Tootfinder

Learning to Sample: Reinforcement Learning-Guided Sampling for Autonomous Vehicle Motion Planning
Korbinian Moller, Roland Stroop, Mattia Piccinini, Alexander Langmann, Johannes Betz
https://arxiv.org/abs/2509.24313

Learning to Sample: Reinforcement Learning-Guided Sampling for Autonomous Vehicle Motion Planning
Sampling-based motion planning is a well-established approach in autonomous driving, valued for its modularity and analytical tractability. In complex urban scenarios, however, uniform or heuristic sampling often produces many infeasible or irrelevant trajectories. We address this limitation with a hybrid framework that learns where to sample while keeping trajectory generation and evaluation fully analytical and verifiable. A reinforcement learning (RL) agent guides the sampling process toward…

💦 Boosting work engagement through a simple smartphone diary
#work

Boosting work engagement through a simple smartphone diary
Work engagement is a positive and persistent state of mind related to one's work. It is characterized by high energy and mental resilience (vigor), enthusiasm and involvement (dedication), and complete concentration in the task at hand (absorption). Engaged workers are not merely more productive; they are more likely to be proactive, creative, and less susceptible to burnout. Most importantly, work engagement has been consistently linked to many health benefits and overall well-being.

Planning Considerations Related to Contamination Control for the Return and Analysis of Martian Samples: #MarsSampleReturnMission

Seeing @anirudh.fi's Tangled post with footnotes... @leaflet.pub footnotes / "asides" (as sub pages????) could be v nice!
I used to run Simply Jekyll which had really nice side notes, marginalia and other interesting interactive pieces for full desktop views simply-jekyll.netlify.app/posts/usage https://

Boris (@bmann.ca)
Seeing @anirudh.fi's Tangled post with footnotes... @leaflet.pub footnotes / "asides" (as sub pages????) could be v nice! I used to run Simply Jekyll which had really nice side notes, marginalia and other interesting interactive pieces for full desktop views simply-jekyll.netlify.app/posts/usage

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
Peter Holderrieth, Uriel Singer, Tommi Jaakkola, Ricky T. Q. Chen, Yaron Lipman, Brian Karrer
https://arxiv.org/abs/2509.25170

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
The performance of flow matching and diffusion models can be greatly improved at inference time using reward alignment algorithms, yet efficiency remains a major limitation. While several algorithms were proposed, we demonstrate that a common bottleneck is the sampling method these algorithms rely on: many algorithms require to sample Markov transitions via SDE sampling, which is significantly less efficient and often less performant than ODE sampling. To remove this bottleneck, we introduce GL…

SymBoltz.jl: a symbolic-numeric, approximation-free and differentiable linear Einstein-Boltzmann solver
Herman Sletmoen
https://arxiv.org/abs/2509.24740 https://

SymBoltz.jl: a symbolic-numeric, approximation-free and differentiable linear Einstein-Boltzmann solver
SymBoltz is a new Julia package that solves the linear Einstein-Boltzmann equations. It features a symbolic-numeric interface for specifying equations, is free of approximation switching schemes and is compatible with automatic differentiation. Cosmological models are built from replaceable physical components in a way that scales well in model space. The modeler should simply write down their equations, and SymBoltz solves them and eliminates much of the friction in the process. SymBoltz enabl…

An Equal-Probability Partition of the Sample Space: A Non-parametric Inference from Finite Samples
Urban Eriksson
https://arxiv.org/abs/2507.21712 https://…

An Equal-Probability Partition of the Sample Space: A Non-parametric Inference from Finite Samples
This paper investigates what can be inferred about an arbitrary continuous probability distribution from a finite sample of $N$ observations drawn from it. The central finding is that the $N$ sorted sample points partition the real line into $N+1$ segments, each carrying an expected probability mass of exactly $1/(N+1)$. This non-parametric result, which follows from fundamental properties of order statistics, holds regardless of the underlying distribution's shape. This equal-probability parti…

The excited miniature pilot behind the controls in the centre of my brain: "This makes me wanna learn Chinese!" ->
Quick and Dirty Introduction to Traditional and Simplified Chinese Transliteration – Potterglot
https://www.potterglot.net/qui…

Systematic Alias Sampling: an efficient and low-variance way to sample from a discrete distribution
Ilari Vallivaara, Katja Poikselk\"a, Pauli Rikula, Juha R\"oning
https://arxiv.org/abs/2509.24089

Systematic Alias Sampling: an efficient and low-variance way to sample from a discrete distribution
In this paper we combine the Alias method with the concept of systematic sampling, a method commonly used in particle filters for efficient low-variance resampling. The proposed method allows very fast sampling from a discrete distribution: drawing k samples is up to an order of magnitude faster than binary search from the cumulative distribution function (cdf) or inversion methods used in many libraries. The produced empirical distribution function is evaluated using a modified Cramér-Von Mis…

MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
Jan Ole von Hartz, Lukas Schweizer, Joschka Boedecker, Abhinav Valada
https://arxiv.org/abs/2509.24956

MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
Generative robot policies such as Flow Matching offer flexible, multi-modal policy learning but are sample-inefficient. Although object-centric policies improve sample efficiency, it does not resolve this limitation. In this work, we propose Multi-Stream Generative Policy (MSG), an inference-time composition framework that trains multiple object-centric policies and combines them at inference to improve generalization and sample efficiency. MSG is model-agnostic and inference-only, hence widely…