the decisions made by machine learning models. However, computing exact Shapley values is diffic…