Zero-Shot Vision Encoder Grafting via LLM Surrogates

• URL: http://arxiv.org/abs/2505.22664v2
• Date: Sat, 02 Aug 2025 22:03:19 GMT
• Title: Zero-Shot Vision Encoder Grafting via LLM Surrogates
• Authors: Kaiyu Yue, Vasu Singla, Menglin Jia, John Kirchenbauer, Rifaa Qadri, Zikui Cai, Abhinav Bhatele, Furong Huang, Tom Goldstein,
• Abstract summary: Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM)<n>We construct small "surrogate models" that share the same embedding space and representation language as the large target LLM.<n> Vision encoders trained on the surrogate can then be directly transferred to the larger model.
• Score: 65.37227522413689
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden during training. To reduce costs, a potential promising strategy is to first train the vision encoder using a small language model before transferring it to the large one. We construct small "surrogate models" that share the same embedding space and representation language as the large target LLM by directly inheriting its shallow layers. Vision encoders trained on the surrogate can then be directly transferred to the larger model, a process we call zero-shot grafting -- when plugged directly into the full-size target LLM, the grafted pair surpasses the encoder-surrogate pair and, on some benchmarks, even performs on par with full decoder training with the target LLM. Furthermore, our surrogate training approach reduces overall VLM training costs by ~45% when using Llama-70B as the decoder. The code is at https://github.com/facebookresearch/zero.

Related papers

• Should We Still Pretrain Encoders with Masked Language Modeling? [27.19054714197245]
  Recent evidence suggests that decoder models pretrained with Causal Language Modeling (CLM) can be effectively repurposed as encoders.<n>We train a total of 38 models ranging from 210 million to 1 billion parameters, and conduct over 15,000 fine-tuning and evaluation runs.<n>We find that while training with high-level CLM yields better performance across text representation tasks, CLM-trained models are more data-efficient and demonstrate improved fine-tuning stability.
  arXiv  Detail & Related papers  (2025-07-01T17:45:48Z)
• 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)
• HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding [91.0552157725366]
  This paper presents a novel high-performance monolithic VLM named HoVLE.<n>It converts visual and textual inputs into a shared space, allowing LLMs to process images in the same way as texts.<n>Our experiments show that HoVLE achieves performance close to leading compositional models on various benchmarks.
  arXiv  Detail & Related papers  (2024-12-20T18:59:59Z)
• SOLO: A Single Transformer for Scalable Vision-Language Modeling [74.05173379908703]
  We present SOLO, a single transformer for visiOn-Language mOdeling.<n>A unified single Transformer architecture, like SOLO, effectively addresses these scalability concerns in LVLMs.<n>In this paper, we introduce the first open-source training recipe for developing SOLO, an open-source 7B LVLM.
  arXiv  Detail & Related papers  (2024-07-08T22:40:15Z)
• 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)
• Dense Connector for MLLMs [89.50595155217108]
  We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs. Building on this, we also propose the Efficient Dense Connector, which achieves performance comparable to LLaVA-v1.5 with only 25% of the visual tokens. Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
  arXiv  Detail & Related papers  (2024-05-22T16:25:03Z)
• mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs [50.17767479660832]
  Vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to understand' the image input. We present mBLIP, the first Vision-LLM leveraging multilingual LLMs, which we obtain in a computationally efficient manner on consumer-level hardware.
  arXiv  Detail & Related papers  (2023-07-13T17:51:58Z)

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.