Vision-Language Navigation on AML-VLN benchmark leaderboard · SOTA2 Research

Vision-Language Navigation on AML-VLN

100T1 PerformanceSeq-FT

Evaluation Results

Method	Links
Seq-FT2026.03		100	100	100	100	100	100	93	100	88	93	94	83	91	92	92	83	87	89	94	73	84	81	78	0	87
LwF-LoRA2026.03		92	100	91	100	100	100	92	89	81	93	95	78	88	93	89	83	85	84	93	71	82	76	73	0	84
EWC-LoRA2026.03		85	92	89	90	94	91	86	87	82	82	92	78	84	78	86	77	75	75	88	72	77	68	66	0	79
Dense MoLE2026.03		80	91	82	73	78	78	81	86	77	81	78	72	73	65	79	72	63	69	85	63	74	64	61	0	72
Sparse MoLE2026.03		68	89	69	64	72	49	58	82	56	68	64	56	68	51	70	58	51	82	82	54	63	59	56	0	62
MoLA2026.03		62	79	59	58	63	62	46	78	43	63	55	42	65	48	68	54	46	60	79	44	55	51	43	0	55
HydraLoRA2026.03		45	64	51	46	60	40	26	67	31	49	49	39	61	44	63	50	44	49	72	29	46	49	38	0	46
BranchLoRA2026.03		34	59	46	36	53	29	13	52	29	48	29	23	58	18	54	32	36	42	56	12	36	36	29	0	36
O-LoRA2026.03		19	41	41	28	38	24	4	38	15	17	11	13	43	2	40	24	32	5	39	2	34	28	20	0	23
SD-LoRA2026.03		12	38	34	13	34	13	4	36	12	1	3	8	37	-2	36	12	26	13	37	3	28	21	17	0	18
AlldayWalker2026.03		2	27	23	8	21	1	0	28	9	0	2	6	30	-3	24	10	1	4	24	-4	18	24	12	0	11