3 papers
cs.CV2026
DOGS: Design-Space Sampling for Prompt-Driven Logo Generation
Ganyu Zou, Chen Dai, Nathan Self +5
Prompt optimization for text-to-image (T2I) generation has been pursued almost entirely as text rewriting, in which a short user brief is expanded into a longer, model-preferred to…
cs.CV2026
Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic Surgery
Chen Dai, Ganyu Zou, Nathan Self +5
Removing copyrighted, unsafe, or user-specified concepts from a deployed text-to-image diffusion model is now a practical requirement. Weight-editing methods can suppress fixed tar…
cs.NI2026
Efficient and Secure Discovery for AI Agents: The Case for DNS
Ramachandra Rao Seethiraju, Sameer Thakar, Karthik Shyamsunder +1
As Artificial Intelligence (AI) agents enter their next stage of ubiquitous deployment throughout the Internet, their discoverability will become a central challenge. The informati…