[2601.14251] LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

Abstract page for arXiv paper 2601.14251: LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

Category : Articles

Updated : 16.07.26

License : Paid

Artificial intelligence is your virtual companion

Official site

Video

Feedback

Comments 0

Alternatives

All →

[2602.03510] Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

Tongyi DeepResearch: A New Era of Open-Source AI Researchers | Tongyi DeepResearch

LeVo

Kimi K2 Thinking

Hunyuan-GameCraft

WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference

DiffusionLight: Light Probes for Free by Painting a Chrome Ball

[2602.04804] OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Vidi2: Large Multimodal Models for Video Understanding and Creation

Qwen3-Coder: Agentic Coding in the World | Qwen

DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance

X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention

AI or Human

[2602.07120] Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

[2601.13976] FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation

Qwen3: Think Deeper, Act Faster | Qwen

Lumiere

[2601.14232] KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

Videos

All →