DFA-GPT, an instruction-tuned multimodal LLM trained on the new DFA-Instruct dataset, answers questions about whether a face is fake, what technique was used, and what artifacts reveal it.
Gpt-4v (ision) system card
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Interactive Deepfake Analysis
DFA-GPT, an instruction-tuned multimodal LLM trained on the new DFA-Instruct dataset, answers questions about whether a face is fake, what technique was used, and what artifacts reveal it.