🔄 In a Training Loop
Kailin Jiang
kailinjiang
AI & ML interests
continual learning
Recent Activity
upvoted a paper about 6 hours ago
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning upvoted a collection about 9 hours ago
OpenETA upvoted a paper about 9 hours ago
ETA: A New Agentic Paradigm for Embodied TasksOrganizations
None yet
models 84
kailinjiang/llava_1.5_13b_covariance_matrices_from_onevision_pre_64_seed_rank233_new222
Updated
kailinjiang/llava_1.5_13b_covariance_matrices_from_onevision_pre_64_seed_rank233_new
Updated
kailinjiang/llava_1.5_7b_covariance_matrices_from_onevision_pre_64_seed_rank233
Updated
kailinjiang/llava_OLoRA_KORE_Aug
Updated • 5
kailinjiang/llava_SEFE_KORE_Aug
Updated • 3
kailinjiang/llava_Replay_KORE_Aug
Updated • 4
kailinjiang/llava_MoELoRA_KORE_Aug
Updated • 9
kailinjiang/llava_7B_replay
7B • Updated • 5
kailinjiang/llava_7B_lora
7B • Updated • 3
kailinjiang/llava_7B_full_ft
7B • Updated • 3
datasets 7
kailinjiang/SetwiseEvalKit
Viewer • Updated • 3 • 316 • 2
kailinjiang/KORE-74K
Updated • 63 • 1
kailinjiang/MMEVOKE
Viewer • Updated • 9.41k • 47 • 2
kailinjiang/MINED
Updated • 20 • 1
kailinjiang/scienceqa
Updated • 27 • 1
kailinjiang/MMKE-Bench-dataset
Preview • Updated • 149 • 3
kailinjiang/punkt
Updated • 64 • 1