Picture for Fei Xia

Fei Xia

Google DeepMind

Vision Language Models are In-Context Value Learners

Add code
Nov 07, 2024
Viaarxiv icon

AutoGameUI: Constructing High-Fidelity Game UIs via Multimodal Learning and Interactive Web-Based Tool

Add code
Nov 06, 2024
Viaarxiv icon

IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation

Add code
Oct 25, 2024
Figure 1 for IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation
Figure 2 for IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation
Figure 3 for IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation
Figure 4 for IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation
Viaarxiv icon

BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning

Add code
Oct 24, 2024
Viaarxiv icon

Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions

Add code
Oct 24, 2024
Viaarxiv icon

DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model

Add code
Oct 14, 2024
Viaarxiv icon

Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

Add code
Sep 24, 2024
Viaarxiv icon

CACER: Clinical Concept Annotations for Cancer Events and Relations

Add code
Sep 05, 2024
Figure 1 for CACER: Clinical Concept Annotations for Cancer Events and Relations
Figure 2 for CACER: Clinical Concept Annotations for Cancer Events and Relations
Figure 3 for CACER: Clinical Concept Annotations for Cancer Events and Relations
Figure 4 for CACER: Clinical Concept Annotations for Cancer Events and Relations
Viaarxiv icon

Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

Add code
Jul 12, 2024
Viaarxiv icon

Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs

Add code
Jul 10, 2024
Figure 1 for Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs
Figure 2 for Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs
Figure 3 for Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs
Figure 4 for Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs
Viaarxiv icon