LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?

• URL: http://arxiv.org/abs/2605.08985v1
• Date: Sat, 09 May 2026 15:10:26 GMT
• Title: LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
• Abstract summary: We present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs.<n>Results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance.
• Score: 7.06721685645839
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT compression. Global encoding produces massive token sequences, while post-ViT compression incurs the full quadratic attention cost of the ViT before any token reduction takes place. In this work, we revisit this convention along two dimensions: the encoding strategy and visual token compression. First, controlled experiments show that slice-based encoding outperforms global encoding across benchmarks, suggesting that preserving local details through sliced views can be more beneficial than applying global attention for fine-grained perception. Second, we introduce intra-ViT early compression, which reduces tokens in shallow ViT layers and substantially lowers visual-encoding FLOPs while preserving downstream performance. By integrating intra-ViT compression into the slice-based encoding framework, we present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs. Across a diverse set of benchmarks covering document understanding, OCR, and general VQA, LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% while matching or even surpassing baseline performance. These results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance, providing a practical design direction for efficient high-resolution MLLMs. All model weights and code will be publicly released to support further research.

Related papers

• PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference [15.233755808671871]
  Existing visual token pruning methods exhibit two fundamental limitations.<n>Most approaches operate exclusively post-vision encoder, leaving the substantial latency of the visual encoding phase unoptimized.<n>We propose PACE, a framework that accelerates both the vision encoder and the Large Language Model.
  arXiv  Detail & Related papers  (2026-08-27T14:52:09Z)
• VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression [52.23010472235226]
  Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference and overhead latency.<n>We propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor.
  arXiv  Detail & Related papers  (2026-07-14T13:21:36Z)
• VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding [52.69880888587866]
  Current Video Large Language Models (Video LLMs) typically encode frames via a encoder vision and employ an autoregressive (AR) LLM for understanding and generation.<n>We propose VidLaDA, a Diffusion Video LLM based on Language Models (DLMs) that leverages bidirectional attention to unlock comprehensive modeling and decode tokens in parallel.<n>Experiments show VidLaDA rivals state-of-the-art AR baselines and outperforms DLM baselines, with MARS-Cache delivering over 12x speedup without compromising accuracy.
  arXiv  Detail & Related papers  (2026-01-25T15:02:01Z)
• Accelerating Streaming Video Large Language Models via Hierarchical Token Compression [12.247532124314402]
  Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks.<n>They face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams.<n>We propose textbfStreaming textbfToken textbfCompression (textbfSTC), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs.
  arXiv  Detail & Related papers  (2025-11-30T13:44:28Z)
• 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)
• VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models [57.2662376527586]
  VScan is a two-stage visual token reduction framework.<n>It addresses token redundancy by: (1) integrating complementary global and local scans with token merging during visual encoding, and (2) introducing pruning at intermediate layers of the language model.<n>VScan achieves a 2.91$times$ speedup in prefilling and a 10$times$ reduction in FLOPs, while retaining 95.4% of the original performance.
  arXiv  Detail & Related papers  (2025-05-28T17:59:08Z)
• VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification [44.97217246897902]
  Large Vision-Language Models (LVLMs) may produce outputs that are unfaithful to reality, also known as visual hallucinations (VH)<n>We propose an efficient plug-and-play decoding algorithm via Visual-Aware Sparsification (VASparse)<n>VASparse achieves state-of-the-art performance for mitigating VH while maintaining competitive decoding speed.
  arXiv  Detail & Related papers  (2025-01-11T14:09:34Z)
• Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks.<n>To reduce inference costs, one can either downsize the Large Language Models (LLMs) or reduce the number of input tokens needed to represent the image.<n>We take the first steps toward designing token compression algorithms tailored for high-compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)
• Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation [67.85309547416155]
  A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions.<n>With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses 50% of its compute only on the transformer encoder.<n>This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer.
  arXiv  Detail & Related papers  (2024-04-23T01:34:20Z)
• VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision [59.632286735304156]
  It is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. We propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis.
  arXiv  Detail & Related papers  (2023-06-19T03:04:57Z)

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.