The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating

• URL: http://arxiv.org/abs/2603.07135v1
• Date: Sat, 07 Mar 2026 09:57:35 GMT
• Title: The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating
• Abstract summary: Visual tokens dominate inference cost in vision-language models (VLMs)<n>We reformulate visual token pruning as capacity constrained communication.<n>We propose AutoSelect, which attaches a lightweight Scorer and Denoiser to a frozen VLM and trains with only the standard next token prediction loss.
• Score: 2.503823246244002
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Visual tokens dominate inference cost in vision-language models (VLMs), yet many carry redundant information. Existing pruning methods alleviate this but typically rely on attention magnitude or similarity scores. We reformulate visual token pruning as capacity constrained communication: given a fixed budget K, the model must allocate limited bandwidth to maximally preserve visual information. We propose AutoSelect, which attaches a lightweight Scorer and Denoiser to a frozen VLM and trains with only the standard next token prediction loss, without auxiliary objectives or extra annotations. During training, a variance preserving noise gate modulates each token's information flow according to its predicted importance so that gradients propagate through all tokens; a diagonal attention Denoiser then recovers the perturbed representations. At inference, only the Scorer and a hard top-K selection remain, adding negligible latency. On ten VLM benchmarks, AutoSelect retains 96.5% of full model accuracy while accelerating LLM prefill by 2.85x with only 0.69 ms overhead, and transfers to different VLM backbones without architecture-specific tuning. Code is available at https://github.com/MedHK23/AutoSelect.

Related papers

• DiffPrune: differentiable information throttling for token pruning in vision-language models [8.48481119028537]
  We propose DiffPrune, which gives token scores a direct meaning.<n>Across ten VLM benchmarks, DiffPrune retains 96.5% of full-model accuracy.
  arXiv  Detail & Related papers  (2026-08-03T09:46:32Z)
• Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs [26.936352183867854]
  CaRe consists of two mutually complementary modules: 1) Perturbation-Robust Anchoring, which identifies anchors with stable model-side influence under multi-directional perturbations; 2) Confidence-Gated Token, which extracts reliable calibration signals from unselected tokens and injects them into anchors.<n>While pruning 94.4% of visual tokens, our method retains 96.4% of the original full-token performance, delivering up to 2.30 times faster end-to-end inference speed relative to unpruned vanilla models.
  arXiv  Detail & Related papers  (2026-07-30T05:36:29Z)
• Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models [8.48481119028537]
  We propose DiffPrune, which reformulates pruning as continuous control of token information instead of discrete selection learning.<n>Across ten VLM benchmarks, DiffPrune retains 96.5% of full-model accuracy while accelerating LLM prefill by 2.85x, with only 0.69 ms of inference overhead.
  arXiv  Detail & Related papers  (2026-05-27T06:52:08Z)
• 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)
• ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference [26.71949723961501]
  We propose ASAP, a novel training-free, KV-Cache-compatible pruning recipe.<n>We mitigate the attention shift by utilizing a dynamic bidirectional soft attention mask.<n>We also posit that high semantic redundancy within the token set degrades performance.
  arXiv  Detail & Related papers  (2026-03-15T18:51:31Z)
• Stateful Token Reduction for Long-Video Hybrid VLMs [69.6930118088911]
  We study query-conditioned token reduction for hybrid video vision-language models (VLMs)<n>We propose a low-to-high progressive reduction schedule and a unified language-aware scoring mechanism for both attention and Mamba blocks.<n>Under an aggressive compression setting, our approach delivers substantial prefilling speedups with near-baseline accuracy at test time.
  arXiv  Detail & Related papers  (2026-02-27T08:11:06Z)
• Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory [50.30283773196725]
  Existing approaches rely on key-value caching to accumulate frame-level details over time, but use a limited number of tokens per frame.<n>We propose scaling the token budget to enable more granular-temporal understanding and reasoning.
  arXiv  Detail & Related papers  (2026-02-20T18:59:50Z)
• Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models [34.12135666939555]
  Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all layers.<n>We introduce Attention-Driven Self-Compression (ADSC), a simple, broadly applicable method that progressively reduces vision tokens using only the LLM's attention mechanism.<n>ADSC reduces FLOPs by 53.7% and peak KV-cache memory by 56.7%, while preserving 98.2% of the original model performance.
  arXiv  Detail & Related papers  (2026-02-13T04:49:27Z)
• PIO-FVLM: Rethinking Training-Free Visual Token Reduction for VLM Acceleration from an Inference-Objective Perspective [59.24570811503256]
  We propose PIO-FVLM to reduce redundant visual tokens in vision-models (VLMs) to accelerate inference.<n>The proposed PIO-FVLM is training-free and compatible with FlashAttention, friendly to practical application and deployment.<n>On LLaVA-Next-7B, PIO-FVLM retains just 11.1% of visual tokens but maintains 97.2% of the original performance.
  arXiv  Detail & Related papers  (2026-02-04T15:33:10Z)
• VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs [82.72388893596555]
  Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks.<n>Previous token compression techniques are often constrained by rules that risk discarding critical information.<n>We reformulate token compression as a lightweight plug-and-play framework that reformulates token compression into an end-to-end learnable decision process.
  arXiv  Detail & Related papers  (2025-10-18T17:54:18Z)
• What Layers When: Learning to Skip Compute in LLMs with Residual Gates [66.23658560048241]
  GateSkip is a residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs.<n>Each Attention/MLP branch is equipped with a sigmoid-linear gate that condenses the branch's output before it re-enters the residual stream.
  arXiv  Detail & Related papers  (2025-10-13T16:31:50Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference [45.11612407862277]
  In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens.<n>We propose a text-guided training-free token optimization mechanism dubbed SparseVLM that eliminates the need of extra parameters or fine-tuning costs.
  arXiv  Detail & Related papers  (2024-10-06T09:18:04Z)
• ToSA: Token Selective Attention for Efficient Vision Transformers [50.13756218204456]
  ToSA is a token selective attention approach that can identify tokens that need to be attended as well as those that can skip a transformer layer. We show that ToSA can significantly reduce computation costs while maintaining accuracy on the ImageNet classification benchmark.
  arXiv  Detail & Related papers  (2024-06-13T05:17:21Z)

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.