A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.
Cheap and quick: Efficient vision-language instruction tuning for large language mod- els.Advances in Neural Information Processing Systems, 36:29615–29627, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Character-Centered Dialogue Generation from Scene-Level Prompts
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.