5 papers · 1 filter
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Peihao Wang, Shan Yang, Xijun Wang +8
Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability…
Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
Konstantinos Emmanouilidis, Tianjiao Ding, Nghia Nguyen +2
Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can achieve strong robustness in pra…
Can Implicit Bias Imply Adversarial Robustness?
Hancheng Min, René Vidal
The implicit bias of gradient-based training algorithms has been considered mostly beneficial as it leads to trained networks that often generalize well. However, Frei et al. (2023…
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
Ambar Pal, Jeremias Sulam, René Vidal
The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these resul…
Certified Robustness against Sparse Adversarial Perturbations via Data Localization
Ambar Pal, René Vidal, Jeremias Sulam
Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that…