Ari Holtzman
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11How Alignment Shrinks the Generative Horizon
arXiv 2025
Byte Latent Transformer: Patches Scale Better Than Tokens
arXiv 2024
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
arXiv 2024
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
arXiv 2024
QLoRA: Efficient Finetuning of Quantized LLMs
NeurIPS 2023 11
Contrastive Decoding: Open-ended Text Generation as Optimization
arXiv 2022
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
arXiv 2022
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
EMNLP 2021 11
DEMix Layers: Disentangling Domains for Modular Language Modeling
NAACL 2022 7
The Curious Case of Neural Text Degeneration
ICLR 2020 1
Defending Against Neural Fake News
defending-against-neural-fake-news-1
Affiliations
Frequent co-authors
10from 11 papers