Tootfinder

Stability of compact actions and a result on divided differences
Carlos Gustavo Moreira, Nicolau C. Saldanha
https://arxiv.org/abs/2506.14446 https://

Stability of compact actions and a result on divided differences
We study smooth locally free actions of ${\mathbb R}^n$ on manifolds $M$ of dimension $n+1$. We are interested in compact orbits and in compact actions: actions with all orbits compact. Given a compact orbit in a neighborhood of compact orbits, we give necessary and sufficient conditions for the existence of a $C^k$ perturbation with noncompact orbits in the given neighborhood. We prove that if such a perturbation exists it can be assumed to differ from the original action only in a smaller nei…

A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions
Stephen Mell, Botong Zhang, David Mell, Shuo Li, Ramya Ramalingam, Nathan Yu, Steve Zdancewic, Osbert Bastani
https://arxiv.org/abs/2506.12202

A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions
Modern large language models (LLMs) are often deployed as agents, calling external tools adaptively to solve tasks. Rather than directly calling tools, it can be more effective for LLMs to write code to perform the tool calls, enabling them to automatically generate complex control flow such as conditionals and loops. Such code actions are typically provided as Python code, since LLMs are quite proficient at it; however, Python may not be the ideal language due to limited built-in support for p…

Iterated finite group actions on closed connected aspherical manifolds
Jordi Daura Serrano
https://arxiv.org/abs/2506.13184 https://a…

Iterated finite group actions on closed connected aspherical manifolds
In this paper we use free iterated actions and the iterated discrete degree of symmetry to obtain rigidity results on aspherical manifolds. We also introduce the concept of the length of an iterated action and we study it for nilmanifolds, solvmanifolds and locally symmetric spaces.

A note on valued fields with finite group actions
Piotr B{\l}aszkiewicz, Jakub Gogolok
https://arxiv.org/abs/2506.13742 https://arxiv…

A note on valued fields with finite group actions
In this preliminary note we prove that the theory of valued fields equipped with an action of a given finite group has a model companion.

A simplified algorithmic realization of Galois actions on special values of modular functions
Ja Kyung Koo, Dong Hwa Shin, Dong Sung Yoon
https://arxiv.org/abs/2506.14139

A simplified algorithmic realization of Galois actions on special values of modular functions
We propose an explicit and practical algorithm for computing Galois conjugates and irreducible polynomials for special values of modular functions evaluated at CM points associated with imaginary quadratic orders. Our approach builds upon the theory of extended form class groups developed by Jung et al., offering a refinement of earlier methods by Stevenhagen and Cho, respectively.

A Study of the Spectral Sequence for Locally Free Isometric Actions of Abelian Lie Groups
Pawe{\l} Ra\'zny
https://arxiv.org/abs/2506.12422 https://

A Study of the Spectral Sequence for Locally Free Isometric Actions of Abelian Lie Groups
We give an upper bound on the number of the page on which the spectral sequence corresponding to a locally free isometric action of an abelian Lie group degenerates. We give examples showing that these bounds are indeed sharp. Finally, we further justify the study of this sequence by exhibiting a potential application to the study of harmonic forms.

Henry Ruggs breaks silence on fatal car crash, says he would 'love' to play for Raiders again

https://www.cbssports.com/nfl/news/henry-r

Continuously Updating Digital Twins using Large Language Models
Harry Amad, Nicol\'as Astorga, Mihaela van der Schaar
https://arxiv.org/abs/2506.12091 …

Continuously Updating Digital Twins using Large Language Models
Digital twins are models of real-world systems that can simulate their dynamics in response to potential actions. In complex settings, the state and action variables, and available data and knowledge relevant to a system can constantly change, requiring digital twins to continuously update with these changes to remain relevant. Current approaches struggle in this regard, as they require fixed, well-defined modelling environments, and they cannot adapt to novel variables without re-designs, or i…

Smart contracts and reaction-function games
Jens Gudmundsson, Jens Leth Hougaard
https://arxiv.org/abs/2506.14413 https://arxiv.org/p…

Smart contracts and reaction-function games
Blockchain-based smart contracts offer a new take on credible commitment, where players can commit to actions in reaction to actions of others. Such reaction-function games extend on strategic games with players choosing reaction functions instead of strategies. We formalize a solution concept in terms of fixed points for such games, akin to Nash equilibrium, and prove equilibrium existence. Reaction functions can mimic "trigger" strategies from folk theorems on infinitely repeated games -- but…

GAF: Gaussian Action Field as a Dvnamic World Model for Robotic Mlanipulation
Ying Chai, Litao Deng, Ruizhi Shao, Jiajun Zhang, Liangjun Xing, Hongwen Zhang, Yebin Liu
https://arxiv.org/abs/2506.14135

GAF: Gaussian Action Field as a Dvnamic World Model for Robotic Mlanipulation
Accurate action inference is critical for vision-based robotic manipulation. Existing approaches typically follow either a Vision-to-Action (V-A) paradigm, predicting actions directly from visual inputs, or a Vision-to-3D-to-Action (V-3D-A) paradigm, leveraging intermediate 3D representations. However, these methods often struggle with action inaccuracies due to the complexity and dynamic nature of manipulation scenes. In this paper, we propose a V-4D-A framework that enables direct action reas…

Krugman continues:
❝While there is a cadre of Trumpist true believers who will obey the Leader under any circumstances, most of those doing the dirty work of undermining democracy and the rule of law are cowards and opportunists. They’re willing to participate in the destruction of America as we know it because they believe that many others will do the same. As a result, they believe that they are unlikely to face any personal consequences for their actions and may even be rewarded for their lawbreaking.
And what of those who oppose Trumpism? While there are heroes willing to take a stand against tyranny whatever the personal cost, most anti-Trumpists are reluctant to stick their necks out unless they believe that they are part of a widespread resistance that will grant them some measure of safety in numbers.
In other words, the victory or defeat of competitive authoritarianism will depend to a large extent on which side ordinary people believe will win. If Trump looks unstoppable, resistance will wither away and democracy will be lost. On the other hand, if he appears weak and stymied, resistance will grow and — just maybe — American democracy will survive.❞
2/

Screen Reader Users in the Vibe Coding Era: Adaptation, Empowerment, and New Accessibility Landscape
Nan Chen, Luna K. Qiu, Arran Zeyu Wang, Zilong Wang, Yuqing Yang
https://arxiv.org/abs/2506.13270

Screen Reader Users in the Vibe Coding Era: Adaptation, Empowerment, and New Accessibility Landscape
The rise of generative AI agents has reshaped human-computer interaction and computer-supported cooperative work by shifting users' roles from direct task execution to supervising machine-driven actions, especially in programming (e.g., "vibe coding"). However, there is limited understanding of how screen reader users engage with these systems in practice. To address this gap, we conducted a longitudinal study with 16 screen reader users, exploring their experiences with AI code assistants in d…

Constrained Diffusers for Safe Planning and Control
Jichen Zhang, Liqun Zhao, Antonis Papachristodoulou, Jack Umenberger
https://arxiv.org/abs/2506.12544 h…

Constrained Diffusers for Safe Planning and Control
Diffusion models have shown remarkable potential in planning and control tasks due to their ability to represent multimodal distributions over actions and trajectories. However, ensuring safety under constraints remains a critical challenge for diffusion models. This paper proposes Constrained Diffusers, a novel framework that incorporates constraints into pre-trained diffusion models without retraining or architectural modifications. Inspired by constrained optimization, we apply a constrained…

Calamus 34 I dreamed in a dream
On the surface this short poem is a sort of City on a Hill vision. But I'm going to go with a more radical reading.
This poem reads to me as a fantasy of a gay society. A city of men, lovers, set apart from the rest of the world.
a city invincible to the attacks of the whole of the rest of the earth ...
the quality of robust love ...
the actions of the men of that city
And in all their looks and words.
I can't plausibly argue Whitman conceived of a city set apart in the way I imagine. Although all of Calamus is him constructing the idea of a society of lovers, comrades, brothers, robust love. That to me is very gay.
Intriguingly, in the unpublished Live Oak draft of this poem it is even more explicitly gay:
I saw them tenderly love each other ...
Nothing was greater there than manly love
It seems to me he dreamed a very gay city.

Tetraplectic structures compatible with local quaternionic toric actions
Panagiotis Batakidis, Ioannis Gkeneralis
https://arxiv.org/abs/2506.10148 https://…

Tetraplectic structures compatible with local quaternionic toric actions
This paper introduces a quaternionic analogue of toric geometry by developing the theory of local $Q^n := Sp(1)^n$-actions on 4n-dimensional manifolds, modeled on the regular representation. We identify obstructions that measure the failure of local properties to globalize and define two invariants: a combinatorial invariant called the characteristic pair and a cohomological invariant called the Euler class, which together classify local quaternionic torus actions up to homeomorphism. We also s…

A Spintronic Battery with Reversible Modulation of Spin Polarization through Li Charge/Discharge: A First Principles Computational Modelling Case Study for an Antiperovskite System
Sk Mujaffer Hossain, Vinila Bedekara, Priyanka Yadavb, Ram Janay Chudhary, Satishchandra Ogale
https://arxiv.org/abs/2506.14401

A Spintronic Battery with Reversible Modulation of Spin Polarization through Li Charge/Discharge: A First Principles Computational Modelling Case Study for an Antiperovskite System
A key notion defining the progress of the emergent fields of modern electronics, renewable energy, and smart systems is charge storage, which is primarily embodied in various battery chemistries and systems. In addition to the charge property, the electron also has the spin property, which is exploited in the field of spintronics to access novel magnetically controlled device actions that are not accessible to conventional electronics. An interesting question is whether the two can be fruitfull…

This https://arxiv.org/abs/2403.07931 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGT_…

Formalizing Feint Actions, and Example Studies in Two-Player Games
Feint actions refer to a set of deceptive actions, which enable players to obtain temporal advantages from their opponents. Such actions are regarded as widely-used tactic in most non-deterministic Two-player Games (e.g. boxing and fencing). However, existing literature does not provide comprehensive and concrete formalization on Feint actions, and their implications on Two-Player Games. We argue that a full exploration on Feint actions is of great importance towards more realistic Two-player G…

Google rolls out "scheduled actions" in the Gemini app, allowing AI Pro and AI Ultra subscribers to ask the AI assistant to perform tasks at specific times (Emma Roth/The Verge)
https://www.theverge.com/news/681762/google-gemini-schedul…

Google Gemini can now handle scheduled tasks like an assistant
Google is rolling out a new “scheduled actions” feature in Gemini that lets subscribers ask Gemini to carry out tasks at certain times.

MSNBC reporter at the 1:15 mark.
“The chaos you’re seeing is not the result of peaceful protestors, it’s the result of actions of law enforcement, specifically the Los Angeles Sheriff’s department.”
(Courtesy of Justin Satzman jsatz.bsky.social - https://bsky.app/profile/jsatz.bsky.so

TIL that go language server gopls can generate the boilerplate for a unit test of a function.
#go #golang #gopls

5 Actions of the Month to Help End Speciesism #AnimalRights

Goodness, does this mean we can expect a strongly-worded letter next? https://mastodon.social/@EndIsraeliApartheid/114675920702558762

Reviewing Certain Presidential Actions (President Donald J. Trump/The White House)
https://www.whitehouse.gov/presidential-actions/2025/06/reviewing-certain-presidential-actions/
http://www.memeorandum.com/250604/p182#a250604p182

Exploring EEG Responses during Observation of Actions Performed by Human Actor and Humanoid Robot
Anh T. Nguyen, Ajay Anand, Michelle J. Johnson
https://arxiv.org/abs/2506.10170

Exploring EEG Responses during Observation of Actions Performed by Human Actor and Humanoid Robot
Action observation (AO) therapy is a promising rehabilitative treatment for motor and language function in individuals recovering from neurological conditions, such as stroke. This pilot study aimed to investigate the potential of humanoid robots to support AO therapy in rehabilitation settings. The brain activity of three healthy right-handed participants was monitored with electroencephalography (EEG) while they observed eight different actions performed by two agents, a human actor and a rob…

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models
Huihan Liu, Rutav Shah, Shuijing Liu, Jack Pittenger, Mingyo Seo, Yuchen Cui, Yonatan Bisk, Roberto Mart\'in-Mart\'in, Yuke Zhu
https://arxiv.org/abs/2506.14727

Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models
Assistive teleoperation, where control is shared between a human and a robot, enables efficient and intuitive human-robot collaboration in diverse and unstructured environments. A central challenge in real-world assistive teleoperation is for the robot to infer a wide range of human intentions from user control inputs and to assist users with correct actions. Existing methods are either confined to simple, predefined scenarios or restricted to task-specific data distributions at training, limit…

The latest executive order from Trump administration removed the following sentence from a previous executive order.
" e) Open source software plays a critical role in Federal information systems."
🔗 https://www…

Sustaining Select Efforts to Strengthen the Nation's Cybersecurity and Amending Executive Order 13694 and Executive Order 14144
By the authority vested in me as President by the Constitution and the laws of the United States of America, including the International Emergency

A Procedural Framework for Assessing the Desirability of Process Deviations
Michael Grohs, Nadine Cordes, Jana-Rebecca Rehse
https://arxiv.org/abs/2506.11525

A Procedural Framework for Assessing the Desirability of Process Deviations
Conformance checking techniques help process analysts to identify where and how process executions deviate from a process model. However, they cannot determine the desirability of these deviations, i.e., whether they are problematic, acceptable or even beneficial for the process. Such desirability assessments are crucial to derive actions, but process analysts typically conduct them in a manual, ad-hoc way, which can be time-consuming, subjective, and irreplicable. To address this problem, this…

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
Ruiyan Zhu, Xi Cheng, Ke Liu, Brian Zhu, Daniel Jin, Neeraj Parihar, Zhoutian Xu, Oliver Gao
https://arxiv.org/abs/2506.12339

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions. The system comprises three specialized agents: a Manager Agent that decomposes complex user instructions into subtasks; an Action Agent that translates these into structured commands using a Backus Naur Form (BNF) grammar; and a Reflection Agent that validates alignment between generated actions and the user's original intent. Integrated int…

Apache Flink is uniquely positioned to serve as the backbone for AI agents, equipping them with the powerful new tool of stream processing. Join Steffen Hoellinger at this year's Berlin Buzzwords to explore how Flink jobs can be transformed into “Agents”—autonomous, goal-driven entities that dynamically interact with data streams, trigger actions, and adapt their behaviour based on real-time insights.
Learn more:

Climate messages focusing solely on personal behaviors, tend to make their recipients less likely to commit to collective actions like voting or demonstrating.
https://phys.org/news/2025-06-common-climate-messaging-backfires.html

Wow. Yes. From a California district court:
“At this early stage of the proceedings, the Court must determine whether the President followed the congressionally mandated procedure for his actions. He did not. His actions were illegal—both exceeding the scope of his statutory authority and violating the Tenth Amendment to the United States Constitution. He must therefore return control of the California National Guard to the Governor of the State of California forthwith.” https://journa.host/@chrisgeidner/114673375048335011

Welp, there goes Posse Comitatus (precluding troops from law enforcement actions such as search, seizure, and arrests). It was nice while we had it.
“Exclusive: US Marines carry out first known detention of civilian in Los Angeles, video shows”
https://www.

Learning The Minimum Action Distance
Lorenzo Steccanella, Joshua B. Evans, \"Ozg\"ur \c{S}im\c{s}ek, Anders Jonsson
https://arxiv.org/abs/2506.09276

Learning The Minimum Action Distance
This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. MAD naturally enables critical downstream tasks such as goal-conditi…

Convergence of Normal Form Power Series for Infinite-Dimensional Lie Pseudo-Group Actions
Peter J. Olver, Masoud Sabzevari, Francis Valiquette
https://arxiv.org/abs/2506.08869

Convergence of Normal Form Power Series for Infinite-Dimensional Lie Pseudo-Group Actions
We prove the convergence of normal form power series for suitably nonsingular analytic submanifolds under a broad class of infinite-dimensional Lie pseudo-group actions. Our theorem is illustrated by a number of examples, and includes, as a particular case, Chern and Moser's celebrated convergence theorem for normal forms of real hypersurfaces. The construction of normal forms relies on the equivariant moving frame method, while the convergence proof is based on the realization that the normal …

Upgrade or Switch: Do We Need a New Registry Architecture for the Internet of AI Agents?
Ramesh Raskar, Pradyumna Chari, Jared James Grogan, Mahesh Lambe, Robert Lincourt, Raghu Bala, Abhishek Singh, Ayush Chopra, Rajesh Ranjan, Shailja Gupta, Dimitris Stripelis, Maria Gorskikh, Sichao Wang
https://arxiv.org/abs/2506.12003

Upgrade or Switch: Do We Need a New Registry Architecture for the Internet of AI Agents?
The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions. Unlike traditional web resources, autonomous AI agents initiate actions, maintain persistent state, spawn sub-agents, and negotiate directly with peers: demanding millisecond-level discovery, instant credential revocation, and cryptographic behavioral proofs that exceed current DNS/PKI capabilities. This paper analyzes whether to upgrade existing infrastructure or implement…

While technically a correct fix, this #dotnet fix is about to break a lot of deployments. This was just deployed in the latest release of .NET 8 and 9.
https://github.com/dotnet/aspnetcore/p

[release/8.0] Forwarded Headers Middleware: Ignore XForwardedHeaders from Unknown Proxy by github-actions[bot] · Pull Request #61623 · dotnet/aspnetcore
Backport of #61530 to release/8.0 /cc @BrennanConroy @yannic-hamann-abb Forwarded Headers Middleware: Ignore XForwardedHeaders from Unknown Proxy Description If the ForwardedHeadersMiddleware middl...

Latent Action Diffusion for Cross-Embodiment Manipulation
Erik Bauer, Elvis Nava, Robert K. Katzschmann
https://arxiv.org/abs/2506.14608 https://

Latent Action Diffusion for Cross-Embodiment Manipulation
End-to-end learning approaches offer great potential for robotic manipulation, but their impact is constrained by data scarcity and heterogeneity across different embodiments. In particular, diverse action spaces across different end-effectors create barriers for cross-embodiment learning and skill transfer. We address this challenge through diffusion policies learned in a latent action space that unifies diverse end-effector actions. We first show that we can learn a semantically aligned laten…

Replaced article(s) found for math.RA. https://arxiv.org/list/math.RA/new
[1/1]:
Group actions and automorphisms of evolution algebras associated to finite graphs

Trump ordered his White House counsel and the attorney general on Wednesday to investigate former President Joseph R. Biden Jr. and his staff -- in Mr. Trump’s latest attempt to stoke outlandish conspiracy theories about his predecessor.
In an executive order, Mr. Trump put the power and resources of the federal government to work examining whether some of Mr. Biden’s presidential actions were legally invalid because his aides had enacted those policies without his knowledge.
The e…

Trump Orders Investigation of Biden and His Aides
The executive order is the latest effort by President Trump to stoke outlandish conspiracy theories about his predecessor and question the legality of his actions in office.

Getting cross compilation setup on gh actions for rust wasn't the easiest as a CI noob

Hopf actions on Poisson algebras
Awn Alqahtani, Jason Gaddis, Xingting Wang
https://arxiv.org/abs/2506.06135 https://arxiv.org/pdf/25…

Hopf actions on Poisson algebras
We study finite-dimensional Hopf actions on Poisson algebras and explore the phenomenon of quantum rigidity in this context. Our main focus is on filtered (and especially quadratic) Poisson algebras, including the Weyl Poisson algebra in $2n$ variables and certain Poisson algebras in two variables. In particular, we show that any finite-dimensional Hopf algebra acting inner faithfully on these Poisson algebras must necessarily factor through a group algebra-mirroring well-known rigidity theorem…

Who and How? Adverse Selection and flexible Moral Hazard
Henrique Castro-Pires, Deniz Kattwinkel, Jan Knoepfle
https://arxiv.org/abs/2506.12979 https://

Who and How? Adverse Selection and flexible Moral Hazard
We characterize the set of incentive compatible mechanisms in problems with hidden productivity types and flexible hidden actions. We demonstrate the tractability of the characterization with applications.

How many of you think that in FFOTUS' recent tariff "deal" with China that FFOTUS secretly gave away something of great value?
My thought (based on no actual facts) is that FFOTUS promised the US would take a "hands off" position with regard to China's actions in the South China Sea.

To the genocide-loving German from mastodon.social who reported @… for being antisemitic:
Fuck you, you genocide-loving piece of shit, opposing genocide isn’t antisemitism. What you’re doing – conflating being anti-genocide with being antisemitic – is the greatest antisemitism as you’re de facto stating that all Jews are pro-genocide.

This https://arxiv.org/abs/2501.14274 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Exotic proper actions on homogeneous spaces via convex cocompact representations
We construct a series of homogeneous spaces G/H of reductive type which admit proper actions of discrete subgroups of G isomorphic to cocompact lattices of O(n,1) (n=2,3,4) but do not admit proper actions of non-compact semisimple subgroups of G. The existence of such homogeneous spaces was previously not known even for n=2. Our construction of proper actions of discrete subgroups is based on Guéritaud-Kassel's work on convex cocompact subgroups of O(n,1) and Danciger-Guéritaud-Kassel's work …

Unstable $1$-semiadditivity as classifying Goodwillie towers
Connor Malin
https://arxiv.org/abs/2506.11245 https://arxiv.org/pdf/2506…

Unstable $1$-semiadditivity as classifying Goodwillie towers
A stable $\infty$-category is $1$-semiadditive if all norms for finite group actions are equivalences. In the presence of $1$-semiadditivity, Goodwillie calculus simplifies drastically. We introduce two unstable analogs of $1$-semiadditivity for an $\infty$-category $C$ and study their relation to the Goodwillie calculus of functors $C \rightarrow \s(C)$. We demonstrate these qualities are complete obstructions to the problem of endowing $\partial_\ast F$ with either a right module or a divided…

Markov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior
Chengyuan Zhang, Cathy Wu, Lijun Sun
https://arxiv.org/abs/2506.14762

Markov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior
Accurate and interpretable car-following models are essential for traffic simulation and autonomous vehicle development. However, classical models like the Intelligent Driver Model (IDM) are fundamentally limited by their parsimonious and single-regime structure. They fail to capture the multi-modal nature of human driving, where a single driving state (e.g., speed, relative speed, and gap) can elicit many different driver actions. This forces the model to average across distinct behaviors, red…

"The TSA has an important job to do. Their actions at airports have been very poor. This creates lots of loss to travelers – waste. And their actions show a disrespect for people and the risks that exist. The security theater is not what we need. We need evidence based security measure while maintaining a focus on the value stream of people flying."

Duality-symmetric D3-brane action with twisted self-dual 2-form doublet
Pichet Vanichchapongjaroen
https://arxiv.org/abs/2506.07219 https://

Duality-symmetric D3-brane action with twisted self-dual 2-form doublet
In this paper we apply the Sen formulation, which is originally developed for chiral form fields, to construct non-linear duality-symmetric actions in four dimensions. In particular, the duality-symmetric D3-brane action coupled to the type IIB supergravity background is constructed in the Sen formulation. Key features of the Sen formulation are also present in the duality-symmetric actions. For example, there are unphysical fields with the wrong sign of kinetic terms. These fields are uncouple…

REGARDING THE PROPOSED ACQUISITION OF UNITED STATES STEEL CORPORATION BY NIPPON STEEL CORPORATION (President Donald J. Trump/The White House)
https://www.whitehouse.gov/presidential-actions/2025/06/regarding-the-proposed-acquisition-of-the-united-states-steel-corporation-by-nippon-steel-corporation/
http://www.memeorandum.com/250613/p153#a250613p153

as a transit advocate, I would like to be able to embrace Scott Wiener as a champion for transit funding, but unfortunately he has also regularly attacked and defamed pro-Palestine activists. his actions have contributed to a neo-McCarthyist atmosphere around this issue that was immediately seized upon by Trump on coming back to power

Doctor Says UCSF Fired Her Due to Pressure From Wiener, Dillers Over Pro-Palestinian Speech
CA State Senator Scott Wiener and UCSF’s largest donor, the Diller Foundation, are named in new allegations by Dr. Rupa Marya, prominent physician, activist, and musician, who is suing UCSF over her recent termination stemming from public criticism of Israel.

Financial Times editorial: ”European states must show Israel that its actions bear consequences. They should ban trade with settlements and sanction extremist settler entities. They should halve offensive weapons sales to Israel and sanction ultranationalists in the government …
Finally, they should lead the way in formally recognising a Palestinian state, before there is nothing left to recognise.” #Gaza

Israel is destroying the foundations of a Palestinian state
The Netanyahu government must be held to account over Gaza and the West Bank

Individuality
My words are easy to understand
And my actions are easy to perform
Yet no other can understand or perform them.
My words have meaning; my actions have reason;
Yet these cannot be known and I cannot be known.
We are each unique, and therefore valuable;
Though the sage wears coarse clothes, his heart is jade.
-- Lao Tse, "Tao Te Ching"

Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes
Yiming Dou, Wonseok Oh, Yuqing Luo, Antonio Loquercio, Andrew Owens
https://arxiv.org/abs/2506.09989

Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes
We study the problem of making 3D scene reconstructions interactive by asking the following question: can we predict the sounds of human hands physically interacting with a scene? First, we record a video of a human manipulating objects within a 3D scene using their hands. We then use these action-sound pairs to train a rectified flow model to map 3D hand trajectories to their corresponding audio. At test time, a user can query the model for other actions, parameterized as sequences of hand pos…

FASCIST-O-METER: Classifier for Neo-fascist Discourse Online
Rudy Alexandro Garrido Veliz, Martin Semmann, Chris Biemann, Seid Muhie Yimam
https://arxiv.org/abs/2506.10789

FASCIST-O-METER: Classifier for Neo-fascist Discourse Online
Neo-fascism is a political and societal ideology that has been having remarkable growth in the last decade in the United States of America (USA), as well as in other Western societies. It poses a grave danger to democracy and the minorities it targets, and it requires active actions against it to avoid escalation. This work presents the first-of-its-kind neo-fascist coding scheme for digital discourse in the USA societal context, overseen by political science researchers. Our work bridges the g…

A part of The Accountant 2's character roster (the tech-wiz kids) is interesting in the relation between ‘modern surveillance’ and established genres. Surveillance cameras in the way? Hack or shut them down. Need an edge for the good guys during the showdown? Take over a bunch of US Air Force drones to: pinpoint the bad guys‘ location in a deserted area; conceal the actions of the heroes dealing with them. You either subvert it or remove it from the equation to make the human plot possib…

This https://arxiv.org/abs/2503.18938 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

AdaWorld: Learning Adaptable World Models with Latent Actions
World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training, making it challenging to adapt to novel environments with heterogeneous actions through limited interactions. This limitation can hinder their applicability across broader domains. To overcome this limitation, we propose AdaWorld, an innovative world model learni…

Almost-invariant elements of group actions on Lip$_0$ spaces
Tom\'a\v{s} Raunig
https://arxiv.org/abs/2506.06770 https://arxiv.or…

Almost-invariant elements of group actions on Lip$_0$ spaces
This work is motivated by a question published in E. Glasner's paper On a question of Kazhdan and Yom Din regarding the possibility to approximate functionals on a Banach space which are almost invariant with respect to an action of a discrete group by functionals that are invariant. We study the case when the Banach space is a Lipschitz-free space equipped with an action induced by an action by isometries on the underlaying space. We find a few different conditions sufficient for the answer to…

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Songze Li, Mingxuan Zhang, Oubo Ma, Kang Wei, Shouling Ji
https://arxiv.org/abs/2506.09562

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attackers can efficiently exploit system vulnerabilities during the training phase to execute backdoor attacks, producing malicious actions when specific trigger patterns are present in the state observations. However, most existing backdoor attacks rely primarily on simplistic and heu…

Skew monoidal structures on actegories
Pavla Proch\'azkov\'a
https://arxiv.org/abs/2506.06847 https://arxiv.org/pdf/2506.0684…

Skew monoidal structures on actegories
We present a construction of skew monoidal structures from strong actions. We prove that the existence of a certain adjoint allows one to equip the actegory with a skew monoidal structure and that this adjunction becomes monoidal. This construction provides a unifying framework for the description of several examples of skew monoidal categories. We also demonstrate how braidings on the original monoidal category of a given action induce braidings on the resulting skew monoidal structure on the …

Viele europäische #Landwirt*innen zeigen mehr #Klimaskepsis als andere Berufsgruppen, vor allem in wohlhabenderen Ländern mit geringerem #Klimarisiko.
Das erschwert

Climate change skepticism of European farmers and implications for effective policy actions - Communications Earth & Environment
The majority of farmers in European Union countries are more skeptical about climate change impact and attribution than the general population, and more so in more innovative and higher-income countries, according to an analysis of European-level surveys.

Functional and structural plasticity induced by audiovisual associations and sensory experiences https://link.springer.com/article/10.1007/s00429-025-02951-3 "widespread increases in functional connectivity between the trained region and higher-order frontal…

Functional and structural plasticity induced by audiovisual associations and sensory experiences - Brain Structure and Function
Crossmodal associations and correspondences play important roles in shaping perception and guiding our actions. However, we still have a limited understanding of association-induced changes in the adult human brain. An important question to address is to what extent passive exposure to crossmodal associations leads to functional and structural changes in the brain. Utilizing an audiovisual association paradigm in which motion stimuli presented in the left visual field were paired with auditory …

Twisted Graded Categories
Shai Keidar, Shaul Ragimov
https://arxiv.org/abs/2506.11240 https://arxiv.org/pdf/2506.11240

Twisted Graded Categories
Given a presentably symmetric monoidal $\infty$-category $\mathcal{C}$ and an $\mathbb{E}_{\infty}$-monoid $M$, we introduce and classify twisted graded categories, which generalize the Day convolution structure on $\mathrm{Fun}(M, \mathcal{C})$. These are characterized by a braiding encoded in symmetric group actions on tensor powers, whose character we show depends only on the $\mathbb{T}$-equivariant monoidal dimension. We analyze the $\mathbb{T}$-action on the dimension of invertible object…

“Noor, who made so many friends on Bluesky since she started an account there in the summer of 2023, had her account suddenly suspended on Friday. Bluesky did not send a reason for the suspension, so while she wrote an appeal, she did not know what actions she was appealing, so as of now it's still suspended. She’s been silenced, and effectively disappeared.”

A Future for Noor and Her Children
Hello! I'm Meave, a U.S. citizen sponsoring this fundraiser on behalf of my dear friend Noor Hassan and her children. Noor and her son Abdul Rahman are kind, generous people; though their original fundraiser succeeded last summer, supporting themselves and their extended family cost them everything. This fundraiser will allow them to support themselves and save up to buy passage to Egypt and pursue a better future.

Imposing Sanctions in Response to the ICC's Illegitimate Actions Targeting the United States and Israel (United States Department of State)
https://www.state.gov/imposing-sanctions-in-response-to-the-iccs-illegitimate-actions-targeting-the-united-states-and-israel/
http://www.memeorandum.com/250606/p52#a250606p52

Apple unveils an updated Spotlight in macOS Tahoe, letting users quickly take actions in apps from playing music to creating notes and files, similar to Raycast (David Pierce/The Verge)
https://www.theverge.com/apple/682950/apple-spotlight-mac-shortcuts

Apple’s Spotlight upgrades look like a power-user dream
At WWDC 2025, Apple announced a big update to Spotlight that makes it a far more powerful system for launching and doing things on your Mac.

This https://arxiv.org/abs/2503.02768 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csPL_…

Denotational Semantics for Probabilistic and Concurrent Programs
We develop a denotational model for probabilistic and concurrent imperative programs, a class of programs with standard control flow via conditionals and while-loops, as well as probabilistic actions and parallel composition. Whereas semantics for concurrent or randomized programs in isolation is well studied, their combination has not been thoroughly explored and presents unique challenges. The crux of the problem is that interactions between control flow, probabilistic actions, and concurrent…

Equivariant periodic cyclic homology for ample groupoids
Francesco Pagliuca, Christian Voigt
https://arxiv.org/abs/2506.06503 https://

Equivariant periodic cyclic homology for ample groupoids
We define and study bivariant equivariant periodic cyclic homology for actions of ample groupoids. In analogy to the group case, we show that the theory satisfies homotopy invariance, stability, and excision in both variables. We also prove an analogue of the Green-Julg theorem for actions of proper groupoids.

Trump administration sanctions International Criminal Court judges | Donald Trump News | Al Jazeera
https://www.aljazeera.com/news/2025/6/5/trump-administration-sanctions-international-criminal-court-judges

Trump sent the National Guard to Los Angeles at a time when state and local officials said they had protests there under control.

The move reflects an increasingly evident pattern of his presidency:
Trump declares an emergency or crisis where many others do not see one,
enabling him to take sweeping actions,
rally supporters and fight on political terrain he finds favorable.

Trump’s declaration of an economic emergency in April enabled sweeping tariffs.
…

For Trump, seizing emergency powers has become central to governing
President Donald Trump has declared emergencies in various areas. He says strong action is needed; critics say the emergencies don’t exist.

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
Gaurav Chaudhary, Wassim Uddin Mondal, Laxmidhar Behera
https://arxiv.org/abs/2506.09574

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
Sample efficiency and exploration remain critical challenges in Deep Reinforcement Learning (DRL), particularly in complex domains. Offline RL, which enables agents to learn optimal policies from static, pre-collected datasets, has emerged as a promising alternative. However, offline RL is constrained by issues such as out-of-distribution (OOD) actions that limit policy performance and generalization. To overcome these limitations, we propose Meta Offline-Online Reinforcement Learning (MOORL), …

Fact Sheet: President Donald J. Trump Directs Review of Certain Presidential Actions (The White House)
https://www.whitehouse.gov/fact-sheets/2025/06/fact-sheet-president-donald-j-trump-directs-review-of-certain-presidential-actions/
http://www.memeorandum.com/250605/p1#a250605p1

"Actions over words:" Bengals wide receiver Jermaine Burton is ready for a challenge https://www.espn.com/nfl/story/_/id/45458576/nfl-jermaine-burton-cincinnati-bengals-second-season

Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation
Ye Niu, Sanping Zhou, Yizhe Li, Ye Den, Le Wang
https://arxiv.org/abs/2506.09422

Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation
In many complex scenarios, robotic manipulation relies on generative models to estimate the distribution of multiple successful actions. As the diffusion model has better training robustness than other generative models, it performs well in imitation learning through successful robot demonstrations. However, the diffusion-based policy methods typically require significant time to iteratively denoise robot actions, which hinders real-time responses in robotic manipulation. Moreover, existing dif…

What Comes After Harm? Mapping Reparative Actions in AI through Justice Frameworks
Sijia Xiao, Haodi Zou, Alice Qian Zhang, Deepak Kumar, Hong Shen, Jason Hong, Motahhare Eslami
https://arxiv.org/abs/2506.05687

What Comes After Harm? Mapping Reparative Actions in AI through Justice Frameworks
As Artificial Intelligence (AI) systems are integrated into more aspects of society, they offer new capabilities but also cause a range of harms that are drawing increasing scrutiny. A large body of work in the Responsible AI community has focused on identifying and auditing these harms. However, much less is understood about what happens after harm occurs: what constitutes reparation, who initiates it, and how effective these reparations are. In this paper, we develop a taxonomy of AI harm rep…

“I witnessed how they put my father in handcuffs, chained him from the waist and from his ankles,”
Contreras said at a press conference in LA on Monday morning.
“My family and I haven’t had communication with my dad.
We don’t know anything.”
Jacob and Romero were among dozens of people arrested in immigration enforcement actions in Los Angeles this weekend,
raids that sparked a roaring backlash and eventually led to the deployment of the national guard in the ci…

Anosov actions: minimality of foliations or suspension action
Rodrigo R. Lopes, Carlos Maquera, R\'egis Var\~ao
https://arxiv.org/abs/2505.24598 https:…

Anosov actions: minimality of foliations or suspension action
We prove that an Anosov action of $\mathbb{R}^k$ over a compact manifold $M$ transitive on regular sub-cones satisfies the dichotomy: each stable and unstable leaf is dense or the Anosov action is topologically conjugated to a suspension of a $\mathbb{Z}^k$-Anosov action. This represents an important progress toward addressing Verjovsky's extended conjecture for Anosov actions, as developed by Barbot and Maquera.

The depth of the damage to the USA by the Republican party and this administration is catastrophic, especially in the long term.
Hundreds or thousands of incredibly damaging actions have been taken this year with seeming dozens more every week.
It is impossible to keep track of the destruction being done to the rule of law, our economy, human rights, our health...

Finiteness properties of stabilisers of oligomorphic actions
Francesco Fournier-Facio, Peter H. Kropholler, Robert Alonzo Lyman, Matthew C. B. Zaremsky
https://arxiv.org/abs/2506.02319

Finiteness properties of stabilisers of oligomorphic actions
An action of a group on a set is oligomorphic if it has finitely many orbits of $n$-element subsets for all $n$. We prove that for a large class of groups (including all groups of finite virtual cohomological dimension and all countable linear groups), for any oligomorphic action of such a group on an infinite set there exists a finite subset whose stabiliser is not of type $\mathrm{FP}_\infty$. This leads to obstructions on finiteness properties for permutational wreath products and twisted Br…

IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents
Shiwei Feng, Xiangzhe Xu, Xuan Chen, Kaiyuan Zhang, Syed Yusuf Ahmed, Zian Su, Mingwei Zheng, Xiangyu Zhang
https://arxiv.org/abs/2506.07524

IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents
LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent's actions that diverge from the user's intended goal, especially as external toolkits evolve. Traditional software testing assumes structured inputs and thus falls short in handling the ambiguity of natural language. We introduce IntenTest, an API-centric stress testing framework th…

Ping-pong dynamics of hyperbolic-like actions with non-simple points
KyeongRo Kim, Michele Triestino
https://arxiv.org/abs/2506.01690 https://

Ping-pong dynamics of hyperbolic-like actions with non-simple points
A hyperbolic-like group is a subgroup of $\operatorname{Homeo}_+(S^1)$ such that every non-trivial element has exactly two fixed points, one attracting and one repelling. We investigate the ping-pong dynamics of hyperbolic-like groups, inspired by a conjecture of Bonatti. We show the existence of a proper ping-pong partition for any pair of non-cyclic point stabilizers. More precisely, our results explicitly provide such a ping-pong partition.

On Loss-Minimal Radial Topologies in MV Systems
Anton Hinneck, Mathias Duckheim, Michael Metzger, Stefan Niessen
https://arxiv.org/abs/2506.03422 https://

On Loss-Minimal Radial Topologies in MV Systems
Distribution system reconfiguration (DSR) means optimizing the topology of a distribution grid using switching actions. Switching actions are a degrees of freedom available to distribution system operators, e.g. to manage planned and unplanned outages. DSR is a NP-hard combinatorial problem. Finding good or even optimal solutions is computationally expensive. While transmission and high-voltage grids are generally operated in a meshed state, MV distribution systems are commonly operated as radi…

Free Circle Actions on the Product of Three Spheres
Dimpi, Hemant Kumar Singh
https://arxiv.org/abs/2505.21993 https://arxiv.org/pdf/…

Free Circle Actions on the Product of Three Spheres
The orbit spaces of free S^0-actions on the mod 2 cohomology product of three spheres, S^n x S^m x S^l, 1 <= n <= m <= l have been determined in [6]. In this paper, we extend these findings to free S^1-actions on the rational cohomology product of three spheres. This extension also builds upon the work of Dotzel et al. [7], who studied free circle actions on the rational cohomology product of two spheres. Additionally, we establish Borsuk-Ulam type theorems.

Rodrigues Network for Learning Robot Actions
Jialiang Zhang, Haoran Geng, Yang You, Congyue Deng, Pieter Abbeel, Jitendra Malik, Leonidas Guibas
https://arxiv.org/abs/2506.02618

Rodrigues Network for Learning Robot Actions
Understanding and predicting articulated actions is important in robot learning. However, common architectures such as MLPs and Transformers lack inductive biases that reflect the underlying kinematic structure of articulated systems. To this end, we propose the Neural Rodrigues Operator, a learnable generalization of the classical forward kinematics operation, designed to inject kinematics-aware inductive bias into neural computation. Building on this operator, we design the Rodrigues Network …

Grasp Prediction based on Local Finger Motion Dynamics
Dimitar Valkov, Pascal Kockwelp, Florian Daiber, Antonio Kr\"uger
https://arxiv.org/abs/2506.10818

Grasp Prediction based on Local Finger Motion Dynamics
The ability to predict the object the user intends to grasp offers essential contextual information and may help to leverage the effects of point-to-point latency in interactive environments. This paper explores the feasibility and accuracy of real-time recognition of uninstrumented objects based on hand kinematics during reach-to-grasp actions. In a data collection study, we recorded the hand motions of 16 participants while reaching out to grasp and then moving real and synthetic objects. Our…

The Trump administration’s cancellation of $766 million in contracts to develop mRNA vaccines against potential pandemic flu viruses -- is the latest blow -- to national defense, former health security officials said.
They warned that the U.S. could be at the mercy of other countries in the next pandemic.
“The administration’s actions are gutting our deterrence from biological threats,” said Beth Cameron, a senior adviser to the Brown University Pandemic Center
"we are…

In Axing mRNA Contract, Trump Delivers Another Blow to US Biosecurity, Former Officials Say - KFF Health News
The Trump administration is eroding national pandemic flu defenses as it guts health agencies, cuts research and health budgets, and withdraws funding for bird flu vaccines, health security experts said.

Department of Defense Security for the Protection of Department of Homeland Security Functions (President Donald J. Trump/The White House)
https://www.whitehouse.gov/presidential-actions/2025/06/department-of-defense-security-for-the-protection-of-department-of-homeland-security-functions/
http://www.memeorandum.com/250607/p62#a250607p62

Free actions on products of real projective spaces
Ergun Yalcin
https://arxiv.org/abs/2506.04067 https://arxiv.org/pdf/2506.04067

Free actions on products of real projective spaces
We prove that if $G=(\mathbb{Z}/2)^r$ acts freely and cellularly on a finite-dimensional CW-complex $X$ homotopy equivalent to $\mathbb{R}P ^{n_1} \times \cdots \times \mathbb{R} P ^{n_k}$ with trivial action on the mod-$2$ cohomology, then $r \leq μ(n_1)+ \cdots + μ(n_k )$ where for each integer $n\geq 0$, $μ(n)=0$ if $n$ is even, $μ(n)=1$ if $n\equiv 1$ mod 4, and $μ(n)=2$ if $n\equiv 3$ mod 4. This proves a homotopy-theoretic version of a conjecture of Cusick.

Locomotion on Constrained Footholds via Layered Architectures and Model Predictive Control
Zachary Olkin, Aaron D. Ames
https://arxiv.org/abs/2506.09979 ht…

Locomotion on Constrained Footholds via Layered Architectures and Model Predictive Control
Computing stabilizing and optimal control actions for legged locomotion in real time is difficult due to the nonlinear, hybrid, and high dimensional nature of these robots. The hybrid nature of the system introduces a combination of discrete and continuous variables which causes issues for numerical optimal control. To address these challenges, we propose a layered architecture that separates the choice of discrete variables and a smooth Model Predictive Controller (MPC). The layered formulatio…

Education Secretary Linda McMahon, in a statement, said Columbia’s leadership
“acted with deliberate indifference towards the harassment of Jewish students on its campus”
and urged the accrediting body to keep the department informed of any actions taken to ensure Columbia’s compliance with accreditation standards.
“Accreditors have an enormous public responsibility as gatekeepers of federal student aid,” McMahon said.
“Just as the Department of Education has an oblig…

Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions
Changmin Park, Beomjoon Lee, Haechan Jung, Haejin Jung, Changjoo Nam
https://arxiv.org/abs/2506.03760

Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions
In this paper, we consider the problem of understanding the physical properties of unseen objects through interactions between the objects and a robot. Handling unseen objects with special properties such as deformability is challenging for traditional task and motion planning approaches as they are often with the closed world assumption. Recent results in Large Language Models (LLMs) based task planning have shown the ability to reason about unseen objects. However, most studies assume rigid o…

In 2018, an #anonymous Trump administration official delivered a stark warning about the threat he said the president posed with his erratic behavior.
The author was later revealed to be #Miles #Taylor.
When Trump returned…

Miles Taylor fights Trump’s order targeting him, calling it ‘an attack on free speech’
In 2018, an anonymous Trump administration official delivered a stark warning about the threat he said the president posed with his erratic behavior. The author was later revealed to be Miles Taylor. When Trump returned to office, he claimed Taylor’s actions could be treasonous and ordered DHS and other agencies to launch an investigation. Taylor joined Amna Nawaz to discuss his legal response.

Some of Trump's Biggest Inaugural Donors Benefit From Early Government Actions (Wall Street Journal)
https://www.wsj.com/politics/policy/trump-inauguration-donors-benefit-2ff3121f
http://www.memeorandum.com/250603/p145#a250603p145

This https://arxiv.org/abs/2301.09002 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

The Gysin braid for $S^3$-actions on manifolds
Given a smooth action of the sphere $\mathbb S^3$ on a manifold $M$, we have previously constructed a Gysin sequence relating the cohomology of the manifold $M$ and that of the orbit space $M/\mathbb S^3$. This sequence involves an exotic term depending on the subset $M^{\mathbb S^1}$. Notice that the orbit space is a stratified pseudomanifold, a kind of singular spaces where intersection cohomology applies. In the case where the the action is semi-free, the first author has already construct…

Analytic Task Scheduler: Recursive Least Squares Based Method for Continual Learning in Embodied Foundation Models
Lipei Xie, Yingxin Li, Huiping Zhuang
https://arxiv.org/abs/2506.09623

Analytic Task Scheduler: Recursive Least Squares Based Method for Continual Learning in Embodied Foundation Models
Embodied foundation models are crucial for Artificial Intelligence (AI) interacting with the physical world by integrating multi-modal inputs, such as proprioception, vision and language, to understand human intentions and generate actions to control robots. While these models demonstrate strong generalization and few-shot learning capabilities, they face significant challenges in continually acquiring new skills without forgetting previously learned skills, a problem known as catastrophic forg…

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
Yiming Zhong, Yumeng Liu, Chuyang Xiao, Zemin Yang, Youzhuo Wang, Yufei Zhu, Ye Shi, Yujing Sun, Xinge Zhu, Yuexin Ma
https://arxiv.org/abs/2506.01583

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
Learning effective visuomotor policies for robotic manipulation is challenging, as it requires generating precise actions while maintaining computational efficiency. Existing methods remain unsatisfactory due to inherent limitations in the essential action representation and the basic network architectures. We observe that representing actions in the frequency domain captures the structured nature of motion more effectively: low-frequency components reflect global movement patterns, while high-…

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Yi Yang, Jiaxuan Sun, Siqi Kou, Yihan Wang, Zhijie Deng
https://arxiv.org/abs/2506.00411

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into sub-tasks) and low-level motion control (i.e., generating precise robot actions). While existing vision language action (VLA) models and hierarchical architectures offer potential in embodied tasks, the former often falter in planning, and the latter can suffe…

Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Muhammad Qasim Ali, Aditya Sridhar, Shahbuland Matiana, Alex Wong, Mohammad Al-Sharman
https://arxiv.org/abs/2506.01182

Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Humanoid robots have the potential to perform complex tasks in human centered environments but require robust predictive models to reason about the outcomes of their actions. We introduce Humanoid World Models (HWM) a family of lightweight open source video based models that forecast future egocentric observations conditioned on actions. We train two types of generative models Masked Transformers and FlowMatching on 100 hours of humanoid demonstrations. Additionally we explore architectural var…

This https://arxiv.org/abs/2409.06990 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SIS: Seam-Informed Strategy for T-shirt Unfolding
Seams are information-rich components of garments. The presence of different types of seams and their combinations helps to select grasping points for garment handling. In this paper, we propose a new Seam-Informed Strategy (SIS) for finding actions for handling a garment, such as grasping and unfolding a T-shirt. Candidates for a pair of grasping points for a dual-arm manipulator system are extracted using the proposed Seam Feature Extraction Method (SFEM). A pair of grasping points for the ro…

This https://arxiv.org/abs/2502.10090 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models
Humans possess an extraordinary ability to understand and execute complex manipulation tasks by interpreting abstract instruction manuals. For robots, however, this capability remains a substantial challenge, as they cannot interpret abstract instructions and translate them into executable actions. In this paper, we present Manual2Skill, a novel framework that enables robots to perform complex assembly tasks guided by high-level manual instructions. Our approach leverages a Vision-Language Mode…