REVIEW 4 cited by
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Multimodal Large Language Models (MLLMs) have shown impressive results on various multimodal tasks. However, most existing MLLMs are not well suited for document-oriented tasks, which require fine-grained image perception and information compression. In this paper, we present TextHawk, a MLLM that is specifically designed for document-oriented tasks, while preserving the general capabilities of MLLMs. TextHawk is aimed to explore efficient fine-grained perception by designing four dedicated components. Firstly, a ReSampling and ReArrangement (ReSA) module is proposed to reduce the redundancy in the document texts and lower the computational cost of the MLLM. We explore encoding the positions of each local feature by presenting Scalable Positional Embeddings (SPEs), which can preserve the scalability of various image sizes. A Query Proposal Network (QPN) is then adopted to initialize the queries dynamically among different sub-images. To further enhance the fine-grained visual perceptual ability of the MLLM, we design a Multi-Level Cross-Attention (MLCA) mechanism that captures the hierarchical structure and semantic relations of document images. Furthermore, we create a new instruction-tuning dataset for document-oriented tasks by enriching the multimodal document data with Gemini Pro. We conduct extensive experiments on both general and document-oriented MLLM benchmarks, and show that TextHawk outperforms the state-of-the-art methods, demonstrating its effectiveness and superiority in fine-grained document perception and general abilities.
Forward citations
Cited by 4 Pith papers
-
Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency
A fine-tuning paradigm that prompts MLLMs to self-generate OCR text before translating document images improves DIMT quality and reduces catastrophic forgetting of OCR.
-
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
M4Doc distills the multimodal representations of a frozen MLLM into an image-only encoder, improving document image translation quality and generalization without requiring the MLLM at inference.
-
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
A two-stage model that analyzes page layout first, then parses text, tables, and formulas in parallel, reports state-of-the-art accuracy and speed on the benchmarks it evaluates.
-
Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models
A new resolution-focused benchmark and an open-source native-resolution training framework show that preserving original image resolution improves VLM performance on fine-grained visual tasks.
Discussion (0). Continue with ORCID to comment.