REVIEW 5 cited by
SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-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
Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which brings challenges related to efficiency, effectiveness, and quality of web data. In this paper, we introduce SynthVLM, a new data synthesis and curation method for generating image-caption pairs. Unlike traditional methods, where captions are generated from images, SynthVLM utilizes advanced diffusion models and high-quality captions to synthesize and select images from text captions, thereby creating precisely aligned image-text pairs. We further introduce SynthVLM-100K, a high-quality dataset consisting of 100K curated and synthesized image-caption pairs. In both model and human evaluations, SynthVLM-100K outperforms traditional real-world datasets. Leveraging this dataset, we develop a new family of multimodal large language models (MLLMs), SynthVLM-7B and SynthVLM-13B, which achieve state-of-the-art (SOTA) performance on various vision question-answering (VQA) tasks. Notably, our models outperform LLaVA across most metrics with only 18\% pretrain data. Furthermore, SynthVLM-7B and SynthVLM-13B attain SOTA performance on the MMLU benchmark, demonstrating that the high-quality SynthVLM-100K dataset preserves language abilities.
Forward citations
Cited by 5 Pith papers
-
Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study
A query-conditioned, snippet-grounded LLM pipeline extracts causal evidence from ReliefWeb reports and triangulates it into a Level-of-Evidence score, reporting high F1 and strong positive convergence for cash assista...
-
LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning
Adapting a text-to-image generator with task-specific LoRA adapters and filtering samples by the model's own confidence improves synthetic replay in continual vision-language learning.
-
Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation
Fine-tuning open vision-language models on 240K synthetic question-answer pairs with exact camera-object labels improves camera-object recognition by 33.4% on average over GPT-4o and Claude-3-Sonnet on the paper's benchmark.
-
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
OpenWorldLib offers a standardized codebase and definition for world models that combine perception, interaction, and memory to understand and predict the world.
-
BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion
A roughly 1.2B-parameter VQA model with a distilled 31M CLIP encoder and Q-gated cross-attention reports accuracies comparable to 7B-13B baselines on GQA, VQAv2, and VizWiz.
Discussion (0). Continue with ORCID to comment.