HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Vision And Language Navigation On Touchdown

평가 지표

Task Completion (TC)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Task Completion (TC)	Paper Title	Repository
Gated Attention (GA)	5.5	Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
FLAME	40.20	FLAME: Learning to Navigate with Multimodal LLM in Urban Environments
VLN Transformer	14.9	Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation
ORAR + junction type + heading delta	29.1	Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas
Gated Attention (GA)	11.9	Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation
Retouch-RConcat	12.8	Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View
RConcat	11.8	Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation
ARC	14.13	Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation	-
ORAR	24.2	Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas
VLN Transformer +M-50 +style	16.2	Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation
RConcat	10.7	Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
ARC + L2STOP	16.68	Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation	-

0 of 12 row(s) selected.