conftrace_

layer skipping

19 papers

Explore in graph

Co-occurring keywords

model compression (3302) inference efficiency (248) inference acceleration (244) large language model (13587) computational efficiency (362) dynamic computation (16) language model (4599) efficient inference (233) dynamic inference (34) early exiting (26)

Papers

Adaptive Compute Efficient Learning via Conceptual-Criticality (Student Abstract) AAAI 2026
CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025
Hopscotch: Discovering and Skipping Redundancies in Language Models EMNLP 2025
Router-Tuning: A Simple and Effective Approach for Dynamic Depth EMNLP 2025
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference AAAI 2025
FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction EMNLP 2025
DiffSkip: Differential Layer Skipping in Large Language Models ACL 2025
Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency ACL 2025
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models NIPS 2024
Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping EMNLP 2024
FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping EMNLP 2024
HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023
SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference IJCAI 2023
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model CVPR 2023
Stop or Forward: Dynamic Layer Skipping for Efficient Action Recognition WACV 2023
SkipBERT: Efficient Inference with Shallow Layer Skipping ACL 2022
Transkimmer: Transformer Learns to Layer-wise Skim ACL 2022
A User-Adaptive Layer Selection Framework for Very Deep Sequential Recommender Models AAAI 2021
Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020