mlsanityData to 7 Oct 2026

TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding

arXiv 2607.11131 ↗First posted 13 Jul 2026cs.CLcited by 2

On the map: Efficient LLM inference and serving → Fast autoregressive visual generation

Abstract (arXiv)

Speculative decoding accelerates autoregressive generation by letting a lightweight drafter propose multiple tokens that are verified by a larger target model. Although effective for text-only LLMs, speculative decoding yields limited gains in VLMs because drafters often diverge on vision-critical content, while existing multimodal acceleration methods do not directly address irrelevant visual evidence or optimize the verifier-accepted prefix length that governs speedup. We propose TIGER, a Text-conditioned vIsual GatEd Routing framework for multimodal speculative decoding. TIGER dynamically selects a sparse set of context-relevant visual tokens based on the drafter's current textual state, rather than expose the full visual token set or a fixed compressed interface. To better align training with inference-time efficiency, we optimize the drafter with acceptance-aligned group-based policy training using verifier-derived rewards based on accepted prefix length, built on top of distillation warm start with KL anchoring. This encourages the drafter not only to imitate the target model, but also to produce speculative continuations that survive verification for longer prefixes. Experiments show that TIGER yields consistent gains in accepted prefix length and speculative speedup under exact verifier-side speculative decoding, while achieving favorable quality-latency trade-offs with comparable downstream accuracy in visual-routing analyses.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Fast autoregressive visual generation, one of 12 directions in Efficient LLM inference and serving. Builds on 18 of its 28 references that are in the map. First posted on arXiv 13 Jul 2026.

Builds on

18 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding17 Sep

Other references · 17

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  3. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  4. 2019Towards VQA Models That Can Readcited by 1,696
  5. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  6. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  7. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  8. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 821
  9. 2018A Corpus for Reasoning About Natural Language Grounded in Photographscited by 457
  10. 2024EAGLE-2: Faster Inference of Language Models with Dynamic Draft Treescited by 362
  11. 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Testcited by 318
  12. 2024PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductioncited by 283
5 more
  1. 2024MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decodingcited by 87
  2. 2024Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recyclingcited by 48
  3. 2025Accelerating Large Language Model Reasoning via Speculative Searchcited by 16
  4. 2025LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentationcited by 4
  5. 2026RACER: Retrieval-Augmented Contextual Rapid Speculative Decodingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosiscited by 0
  2. 2026FOVEA: Focused On-Demand Visual Evidence Adaptation for Cache-Friendly Multimodal Speculative Decodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation
  2. 2025Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
  3. 2026HAWK: Rethinking Multimodal Drafting for Speculative Decoding
  4. 2025LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
  5. 2025DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
  6. 2026See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
  7. 2026FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
  8. 2025SpecVLM: Fast Speculative Decoding in Vision-Language Models