OXR Releases Open-Source Document Parser with RSI Training Loop

1 reports archived1 independent sourcesupdated 10/21/2026, 03:39:01

Synthesis & Latest Updates

1 Sources Cross-Validated

OXR releases a 1.3B-parameter open-source document parser that pioneers Recursive Self-Improvement (RSI) in OCR training. By using VLMs to evaluate outputs and cluster failure causes for targeted data generation, the model tops olmOCR-Bench, OmniDocBench, and DocParsingBench while achieving 3.05x the throughput of GLM-OCR on a single RTX PRO 6000.

LATEST/OXR releases a 1.3B-parameter open-source document parser that pioneers Recursive Self-Improvement (RSI) in OCR training. By using VLMs to evaluate outputs and cluster failure causes for targeted data generation, the model tops olmOCR-Bench, OmniDocBench, and DocParsingBench while achieving 3.05x the throughput of GLM-OCR on a single RTX PRO 6000.

HEAT TRENDHourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

TIMELINECoverage timeline

Total 1 reports · Latest first

Rohan Paul (@rohanpaul_ai)T2·Oct 21, 03:3978 pts
OXR Releases Open-Source Document Parser with RSI Training Loop
- First open-source document parser to use Recursive Self-Improvement (RSI) in post-training
- The 1.3B parameter model ranks #1 on olmOCR-Bench, OmniDocBench, and DocParsingBench
- Achieves 3.05x the throughput of GLM-OCR on a single RTX PRO 6000 GPU
View Related Reports & Analysis Original Source