dynamic computation

COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 DiffSkip: Differential Layer Skipping in Large Language Models ACL 2025 Dynamic Diffusion Transformer ICLR 2025 Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking ACL 2025 MIND over Body: Adaptive Thinking using Dynamic Computation ICLR 2025 Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency ACL 2025 Mixture of Nested Experts: Adaptive Processing of Visual Tokens NeurIPS 2024 Adaptive Computation with Elastic Input Sequence ICML 2023 Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing EMNLP 2023 Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023 You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model CVPR 2023 Compute Cost Amortized Transformer for Streaming ASR Interspeech 2022 Multi-Dimensional Dynamic Model Compression for Efficient Image Super-Resolution WACV 2022 Faster Depth-Adaptive Transformers AAAI 2021 Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition NeurIPS 2021 Depth-Adaptive Transformer ICLR 2020 Resolution Adaptive Networks for Efficient Inference CVPR 2020 LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition NeurIPS 2019 Towards Dynamic Computation Graphs via Sparse Latent Structure EMNLP 2018