arXiv:2602.12433v1 Announce Type: new Abstract: Homomorphic encryption (HE) is a promising technology for confidential cloud computing, as it allows computations on encrypted data. However, HE is computationally expensive and often memory-bound on conventional computer architectures. Processing-in-Memory (PIM) is an alternative hardware architecture that integrates processing units and memory on the same chip or memory module. PIM enables higher memory bandwidth than conventional architectures and could thus be suitable for accelerating HE. In this work, we present DRAMatic, which […]

Ver mais

Check Point’s Cyber Security Report 2026 shows 70% increase in cyber attacks since 2023. 60% of executives reported their organizations faced AI-powered attacks, but only 7% had deployed AI defenses at scale. Moody’s 2026 cyber outlook warns that AI-related threats will “become more prevalent and pronounced”

Ver mais

arXiv:2509.22341v2 Announce Type: replace Abstract: Model collapse occurs when generative models degrade after repeatedly training on their own synthetic outputs. We study this effect in overparameterized linear regression in a setting where each iteration mixes fresh real labels with synthetic labels drawn from the model fitted in the previous iteration. We derive precise generalization error formulae for minimum-$ell_2$-norm interpolation and ridge regression under this iterative scheme. Our analysis reveals intriguing properties of the optimal mixing weight that minimizes […]

Ver mais

Model-based offline reinforcement learning is brittle under distribution shift: policy improvement drives rollouts into state–action regions weakly supported by the dataset, where compounding model error yields severe value overestimation. We propose Manifold-Constrained Energy-based Transition Models (MC-ETM), which train conditional energy-based transition models using a manifold projection–diffusion negative sampler. MC-ETM learns a latent manifold of next states and generates near-manifold hard negatives by perturbing latent codes and running Langevin dynamics in latent space with the learned conditional energy, sharpening […]

Ver mais

arXiv:2601.21942v1 Announce Type: new Abstract: Transformers have revolutionized deep learning across various domains but understanding the precise token dynamics remains a theoretical challenge. Existing theories of deep Transformers with layer normalization typically predict that tokens cluster to a single point; however, these results rely on deterministic weight assumptions, which fail to capture the standard initialization scheme in Transformers. In this work, we show that accounting for the intrinsic stochasticity of random initialization alters this picture. More precisely, we […]

Ver mais

arXiv:2601.16403v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) and its variants have emerged as the dominant approaches for aligning Large Language Models with human intent. While empirically effective, the theoretical generalization properties of these methods in high-dimensional settings remain to be explored. To this end, we build the generalization theory on RLHF of LLMs under the linear reward model, through the framework of algorithmic stability. In contrast to the existing works built upon the consistency […]

Ver mais

arXiv:2602.06157v1 Announce Type: new Abstract: DNA storage has matured from concept to practical stage, yet its integration with neural compression pipelines remains inefficient. Early DNA encoders applied redundancy-heavy constraint layers atop raw binary data – workable but primitive. Recent neural codecs compress data into learned latent representations with rich statistical structure, yet still convert these latents to DNA via naive binary-to-quaternary transcoding, discarding the entropy model’s optimization. This mismatch undermines compression efficiency and complicates the encoding stack. A […]

Ver mais

How ShareChat engineers rebuilt a low-latency ML feature store on ScyllaDB after an initial scalability failure — and what they learned along the way The demand for low-latency machine learning feature stores is higher than ever, but actually implementing one at scale remains a challenge. That became clear when ShareChat engineers Ivan Burmistrov and Andrei Manakov took the P99 CONF 23 stage to share how they built a low-latency ML feature store based on ScyllaDB. This isn’t a […]

Ver mais

arXiv:2602.14520v1 Announce Type: new Abstract: Posterior inference from pulsar observations in the form of light curves is commonly performed using Markov chain Monte Carlo methods, which are accurate but computationally expensive. We introduce a framework that accelerates posterior inference while maintaining accuracy by combining learned latent representations with local simulator-guided optimization. A masked U-Net is first pretrained to reconstruct complete light curves from partial observations and to produce informative latent embeddings. Given a query light curve, we identify […]

Ver mais

arXiv:2512.17340v2 Announce Type: replace-cross Abstract: Fair regression methods have the potential to mitigate societal bias concerns in health care, but there has been little work on penalized fair regression when multiple groups experience such bias. We propose a general regression framework that addresses this gap with unfairness penalties for multiple groups. Our approach is demonstrated for binary outcomes with true positive rate disparity penalties. It can be efficiently implemented through reduction to a cost-sensitive classification problem. We additionally […]

Ver mais