LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models

• URL: http://arxiv.org/abs/2603.14882v1
• Date: Mon, 16 Mar 2026 06:29:43 GMT
• Title: LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models
• Abstract summary: We present the first systematic analysis of bio-inspired visual representation methods.<n>We propose LLMind, a training-free framework that mimics foveated encoding and cortical magnification in human vision.<n>We show dramatic gains, with average improvements of +20% on VQAv2, +38% on Seed-Bench, and +37% on A-OKVQA compared to uniform sampling under tight pixel budgets.
• Score: 4.367067873280894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precision to even the uninformative regions. By contrast, human vision is neither uniform nor static; it is adaptive, selective, and resource-efficient. In light of this, we present the first systematic analysis of bio-inspired visual representation methods, providing insights for more efficient and adaptive VLMs. We propose LLMind (Looking Like the Mind), a novel training-free framework that mimics foveated encoding and cortical magnification in human vision to achieve adaptive, efficient representations for VLMs under tight pixel budgets. Our key idea is to explore a Bio-inspired Adaptive Sampling Strategy (BASS), enabling a Mobius-parameterized module that performs non-uniform sampling while preserving global scene structure. On top of BASS, we introduce closed-loop semantic feedback (CSF) via test-time adaptation to align perceptual saliency with textual information from the frozen VLM. We evaluate LLMind against uniform and other sampling baselines across diverse scene-level and region-guided visual question answering benchmarks. The results show dramatic gains, with average improvements of +20% on VQAv2, +38% on Seed-Bench, and +37% on A-OKVQA compared to uniform sampling under tight pixel budgets. More surprisingly, LLMind retains up to 82%, 92%, and 97% of the full-resolution performance using only 1%, 3%, and 5% of the pixels, respectively. Moreover, LLMind is lightweight, plug-and-play, and compatible with existing VLMs without requiring architectural changes.

Related papers

• Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance [65.36257254806647]
  Vision-Language Models (VLMs) have enhanced traditional LLMs with visual capabilities through the integration of vision encoders.<n>We show that common practices, such as choosing encoders with the largest size or highest zero-shot accuracy, consistently fail to identify optimal models.<n>This intriguing finding begs a fundamental question: What factors of vision-encoders matter in VLM?
  arXiv  Detail & Related papers  (2026-05-02T08:42:13Z)
• Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning [82.39668822222386]
  Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM)<n>We propose $textNwa$, a two-stage token pruning framework that enables efficient feature aggregation while maintaining spatial integrity.<n>Experiments demonstrate that $textNwa$ achieves SOTA performance on multiple VQA benchmarks (from 94% to 95%) and yields substantial improvements on visual grounding tasks (from 7% to 47%)
  arXiv  Detail & Related papers  (2026-02-03T00:51:03Z)
• AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition [21.989922235835067]
  AdaptVision is an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach.<n>We show that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.
  arXiv  Detail & Related papers  (2025-12-03T13:43:30Z)
• Learning Hyperspectral Images with Curated Text Prompts for Efficient Multimodal Alignment [1.7188280334580195]
  We make an attempt to optimize a Vision-Language Model (VLM) for hyperspectral scene understanding by exploiting a CLIP-style contrastive training framework.<n>Our framework maps voxel-level embeddings from a vision backbone onto the latent space of a frozen large embedding model.<n>It is seen that the proposed method updates only 0.07 percent of the total parameters, yet yields state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-09-20T23:23:04Z)
• BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding [51.49345400300556]
  Large video-language models (VLMs) have demonstrated promising progress in various video understanding tasks.<n>Traditional approaches, such as uniform frame sampling, often inevitably allocate resources to irrelevant content.<n>We introduce BOLT, a method to BOost Large VLMs without additional Training through a comprehensive study of frame selection strategies.
  arXiv  Detail & Related papers  (2025-03-27T13:18:40Z)
• Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection [53.558449071113245]
  Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM)<n>Recent advancements in vision-language modeling introduce image cropping techniques that feed all encoded sub-images into the model.<n>We propose a lightweight, universal framework that seamlessly integrates with existing VLMs to enhance their ability to process finegrained details.
  arXiv  Detail & Related papers  (2025-03-14T18:33:31Z)
• Image Embedding Sampling Method for Diverse Captioning [2.705107928847026]
  We introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions.<n>We demonstrate that our method allows smaller VLMs to achieve performance comparable to larger models in terms of image-caption alignment, semantic integrity, and diversity.
  arXiv  Detail & Related papers  (2025-02-14T12:33:19Z)
• Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference [46.00657360369715]
  We investigate the existence of a visual region in Large Vision-Language Models (LVLMs) that functions as a cognitive core.<n>We find that selectively updating 25% of LLMs layers, when sparsely and uniformly distributed, can preserve nearly 99% of visual performance.<n>We propose a novel visual region-based pruning paradigm, removing non-critical layers outside the visual region, which can achieve minimal performance loss.
  arXiv  Detail & Related papers  (2024-12-17T10:44:47Z)
• Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation [109.5893580175657]
  In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision.<n>This approach often causes models to lean towards language comprehension and undermine the rich visual perception signals present in the data.<n>We propose VisPer-LM, the first approach that infuses visual perception knowledge from expert vision encoders into the LLM's hidden representations.
  arXiv  Detail & Related papers  (2024-12-12T18:55:18Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)

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.