Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

• URL: http://arxiv.org/abs/2603.06569v1
• Date: Fri, 06 Mar 2026 18:58:04 GMT
• Title: Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
• Abstract summary: Vision Language Model (VLM) development has largely relied on scaling model size.<n>We present Penguin-VL, whose vision encoder is from a text-only LLM.<n>Our experiments reveal that Penguin-Encoder serves as a superior alternative to traditional contrastive pretraining.
• Score: 40.81958598891815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pretraining (e.g., CLIP/SigLIP). We identify an objective mismatch: contrastive learning, optimized for discrimination, enforces coarse and category-level invariances that suppress fine-grained visual cues needed for dense captioning and complex VLM reasoning. To address this issue, we present Penguin-VL, whose vision encoder is initialized from a text-only LLM. Our experiments reveal that Penguin-Encoder serves as a superior alternative to traditional contrastive pretraining, unlocking a higher degree of visual fidelity and data efficiency for multimodal understanding. Across various image and video benchmarks, Penguin-VL achieves performance comparable to leading VLMs (e.g., Qwen3-VL) in mathematical reasoning and surpasses them in tasks such as document understanding, visual knowledge, and multi-perspective video understanding. Notably, these gains are achieved with a lightweight architecture, demonstrating that improved visual representation rather than model scaling is the primary driver of performance. Our ablations show that Penguin-Encoder consistently outperforms contrastive-pretrained encoders, preserving fine-grained spatial and temporal cues that are critical for dense perception and complex reasoning. This makes it a strong drop-in alternative for compute-efficient VLMs and enables high performance in resource-constrained settings. Code: https://github.com/tencent-ailab/Penguin-VL

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)
• Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation [7.6937364614883625]
  Firebolt-VL is an efficient vision-language model that replaces the Transformer-based decoder with a Liquid Foundation Model (LFM) decoder.<n>To further enhance visual grounding, we propose a Token-Grid Correlation Module, which computes lightweight correlations between text tokens and image patches.
  arXiv  Detail & Related papers  (2026-04-06T10:25:16Z)
• CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning [79.07656918674684]
  CoME-VL is a modular fusion framework that integrates a contrastively trained vision encoder with a self-supervised DINO encoder.<n>Our method achieves state-of-the-art performance on RefCOCO for detection while improving over the baseline by a large margin.
  arXiv  Detail & Related papers  (2026-04-03T17:59:51Z)
• Event-Priori-Based Vision-Language Model for Efficient Visual Understanding [13.540340702321911]
  Event-Priori-Based Vision-Language Model (EP-VLM) improves VLM inference efficiency.<n>EP-VLM uses motion priors derived from dynamic event vision to enhance VLM efficiency.
  arXiv  Detail & Related papers  (2025-06-09T10:45:35Z)
• EVEv2: Improved Baselines for Encoder-Free Vision-Language Models [72.07868838411474]
  Existing encoder-free vision-language models (VLMs) are narrowing the performance gap with their encoder-based counterparts.<n>We develop efficient strategies for encoder-free VLMs that rival mainstream encoder-based ones.<n>We show that properly and hierarchically associating vision and language within a unified model reduces interference between modalities.
  arXiv  Detail & Related papers  (2025-02-10T18:59:58Z)
• 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)
• Unveiling Encoder-Free Vision-Language Models [62.52803514667452]
  Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. We bridge the gap between encoder-based and encoder-free models, and present a simple yet effective training recipe towards pure VLMs. We launch EVE, an encoder-free vision-language model that can be trained and forwarded efficiently.
  arXiv  Detail & Related papers  (2024-06-17T17:59:44Z)

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.