conftrace_

tree attention

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

speculative decoding (2) token recycling (1) breadth-first search (1) long-context inference (1) large language model (1) lossless acceleration (1) sememe knowledge base (1) sememe prediction (1) sememe tree (1) shared prefix (1)

Papers

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026 DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference ICLR 2025 Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling ACL 2025 Going “Deeper”: Structured Sememe Prediction via Transformer with Tree Attention ACL 2022