3 papers indexed
Minghao Hu, Lannan Luo, Allen Roush, Phillip Howard
Large language models are widely used for code generation, but they can also produce insecure programs due to patterns learned from their pretraining data. Decoding-time steering has become an important solution to this problem: a small expert model is combined with the target mo…
Phillip Howard, Xin Su, Allen Roush, Manikandan Ravikiran, Amir Abdullah
High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs. Recent advances in truncation-based sampling techniques have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater diversity in…
Trang Nguyen, Shuang Wu, Runyan Tan, Phillip Howard
While diffusion models achieve state-of-the-art image quality for text-to-image (T2I) generation, recent work has demonstrated that they suffer from sample diversity collapse. In this work, we investigate whether autoregressive (AR) image generation models can push the Pareto fro…