HyperAI초신경

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

한국어

HyperAI초신경

Visual Navigation On Room To Room 1

평가 지표

spl

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	spl	Paper Title	Repository
BEV-BERT	0.60	BEVBert: Multimodal Map Pre-training for Language-guided Navigation
NaviLLM	0.60	Towards Learning a Generalist Model for Embodied Navigation
VLN-BERT	0.57	A Recurrent Vision-and-Language BERT for Navigation
Meta-Explore	0.61	Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding	-
RCM+SIL(no early exploration)	0.38	Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation	-
VLN-PETL	0.58	VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation
Seq2Seq baseline	0.18	Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
Prevalent	0.51	Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
HOP	0.59	HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation
SUSA	0.6383	Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation
DUET	0.58	Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation

0 of 11 row(s) selected.