activity
20172026
most citedLayer-wise training of deep networks using kernel similarity

16 citations · 36 across the 20 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

ArtMine: Discovering and Formalizing Artistic Processes

Kaustubh Kumar, Ashutosh Ranjan, Vivek Srivastava +2

Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent…

cs.LG2026

Democratic ICAI: Debating Our Way to Steering Principles from Preferences

Kevin Kingslin, Anish Natekar, Ashutosh Ranjan +3

Preference-based alignment often struggles to capture the reasoning that underlies human judgments. Many evaluations rely on multiple interacting criteria, yet pairwise labels reve…

cs.LG2026

The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation

Ninad Joshi, Ashutosh Ranjan, Vivek Srivastava +1

Generative text-to-image models are typically trained on large-scale web-scraped datasets that include diverse visual content such as copyrighted and stylistically distinctive artw…

cs.LG2026

Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

Aditya Kakade, Vivek Srivastava, Shirish Karande

Gödel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, Gödel agent for co…

cs.LG2026

Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models

Ashutosh Ranjan, Vivek Srivastava, Shirish Karande +1

Deployed text-to-image diffusion models increasingly require post-hoc concept unlearning for copyright claims, artist opt-outs, safety updates, and protected-content mitigation wit…

cs.LG2023

Can Physics Informed Neural Operators Self Improve?

Ritam Majumdar, Amey Varhade, Shirish Karande +1

Self-training techniques have shown remarkable value across many deep learning models and tasks. However, such techniques remain largely unexplored when considered in the context o…