会员服务
RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
Arxiv
0+阅读 · 6月22日
A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR
A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR
Arxiv
0+阅读 · 6月23日
Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR
Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR
Arxiv
0+阅读 · 6月22日
Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline
Arxiv
0+阅读 · 6月21日
Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri
Arxiv
0+阅读 · 6月22日
Unlimited OCR Works
Arxiv
0+阅读 · 6月22日
SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering
Arxiv
0+阅读 · 6月17日
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
Arxiv
0+阅读 · 6月18日
PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction
Arxiv
0+阅读 · 6月17日
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
Arxiv
0+阅读 · 6月16日
MixTeX: Data-Efficient LaTeX OCR via Synthetic Pretraining and Limited Fine-Tuning
Arxiv
0+阅读 · 6月15日
Manga109-v2026: Revisiting Manga109 Annotations for Modern Manga Understanding
Arxiv
0+阅读 · 6月12日
Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs
Arxiv
0+阅读 · 6月12日
Hierarchical Online Prompt Mutation with Dual-Loop Feedback for Guardrailed Evidence Document Generation: A Production-Evaluation Case Study
Arxiv
0+阅读 · 5月31日
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
Arxiv
0+阅读 · 5月6日
参考链接
微信扫码咨询专知VIP会员
Top