I’m researching in Model-bases RL. I implement DreamerV3 and train on DeepMind Control Suite. I benchmark on 4 environments. I try some research directions like representation collapse, compounding error/stability, adaptive imagination horizon, reconstruction-free imagination quality, prior-rollout reward-overestimation. But it failed with 3 reasons: Variance swamps small effects. Two near-identical configs, same seed, differed 2–4× at a checkpoint on a small (size-1m) model. 10–30% sample-eff gains are basically unmeasurable here without many-seed sweeps I can’t afford everywhere. The proprio-standard […]

Ver mais

arXiv:2204.09155v3 Announce Type: replace Abstract: Persistent homology is an important methodology in topological data analysis which adapts theory from algebraic topology to data settings. Computing persistent homology produces persistence diagrams, which have been successfully used in diverse domains. Despite its widespread use, persistent homology is simply impossible to compute when a dataset is very large. We study a statistical approach to the problem of computing persistent homology for massive datasets using a multiple subsampling framework and extend it […]

Ver mais

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

This week’s edition of my email newsletter (aka content from this blog delivered to your inbox) features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new chapter of my Agentic Engineering Patterns guide. Tags: newsletter

Ver mais

arXiv:2603.22432v1 Announce Type: new Abstract: Spin-glasses are natural Gibbs distributions that have been studied in Theoretical CS for many decades. Recently, they have been gaining attention from the community as they emerge naturally in neural computation and learning, network inference, optimisation and other areas. We study the problem of efficiently sampling from spin-glass distributions when the underlying graph is a typical instance of $G(n,d/n)$, i.e., the random graph on $n$ vertices such that each edge appears independently with […]

Ver mais

arXiv:2603.15672v1 Announce Type: new Abstract: Hardware design errors discovered after fabrication require costly physical respins that can delay products by months. Existing electronic design automation (EDA) tools enforce structural connectivity rules. However, they cannot verify that connections are emph{semantically} correct with respect to component datasheets. For example, that a symbol’s pinout matches the manufacturer’s specification, or that a voltage regulator’s feedback resistors produce the intended output. We present DRCY, the first production-ready multi-agent LLM system that automates first-pass […]

Ver mais