Tootfinder

TIL this is a thing. i'm now nerdsniped and playing around with it, lol.
https://myscope.training/FIB_simulator.html
The quad layout, nav-cam, and stage design scream "~2010 or newer FEI dual beam, Versa/Helios family probably" to me, althouhg the softwa…

Memory Access Vectors: Improving Sampling Fidelity for CPU Performance Simulations
Sriyash Caculo, Mahesh Madhav, Jeff Baxter
https://arxiv.org/abs/2506.02344

Memory Access Vectors: Improving Sampling Fidelity for CPU Performance Simulations
Accurate performance projection of large-scale benchmarks is essential for CPU architects to evaluate and optimize future processor designs. SimPoint sampling, which uses Basic Block Vectors (BBVs), is a widely adopted technique to reduce simulation time by selecting representative program phases. However, BBVs often fail to capture the behavior of applications with extensive array-indirect memory accesses, leading to inaccurate projections. In particular, the 523.xalancbmk_r benchmark exhibits…

Power Enhancement of Permutation-Augmented Partial-Correlation Tests via Fixed-Row Permutations
Tianyi Wang, Guanghui Wang, Zhaojun Wang, Changliang Zou
https://arxiv.org/abs/2506.02906

Power Enhancement of Permutation-Augmented Partial-Correlation Tests via Fixed-Row Permutations
Permutation-based partial-correlation tests guarantee finite-sample Type I error control under any fixed design and exchangeable noise, yet their power can collapse when the permutation-augmented design aligns too closely with the covariate of interest. We remedy this by fixing a design-driven subset of rows and permuting only the remainder. The fixed rows are chosen by a greedy algorithm that maximizes a lower bound on power. This strategy reduces covariate-permutation collinearity while prese…

BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies
Kourosh Shahnazari, Seyed Moein Ayyoubzadeh, Mohammadali Keshtparvar
https://arxiv.org/abs/2506.00328

BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies
The quest for interpretable reinforcement learning is a grand challenge for the deployment of autonomous decision-making systems in safety-critical applications. Modern deep reinforcement learning approaches, while powerful, tend to produce opaque policies that compromise verification, reduce transparency, and impede human oversight. To address this, we introduce BASIL (Best-Action Symbolic Interpretable Learning), a systematic approach for generating symbolic, rule-based policies via online ev…

This https://arxiv.org/abs/2506.01538 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low sample efficiency and requires iterative manual reward tuning. Large Language Models (LLMs) have shown promise in single-robot settings, but their application in multi-robot systems remains largely unexplored. This paper introduces a novel LLM-Aided MARL (LAMARL) approach, which integrates MARL with LLMs, significantly enhancing sample efficiency without requiring manual design. LA…

This https://arxiv.org/abs/2412.15289 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing methods primarily design sophisticated instructions for the LLM to follow, or rely on multiple iterations, which could hinder the performance and efficiency of jailbreaks. In this work, we propose a novel jailbreak paradigm, Simple Assistive Task Linkage (SA…

I've just upgraded my self-hosted #Listmonk instance to 5.0.0, and I absolutely LOVE the new visual email template builder powered by EmailBuilder.js!
I can't wait to start creating new templates for the candide ꘎ media newsletter ✨
More on the software: …

This https://arxiv.org/abs/2503.01112 has been replaced.
initial toot: https://mastoxiv.page/@arXi…

Nonreciprocal field theory for decision-making in multi-agent control systems
Field theories for complex systems traditionally focus on collective behaviors emerging from simple, reciprocal pairwise interaction rules. However, many natural and artificial systems exhibit behaviors driven by microscopic decision-making processes that introduce both nonreciprocity and many-body interactions, challenging these conventional approaches. We develop a theoretical framework to incorporate decision-making into field theories using the shepherding control problem as a paradigmatic …

This https://arxiv.org/abs/2505.23585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

On-Policy RL with Optimal Reward Baseline
Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability due to loose on-policy constraints and computational inefficiency due to auxiliary models. In this work, we propose On-Policy RL with Optimal reward baseline (OPO), a novel and simplified reinforcement learning algorithm designed to address these challenges. O…

Simulation-Based Inference for Adaptive Experiments
Brian M Cho, Aur\'elien Bibaut, Nathan Kallus
https://arxiv.org/abs/2506.02881 https://

Simulation-Based Inference for Adaptive Experiments
Multi-arm bandit experimental designs are increasingly being adopted over standard randomized trials due to their potential to improve outcomes for study participants, enable faster identification of the best-performing options, and/or enhance the precision of estimating key parameters. Current approaches for inference after adaptive sampling either rely on asymptotic normality under restricted experiment designs or underpowered martingale concentration inequalities that lead to weak power in p…