conftrace_

token generation

57 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (22) speculative decoding (20) inference acceleration (10) inference optimization (8) autoregressive model (6) parallel decoding (4) language model inference (4) test-time scaling (3) autoregressive decoding (3) draft model (3)

Papers

SpecTr: Fast Speculative Decoding via Optimal Transport NeurIPS 2023 A Unified Sequence Interface for Vision Tasks NeurIPS 2022 Selective Token Generation for Few-shot Natural Language Generation COLING 2022 Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers NeurIPS 2021 Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation ICML 2021 Understanding Neural Abstractive Summarization Models via Uncertainty EMNLP 2020 The Importance of Generation Order in Language Modeling EMNLP 2018