paper-with-me

Papers

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

2024-03-12 · CVPR 2024 1 · Lei Zhu, Fangyun Wei, Yanye Lu

In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views an image as a linguistic entity, and translates it to a set of discrete words derived from the LLM's vocabulary. To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model. With this innovative image encoding, the LLM gains the ability not only for visual comprehension but also for image denoising and restoration in an auto-regressive fashion-crucially, without any fine-tuning. We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration. Code and models are available at https://github.com/zh460045050/V2L-Tokenizer.

📄 PDF Abstract BibTeX arXiv:2403.07874

Code (1)

zh460045050/v2l-tokenizer 공식 구현 pytorch

Tasks

DeblurringDecoderDenoisingImage CaptioningImage DenoisingLanguage ModelingLanguage ModellingLarge Language ModelQuestion AnsweringVisual Question Answering

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm

2026-05-12 · Yaofang Liu, Kangning Cui, Meng Chu, Zhaoqing Li 외 arxiv

Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck…

Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models

2025-12-17 · Davide Caffagni, Sara Sarto, Marcella Cornia, Lorenzo Baraldi 외 arxiv

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning tasks remains limited. This limitation …

Multimodal ReasoningVisual Reasoning

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations

2025-07-07 · A. Bochkov

Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as found…

AttributeMMLU

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

2026-06-13 · Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja arxiv

Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either…

Image Retrieval

Frozen Binomials on the Web: Word Ordering and Language Conventions in Online Text

2020-03-07 · Katherine Van Koevering, Austin R. Benson, Jon Kleinberg

There is inherent information captured in the order in which we write words in a list. The orderings of binomials --- lists of two words separated by `and' or `or' --- has been studied for more than a century. These bino…