Soohyun Ryu

rsoohyun213's activity

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

updated a model 1 day ago

rsoohyun213/Qwen2.5-VL-7B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_filtered-full_SFT

Image-Text-to-Text • 849k • Updated 1 day ago • 73

published a model 1 day ago

rsoohyun213/Qwen2.5-VL-7B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_filtered-full_SFT

Image-Text-to-Text • 849k • Updated 1 day ago • 73

updated a model 1 day ago

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_filtered-full_SFT

Image-Text-to-Text • 756k • Updated 1 day ago • 67

published a model 1 day ago

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_filtered-full_SFT

Image-Text-to-Text • 756k • Updated 1 day ago • 67

updated 2 models 1 day ago

rsoohyun213/Qwen2.5-VL-7B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver3_filtered-rank16-dr0.05-lr1e-05

Image-Text-to-Text • 8B • Updated 1 day ago • 26

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver3_filtered-rank8-dr0.05-lr1e-04

Image-Text-to-Text • 4B • Updated 1 day ago • 25

published 2 models 1 day ago

rsoohyun213/Qwen2.5-VL-7B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver3_filtered-rank16-dr0.05-lr1e-05

Image-Text-to-Text • 8B • Updated 1 day ago • 26

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver3_filtered-rank8-dr0.05-lr1e-04

Image-Text-to-Text • 4B • Updated 1 day ago • 25

upvoted 2 papers about 1 month ago

TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs

Paper • 2606.09030 • Published Jun 8 • 30

Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models

Paper • 2606.16281 • Published Jun 15 • 34

published a model 2 months ago

rsoohyun213/Qwen2.5-VL-7B-Instruct-v6_s5_exp1_only_blocks_ver3-full_SF

Updated May 13

updated 3 models 2 months ago

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s4_exp2_s5_exp1_only_blocks_ver3-full_SFT

Image-Text-to-Text • 756k • Updated May 13 • 4

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s5_exp1_only_blocks_ver3-full_SFT

Image-Text-to-Text • 756k • Updated May 13 • 7

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_only_blocks_ver3-full_SFT

Image-Text-to-Text • 756k • Updated May 13 • 6

upvoted a paper 2 months ago

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Paper • 2605.08735 • Published May 9 • 71

published 3 models 3 months ago

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s4_exp2_s5_exp1_only_blocks_ver3-full_SFT

Image-Text-to-Text • 756k • Updated May 13 • 4

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s5_exp1_only_blocks_ver3-full_SFT

Image-Text-to-Text • 756k • Updated May 13 • 7

rsoohyun213/Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_only_blocks_ver3-full_SFT

Image-Text-to-Text • 756k • Updated May 13 • 6

updated a model 3 months ago

rsoohyun213/Qwen2.5-VL-3B-Instruct-cold_start_gpt-5

Image-Text-to-Text • 4B • Updated May 7 • 3

published a model 3 months ago

rsoohyun213/Qwen2.5-VL-3B-Instruct-cold_start_gpt-5

Image-Text-to-Text • 4B • Updated May 7 • 3