OCRia-1 Technical Report
cs.CV
Submitted: 2026-10-22
Updated: 2026-11-09
Code: https://github.com/datalab-to/chandra
Terminology
Sources
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
- Accelerating Large Language Model Decoding with Speculative Sampling
- DFlash: Block Diffusion for Flash Speculative Decoding
- Self-Evolving Curriculum for LLM Reasoning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- GLM-OCR Technical Report
- Constrained Group Relative Policy Optimization
- Infinity-Parser2 Technical Report
- MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems
- Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
- SCORE: A Semantic Evaluation Framework for Generative Document Parsing
- LIMR: Less is More for RL Scaling
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model
- DODO: Discrete OCR Diffusion Models
- olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models
- olmOCR 2: Unit Test Rewards for Document OCR
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs