conftrace_

attention mask

29 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) vision transformer (1106) parallel decoding (74) parse tree (32) multi-turn reasoning (15) neural network (6616) token duplication (2) retrieval-augmented generation (1592) inference optimization (219) language model (4599)

Papers

SparseBERT: Rethinking the Importance Analysis in Self-attention ICML 2021
Non-autoregressive Machine Translation with Disentangled Context Transformer ICML 2020
Speaker-Utterance Dual Attention for Speaker and Utterance Verification INTERSPEECH 2020
AttentionRNN: A Structured Spatial Attention Mechanism ICCV 2019