詹佳豪

JohnZhan

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

upvoted a paper 26 days ago

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

upvoted a paper 27 days ago

SpatialASM: Internalizing Active Mentalization for Spatial Reasoning

View all activity

Organizations

Papers 7

arxiv:2610.03543

arxiv:2609.37030

arxiv:2609.06758

arxiv:2510.06231

models 13

JohnZhan/MotionInsight-8B

Video-Text-to-Text • 832k • Updated Oct 3 • 44 • 2

JohnZhan/DuoMatching

Updated Oct 2 • 4

JohnZhan/StateTransformer2

Updated Oct 14, 2024 • 1

JohnZhan/str_dp

Updated May 31, 2024

JohnZhan/moe_formal

Updated May 29, 2024

JohnZhan/str_one_frame_formal

Updated May 28, 2024

JohnZhan/str_formal

Updated May 27, 2024

JohnZhan/str_warmup

Updated May 26, 2024

JohnZhan/ADD_traj_DP

Updated May 26, 2024

JohnZhan/str_model

Updated May 25, 2024

datasets 1

JohnZhan/StateTransformer_processes_NuPlan

Updated Oct 19, 2024 • 3