kelatte

kelatte's activity

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

upvoted a paper 5 days ago

SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents

Paper • 2607.23263 • Published Jul 25 • 1

updated a dataset 28 days ago

ZJUSCL/CUAStepBench

Viewer • Updated 28 days ago • 212 • 6.08k • 1

published a dataset about 1 month ago

ZJUSCL/CUAStepBench

Viewer • Updated 28 days ago • 212 • 6.08k • 1

published a model about 1 month ago

ZJUSCL/SeekJudge-9B

Image-Text-to-Text • 1.47M • Updated Jul 24 • 14

updated a model about 1 month ago

ZJUSCL/SeekJudge-9B

Image-Text-to-Text • 1.47M • Updated Jul 24 • 14

updated a model 2 months ago

kelatte/qwen3_8b_dpo_mitigating_inertia

Updated Jun 27 • 1

published a model 2 months ago

kelatte/qwen3_8b_dpo_mitigating_inertia

Updated Jun 27 • 1

updated a dataset 3 months ago

kelatte/qwen3-8b-dpo-agentgym-rft-data

Viewer • Updated Jun 15 • 8k • 38

published a dataset 3 months ago

kelatte/qwen3-8b-dpo-agentgym-rft-data

Viewer • Updated Jun 15 • 8k • 38

updated a model 3 months ago

kelatte/qwen3_8b_dpo_8env2_allstep4x_forcediff_r16a16

Text Generation • Updated Jun 15 • 5

published a model 3 months ago

kelatte/qwen3_8b_dpo_8env2_allstep4x_forcediff_r16a16

Text Generation • Updated Jun 15 • 5

upvoted a paper 3 months ago

VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

Paper • 2606.05259 • Published Jun 3 • 39

upvoted a paper over 1 year ago

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing

Paper • 2502.17258 • Published Feb 24, 2025 • 79