Search Results for author:
Found 16 papers, 8 papers with code
Multi-Object Hallucination in Vision-Language Models
Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images.
3D-MVP: 3D Multiview Pretraining for Robotic Manipulation
Our results suggest that 3D-aware pretraining is a promising approach to improve sample efficiency and generalization of vision-based robotic manipulation policies.
Multimodal Graph Benchmark
Associating unstructured data with structured information is crucial for real-world tasks that require relevance search.
LinkGPT: Teaching Large Language Models To Predict Missing Links
To address the efficiency challenges at inference time, we introduce a retrieval-reranking scheme.
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
The integration of language and 3D perception is crucial for developing embodied agents and robots that comprehend and interact with the physical world.
AffordanceLLM: Grounding Affordance from Vision Language Models
Affordance grounding refers to the task of finding the area of an object with which one can interact.
LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent
While existing approaches often rely on extensive labeled data or exhibit limitations in handling complex language queries, we propose LLM-Grounder, a novel zero-shot, open-vocabulary, Large Language Model (LLM)-based 3D visual grounding pipeline.
Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including the edges being predicted in the graph at training and/or test have outsized impact on the performance of low-degree nodes.
Understanding 3D Object Interaction from a Single Image
Humans can easily understand a single image as depicting multiple potential objects permitting interaction.
Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation
In this paper, we use these cues to solve a problem we call Sound Localization from Motion (SLfM): jointly estimating camera rotation and localizing sound sources.
Understanding 3D Object Articulation in Internet Videos
We propose to investigate detecting and characterizing the 3D planar articulation of objects from ordinary videos.
Recognizing Scenes from Novel Viewpoints
Humans can perceive scenes in 3D from a handful of 2D views.
Planar Surface Reconstruction from Sparse Views
The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera poses.
Associative3D: Volumetric Reconstruction from Sparse Views
This information is then jointly reasoned over to produce the most likely explanation of the scene.
OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
Single-view 3D is the task of recovering 3D properties such as depth and surface normals from a single image.
Learning Single-Image Depth from Videos using Quality Assessment Networks
Depth estimation from a single image in the wild remains a challenging problem.
