Multimodal OCR: Parse Anything from Documents
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
models 8
rednote-hilab/dots.mocr
Image-Text-to-Text • 3B • Updated • 639k • 129
rednote-hilab/dots.mocr-svg
Image-Text-to-Text • 3B • Updated • 532 • 28
rednote-hilab/dots.ocr.base
Image-Text-to-Text • 3B • Updated • 27 • 13
rednote-hilab/dots.ocr
Image-Text-to-Text • 3B • Updated • 235k • 1.31k
rednote-hilab/dots.vlm1.inst
Image-Text-to-Text • Updated • 688 • 82
rednote-hilab/dots.llm1.inst
Text Generation • 143B • Updated • 25.3k • 177
rednote-hilab/dots.llm1.base
Text Generation • 143B • Updated • 1.06k • 65
rednote-hilab/dots.llm1.inst-FP8-dynamic
Text Generation • 1B • Updated • 81 • 5
datasets 0
None public yet