38 citations · 110 across the 24 of their papers we have counts for
24 papers
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
Qizhen Ying, Guangming Wang, Yangchen Pan +3
Physics-grounded video generation requires controllable 3D object dynamics that remain physically consistent under contact, deformation, and external forcing. Existing trajectory-b…
Temporal Difference Learning for Diffusion Models
Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu +1
Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between…
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
Avery Ma, Yangchen Pan, Amir-massoud Farahmand
Many-shot jailbreaking circumvents the safety alignment of LLMs by exploiting their ability to process long input sequences. To achieve this, the malicious target prompt is prefixe…
Improving Adversarial Transferability via Model Alignment
Avery Ma, Amir-massoud Farahmand, Yangchen Pan +2
Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at i…
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods
Avery Ma, Yangchen Pan, Amir-massoud Farahmand
Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while th…
An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient
Yudong Luo, Guiliang Liu, Pascal Poupart +1
Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning (RL) due to its clear mathematical definition and easy interpretability. Tra…