Obliviate erases targeted concepts from autoregressive image generators via KL supervision on visual tokens over full trajectories, cutting nudity rates sharply on benchmarks while keeping general performance.
Analyzing the language of visual tokens
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.
citing papers explorer
-
Obliviate: Erasing Concepts from Autoregressive Image Generation Models
Obliviate erases targeted concepts from autoregressive image generators via KL supervision on visual tokens over full trajectories, cutting nudity rates sharply on benchmarks while keeping general performance.
-
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.