Kaiyu Yue

kaiyuyue's activity

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

upvoted a paper 17 days ago

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

Paper • 2511.07384 • Published 18 days ago • 15

updated a model 26 days ago

kaiyuyue/FLUX.1-dev-vae

Updated 26 days ago • 33

published a model 26 days ago

kaiyuyue/FLUX.1-dev-vae

Updated 26 days ago • 33

New activity in tomg-group-umd/pixelprose 3 months ago

Can you provide the id mapping from pixelprose-cc12m-annos to the original cc12m-wds?

1

#9 opened 3 months ago by

Evanxuliu

upvoted a paper 3 months ago

DynaGuard: A Dynamic Guardrail Model With User-Defined Policies

Paper • 2509.02563 • Published Sep 2 • 20

New activity in tomg-group-umd/zero-model-checkpoints 4 months ago

Improve model card: Update license, add abstract, usage, and citation

1

#2 opened 4 months ago by

nielsr

New activity in kaiyuyue/llava-1.5-665k-instructions 4 months ago

Update dataset card: Link to paper and code, add task category and tags

#2 opened 4 months ago by

nielsr

New activity in kaiyuyue/llava-1.5-665k-genqa-500k-instructions 4 months ago

Update dataset card: correct license, task category, and add paper/code links

#1 opened 4 months ago by

nielsr

updated a dataset 4 months ago

multimodal-reasoning-lab/Zebra-CoT

Viewer • Updated Jul 26 • 160k • 10k • 58

authored a paper 4 months ago

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Paper • 2507.16746 • Published Jul 22 • 35

liked a dataset 4 months ago

multimodal-reasoning-lab/Zebra-CoT

Viewer • Updated Jul 26 • 160k • 10k • 58

upvoted a paper 4 months ago

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Paper • 2507.16746 • Published Jul 22 • 35

published a dataset 5 months ago

tomg-group-umd/pixelprose-jsons

Preview • Updated Jul 3 • 79

updated a dataset 5 months ago

tomg-group-umd/pixelprose-jsons

Preview • Updated Jul 3 • 79

updated a model 5 months ago

tomg-group-umd/zero-model-checkpoints

Image-Text-to-Text • Updated Aug 5 • 2

upvoted a paper 5 months ago

Zero-Shot Vision Encoder Grafting via LLM Surrogates

Paper • 2505.22664 • Published May 28 • 7

upvoted 2 papers 6 months ago

ARGUS: Hallucination and Omission Evaluation in Video-LLMs

Paper • 2506.07371 • Published Jun 9 • 8

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Paper • 2506.05523 • Published Jun 5 • 34

New activity in tomg-group-umd/zero-model-checkpoints 6 months ago

Fix pipeline tag and add link to paper

1

#1 opened 6 months ago by

nielsr

authored a paper 6 months ago

Zero-Shot Vision Encoder Grafting via LLM Surrogates

Paper • 2505.22664 • Published May 28 • 7