MergeOver: Post-Training Token Merging for Recursive Vision Transformers

arXiv:2608.13141v1 Announce Type: new Abstract: Vision Transformers (ViTs) demonstrate exceptional performance in computer vision but suffer from large parameter counts and quadratic computational complexity, severely limiting their deployment on resource-constrained edge hardware. While recursive weight-sharing reduces parameter counts and token merging mitigates computational and memory bottlenecks, integrating these two paradigms without costly retraining is non-trivial, leaving this intersection largely unexplored. We propose MergeOver, a post-training approach that integrates Token Merging (ToMe) into the recursively weight-shared Sliced Recursive Transformer (SReT). Through an Unmerge tracking stack, constraint-safe merge-rate adjustment, and synchronised token-mass tracking across spatial permutations, MergeOver resolves the spatial and merging constraints of this integration. We further employ a stage-wise single-shot schedule that performs token reduction at the first block of each stage and maintains a fixed sequence length throughout its subsequent recursive iterations. Benchmarked on ImageNet-1K, our selected configuration reduces top-1 accuracy by 1.47 percentage points. On the GPU, it reduces peak activation memory by 37.3% and 38.4% at batch sizes 1 and 16, while throughput decreases by 21.7% at batch size 1 but increases by 21.7% at batch size 16. On a Raspberry Pi 5 (ARM CPU), it reduces latency by 2.4% and 17.6% at batch sizes 1 and 16. These results show that MergeOver can recover a meaningful part of the throughput and memory cost that recursive weight-sharing introduces, without retraining, and provides a baseline for combining token merging with hierarchical recursive transformers.

Related

• Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision
• RD-ViT: Recurrent-Depth Vision Transformer for Semantic Segmentation with Reduced Data Dependence Extending the Recurrent-Depth Transformer Architecture to Dense Prediction
• SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models
• Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
• Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers

Source: arXiv cs.CV | 2026-08-14