ProARD: progressive adversarial robustness distillation: provide wide range of robust students arXiv:2506.07666v3 Announce Type: replace Abstract: Adversarial Robustness Distillation (ARD) has emerged as an effective method to enhance the robustness of lightweight deep neural networks against adversarial attacks. Current ARD…
Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization arXiv:2508.19443v1 Announce Type: new Abstract: Producing large complex simulation datasets can often be a time and resource consuming task. Especially when these experiments are very expensive, it is becoming more reasonable…
GTPO: Trajectory-Based Policy Optimization in Large Language Models arXiv:2508.03772v3 Announce Type: replace Abstract: Policy-based optimizations are widely adopted today for the training and alignment of language models, where one of the most recent and effective approaches is Group-relative Policy Optimization…
On Surjectivity of Neural Networks: Can you elicit any behavior from your model? arXiv:2508.19445v1 Announce Type: new Abstract: Given a trained neural network, can any specified output be generated by some input? Equivalently, does the network correspond to a function…
Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement arXiv:2508.18765v2 Announce Type: replace Abstract: As AI systems evolve into distributed ecosystems with autonomous execution, asynchronous reasoning, and multi-agent coordination, the absence of scalable, decoupled governance poses a structural…
The Sample Complexity of Membership Inference and Privacy Auditing arXiv:2508.19458v1 Announce Type: new Abstract: A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a member of the…
From Optimization to Control: Quasi Policy Iteration arXiv:2311.11166v3 Announce Type: replace-cross Abstract: Recent control algorithms for Markov decision processes (MDPs) have been designed using an implicit analogy with well-established optimization algorithms. In this paper, we adopt the quasi-Newton method (QNM)…
Incentivized Lipschitz Bandits arXiv:2508.19466v1 Announce Type: new Abstract: We study incentivized exploration in multi-armed bandit (MAB) settings with infinitely many arms modeled as elements in continuous metric spaces. Unlike classical bandit models, we consider scenarios where the decision-maker (principal) incentivizes…
X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models arXiv:2412.01824v2 Announce Type: replace-cross Abstract: In-context generation is a key component of large language models’ (LLMs) open-task generalization capability. By leveraging a few examples as context, LLMs can…
DeepAtlas: a tool for effective manifold learning arXiv:2508.19479v1 Announce Type: new Abstract: Manifold learning builds on the “manifold hypothesis,” which posits that data in high-dimensional datasets are drawn from lower-dimensional manifolds. Current tools generate global embeddings of data, rather than…
