FOVEA: Focused On-Demand Visual Evidence Adaptation for Cache-Friendly Multimodal Speculative Decoding

• URL: http://arxiv.org/abs/2608.22883v1
• Date: Mon, 24 Aug 2026 07:09:02 GMT
• Title: FOVEA: Focused On-Demand Visual Evidence Adaptation for Cache-Friendly Multimodal Speculative Decoding
• Abstract summary: Multimodal speculative decoding accelerates vision-language models by allowing a lightweight draft model to propose candidate tokens for parallel verification by a larger target model.<n>Existing methods typically condition the drafter on a fixed visual interface, such as a predefined visual-token budget or a static compressed representation.<n>We propose FOVEA, a cache-friendly approach that builds a reusable visual memory and dynamically retrieves a bounded subset for a draft state.
• Score: 42.559533294854134
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal speculative decoding accelerates vision-language models by allowing a lightweight draft model to propose candidate tokens for parallel verification by a larger target model. Existing methods typically condition the drafter on a fixed visual interface, such as a predefined visual-token budget or a static compressed representation. However, our controlled visual-budget analysis shows that visual demand varies substantially across tasks and decoding stages, which means more visual input is not always beneficial. Actually, insufficient evidence may weaken visual grounding, while excessive context adds overhead and may disrupt drafting. We propose FOVEA (Focused On-demand Visual Evidence Adaptation), a cache-friendly approach that builds a reusable visual memory and dynamically retrieves a bounded subset for a draft state. A cumulative-mass rule determines both how many and which entries are selected. The selected entries are aggregated into a visual readout and fused with the current draft hidden state through a lightweight gated residual correction. Rather than inserting visual tokens into the autoregressive context, the correction modifies only the representation passed to the language-model head. Experiments across multiple vision-language backbones and multimodal benchmarks show that FOVEA improves draft acceptance and end-to-end decoding speed, achieving up to $2.13\times$ speedup over autoregressive decoding. These results demonstrate that state-conditioned evidence retrieval is an effective alternative to reusing a fixed visual representation throughout multimodal generation.

Related papers

• State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models [49.57973975600996]
  Document parsing places stronger demands on fine-grained visual perception.<n>Existing vision-language model (VLM)-based parsing approaches rely on globally compressed visual tokens.<n>We formulate perception as state-conditioned visual evidence retrieval (SCVER) during autoregressive decoding.
  arXiv  Detail & Related papers  (2026-08-27T12:56:45Z)
• TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding [8.451420931444215]
  Speculative decoding accelerates autoregressive generation by letting a drafter propose multiple tokens that are verified by a larger target model.<n>We propose TIGER, a Text-conditioned vIsual GatEd framework for multimodal speculative decoding.<n>We show TIGER yields consistent gains in accepted prefix length and speculative speedup under exact verifier-side speculative decoding.
  arXiv  Detail & Related papers  (2026-07-13T06:06:27Z)
• Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification [80.62512020268626]
  UniAR is a unified autoregressive framework where a single visual tokenizer serves as the key bridge between understanding and generation.<n>UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme.<n>A diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images.
  arXiv  Detail & Related papers  (2026-06-16T17:59:22Z)
• MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval [111.99106496142474]
  Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure.<n>Existing VDR models struggle to balance effectiveness and efficiency when processing high-resolution documents.<n>We propose a new X-VisEmb paradigm that progresses from multi-resolution sampling and encoding, through cross-granularity feature fusion, to adaptive representation distillation.
  arXiv  Detail & Related papers  (2026-03-07T15:17:22Z)
• RECODE: Reasoning Through Code Generation for Visual Question Answering [68.86938437188964]
  We propose to leverage derendering -- the process of reverse-engineering visuals into executable code -- as a new modality for verifiable visual reasoning.<n>Our work demonstrates that grounding visual perception in executable code provides a new path toward more accurate and verifiable multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-15T17:05:37Z)
• HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models [23.98782884568504]
  We propose Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models (HiViS)<n>HiViS is an explicit-implicit input decomposition framework that alleviates the inefficiency of Speculative Decoding in Vision-Language Models.<n>Our approach compresses the prefill sequence length of the drafter to only 0.7%-1.3% of the target VLM's input.
  arXiv  Detail & Related papers  (2025-09-28T15:05:21Z)
• CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models [75.88232735646018]
  Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos.<n>Existing methods attempt to prune redundant vision tokens, revealing substantial redundancy in visual representations.<n>We propose CoViPAL, a layer-wise contextualized visual token pruning method that employs a Plug-and-Play Pruning Module (PPM) to predict and remove redundant vision tokens before they are processed by the LVLM.
  arXiv  Detail & Related papers  (2025-08-24T07:47:00Z)
• Rethinking Visual Token Reduction in LVLMs under Cross-modal Misalignment [38.04426918886084]
  Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics.<n>Previous efforts have explored visual token reduction either prior to or within the large language models (LLMs)<n>We introduce VisionDrop, a training-free, visual-only pruning framework that selects informative visual tokens based on intra-modal (visual-to-visual) attention.
  arXiv  Detail & Related papers  (2025-06-27T14:55:40Z)
• Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding [5.71478837100808]
  Large Vision-Language Models (LVLMs) generate descriptions that inaccurately reflect the visual content by including nonexistent objects or misrepresenting existing ones.<n>We propose Ensemble Decoding (ED), a novel strategy that splits the input image into sub-images and combines logit distributions by assigning weights through the attention map.<n>Our proposed method achieves state-of-the-art performance, validating the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-05-23T06:35:43Z)
• D-Attn: Decomposed Attention for Large Vision-and-Language Models [29.611769371733672]
  We propose Decomposed Attention (D-Attn), a more flexible attention architecture for large vision-and-language models (LVLMs)<n>D-Attn decomposes the 1-D causal self-attention of LVLMs into visual-to-visual, textual-to-visual, and textual-to-textual attentions.<n>Experiments and analysis validate the effectiveness of D-Attn, demonstrating significant improvements on multiple image benchmarks.
  arXiv  Detail & Related papers  (2025-02-04T00:46:11Z)

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.