A self-supervision method makes multimodal LLMs align their input image embeddings with the model's own refined internal representations, improving visual QA scores over LLaVA baselines.
Multi-modal Auto-regressive Modeling via Visual Words
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
A self-supervision method makes multimodal LLMs align their input image embeddings with the model's own refined internal representations, improving visual QA scores over LLaVA baselines.