Picture for Tianwei Lin

Tianwei Lin

HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models

Add code
Mar 20, 2024
Figure 1 for HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Figure 2 for HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Figure 3 for HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Figure 4 for HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Viaarxiv icon

WidthFormer: Toward Efficient Transformer-based BEV View Transformation

Add code
Jan 15, 2024
Viaarxiv icon

EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction

Add code
Dec 15, 2023
Viaarxiv icon

Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation

Add code
Dec 15, 2023
Viaarxiv icon

Sparse4D v3: Advancing End-to-End 3D Detection and Tracking

Add code
Nov 20, 2023
Viaarxiv icon

Sparse4D v2: Recurrent Temporal Fusion with Sparse Model

Add code
May 24, 2023
Figure 1 for Sparse4D v2: Recurrent Temporal Fusion with Sparse Model
Figure 2 for Sparse4D v2: Recurrent Temporal Fusion with Sparse Model
Figure 3 for Sparse4D v2: Recurrent Temporal Fusion with Sparse Model
Figure 4 for Sparse4D v2: Recurrent Temporal Fusion with Sparse Model
Viaarxiv icon

DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection

Add code
May 24, 2023
Figure 1 for DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection
Figure 2 for DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection
Figure 3 for DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection
Figure 4 for DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection
Viaarxiv icon

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

Add code
Apr 24, 2023
Figure 1 for Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
Figure 2 for Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
Figure 3 for Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
Figure 4 for Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
Viaarxiv icon

DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation

Add code
Mar 11, 2023
Figure 1 for DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Figure 2 for DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Figure 3 for DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Figure 4 for DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Viaarxiv icon

Goal-oriented Autonomous Driving

Add code
Dec 20, 2022
Figure 1 for Goal-oriented Autonomous Driving
Figure 2 for Goal-oriented Autonomous Driving
Figure 3 for Goal-oriented Autonomous Driving
Figure 4 for Goal-oriented Autonomous Driving
Viaarxiv icon