Smoothie performs diffusion by smoothing token embeddings based on semantic similarity, outperforming prior diffusion models on sequence-to-sequence and unconditional text generation tasks.
The spread of low-credibility content by social bots.Nature Communications, 9(1), November 2018
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Election tweet analysis shows 2024 content is mostly original with low lexical overlap and narrative-focused timing, unlike the high-repetition retweet patterns of 2016, suggesting a move to AI-assisted synthesis in cognitive operations.
citing papers explorer
-
Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation
Smoothie performs diffusion by smoothing token embeddings based on semantic similarity, outperforming prior diffusion models on sequence-to-sequence and unconditional text generation tasks.
-
Amplification to Synthesis: A Comparative Analysis of Cognitive Operations Before and After Generative AI
Election tweet analysis shows 2024 content is mostly original with low lexical overlap and narrative-focused timing, unlike the high-repetition retweet patterns of 2016, suggesting a move to AI-assisted synthesis in cognitive operations.