conftrace_

adaptive computation

39 papers

Explore in graph

Also known as

AC

Co-occurring keywords

efficient computing (781) computational efficiency (362) early exit (79) reinforcement learning (4352) model compression (3302) video recognition (109) convolutional neural network (4226) inference optimization (219) open-domain question answering (176) neural network (6616)

Papers

MARS: Multimodal Adaptive Reasoning Model for Avoiding Overthinking AAAI 2026
Adaptive Compute Efficient Learning via Conceptual-Criticality (Student Abstract) AAAI 2026
T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering EMNLP 2025
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning ACL 2025
Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference AAAI 2025
Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning EMNLP 2025
HARP: Hesitation-Aware Reframing in Transformer Inference Pass NAACL 2025
𝜙-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation ACL 2025
ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models CVPR 2025
Hierarchical Patch Diffusion Models for High-Resolution Video Generation CVPR 2024
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding EMNLP 2023
Adaptive Computation with Elastic Input Sequence ICML 2023
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation ACL 2023
Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels NIPS 2023
Scalable Adaptive Computation for Iterative Generation ICML 2023
AdaViT: Adaptive Vision Transformers for Efficient Image Recognition CVPR 2022
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition CVPR 2022
A-ViT: Adaptive Tokens for Efficient Vision Transformer CVPR 2022
PALBERT: Teaching ALBERT to Ponder NIPS 2022
MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation AAAI 2022
DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference ACL 2022
Confident Adaptive Language Modeling NIPS 2022
LeeBERT: Learned Early Exit for BERT with cross-level optimization ACL 2021
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition ICCV 2021