SOTAVerified

Embodied Question Answering

Papers

Showing 1–25 of 40 papers

TitleStatusHype
MEIA: Multimodal Embodied Perception and Interaction in Unknown EnvironmentsCode5
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video UnderstandingCode4
Towards Learning a Generalist Model for Embodied NavigationCode2
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual PreferencesCode2
VideoNavQA: Bridging the Gap between Visual and Embodied Question AnsweringCode1
CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City SpaceCode1
Map-based Modular Approach for Zero-shot Embodied Question AnsweringCode1
Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual SpaceCode1
AllenAct: A Framework for Embodied AI ResearchCode1
MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task PlanningCode0
EQA-RM: A Generative Embodied Reward Model with Test-time ScalingCode0
Blindfold Baselines for Embodied QACode0
ToSA: Token Merging with Spatial AwarenessCode0
Multi-Target Embodied Question AnsweringCode0
Neural Modular Control for Embodied Question AnsweringCode0
Embodied Question AnsweringCode0
GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering—0
"Is This It?": Towards Ecologically Valid Benchmarks for Situated Collaboration—0
LLM as A Robotic Brain: Unifying Egocentric Memory and Control—0
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen—0
A Survey of Embodied AI: From Simulators to Research Tasks—0
Memory-Centric Embodied Question Answer—0
Multi-Agent Embodied Question Answering in Interactive Environments—0
NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries—0
OpenEQA: Embodied Question Answering in the Era of Foundation Models—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.