Soohyun Ryu
rsoohyun
AI & ML interests
None yet
Recent Activity
upvoted a paper about 15 hours ago
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs upvoted a paper 4 days ago
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL upvoted a paper 16 days ago
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache QuantizationOrganizations
None yet
models 6
rsoohyun/SpatialBlock-4B-reason
Image-Text-to-Text • 5B • Updated • 32 • 1
rsoohyun/SpatialBlock-4B-direct
Image-Text-to-Text • 4B • Updated • 38 • 1
rsoohyun/SpatialBlock-7B-reason
Image-Text-to-Text • 8B • Updated • 33
rsoohyun/SpatialBlock-7B-direct
Image-Text-to-Text • 8B • Updated • 33
rsoohyun/SpatialBlock-3B-reason
Image-Text-to-Text • 4B • Updated • 25
rsoohyun/SpatialBlock-3B-direct
Image-Text-to-Text • 4B • Updated • 46 • 2