REVIEW 26 cited by
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
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
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
read the original abstract
With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations including clean image captions and regional labels limits the scalability of existing approaches, and complicates the pretraining procedure with the introduction of multiple dataset-specific objectives. In this work, we relax these constraints and present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM). Unlike prior work, SimVLM reduces the training complexity by exploiting large-scale weak supervision, and is trained end-to-end with a single prefix language modeling objective. Without utilizing extra data or task-specific customization, the resulting model significantly outperforms previous pretraining methods and achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks, including VQA (+3.74% vqa-score), NLVR2 (+1.17% accuracy), SNLI-VE (+1.37% accuracy) and image captioning tasks (+10.1% average CIDEr score). Furthermore, we demonstrate that SimVLM acquires strong generalization and transfer ability, enabling zero-shot behavior including open-ended visual question answering and cross-modality transfer.
Forward citations
Cited by 26 Pith papers
-
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
-
PaLI: A Jointly-Scaled Multilingual Language-Image Model
PaLI jointly scales a 4B-parameter vision transformer with language models on a new 10B multilingual image-text dataset to reach state-of-the-art results on vision-language tasks while keeping a simple modular design.
-
A Generalist Agent
Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.
-
Flamingo: a Visual Language Model for Few-Shot Learning
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
-
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
-
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
Attenuating FFN outputs at mid-to-late transformer layers reduces language-prior dominance and thereby mitigates object hallucinations in LVLMs while preserving efficiency.
-
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
FADE attenuates FFN outputs in LVLMs based on layer-wise information flow analysis to mitigate hallucinations, shown effective on POPE, CHAIR, and MME benchmarks.
-
KidRisk: Benchmark Dataset for Children Dangerous Action Recognition
KidRisk is a new benchmark dataset for children's dangerous action recognition where vision-language models reach 96.14% accuracy on danger detection, outperforming traditional deep learning.
-
Let ViT Speak: Generative Language-Image Pre-training
GenLIP pretrains ViTs to generate language tokens from images via LM objective without contrastive batches or extra decoders, matching baselines on less data and improving on OCR after multi-resolution continued pretraining.
-
RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation
RIHA proposes a hierarchical alignment transformer that uses multi-scale visual and textual feature pyramids plus optimal transport to generate more accurate radiology reports from medical images.
-
MApLe: Multi-instance Alignment of Diagnostic Reports and Large Medical Images
MApLe disentangles anatomy and pathology to align free-text diagnostic sentences with specific patches in large medical images via multi-instance learning.
-
Inner Monologue: Embodied Reasoning through Planning with Language Models
LLMs form an inner monologue from closed-loop language feedback to improve high-level instruction completion in simulated and real robotic rearrangement and kitchen manipulation tasks.
-
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Scaling an autoregressive Transformer to 20B parameters for text-to-image generation using image token sequences achieves new SOTA zero-shot FID of 7.23 and fine-tuned FID of 3.22 on MS-COCO.
-
CoCa: Contrastive Captioners are Image-Text Foundation Models
CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.
-
Florence: A New Foundation Model for Computer Vision
Florence is a new vision foundation model that learns universal visual-language representations from web-scale data and reports state-of-the-art results on 44 benchmarks including 83.74% zero-shot ImageNet top-1 accuracy.
-
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
FADE attenuates FFN outputs at critical layers in LVLMs to curb language-prior dominance and cut hallucinations, shown effective on POPE, CHAIR, and MME across three models.
-
WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning
WEQA proposes a query-adaptive agent framework combining LLMs with wearable data tools, achieving 24% higher accuracy than baselines on a benchmark from four open datasets, with gains in expert-rated usefulness.
-
ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
ECA introduces continual alignment with MoQ, FeDEx, and DR for exemplar-free incremental learning in open-ended image-to-text generation, evaluated on four new benchmarks showing reduced forgetting.
-
Let ViT Speak: Generative Language-Image Pre-training
GenLIP pretrains ViTs to generate language tokens from visual tokens via autoregressive language modeling, matching strong baselines on multimodal tasks with less data.
-
WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval
WRF4CIR uses weight-regularized fine-tuning with adversarial perturbations to mitigate overfitting in composed image retrieval and narrows the generalization gap on benchmarks.
-
Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method
A progressive curriculum that trains open-vocabulary detectors on low-ambiguity, high-signal cross-modal alignments first improves robustness to visual domain shifts, with modest, test-tuned gains.
-
Medical Report Generation: A Hierarchical Task Structure-Based Cross-Modal Causal Intervention Framework
HTSC-CIF applies hierarchical task decomposition and cross-modal causal intervention to generate medical reports from images while addressing domain knowledge, alignment, and bias challenges.
-
Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments
Introduces GRIT, LTMI, and a hierarchical attention framework claiming performance gains on image captioning, visual dialog, and ALFRED instruction following.
-
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
-
A Survey on Multimodal Large Language Models
This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.