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.
International Conference on Machine Learning , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Covariance structure and coordinate heterogeneity in InfoNCE embeddings control binary quantization fidelity, with off-diagonals contributing 30-50% of signal and heterogeneity determining rotation benefit and bit utility under a Gaussian model.
MMGuard generates unlearnable multimodal examples via perturbations that exploit LVLM optimization shortcuts and disrupt cross-modal bindings, providing robust protection against unauthorized fine-tuning across threat models.
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
CoRe combines VLM-designed formal rewards with VLM-labeled residual rewards to produce preference-aligned policies on robotic manipulation tasks.
citing papers explorer
-
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.
-
Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings
Covariance structure and coordinate heterogeneity in InfoNCE embeddings control binary quantization fidelity, with off-diagonals contributing 30-50% of signal and heterogeneity determining rotation benefit and bit utility under a Gaussian model.
-
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
MMGuard generates unlearnable multimodal examples via perturbations that exploit LVLM optimization shortcuts and disrupt cross-modal bindings, providing robust protection against unauthorized fine-tuning across threat models.
-
Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
-
CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning
CoRe combines VLM-designed formal rewards with VLM-labeled residual rewards to produce preference-aligned policies on robotic manipulation tasks.