Hejun Dong

fickle1101's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

published a model 2 days ago

fickle1101/diffocr_ckpt10k

Image-Text-to-Text • 1B • Updated 2 days ago • 12

updated a model 2 days ago

fickle1101/diffocr_ckpt10k

Image-Text-to-Text • 1B • Updated 2 days ago • 12

upvoted a paper 14 days ago

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Paper • 2606.11817 • Published 15 days ago • 18

upvoted a paper 21 days ago

OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs

Paper • 2606.03890 • Published 23 days ago • 31

upvoted a paper 3 months ago

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

Paper • 2604.04771 • Published Apr 6 • 124

commented a paper 3 months ago

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Paper • 2603.22458 • Published Mar 23 • 138 •

6

upvoted a paper 3 months ago

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Paper • 2603.22458 • Published Mar 23 • 138

updated a Space 3 months ago

Running

Agents

8

MinerU Diffusion V1 0320 2.5B

🦀

8

demo of MinerU-Diffusion

published a Space 3 months ago

Running

Agents

8

MinerU Diffusion V1 0320 2.5B

🦀

8

demo of MinerU-Diffusion

updated a model 5 months ago

fickle1101/nolayout_final_108k

3B • Updated Jan 30 • 4

published a model 5 months ago

fickle1101/nolayout_final_108k

3B • Updated Jan 30 • 4

updated a model 5 months ago

fickle1101/no_merger_pm2x_custom_lr_best_results

Updated Jan 26

published a model 5 months ago

fickle1101/no_merger_pm2x_custom_lr_best_results

Updated Jan 26

updated a model 5 months ago

fickle1101/no_merger_pm2x_s2_4e_best

3B • Updated Jan 20 • 1

published a model 5 months ago

fickle1101/no_merger_pm2x_s2_4e_best

3B • Updated Jan 20 • 1

liked a model 9 months ago

opendatalab/MinerU2.5-2509-1.2B

Image-Text-to-Text • 1B • Updated Apr 9 • 22.3k • 362

upvoted a paper 9 months ago

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Paper • 2509.22186 • Published Sep 26, 2025 • 169

published a model about 1 year ago

fickle1101/native_qwen2_5_vit_ocr

1B • Updated Jun 16, 2025 • 2

updated a model about 1 year ago

fickle1101/native_qwen2_5_vit_ocr

1B • Updated Jun 16, 2025 • 2

upvoted a paper about 1 year ago

FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

Paper • 2504.09925 • Published Apr 14, 2025 • 39