Picture for Zhigang Zhu

Zhigang Zhu

Dept. of Computer Science, City College of New York

VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers

Add code
Oct 10, 2024
Figure 1 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Figure 2 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Figure 3 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Figure 4 for VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers
Viaarxiv icon

GMC: A General Framework of Multi-stage Context Learning and Utilization for Visual Detection Tasks

Add code
Jul 08, 2024
Viaarxiv icon

Segment Anything Model for Pedestrian Infrastructure Inventory: Assessing Zero-Shot Segmentation on Multi-Mode Geospatial Data

Add code
Oct 24, 2023
Viaarxiv icon

Robots in the Garden: Artificial Intelligence and Adaptive Landscapes

Add code
May 22, 2023
Viaarxiv icon

Context Understanding in Computer Vision: A Survey

Add code
Feb 10, 2023
Viaarxiv icon

SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data

Add code
Jan 13, 2022
Figure 1 for SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data
Figure 2 for SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data
Figure 3 for SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data
Figure 4 for SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data
Viaarxiv icon

NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks

Add code
Oct 27, 2021
Figure 1 for NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks
Figure 2 for NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks
Figure 3 for NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks
Viaarxiv icon

Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network

Add code
May 03, 2019
Figure 1 for Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
Figure 2 for Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
Figure 3 for Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
Figure 4 for Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
Viaarxiv icon

Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling

Add code
Mar 29, 2019
Figure 1 for Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
Figure 2 for Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
Figure 3 for Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
Figure 4 for Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
Viaarxiv icon

Generalizing semi-supervised generative adversarial networks to regression

Add code
Nov 27, 2018
Figure 1 for Generalizing semi-supervised generative adversarial networks to regression
Figure 2 for Generalizing semi-supervised generative adversarial networks to regression
Figure 3 for Generalizing semi-supervised generative adversarial networks to regression
Figure 4 for Generalizing semi-supervised generative adversarial networks to regression
Viaarxiv icon