seohyun PRO
happy8825
AI & ML interests
VLM, Generative Models
Recent Activity
authored a paper 1 day ago
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models authored a paper 1 day ago
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query RefinementOrganizations
models 12
happy8825/ecva-sft-20251224
2B • Updated • 1
happy8825/siglip-ecva-best
92.9M • Updated • 2
happy8825/internvideo_tuned
Updated
happy8825/best77ecva_tuned-20251223
2B • Updated • 1
happy8825/siglip-ecva-main
92.9M • Updated • 3
happy8825/ecva_instruction_tuned-20251216
Image-Text-to-Text • 2B • Updated • 1
happy8825/ecvatuned-20251216
Image-Text-to-Text • 2B • Updated • 2
happy8825/ecvatuned-20251215
Updated
happy8825/qweninstruct_sft-20251211
Image-Text-to-Text • 2B • Updated • 5
happy8825/sft-20251126
Image-Text-to-Text • 2B • Updated • 2
datasets 119
happy8825/internvideo_result_
Viewer • Updated • 924 • 12
happy8825/MMLongBench_var9_exp_with_image_verifier_n
Viewer • Updated • 1.07k • 17
happy8825/MMLongBench_var11_prompt_enhanced_0112
Viewer • Updated • 16 • 10
happy8825/MMLongBench_var11_prompt_enhanced_0111
Viewer • Updated • 345 • 17
happy8825/MMLongBench_var11_prompt_enhanced
Viewer • Updated • 1.07k • 17
happy8825/experiment_qualcheck
Viewer • Updated • 924 • 19
happy8825/experiment_instruction_notune_
Viewer • Updated • 924 • 15
happy8825/experiment_real_bitsandbytes
Viewer • Updated • 924 • 24
happy8825/experiment_real_fp8
Viewer • Updated • 924 • 22
happy8825/experiment_fp8
Viewer • Updated • 924 • 22