Model Detail
Polaris_Pro
—Polaris_Pro is a multimodal model with 8B parameters released by sais-org. The model is registered under the image-text-to-text pipeline tag on Hugging Face, distributed under a other license.
Polaris_Pro ships with 8B parameters. Total weight footprint is approximately 11.7 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.
Polaris_Pro is best fit for mixed text-and-image reasoning tasks such as document understanding. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
POLARIS: Guiding Small Models to Write Long Stories
arXiv:2606.04095v2 Announce Type: replace-cross Abstract: Small open-weight models struggle at long-form creative writing: their generated stories either fall far short of the requested length, or their quality significantly degrades as length increases, especially when compared to frontier models.
Polaris: A G\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
arXiv:2603.23129v4 Announce Type: replace Abstract: G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, G\"odel agent for compact models that performs policy repair via experience abstract
Polaris: A Godel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
arXiv:2603.23129v3 Announce Type: replace Abstract: G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, a G\"odel agent for compact models that performs policy repair via experience abstra
Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning
arXiv:2605.00265v2 Announce Type: replace Abstract: Real-world knowledge is often organized as hierarchies such as product taxonomies, medical ontologies, and label trees, yet learning hierarchical representations is challenging due to asymmetric structure and noisy semantics. We introduce Polaris,
