Unverified50% confidenceReleaseExact time
The SoMarkAI team has open-sourced a 1.3B-parameter document parsing model, OXR.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedOXR decouples layout analysis from recognition: recognition and reading order are executed in parallel within the same model to ensure speed, while layout analysis is an independent model that can be replaced as needed.61% similarUnverifiedOllama通过Modelfile定义模型的配置、系统提示与量化参数，形成可版本化、可分发的模型镜像60% similarUnverifiedAntAngelMed is a medical-domain Mixture-of-Experts (MoE) model with 103B total parameters and 6.1B activated parameters.59% similarUnverifiedVarious labs have released reasoning models, such as the o1 and o3 series.58% similarUnverifiedOXR's post-training stage employs error-sample-driven iterative data augmentation: samples where the model errs or is uncertain are converted into textual rationales, and the rationales are clustered to drive the generation of targeted training data for the next round.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115193API
curl https://kongchang.com/api/v1/knowledge/claims/1115193MCP
get_claim(id=1115193)