Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

• URL: http://arxiv.org/abs/2606.24156v1
• Date: Tue, 23 Jun 2026 05:24:50 GMT
• Title: Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction
• Abstract summary: We show that attention is often dominated by a model-induced prior in Multimodal Large Language Models (MLLMs)<n>We propose Prior-Corrected Token Reduction (PriorTR) to separate task-conditioned attention from the model-induced prior.<n>PriorTR consistently improves the trade-off between accuracy and efficiency over strong training-free baselines.
• Score: 42.23525789989544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune tokens by ranking text-visual attention scores. However, we show that attention is often dominated by a model-induced prior: even without textual instruction, MLLMs tend to focus on certain task-agnostic regions. Consequently, the attention scores of instruction-conditioned tokens are suppressed, increasing the risk that these tokens are discarded during pruning. To address this issue, we propose Prior-Corrected Token Reduction (PriorTR), a training-free token reduction method that explicitly separates task-conditioned attention from the model-induced prior. PriorTR estimates the attention map of the prior, and contrasts it with the task-conditioned attention distribution to measure the additional usable information contributed by each visual token. Importantly, PriorTR computes both the model-induced prior and the task-conditioned posterior within a single forward pass by introducing a null token that serves as an instruction-agnostic probe in the attention block. This design avoids duplicated propagation. Extensive experiments across multiple multimodal benchmarks and MLLMs demonstrate that PriorTR consistently improves the trade-off between accuracy and efficiency over strong training-free baselines, particularly under aggressive token budgets.

Related papers

• Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models [86.02826269126308]
  We propose Trend-aware Pruning, a novel framework that elevates pruning from a local snapshot decision to a temporal trajectory modeling problem.<n>This enables a dynamic rectification mechanism that selectively reactivates "late-blooming" tokens, those initially undervalued but exhibiting rising semantic importance, thereby preventing the loss of critical visual cues.
  arXiv  Detail & Related papers  (2026-07-30T15:07:00Z)
• 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)
• Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models [75.27089289058613]
  We introduce textbfTIES (textbfTau-guided textbfInter-layer textbfEfficient textbfSelection), a dynamic framework guided by inter-layer token ranking consistency.<n>On the CogACT + SIMPLER benchmark, TIES improves average success rates by 6% while reducing token usage by 78%, and demonstrate strong generalization across diverse decoders and benchmarks.
  arXiv  Detail & Related papers  (2026-03-26T02:13:03Z)
• ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models [7.7352936204066]
  We propose a novel, zero-shot method to model visual token pruning as a balance between task relevance and information diversity.<n>Our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss.<n>These gains are accompanied by significant reductions in GPU memory footprint and inference latency.
  arXiv  Detail & Related papers  (2025-10-20T06:18:47Z)
• FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution [3.4666771782038652]
  Large language models (LLMs) owe much of their stellar performance to expansive input contexts, yet such verbosity inflates monetary costs, carbon footprint, and inference-time latency.<n>We introduce FrugalPrompt, a novel prompt compression framework for LLMs, which retains only the most semantically significant tokens.<n>We evaluate the approach across four NLP tasks: Sentiment Analysis, Commonsense QA, Summarization, and Mathematical Reasoning.
  arXiv  Detail & Related papers  (2025-10-18T10:22:13Z)
• Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization [56.083511902353365]
  Reinforcement learning (RL) typically applies uniform credit across an entire generation of Large language models.<n>This work positions attention as a privileged substrate that renders the internal logic of LLMs as a mechanistic blueprint of reasoning itself.<n>We introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes.
  arXiv  Detail & Related papers  (2025-10-15T13:49:51Z)
• Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models [16.540220733551823]
  Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens.<n> Attention-based methods rely on raw attention scores, which are often unstable across layers and heads.<n>We propose ours, a training-free framework built on a simple intuition.
  arXiv  Detail & Related papers  (2025-09-29T14:20:05Z)
• Multipole Attention for Efficient Long Context Reasoning [64.94673641704289]
  Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks.<n>LRMs need to generate long chain-of-thought reasoning in order to think before answering.<n>We introduce Multipole Attention, which accelerates autoregressive reasoning by only computing exact attention for the most important tokens.
  arXiv  Detail & Related papers  (2025-06-16T03:00:40Z)
• STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference [3.9464481148889354]
  We propose STAR (Stage-wise Attention-guided token Reduction), a training-free, plug-and-play framework that approaches token pruning from a global perspective.<n>Instead of pruning at a single point, STAR performs attention-guided reduction in two complementary stages: an early-stage pruning based on visual self-attention to remove redundant low-level features, and a later-stage pruning guided by cross-modal attention to discard task-irrelevant tokens.
  arXiv  Detail & Related papers  (2025-05-18T10:44:45Z)
• ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training [15.783265191574392]
  We introduce ZeroTuning: a training-free method that improves LLM performance by applying head-specific attention adjustments to the initial token.<n>We show theoretically that adding lightweight biases to this token's attention logits monotonically controls the entropy of the downstream attention distribution.<n>We present two variants: a supervised mode that calibrates on validation examples, and a novel unsupervised mode that directly minimizes the model's output entropy.
  arXiv  Detail & Related papers  (2025-05-16T22:52:24Z)
• AttentionPredictor: Temporal Patterns Matter for KV Cache Compression [64.75459635661562]
  We propose AttentionPredictor, which is the first learning-based method to directly predict attention patterns for KV cache compression and critical token identification.<n> AttentionPredictor accurately predicts the attention score and shares the unified prediction model, which consumes negligible memory.<n>By retaining most of the attention information, AttentionPredictor achieves 13$times$ KV cache compression and 5.6$times$ speedup in a cache offloading scenario.
  arXiv  Detail & Related papers  (2025-02-06T13:41:46Z)
• RefreshKV: Updating Small KV Cache During Long-form Generation [54.00118604124301]
  We propose a new inference method, RefreshKV, that flexibly alternates between full context attention and attention over a subset of input tokens during generation.<n>Applying our method to off-the-shelf LLMs achieves comparable speedup to eviction-based methods while improving performance for various long-form generation tasks.
  arXiv  Detail & Related papers  (2024-11-08T18:57:07Z)

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.