9 papers
Vision-Language Binding in In-Context Image Generation
Chris Ge, Rohit Gandikota, Antonio Torralba +1
In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, re…
In-Context Algebra
Eric Todd, Jannik Brinkmann, Rohit Gandikota +1
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their in…
Distilling Diversity and Control in Diffusion Models
Rohit Gandikota, David Bau
Distilled diffusion models generate images in far fewer timesteps but suffer from reduced sample diversity when generating multiple outputs from the same prompt. To understand this…
When Are Concepts Erased From Diffusion Models?
Kevin Lu, Nicky Kriplani, Rohit Gandikota +4
In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly…
Erasing Conceptual Knowledge from Language Models
Rohit Gandikota, Sheridan Feucht, Samuel Marks +1
In this work, we introduce Erasure of Language Memory (ELM), a principled approach to concept-level unlearning that operates by matching distributions defined by the model's own in…
Discovering Forbidden Topics in Language Models
Can Rager, Chris Wendler, Rohit Gandikota +1
Refusal discovery is the task of identifying the full set of topics that a language model refuses to discuss. We introduce this new problem setting and develop a refusal discovery…