AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference

• URL: http://arxiv.org/abs/2609.15131v1
• Date: Mon, 14 Sep 2026 07:07:51 GMT
• Title: AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
• Abstract summary: Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers.<n>We propose AdaVSkip, which equips each layer with two lightweight routers that independently determine whether visual tokens pass through by or skip the self-attention and modules.<n>AdaVSkip maintains strong task performance with substantially less computation.
• Score: 14.50173720268662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers. Most methods for efficient MLLM inference exploit horizontal redundancy by compressing visual tokens. Beyond token reduction, recent studies exploit vertical redundancy through early exit or fixed-layer skipping. However, we find that the extent and distribution of this redundancy vary across inputs and differ between self-attention and MLP modules. Motivated by these observations, we propose AdaVSkip, which equips each layer with two lightweight routers that independently determine whether visual tokens pass through by or skip the self-attention and MLP modules. These decisions collectively define an input-specific visual-computation path, but their discrete and non-differentiable nature makes learning effective paths challenging. To address this challenge, we develop a progressive two-stage training framework that updates only the routers while keeping the backbone frozen. Stage I establishes an initial routing policy through supervised training with input-specific targets derived from module-wise necessity scores. To further align the routing policy with task performance, Stage II uses reinforcement learning to optimize routing decisions with direct feedback from generated answers. It combines an answer correctness reward with a skip-consistency reward that discourages excessive retention of visual-token computation. Across three MLLM backbones, AdaVSkip maintains strong task performance with substantially less computation. On LLaVA-NeXT-7B, AdaVSkip reduces FLOPs by 53.2\% while preserving the original model's average performance. Combining it with visual token compression increases this reduction to 91.2\%, while retaining 97.2\% of the original performance on average.

Related papers

• ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs [77.57757084153083]
  We propose ERA, an Entropy-guided visual token pruning framework with Rectified Attention for efficient MLLMs.<n> ERA comprises three crucial components: Dual-view Entropy Pruning (DEP), Bias-aware Token Recycling (BTR), and Logit-preserving Attention Rectification (LAR)
  arXiv  Detail & Related papers  (2026-06-30T17:20:29Z)
• One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs [18.48496973561215]
  Large Vision-Language Models (LVLMs) have achieved remarkable success across diverse multimodal tasks, yet their practical deployment remains constrained by the computational burden arising from lengthy visual tokens.<n>We propose Adaptive Layer-wise Visual Token Selection (ALVTS), a novel framework that breaks away from the conventional static token pruning paradigm.<n>With an 89% token compression ratio, ALVTS retains 96.7% of the original model's accuracy, achieving a superior efficiency-accuracy trade-off for LVLM inference.
  arXiv  Detail & Related papers  (2026-06-12T08:58:58Z)
• Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs [89.7106332677868]
  We present Visual-Skip, a training-free inference paradigm that decouples spatial interaction from semantic evolution.<n>V-Skip effectively bypasses redundant vision attention to achieve block-wise sparsity, maintaining a 94.16% to 100.31% performance retention across diverse MLLMs.
  arXiv  Detail & Related papers  (2026-06-07T08:32:13Z)
• Stage-adaptive Token Selection for Efficient Omni-modal LLMs [17.161087166882744]
  We analyze the layer-wise token dependency of om-LLMs.<n>We propose a training-free, stage-adaptive token selection method for efficient om-LLM inference.
  arXiv  Detail & Related papers  (2026-05-19T15:55:16Z)
• Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference [68.4758228017823]
  ParVTS partitions visual tokens into subject and non-subject groups, processes them in parallel to transfer their semantics into question tokens, and discards the non-subject path mid-inference.<n>Experiments show that ParVTS prunes up to 88.9% of visual tokens with minimal performance drop, achieving 1.77x speedup and 70% FLOPs reduction.
  arXiv  Detail & Related papers  (2025-11-24T08:29:36Z)
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models [85.30893355216486]
  We study how visual token redundancy evolves with different dMLLM architectures and tasks.<n>Our study reveals that visual redundancy emerges only in from-scratch dMLLMs while handling long-answer tasks.<n>Layer-skipping is promising for accelerating AR-to-diffusion dMLLMs, whereas progressive or late-step pruning is more effective for from-scratch dMLLMs.
  arXiv  Detail & Related papers  (2025-11-19T04:13:36Z)
• $\mathcal{V}isi\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs [26.779915891040236]
  We propose emphVisiPruner, a training-free pruning framework that reduces up to 99% of vision-related attention computations and 53.9% of FLOPs on LLaVA-v1.5 7B.<n>Our insights further provide actionable guidelines for training efficient MLLMs by aligning model architecture with its intrinsic layer-wise processing dynamics.
  arXiv  Detail & Related papers  (2025-10-20T06:40:17Z)
• Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation [61.67090981767583]
  We introduce Mixture-of-Recursions (MoR), a unified framework that combines the two axes of efficiency inside a single Recursive Transformer.<n>MoR reuses a shared stack of layers across recursion steps to achieve parameter efficiency, while lightweight routers enable adaptive token-level thinking.<n>We also propose a KV sharing variant that reuses KV pairs from the first recursion, specifically designed to further decrease memory footprint.
  arXiv  Detail & Related papers  (2025-07-14T17:49:00Z)
• Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping [13.846838416902575]
  A key bottleneck stems from the proliferation of visual tokens required for fine-grained image understanding.<n>We propose Skip-Vision, a unified framework addressing both training and inference inefficiencies in vision-language models.<n> Experimental results demonstrate that Skip-Vision reduces training time by up to 35%, inference FLOPs by 75%, and latency by 45%.
  arXiv  Detail & Related papers  (2025-03-26T04:16:48Z)
• ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models [32.6661928486072]
  ATP-LLaVA is a novel approach that adaptively determines instance-specific token pruning ratios for each Large Language Model layer.<n>Our approach reduces the average token count by 75% while maintaining performance, with only a minimal 1.9% degradation across seven widely used benchmarks.
  arXiv  Detail & Related papers  (2024-11-30T11:42:35Z)
• Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training [55.12082817901671]
  We propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT)<n>MaPeT employs autoregressive and permuted predictions to capture intra-patch dependencies.<n>Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting.
  arXiv  Detail & Related papers  (2023-06-12T18:12:19Z)

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.