Picture for Junchi Yan

Junchi Yan

Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues

Add code
Oct 14, 2024
Figure 1 for Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
Figure 2 for Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
Figure 3 for Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
Figure 4 for Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
Viaarxiv icon

Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

Add code
Oct 13, 2024
Figure 1 for Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Figure 2 for Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Figure 3 for Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Figure 4 for Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Viaarxiv icon

DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Autonomous Driving

Add code
Sep 15, 2024
Viaarxiv icon

Neural Message Passing Induced by Energy-Constrained Diffusion

Add code
Sep 13, 2024
Viaarxiv icon

SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity

Add code
Sep 13, 2024
Figure 1 for SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Figure 2 for SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Figure 3 for SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Figure 4 for SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Viaarxiv icon

Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation

Add code
Sep 13, 2024
Viaarxiv icon

Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

Add code
Aug 27, 2024
Viaarxiv icon

Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation

Add code
Aug 22, 2024
Viaarxiv icon

PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

Add code
Aug 16, 2024
Viaarxiv icon

FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving

Add code
Aug 13, 2024
Viaarxiv icon