Picture for Hang Su

Hang Su

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue

Add code
Nov 06, 2024
Viaarxiv icon

ManiBox: Enhancing Spatial Grasping Generalization via Scalable Simulation Data Generation

Add code
Nov 04, 2024
Viaarxiv icon

Learning to Summarize from LLM-generated Feedback

Add code
Oct 17, 2024
Viaarxiv icon

nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Vision

Add code
Oct 15, 2024
Viaarxiv icon

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

Add code
Oct 12, 2024
Viaarxiv icon

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Add code
Oct 10, 2024
Figure 1 for RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Figure 2 for RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Figure 3 for RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Figure 4 for RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Viaarxiv icon

UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs

Add code
Sep 30, 2024
Figure 1 for UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs
Figure 2 for UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs
Figure 3 for UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs
Figure 4 for UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs
Viaarxiv icon

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model

Add code
Sep 14, 2024
Viaarxiv icon

HybridDepth: Robust Depth Fusion for Mobile AR by Leveraging Depth from Focus and Single-Image Priors

Add code
Jul 26, 2024
Viaarxiv icon

Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights

Add code
Jul 16, 2024
Viaarxiv icon