Papers with causal generation
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)
Copied to clipboard
| Challenge: | Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts. |
| Approach: | They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations. |
| Outcome: | The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding. |
COD3S: Diverse Generation with Discrete Semantic Signatures (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for generating semantically diverse sentences are based on locality-sensitive hash (LSH)-based semantic sentence codes that explicitly capture meaningful semantic differences. |
| Approach: | They propose a method for generating semantically diverse sentences using neural sequence-to-sequence models by conditioned on locality-sensitive hash-based semantic sentence codes whose Hamming distances correlate with human judgments of semantic textual similarity. |
| Outcome: | The proposed method improves output diversity without degrading performance on causal generation tasks. |