Pith. sign in

Gpt-4v (ision) system card

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Towards Interactive Deepfake Analysis

cs.CV · 2025-01-02 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Towards Interactive Deepfake Analysis cs.CV · 2025-01-02 · conditional · none · ref 6

    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.