seohyun PRO
happy8825
AI & ML interests
VLM, Generative Models
Recent Activity
upvoted a paper about 3 hours ago
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems upvoted a paper 10 days ago
RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting authored a paper 11 days ago
Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMsOrganizations
doc_experiment_result
-
happy8825/MMLongBench_image_question_only_deepeyes_multi_viz_2_1120_new
Viewer • Updated • 1.07k • 18 -
happy8825/MMLongBench_base_deepeyes_multi_2_iter_1120_new
Viewer • Updated • 1.07k • 10 -
happy8825/MMLongBench_base_deepeyes_wo_image
Viewer • Updated • 1.07k • 10 -
happy8825/mmlongbench_evl_result
Viewer • Updated • 1.07k • 13
video experiment result
my_robot_arm_recorded
ECVA_fixed_data
abnormal_data
doc_experiment_result
-
happy8825/MMLongBench_image_question_only_deepeyes_multi_viz_2_1120_new
Viewer • Updated • 1.07k • 18 -
happy8825/MMLongBench_base_deepeyes_multi_2_iter_1120_new
Viewer • Updated • 1.07k • 10 -
happy8825/MMLongBench_base_deepeyes_wo_image
Viewer • Updated • 1.07k • 10 -
happy8825/mmlongbench_evl_result
Viewer • Updated • 1.07k • 13
Video-Retrieval-Dataset
video experiment result
vid_fixed_train_validset
my_robot_arm_recorded
doc_agent_dataset