Picture for Wenxiao Wang

Wenxiao Wang

Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection

Jun 11, 2024
Viaarxiv icon

From Redundancy to Relevance: Enhancing Explainability in Multimodal Large Language Models

Jun 04, 2024
Viaarxiv icon

G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction

Add code
Apr 30, 2024
Viaarxiv icon

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

Add code
Apr 30, 2024
Viaarxiv icon

Model Compression and Efficient Inference for Large Language Models: A Survey

Feb 15, 2024
Viaarxiv icon

Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving

Add code
Dec 19, 2023
Viaarxiv icon

To be or not to be? an exploration of continuously controllable prompt engineering

Nov 16, 2023
Figure 1 for To be or not to be? an exploration of continuously controllable prompt engineering
Figure 2 for To be or not to be? an exploration of continuously controllable prompt engineering
Figure 3 for To be or not to be? an exploration of continuously controllable prompt engineering
Figure 4 for To be or not to be? an exploration of continuously controllable prompt engineering
Viaarxiv icon

Few-shot Hybrid Domain Adaptation of Image Generators

Add code
Oct 30, 2023
Figure 1 for Few-shot Hybrid Domain Adaptation of Image Generators
Figure 2 for Few-shot Hybrid Domain Adaptation of Image Generators
Figure 3 for Few-shot Hybrid Domain Adaptation of Image Generators
Figure 4 for Few-shot Hybrid Domain Adaptation of Image Generators
Viaarxiv icon

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

Add code
Sep 29, 2023
Figure 1 for Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Figure 2 for Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Figure 3 for Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Figure 4 for Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Viaarxiv icon

M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders

Add code
Sep 23, 2023
Figure 1 for M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders
Figure 2 for M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders
Figure 3 for M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders
Figure 4 for M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders
Viaarxiv icon