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.
Advances in Neural Information Processing Systems , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
MPD reduces hallucinations in LVLMs by 23.4% while retaining 97.4% of general capability through semantic disentanglement and selective parameter updates.
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.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
MPD reduces hallucinations in LVLMs by 23.4% while retaining 97.4% of general capability through semantic disentanglement and selective parameter updates.