early exiting

Vision-MoR: Scaling Vision Transformer via Patch-Level Mixture-of-Recursions AAAI 2026 When Do Models Actually Decide? Mapping the Layer-Wise Decision Timeline in Pretrained Neural Networks CVPR 2026 COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning ICCV 2025 E4: Energy-Efficient DNN Inference for Edge Video Analytics via Early Exiting and DVFS AAAI 2025 Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection IJCAI 2025 A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models ICML 2024 ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference AAAI 2024 Fast yet Safe: Early-Exiting with Risk Control NeurIPS 2024 Jointly-Learned Exit and Inference for a Dynamic Neural Network ICLR 2024 Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting NeurIPS 2024 Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism ACL 2024 Understanding the Training Speedup from Sampling with Approximate Losses ICML 2024 Dynamic Perceiver for Efficient Visual Recognition ICCV 2023 Dynamic Voting for Efficient Reasoning in Large Language Models EMNLP 2023 Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding EMNLP 2023 HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023 You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model CVPR 2023 Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting COLING 2022 A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation ACL 2022 COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models EMNLP 2022 DeeCap: Dynamic Early Exiting for Efficient Image Captioning CVPR 2022 PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting NAACL 2022 Towards Efficient NLP: A Standard Evaluation and A Strong Baseline NAACL 2022 BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression EACL 2021