MPM: Mutual Pair Merging for Efficient Vision Transformers

• URL: http://arxiv.org/abs/2604.05718v1
• Date: Tue, 07 Apr 2026 11:16:18 GMT
• Title: MPM: Mutual Pair Merging for Efficient Vision Transformers
• Abstract summary: Mutual Pair Merging (MPM) is a training-free token aggregation module that forms mutual nearest-neighbor pairs in cosine space.<n>On ADE20K, MPM reduces per-image latency by up to 60% for ViT-Tiny on Raspberry Pi 5, and increases throughput by up to 20% on H100 with FlashAttention-2.
• Score: 2.3741226173924073
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Decreasing sequence length is a common way to accelerate transformers, but prior token reduction work often targets classification and reports proxy metrics rather than end-to-end latency. For semantic segmentation, token reduction is further constrained by the need to reconstruct dense, pixel-aligned features, and on modern accelerators the overhead of computing merge maps can erase expected gains. We propose Mutual Pair Merging (MPM), a training-free token aggregation module that forms mutual nearest-neighbor pairs in cosine space, averages each pair, and records a merge map enabling a gather-based reconstruction before the decoder so that existing segmentation heads can be used unchanged. MPM introduces no learned parameters and no continuous compression knob (no keep-rate or threshold). The speed-accuracy trade-off is set by a discrete insertion schedule. We benchmark end-to-end latency on an NVIDIA H100 GPU (with and without FlashAttention-2) and a Raspberry Pi 5 across standard segmentation datasets. On ADE20K, MPM reduces per-image latency by up to 60% for ViT-Tiny on Raspberry Pi 5, and increases throughput by up to 20% on H100 with FlashAttention-2 while keeping the mIoU drop below 3%. These results suggest that simple, reconstruction-aware, training-free token merging can translate into practical wall-clock gains for segmentation when overhead is explicitly accounted for.

Related papers

• N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation [68.47358899451255]
  N-vium is a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware.<n>N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits.
  arXiv  Detail & Related papers  (2026-05-13T08:46:17Z)
• Small Vision-Language Models are Smart Compressors for Long Video Understanding [73.65465038390771]
  Long-form video understanding relies on intent-driven efficiency rather than greedily padded context.<n>We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding.<n>Tests show Tempo compresses hour-long videos substantially below theoretical limits, proving true long-form video understanding relies on intent-driven efficiency.
  arXiv  Detail & Related papers  (2026-04-09T11:40:25Z)
• Breaking the KV Cache Bottleneck: Fan Duality Model Achieves O(1) Decode Memory with Superior Associative Recall [0.0]
  Fan Duality Model resolves tension between memory efficiency and associative recall in sequence modeling.<n>FDM separates sequence processing into two components: a wave component that compresses long-range patterns into a hidden state, and a particle component that retrieves specific tokens.<n>We propose Freeze-Scan, a two-phase training strategy that freezes the recurrent scan and optimize the cache jointly with embeddings.
  arXiv  Detail & Related papers  (2026-04-09T02:00:30Z)
• ToMA: Token Merge with Attention for Diffusion Models [8.079656935981193]
  Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity.<n>We propose Token Merge with Attention (ToMA), an off-the-shelf method that negates token reduction for GPU-aligned efficiency.<n>ToMA reduces SDXL/Flux generation latency by 24%/23%, respectively (with DINO $Delta 0.07$), outperforming prior methods.
  arXiv  Detail & Related papers  (2025-09-13T17:35:00Z)
• TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference [48.40143137402824]
  Multi-Head Latent Attention (MLA) compresses key-value states into a low-rank latent vector, caching only this vector to reduce memory.<n>In tensor parallelism (TP), however, attention heads are computed across multiple devices, and each device must load the full cache.<n>We propose-Parallel Latent Attention (TPLA), a scheme that partitions both the latent representation and each head's input dimension across devices, performs attention independently per shard, and then combines results with an all-reduce.
  arXiv  Detail & Related papers  (2025-08-21T15:25:40Z)
• QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization [7.188043811595143]
  Inference accounts for the majority of latency and energy consumption in large language models.<n>We introduce QuickSilver, a modular, token-level framework that enables semantic adaptivity at inference time without altering model weights or structure.
  arXiv  Detail & Related papers  (2025-06-27T17:10:32Z)
• Speedy MASt3R [68.47052557089631]
  MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme.<n>Fast MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy.<n>This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-03-13T03:56:22Z)
• CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs [89.79139531731637]
  Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks.<n>We propose a joint underlinecompression method for ViTs that achieves a harmonious blend of high underlineaccuracy, fast underlineinference speed, and favorable underlinetransferability to downstream tasks.
  arXiv  Detail & Related papers  (2023-09-27T16:12:07Z)
• SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers [76.13755422671822]
  This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework. We introduce a novel Attention-to-Mask (atm) module to design a lightweight decoder effective for plain ViT. Our decoder outperforms the popular decoder UPerNet using various ViT backbones while consuming only about $5%$ of the computational cost.
  arXiv  Detail & Related papers  (2023-06-09T22:29:56Z)
• Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration [138.24994198567794]
  iTPN is born with two elaborated designs: 1) The first pre-trained feature pyramid upon vision transformer (ViT) Fast-iTPN can accelerate the inference procedure by up to 70%, with negligible performance loss.
  arXiv  Detail & Related papers  (2022-11-23T06:56:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.