GLM-OCR Technical Report
This addresses document understanding for applications in resource-constrained edge deployment and large-scale production systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of real-world document understanding by developing GLM-OCR, a compact multimodal model that achieves competitive or state-of-the-art performance in tasks like document parsing and text transcription, with a 0.9B-parameter architecture designed for efficiency.
GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance between computational efficiency and recognition performance. To address the inefficiency of standard autoregressive decoding in deterministic OCR tasks, GLM-OCR introduces a Multi-Token Prediction (MTP) mechanism that predicts multiple tokens per step, significantly improving decoding throughput while keeping memory overhead low through shared parameters. At the system level, a two-stage pipeline is adopted: PP-DocLayout-V3 first performs layout analysis, followed by parallel region-level recognition. Extensive evaluations on public benchmarks and industrial scenarios show that GLM-OCR achieves competitive or state-of-the-art performance in document parsing, text and formula transcription, table structure recovery, and key information extraction. Its compact architecture and structured generation make it suitable for both resource-constrained edge deployment and large-scale production systems.