DORA: Dynamic Online Reinforcement Agent for Token Pruning in Vision Transformers

arXiv:2609.34325 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Accuracy — 48× in this paper · explained in 1 episode
• Pruning — 47× in this paper · explained in 4 episodes
• Fidelity — 24× in this paper · explained in 2 episodes
• Actor — 23× in this paper · explained in 3 episodes
• Transformer — 20× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Dynamic Online Reinforcement Agent — 3× in this paper
• Embeddings — 3× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 3× in this paper · explained in 4 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptivity — 1× in this paper · explained in 1 episode
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Markov Decision Process (MDP) — 1× in this paper · explained in 11 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes

Sources

• Token Merging: Your ViT But Faster
• Representation Shift: Unifying Token Compression with FlashAttention
• Adaptive Token Sampling For Efficient Vision Transformers
• Agglomerative Token Clustering
• Natural Adversarial Examples
• Distilling the Knowledge in a Neural Network
• Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
• Reinforcement Learning-based Token Pruning in Vision Transformers: A Markov Game Approach
• DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Proximal Policy Optimization Algorithms
• Accelerating Transformers with Spectrum-Preserving Token Merging
• Gradient Surgery for Multi-Task Learning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models