Picture for Chenliang Xu

Chenliang Xu

Learning to Transform Dynamically for Better Adversarial Transferability

Add code
May 23, 2024
Viaarxiv icon

V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning

Add code
Apr 18, 2024
Viaarxiv icon

AVicuna: Audio-Visual LLM with Interleaver and Context-Boundary Alignment for Temporal Referential Dialogue

Mar 24, 2024
Viaarxiv icon

Adaptive Super Resolution For One-Shot Talking-Head Generation

Add code
Mar 23, 2024
Viaarxiv icon

Forward Learning for Gradient-based Black-box Saliency Map Generation

Mar 22, 2024
Viaarxiv icon

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers

Add code
Mar 20, 2024
Figure 1 for Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Figure 2 for Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Figure 3 for Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Figure 4 for Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Viaarxiv icon

Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training

Mar 18, 2024
Figure 1 for Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
Figure 2 for Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
Figure 3 for Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
Figure 4 for Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
Viaarxiv icon

OSCaR: Object State Captioning and State Change Representation

Add code
Feb 28, 2024
Viaarxiv icon

Efficiently Leveraging Linguistic Priors for Scene Text Spotting

Feb 27, 2024
Figure 1 for Efficiently Leveraging Linguistic Priors for Scene Text Spotting
Figure 2 for Efficiently Leveraging Linguistic Priors for Scene Text Spotting
Figure 3 for Efficiently Leveraging Linguistic Priors for Scene Text Spotting
Figure 4 for Efficiently Leveraging Linguistic Priors for Scene Text Spotting
Viaarxiv icon

Emo-Avatar: Efficient Monocular Video Style Avatar through Texture Rendering

Feb 01, 2024
Viaarxiv icon