STROP learns variable-length discrete visual programs for images by training a length head against frozen DINOv3 features in a four-phase curriculum while bypassing pixel reconstruction.
arXiv preprint arXiv:2406.07550 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
fields
cs.CV 7representative citing papers
Engram in AR image generation saves backbone FLOPs but trails pure AR baselines in FID and behaves as a gated side-pathway rather than a content-addressed retriever.
VFMTok builds a generalist image tokenizer on frozen VFMs using adaptive quantization and semantic alignment, delivering gFID 1.36 for autoregressive and 1.25 for continuous generation on ImageNet with 3x faster convergence.
ViTok-v2 is a 5B-parameter native-resolution image autoencoder using NaFlex and DINOv3 loss that matches or exceeds prior tokenizers at 256p and outperforms them at 512p and above while advancing the Pareto frontier in joint scaling with generators.
CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation.
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
citing papers explorer
-
Structure over Pixels: Learning Variable-Length Visual Programs
STROP learns variable-length discrete visual programs for images by training a length head against frozen DINOv3 features in a four-phase curriculum while bypassing pixel reconstruction.
-
Vision Foundation Models as Generalist Tokenizers for Image Generation
VFMTok builds a generalist image tokenizer on frozen VFMs using adaptive quantization and semantic alignment, delivering gFID 1.36 for autoregressive and 1.25 for continuous generation on ImageNet with 3x faster convergence.
-
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
ViTok-v2 is a 5B-parameter native-resolution image autoencoder using NaFlex and DINOv3 loss that matches or exceeds prior tokenizers at 256p and outperforms them at 512p and above while advancing the Pareto frontier in joint scaling with generators.
-
CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.