49 citations · 61 across the 12 of their papers we have counts for
12 papers
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Zishuo Li, Bowen Yang, Changtao Miao +29
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-leve…
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
Hao Cheng, Changtao Miao, Tianle Song +21
Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world…
Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
Hao Cheng, Erjia Xiao, Jiayan Yang +6
Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Ima…
Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model
Hao Cheng, Erjia Xiao, Jindong Gu +6
Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of…
Pursing the Sparse Limitation of Spiking Deep Learning Structures
Hao Cheng, Jiahang Cao, Erjia Xiao +7
Spiking Neural Networks (SNNs), a novel brain-inspired algorithm, are garnering increased attention for their superior computation and energy efficiency over traditional artificial…
RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias
Hao Cheng, Jinhao Duan, Hui Li +6
Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP). Compared with…
Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Network
Hao Cheng, Jiahang Cao, Erjia Xiao +2
Deploying energy-efficient deep learning algorithms on computational-limited devices, such as robots, is still a pressing issue for real-world applications. Spiking Neural Networks…
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness
James Diffenderfer, Brian R. Bartoldson, Shreya Chaganti +2
Successful adoption of deep learning (DL) in the wild requires models to be: (1) compact, (2) accurate, and (3) robust to distributional shifts. Unfortunately, efforts towards simu…
Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows
Jize Zhang, Bhavya Kailkhura, T. Yong-Jin Han
In this paper, we leverage predictive uncertainty of deep neural networks to answer challenging questions material scientists usually encounter in machine learning based materials…
Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design
Shusen Liu, Bhavya Kailkhura, Jize Zhang +4
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in buildin…
Actionable Attribution Maps for Scientific Machine Learning
Shusen Liu, Bhavya Kailkhura, Jize Zhang +4
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in buildin…
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
Jize Zhang, Bhavya Kailkhura, T. Yong-Jin Han
This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving,…