Skip to content
conftrace_

token selection

36 papers

Explore in graph

Co-occurring keywords · papers mentioning both

attention mechanism (8) model compression (6) large language model (5) multimodal learning (4) efficient computing (3) parameter-efficient fine-tuning (3) inference optimization (3) large vision-language model (3) inference acceleration (3) kv cache (3)

Papers

TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding ACL 2025 TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection EMNLP 2025 TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning ICCV 2025 Uncertainty-Aware Contrastive Decoding ACL 2025 Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification CVPR 2024 Memory-Efficient Fine-Tuning of Transformers via Token Selection EMNLP 2024 What Are You Token About? Differentiable Perturbed Top-k Token Selection for Scientific Document Summarization ACL 2024 Max-Margin Token Selection in Attention Mechanism NeurIPS 2023 TRAMS: Training-free Memory Selection for Long-range Language Modeling EMNLP 2023 Document-level Event Factuality Identification via Reinforced Multi-Granularity Hierarchical Attention Networks IJCAI 2022 Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection ACL 2022