OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport

• URL: http://arxiv.org/abs/2602.20205v2
• Date: Wed, 25 Feb 2026 03:48:00 GMT
• Title: OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
• Abstract summary: Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens.<n>Recent work explores visual token pruning to accelerate inference, while existing pruning methods overlook the underlying distributional structure of visual representations.<n>We propose OTPrune, a training-free framework that formulates pruning as distribution alignment via optimal transport.
• Score: 20.586206895801258
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual token pruning to accelerate inference, while existing pruning methods overlook the underlying distributional structure of visual representations. We propose OTPrune, a training-free framework that formulates pruning as distribution alignment via optimal transport (OT). By minimizing the 2-Wasserstein distance between the full and pruned token distributions, OTPrune preserves both local diversity and global representativeness while reducing inference cost. Moreover, we derive a tractable submodular objective that enables efficient optimization, and theoretically prove its monotonicity and submodularity, providing a principled foundation for stable and efficient pruning. We further provide a comprehensive analysis that explains how distributional alignment contributes to stable and semantically faithful pruning. Comprehensive experiments on wider benchmarks demonstrate that OTPrune achieves superior performance-efficiency tradeoffs compared to state-of-the-art methods. The code is available at https://github.com/xiwenc1/OTPrune.

Related papers

• CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport [50.2610873651284]
  Existing token pruning methods rely on diversity-based selection, discarding similar tokens to maximize dispersion.<n>In 3D environments, this approach frequently drops representative prototype tokens in favor of outliers.<n>We propose a paradigm shift for 3D VLM token pruning: from maximizing OT to preserving visual evidence coverage.
  arXiv  Detail & Related papers  (2026-08-13T13:29:15Z)
• PrunePath: Towards Highly Structured Sparse Language Models [8.390447915838122]
  We introduce textbfPrunePath, a budget-adaptive structured sparsification framework for FFN layers.<n>PrunePath replaces independent expert-wise thresholding with a softmax-normalized routing distribution.<n>Across NLU, NLG, and instruction-tuning evaluations, PrunePath achieves a favorable sparsity--performance trade-off.
  arXiv  Detail & Related papers  (2026-05-27T10:29:52Z)
• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models [54.597200388738656]
  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples.<n>We show that many can be written under a common framework, which we call reward score matching (RSM)
  arXiv  Detail & Related papers  (2026-04-19T12:47:52Z)
• EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models [35.12029704777804]
  We introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop.<n>We propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual tokens and prunes redundant ones.<n>Experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-02-19T09:29:43Z)
• Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training [61.1421888242439]
  Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL)<n>We propose a framework to bridge this chasm by enabling On-Policy SFT.
  arXiv  Detail & Related papers  (2026-02-12T17:59:58Z)
• FAIL: Flow Matching Adversarial Imitation Learning for Image Generation [52.643484089126844]
  Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to Imitation learning.<n>We propose Flow Matching Adrial Learning (FAIL), which minimizes policy-expert divergence through adversarial training without explicit rewards or pairwise comparisons.
  arXiv  Detail & Related papers  (2026-02-12T16:36:33Z)
• Variational Entropic Optimal Transport [67.76725267984578]
  We propose Variational Entropic Optimal Transport (VarEOT) for domain translation problems.<n>VarEOT is based on an exact variational reformulation of the log-partition $log mathbbE[exp(cdot)$ as a tractable generalization over an auxiliary positive normalizer.<n> Experiments on synthetic data and unpaired image-to-image translation demonstrate competitive or improved translation quality.
  arXiv  Detail & Related papers  (2026-02-02T15:48:44Z)
• Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization [16.627496870394456]
  T'yr-the-Pruner is an efficient end-to-end search-based global structural pruning framework.<n>We introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction.<n>Results show that T'yr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance.
  arXiv  Detail & Related papers  (2025-03-12T11:52:49Z)
• Progressive Binarization with Semi-Structured Pruning for LLMs [36.91249209658632]
  We propose Progressive Binarization with Semi-Structured Pruning (PBS$2$P), a novel post-training framework that seamlessly integrates binarization and semi-structured pruning.<n>We show that PBS$2$P consistently outperforms state-of-the-art (SOTA) binary post-training quantization methods in both perplexity and downstream accuracy.
  arXiv  Detail & Related papers  (2025-02-03T13:30:29Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning that learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model.<n>We achieve this by learning an underlying Bernoulli distribution to sample binary pruning masks.<n>Experiments conducted on LLaMA, LLaMA-2, LLaMA-3, Vicuna, and Mistral models demonstrate the promising performance of our method in efficiency and effectiveness.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Alleviating Over-smoothing for Unsupervised Sentence Representation [96.19497378628594]
  We present a Simple method named Self-Contrastive Learning (SSCL) to alleviate this issue. Our proposed method is quite simple and can be easily extended to various state-of-the-art models for performance boosting.
  arXiv  Detail & Related papers  (2023-05-09T11:00:02Z)
• Advancing Model Pruning via Bi-level Optimization [89.88761425199598]
  iterative magnitude pruning (IMP) is the predominant pruning method to successfully find 'winning tickets' One-shot pruning methods have been developed, but these schemes are usually unable to find winning tickets as good as IMP. We show that the proposed bi-level optimization-oriented pruning method (termed BiP) is a special class of BLO problems with a bi-linear problem structure.
  arXiv  Detail & Related papers  (2022-10-08T19:19:29Z)
• Cooperative Distribution Alignment via JSD Upper Bound [7.071749623370137]
  Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution. This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning. We propose to unify and generalize previous flow-based approaches under a single non-adversarial framework.
  arXiv  Detail & Related papers  (2022-07-05T20:09:03Z)

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.