vangard703/output_fast_200K
Image-Text-to-Text • 8B • Updated
dongyoung kim
vangard703
AI & ML interests
None yet
Recent Activity
upvoted a paper 24 days ago
Trust Region Q Adjoint Matching upvoted a paper 24 days ago
Benchmarking Visual State Tracking in Multimodal Video UnderstandingOrganizations
vangard703/vlm_1500k_reasoning_100k_fast_400k_v6
Image-Text-to-Text • 8B • Updated
vangard703/vlm_200k_fast_full_v3_1
Image-Text-to-Text • 8B • Updated
vangard703/vlm_1600k_fast_400k_with_cot_v4
Image-Text-to-Text • 8B • Updated • 1
vangard703/output_stage2_v3_1100K_vlm_200K_fast_10
Image-Text-to-Text • 8B • Updated • 1
vangard703/ROBOTR1_split2_v3_110K_vlm_110K_fast
Image-Text-to-Text • 8B • Updated • 2
vangard703/output_stage2_v3_1100K_vlm_200K_fast
Image-Text-to-Text • 8B • Updated • 1
vangard703/output_stage2_v3_fast_600_140_full_10
Image-Text-to-Text • 8B • Updated
vangard703/output_stage2_v3_fast_600_140
Updated
vangard703/output_stage2_v2_fast
Image-Text-to-Text • 8B • Updated
vangard703/output_refspatial_only_llm
Image-Text-to-Text • 8B • Updated
vangard703/output_stage2_v2
Image-Text-to-Text • 8B • Updated
vangard703/output_stage2
Image-Text-to-Text • 8B • Updated
vangard703/output_stage1
Image-Text-to-Text • 8B • Updated
vangard703/output_only_llm
Image-Text-to-Text • 8B • Updated
vangard703/output_full_no_robovqa
Image-Text-to-Text • 8B • Updated • 1
vangard703/output_full_no_multiview
Image-Text-to-Text • 8B • Updated • 3
vangard703/output_full_no_temporal
Image-Text-to-Text • 8B • Updated • 1
vangard703/output_full_no_trajectory
Image-Text-to-Text • 8B • Updated • 1
vangard703/EmbodiedVLM_1.7M_Without_Fast_video
Image-Text-to-Text • 8B • Updated • 1
vangard703/cot_qwen
Image-Text-to-Text • 8B • Updated • 1
vangard703/fix_5_tasks_QA_state_waypoint_primitive_sum
Image-Text-to-Text • 8B • Updated
vangard703/zephyr-7b-sft-full
Updated
vangard703/gpt4o-dpo-10k-sys_no_distribution_relabeling_gpto_small_iter_3
Text Generation • 7B • Updated
vangard703/SELFEE-DPO-10K_without_sys_medium_iter_2
7B • Updated • 1