Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

Posted by klaurent UCAS

Kavli Affiliate: Biao Huang| First 5 Authors: Baode Wang, Baode Wang, , , | Summary:Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse layouts. We introduce layoutRL, an end-to-end reinforcement learning framework that trains […]


Continue.. Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models

Posted by klaurent Stanford

Kavli Affiliate: Hsiao-Mei (Sherry) Cho| First 5 Authors: [#item_custom_name[1, [#item_custom_name[2, [#item_custom_name[3, [#item_custom_name[4, [#item_custom_name[5| Summary:Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional generation often rely on external encoders or architectural modifications, which demand large datasets and are […]


Continue.. Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models

L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning

Posted by dbos Berkeley

Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiang Zhang, Run He, Jiao Chen, Di Fang, Ming Li | Summary: Class-incremental learning (CIL) enables models to learn new classes continually without forgetting previously acquired knowledge. Multi-label CIL (MLCIL) extends CIL to a real-world scenario where each sample may belong to multiple classes, introducing several challenges: […]


Continue.. L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning