Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.
ArXiv , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Non-autoregressive ionic transport predictor learns dynamics from auxiliary trajectory data during training only, achieving over 200x speedup versus autoregressive models and lower error than non-autoregressive baselines on both dataset types.
DistilBERT compresses BERT by 40% via pre-training distillation with a triple loss, retaining 97% performance and running 60% faster.
A reasoning-distillation plus dual-reward GRPO method for multi-role dialogue summarization matches ROUGE and BERTScore baselines while improving factual faithfulness and preference alignment on CSDS and SAMSum.
A case-driven multi-agent system automates the full pipeline of bad-case detection, annotation, and resolution for e-commerce search relevance using Annotator, Optimizer, and User agents plus supporting components.
citing papers explorer
-
Fast Inference from Transformers via Speculative Decoding
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.
-
Teaching Molecular Dynamics to a Non-Autoregressive Ionic Transport Predictor
Non-autoregressive ionic transport predictor learns dynamics from auxiliary trajectory data during training only, achieving over 200x speedup versus autoregressive models and lower error than non-autoregressive baselines on both dataset types.
-
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
DistilBERT compresses BERT by 40% via pre-training distillation with a triple loss, retaining 97% performance and running 60% faster.
-
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization
A reasoning-distillation plus dual-reward GRPO method for multi-role dialogue summarization matches ROUGE and BERTScore baselines while improving factual faithfulness and preference alignment on CSDS and SAMSum.
-
A Case-Driven Multi-Agent Framework for E-Commerce Search Relevance
A case-driven multi-agent system automates the full pipeline of bad-case detection, annotation, and resolution for e-commerce search relevance using Annotator, Optimizer, and User agents plus supporting components.