Picture for Jiawei Peng

Jiawei Peng

VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism

Add code
Jun 10, 2025
Viaarxiv icon

PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation

Add code
May 27, 2025
Viaarxiv icon

Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization

Add code
Apr 19, 2025
Viaarxiv icon

Learnable In-Context Vector for Visual Question Answering

Add code
Jun 19, 2024
Viaarxiv icon

Exploring the Distinctiveness and Fidelity of the Descriptions Generated by Large Vision-Language Models

Add code
Apr 26, 2024
Viaarxiv icon

How to Configure Good In-Context Sequence for Visual Question Answering

Add code
Dec 04, 2023
Viaarxiv icon

Learning Part Segmentation from Synthetic Animals

Add code
Nov 30, 2023
Figure 1 for Learning Part Segmentation from Synthetic Animals
Figure 2 for Learning Part Segmentation from Synthetic Animals
Figure 3 for Learning Part Segmentation from Synthetic Animals
Figure 4 for Learning Part Segmentation from Synthetic Animals
Viaarxiv icon

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

Add code
Aug 22, 2023
Figure 1 for Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Figure 2 for Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Figure 3 for Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Figure 4 for Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Viaarxiv icon

Enhancing Language Representation with Constructional Information for Natural Language Understanding

Add code
Jun 05, 2023
Figure 1 for Enhancing Language Representation with Constructional Information for Natural Language Understanding
Figure 2 for Enhancing Language Representation with Constructional Information for Natural Language Understanding
Figure 3 for Enhancing Language Representation with Constructional Information for Natural Language Understanding
Figure 4 for Enhancing Language Representation with Constructional Information for Natural Language Understanding
Viaarxiv icon

Transforming Visual Scene Graphs to Image Captions

Add code
May 05, 2023
Viaarxiv icon