Kaicheng Yang

Kaicheng Yang on Hugging Face Daily Papers: 14 papers, 0 in the top 3 of their day, 287 upvotes.

  1. NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents 6 upvotes, #27 of 2026-08-18
  2. Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval 40 upvotes, #7 of 2026-08-07
  3. UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards 15 upvotes, #9 of 2026-04-17
  4. DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset 36 upvotes, #7 of 2026-01-16
  5. ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder 9 upvotes, #18 of 2025-10-22
  6. UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning 11 upvotes, #18 of 2025-10-16
  7. LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training 38 upvotes, #8 of 2025-09-29
  8. Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval 7 upvotes, #15 of 2025-09-12
  9. ForCenNet: Foreground-Centric Network for Document Image Rectification 11 upvotes, #14 of 2025-07-29
  10. Region-based Cluster Discrimination for Visual Representation Learning 17 upvotes, #10 of 2025-07-29
  11. Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs 38 upvotes, #4 of 2025-04-25
  12. Decoupled Global-Local Alignment for Improving Compositional Understanding 15 upvotes, #10 of 2025-04-24
  13. RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm 15 upvotes, #14 of 2025-02-19
  14. ORID: Organ-Regional Information Driven Framework for Radiology Report Generation 2 upvotes, #11 of 2024-11-21

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.