aries huang

skyai798's activity

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

upvoted a paper 9 days ago

Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks

Paper • 2610.35671 • Published 14 days ago • 8

published 2 datasets 3 months ago

T-STAR-Lab/BehaviouralLoC-Mitigation

Viewer • Updated Jul 31 • 15.1k • 37

T-STAR-Lab/BehaviouralLoC

Viewer • Updated Jul 31 • 25.1k • 86

updated 2 datasets 3 months ago

T-STAR-Lab/BehaviouralLoC-Mitigation

Viewer • Updated Jul 31 • 15.1k • 37

T-STAR-Lab/BehaviouralLoC

Viewer • Updated Jul 31 • 25.1k • 86

updated 3 models 7 months ago

skyai798/qwen3.5-27b-concat-v2

Image-Text-to-Text • 3.05M • Updated Apr 20 • 12

skyai798/qwen3.5-27b-targeted-v2

Image-Text-to-Text • 3.05M • Updated Apr 20 • 6

skyai798/qwen3.5-27b-single-v2

Image-Text-to-Text • 3.05M • Updated Apr 20 • 6

published 3 models 7 months ago

skyai798/qwen3.5-27b-targeted-v2

Image-Text-to-Text • 3.05M • Updated Apr 20 • 6

skyai798/qwen3.5-27b-single-v2

Image-Text-to-Text • 3.05M • Updated Apr 20 • 6

skyai798/qwen3.5-27b-concat-v2

Image-Text-to-Text • 3.05M • Updated Apr 20 • 12

liked a dataset 11 months ago

skyai798/DeceptionBench

Viewer • Updated Nov 26, 2025 • 150 • 493 • 4

updated a dataset 12 months ago

skyai798/DeceptionBench

Viewer • Updated Nov 26, 2025 • 150 • 493 • 4

New activity in skyai798/DeceptionBench 12 months ago

Improve dataset card: Add paper, code, task categories, overview, data structure, and sample usage

#2 opened 12 months ago by

nielsr

New activity in hlttxdy/STAR-1_DeepSeek-R1-Distill-Qwen-7B_dpo_over_refusal_mix_safep0.7_epoch2_lr1e-6_beta0.05_ftx0.2 about 1 year ago

Upload all_results.json with huggingface_hub

#1 opened about 1 year ago by

skyai798

updated a model about 1 year ago

skyai798/STAR-1_DeepSeek-R1-Distill-Llama-8B_sft-complete-dpo

Text Generation • 8B • Updated Sep 2, 2025 • 14

published a model about 1 year ago

skyai798/STAR-1_DeepSeek-R1-Distill-Llama-8B_sft-complete-dpo

Text Generation • 8B • Updated Sep 2, 2025 • 14

published a dataset over 1 year ago

skyai798/DeceptionBench

Viewer • Updated Nov 26, 2025 • 150 • 493 • 4

updated a model over 1 year ago

thu-ml/STAIR-Llama-3.1-8B-DPO-3

Text Generation • 8B • Updated Feb 26, 2025 • 23

published a model over 1 year ago

thu-ml/STAIR-Llama-3.1-8B-DPO-3

Text Generation • 8B • Updated Feb 26, 2025 • 23