InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

• URL: http://arxiv.org/abs/2512.08829v1
• Date: Tue, 09 Dec 2025 17:18:32 GMT
• Title: InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
• Authors: Hongyuan Tao, Bencheng Liao, Shaoyu Chen, Haoran Yin, Qian Zhang, Wenyu Liu, Xinggang Wang,
• Abstract summary: We propose InfiniteVL, a linear-complexity VLM architecture that synergizes sliding window attention (SWA) with Gated DeltaNet.<n>We show that InfiniteVL achieves over 3.6times inference speedup while maintaining constant latency and memory footprint.<n>In streaming video understanding scenarios, it sustains a stable 24 FPS real-time prefill speed while preserving long-term memory cache.
• Score: 49.08289742711585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Window attention and linear attention represent two principal strategies for mitigating the quadratic complexity and ever-growing KV cache in Vision-Language Models (VLMs). However, we observe that window-based VLMs suffer performance degradation when sequence length exceeds the window size, while linear attention underperforms on information-intensive tasks such as OCR and document understanding. To overcome these limitations, we propose InfiniteVL, a linear-complexity VLM architecture that synergizes sliding window attention (SWA) with Gated DeltaNet. For achieving competitive multimodal performance under constrained resources, we design a three-stage training strategy comprising distillation pretraining, instruction tuning, and long-sequence SFT. Remarkably, using less than 2\% of the training data required by leading VLMs, InfiniteVL not only substantially outperforms previous linear-complexity VLMs but also matches the performance of leading Transformer-based VLMs, while demonstrating effective long-term memory retention. Compared to similar-sized Transformer-based VLMs accelerated by FlashAttention-2, InfiniteVL achieves over 3.6\times inference speedup while maintaining constant latency and memory footprint. In streaming video understanding scenarios, it sustains a stable 24 FPS real-time prefill speed while preserving long-term memory cache. Code and models are available at https://github.com/hustvl/InfiniteVL.

Related papers

• Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing [16.063514680699576]
  Multimodal large language models (MLLMs) extend visual understanding through a three-stage pipeline.<n> multimodal preprocessing-especially video decoding-often dominates Time-to-First-Token (TTFT)<n>We present FlashCodec and UnifiedServe, two complementary designs that jointly optimize the end-to-end MLLM pipeline.
  arXiv  Detail & Related papers  (2025-12-19T13:40:13Z)
• LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs [52.24096832965001]
  We present LLaVA-UHD v3, an MLLM centered upon our proposed Progressive Visual Compression (PVC) method.<n>The PVC method can be seamlessly integrated into standard Vision Transformer (ViT) to enable efficient native-resolution encoding.<n>Building upon ViT-UHD, LLaVA-UHD v3 also achieves competitive performance to Qwen2-VL, while further reducing TTFT by 1.9x.
  arXiv  Detail & Related papers  (2025-11-26T08:11:10Z)
• FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning [16.753299634529736]
  Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency.<n>Reducing redundant visual tokens is critical to ease computational/memory burdens while preserving performance, enabling MLLM deployment in resource-constrained or latency-sensitive scenarios.<n>We propose Fast Multimodal Mixture-of-Experts (FastMMoE), a training-free acceleration framework for mixture-of-experts (MoE) based MLLMs, developed from a routing analysis perspective.
  arXiv  Detail & Related papers  (2025-11-22T02:25:00Z)
• SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference [49.84148668264725]
  We present SparseVILA, a new paradigm for efficient VLM inference that decouples visual sparsity across the prefilling and decoding stages.<n>Built on an AWQ-optimized inference pipeline, SparseVILA achieves up to 4.0 times faster prefilling, 2.5 times faster decoding, and an overall 2.6 times end-to-end speedup on long-context video tasks.
  arXiv  Detail & Related papers  (2025-10-20T17:35:47Z)
• SpecVLM: Fast Speculative Decoding in Vision-Language Models [14.243294546325714]
  Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs)<n>We study speculative decoding for vision-language models (VLMs)<n>We introduce SpecVLM, a practical system that delivers 1.5--2.3x end-to-end speedups over full autoregressive inference.
  arXiv  Detail & Related papers  (2025-09-15T11:53:56Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding [29.719450799231705]
  Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input.<n>Video Large Language Models (Video-LLMs) capture temporal relationships within visual features but are limited by the scarcity of high-quality video-text datasets.<n>We propose Lightweight Video Compression (LVC), a novel method featuring the Query-Attention Video Compression mechanism.
  arXiv  Detail & Related papers  (2025-04-09T12:51:10Z)
• STORM: Token-Efficient Long Video Understanding for Multimodal LLMs [116.4479155699528]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs.<n>We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention [26.54297116028556]
  Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks.<n>We introduce LServe, an efficient system that accelerates long-sequence LLM serving via hybrid sparse attention.<n>On average, LServe accelerates LLM prefilling by up to 2.9x and decoding by 1.3-2.1x over vLLM.
  arXiv  Detail & Related papers  (2025-02-20T18:59:52Z)
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)

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.