13 papers
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…
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…
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…
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…
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…
The Realignment Problem: When Right becomes Wrong in LLMs
Aakash Sen Sharma, Debdeep Sanyal, Manodeep Ray +3
Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinte…