KORE uses knowledge-oriented control as its pivot to synergistically optimize the balance between knowledge adaptation and retention at different stag
🔄 In a Training Loop
Kailin Jiang
kailinjiang
AI & ML interests
continual learning
Recent Activity
authored a paper 5 days ago
AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research submitted a paper 5 days ago
AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep ResearchOrganizations
None yet
KORE uses knowledge-oriented control as its pivot to synergistically optimize the balance between knowledge adaptation and retention at different stag
MMEVOKE introduces the first comprehensive benchmark and systematic evaluation framework designed to investigate multimodal evolving knowledge injecti
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 • 8
kailinjiang/llava_SEFE_KORE_Aug
Updated • 10
kailinjiang/llava_Replay_KORE_Aug
Updated • 4
kailinjiang/llava_MoELoRA_KORE_Aug
Updated • 9
kailinjiang/llava_7B_replay
7B • Updated • 10
kailinjiang/llava_7B_lora
7B • Updated • 13
kailinjiang/llava_7B_full_ft
7B • Updated • 9
datasets 8
kailinjiang/AdaTutoRank-Train-Data
Viewer • Updated • 8.96k • 66
kailinjiang/SetwiseEvalKit
Viewer • Updated • 3 • 77 • 2
kailinjiang/KORE-74K
Updated • 415 • 1
kailinjiang/MMEVOKE
Viewer • Updated • 9.41k • 18 • 2
kailinjiang/MINED
Updated • 25 • 1
kailinjiang/scienceqa
Updated • 6 • 1
kailinjiang/MMKE-Bench-dataset
Preview • Updated • 142 • 4
kailinjiang/punkt
Updated • 84 • 1