Picture for Hanqing Wang

Hanqing Wang

Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation

Add code
Apr 13, 2025
Viaarxiv icon

Evolving Symbolic 3D Visual Grounder with Weakly Supervised Reflection

Add code
Feb 03, 2025
Viaarxiv icon

SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model

Add code
Dec 02, 2024
Figure 1 for SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
Figure 2 for SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
Figure 3 for SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
Figure 4 for SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
Viaarxiv icon

MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning

Add code
Oct 30, 2024
Figure 1 for MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Figure 2 for MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Figure 3 for MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Figure 4 for MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Viaarxiv icon

GRUtopia: Dream General Robots in a City at Scale

Add code
Jul 15, 2024
Viaarxiv icon

OVExp: Open Vocabulary Exploration for Object-Oriented Navigation

Add code
Jul 12, 2024
Figure 1 for OVExp: Open Vocabulary Exploration for Object-Oriented Navigation
Figure 2 for OVExp: Open Vocabulary Exploration for Object-Oriented Navigation
Figure 3 for OVExp: Open Vocabulary Exploration for Object-Oriented Navigation
Figure 4 for OVExp: Open Vocabulary Exploration for Object-Oriented Navigation
Viaarxiv icon

Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models

Add code
Jun 13, 2024
Figure 1 for Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Figure 2 for Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Figure 3 for Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Figure 4 for Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Viaarxiv icon

MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning

Add code
Jun 13, 2024
Figure 1 for MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
Figure 2 for MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
Figure 3 for MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
Figure 4 for MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
Viaarxiv icon

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks

Add code
Feb 18, 2024
Figure 1 for LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Figure 2 for LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Figure 3 for LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Figure 4 for LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Viaarxiv icon

StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation

Add code
Oct 26, 2023
Figure 1 for StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation
Figure 2 for StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation
Figure 3 for StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation
Figure 4 for StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation
Viaarxiv icon