paper-with-me

홈 › Papers

Multi-modal Auto-regressive Modeling via Visual Words

2024-03-12 · Tianshuo Peng, Zuchao Li, Lefei Zhang, Hai Zhao, Ping Wang, Bo Du

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive modelling to multi-modal scenarios to build Large Multi-modal Models (LMMs), there lies a great difficulty that the image information is processed in the LMM as continuous visual embeddings, which cannot obtain discrete supervised labels for classification.In this paper, we successfully perform multi-modal auto-regressive modeling with a unified objective for the first time.Specifically, we propose the concept of visual tokens, which maps the visual features to probability distributions over LLM's vocabulary, providing supervision information for visual modelling.We further explore the distribution of visual features in the semantic space within LMM and the possibility of using text embeddings to represent visual information.Experimental results and ablation studies on 5 VQA tasks and 4 benchmark toolkits validate the powerful performance of our proposed approach.

📄 PDF Abstract BibTeX arXiv:2403.07720

Code (1)

pengts/vw-lmm 공식 구현 pytorch

Tasks

Visual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer

2024-12-10 · Jinyi Hu, Shengding Hu, Yuxuan Song, Yufei Huang 외

The recent surge of interest in comprehensive multimodal models has necessitated the unification of diverse modalities. However, the unification suffers from disparate methodologies. Continuous visual generation necessit…

DenoisingImage GenerationVideo Generation

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

2026-05-08 · Ying Shen, Tianrong Chen, Yuan Gao, Yizhe Zhang 외 arxiv

Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine…

multimodal generationImage GenerationText Generation

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

2026-06-16 · Wujian Peng, Lingchen Meng, Yuxuan Cai, Xianwei Zhuang 외 arxiv

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation sp…

Reinforcement LearningImage GenerationImage Editing

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

2026-03-29 · Meituan LongCat Team, Bin Xiao, Chao Wang, Chengjiang Li 외 arxiv

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treati…

DepthART: Monocular Depth Estimation as Autoregressive Refinement Task

2024-09-23 · Bulat Gabdullin, Nina Konovalova, Nikolay Patakin, Dmitry Senushkin 외

Despite recent success in discriminative approaches in monocular depth estimation its quality remains limited by training datasets. Generative approaches mitigate this issue by leveraging strong priors derived from train…

Depth EstimationImage GenerationMonocular Depth Estimation