Tootfinder

Verifier-free Test-Time Sampling for Vision Language Action Models
Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, Jinwoo Shin
https://arxiv.org/abs/2510.05681 https:/…

Verifier-free Test-Time Sampling for Vision Language Action Models
Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in tasks that require high precision due to their single-inference paradigm. While test-time scaling approaches using external verifiers have shown promise, they require additional training and fail to generalize to unseen conditions. We propose Masking Distribution Guided Selection (MG-Select), a novel test-time scaling framework for VLAs that leverages the…

"UK government and public overestimate time left for climate action, study finds"
#UK #UnitedKingdom #Climate #ClimateChange

UK government and public overestimate time left for climate action, study finds
A new study has found that UK Members of Parliament (MPs) and the public overestimate the time left to meet a critical deadline for limiting global warming.

So, we came early to the #baseball game for the Chipper Jones Bobblehead. We were successful, but we'll see how the game looks come the 6:05pm start time. The game is Stripers vs Durham Bulls.
#milb

Real-Time Iteration Scheme for Diffusion Policy
Yufei Duan, Hang Yin, Danica Kragic
https://arxiv.org/abs/2508.05396 https://arxiv.org/pdf/2508.05396

Real-Time Iteration Scheme for Diffusion Policy
Diffusion Policies have demonstrated impressive performance in robotic manipulation tasks. However, their long inference time, resulting from an extensive iterative denoising process, and the need to execute an action chunk before the next prediction to maintain consistent actions limit their applicability to latency-critical tasks or simple tasks with a short cycle time. While recent methods explored distillation or alternative policy structures to accelerate inference, these often demand addi…

Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
Davide Paglieri, Bart{\l}omiej Cupia{\l}, Jonathan Cook, Ulyana Piterbarg, Jens Tuyls, Edward Grefenstette, Jakob Nicolaus Foerster, Jack Parker-Holder, Tim Rockt\"aschel
https://arxiv.org/abs/2509.03581

Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action; however, we demonstrate that always planning is computationally expensive and degrades performance on long-horizon tasks, while never planning further limits performance. To address this, we introduce a conceptual framework formalizing dynamic planning for LL…

The Study on Modified Theories of General Relativity: A Differential Geometric Approach
N. S. Kavya
https://arxiv.org/abs/2507.04031 https://

The Study on Modified Theories of General Relativity: A Differential Geometric Approach
The introduction of General Relativity (GR) in 1915 revolutionized our understanding of gravity, but over time, its limitations in explaining phenomena like dark energy, dark matter, and quantum gravity have motivated alternative theories. Early modifications, such as Weyl's 1919 proposal, focused on adding higher-order terms to the Einstein-Hilbert action. GR's non-renormalizability further strengthened the case for extending it. A central theme of modern gravity research is modifying the geom…

SITCOM: Scaling Inference-Time COMpute for VLAs
Ayudh Saxena, Harsh Shah, Sandeep Routray, Rishi Rajesh Shah, Esha Pahwa
https://arxiv.org/abs/2510.04041 https://

SITCOM: Scaling Inference-Time COMpute for VLAs
Learning robust robotic control policies remains a major challenge due to the high cost of collecting labeled data, limited generalization to unseen environments, and difficulties in planning over long horizons. While Vision-Language-Action (VLA) models offer a promising solution by grounding natural language instructions into single-step control commands, they often lack mechanisms for lookahead and struggle with compounding errors in dynamic tasks. In this project, we introduce Scaling Infere…

A rigorous Keldysh functional integral for fermions
Philipp Benjamin Aretz, Manfred Salmhofer
https://arxiv.org/abs/2508.01787 https://arxiv.org/pdf/2508.0…

A rigorous Keldysh functional integral for fermions
We provide a mathematically rigorous Keldysh functional integral for fermionic quantum field theories. We show convergence of a discrete-time Grassmann Gaussian integral representation in the time-continuum limit under very general hypotheses. We also prove analyticity of the effective action and explicit bounds for the truncated (connected) expectation values of the non-equilibrium system. These bounds imply clustering with a summable decay in the thermodynamic limit, provided these properties…

Learning the action for long-time-step simulations of molecular dynamics
Filippo Bigi, Michele Ceriotti
https://arxiv.org/abs/2508.01068 https://arxiv.org/…

Learning the action for long-time-step simulations of molecular dynamics
The equations of classical mechanics can be used to model the time evolution of countless physical systems, from the astrophysical to the atomic scale. Accurate numerical integration requires small time steps, which limits the computational efficiency -- especially in cases such as molecular dynamics that span wildly different time scales. Using machine-learning (ML) algorithms to predict trajectories allows one to greatly extend the integration time step, at the cost of introducing artifacts s…

It\^{o}-Stratonovich Conversion in Infinite Dimensions for Unbounded, Time-Dependent, Nonlinear Operators
Daniel Goodair
https://arxiv.org/abs/2508.03424 https://

Itô-Stratonovich Conversion in Infinite Dimensions for Unbounded, Time-Dependent, Nonlinear Operators
We prove that a solution, in a variational framework, to the Stratonovich stochastic partial differential equation with noise $G\left(t, Ψ_t\right) \circ dW_t$ is given by a solution to the Itô equation with Itô-Stratonovich corrector $\frac{1}{2}\sum_{i=1}^\infty D_uG_i\left(t, Ψ_t\right)\left[G_i(t,Ψ_t)\right]dt$. Here $G_i$ denotes the action of $G$ on the $i^{th}$ component of the cylindrical noise, and $D_uG_i$ its Fréchet partial derivative in the Hilbert space for which the Itô fo…

The US has about two dozen of its 71 nuclear-powered submarines at sea at any one time
and they are routinely moved into areas close to Russia, especially at times of heightened tension.
What is unusual is for the US to broadcast it, betraying the real point of Trump’s post,
which is: to demonstrate he is a man of action and to send a message.
The action is important to Trump as the most performative president of the modern era,
his now-familiar style being to r…

Why has Trump deployed nuclear submarines?
The US president wants to demonstrate that he is a man of action and send a message to President Putin after the Russian leader rejected his calls for a truce

In the UK, you can now get arrested under the Terrorist Act for wearing a T-shirt against Israel's ongoing genocide in Gaza.
Paul Laverty is to be charged under section 13 of the Terrorist Act for wearing a T-shirt with the words: “Genocide in Palestine, time to take Action”, thought to show support for activist group Palestine Action, proscribed as a terrorist organisation by the UK Labour government for painting fighter jets in a protest.

"""
In the sixteenth century, lunacy was a constant theme that was never questioned. It was still frequent in the seventeenth century, but started to disappear, and by 1707, the year in which Le François asked the question ‘Estne aliquod lunae in corpora humana imperium?’ (Does the moon have any influence over the human body?), after lengthy discussions, the university decided that their reply was in the negative. In the course of the eighteenth century the moon was rarely cited among the causes of madness, even as a possible factor or an aggravation. But right at the end of the century the idea reappears, perhaps under the influence of English medicine, which had never entirely forgotten the moon, and Daquin, followed by Leuret and Guislain, all admitted the influence of the moon on the phases of maniacal excitement, or at the least on the agitation of their patients. But what is important here is not so much the return of the theme as the possibility and conditions necessary for its reappearance. It reappears entirely transformed, filled with a new significance that it did not formerly possess. In its traditional form, it designated an immediate influence, a direct coincidence in time and intersection in space, whose mode of action was entirely situated in the power of the stars. But in Daquin by contrast, the influence of the moon acts through a whole series of mediations, in a kind of hierarchy, surrounding man. The moon acts on the atmosphere with such intensity that it can set in motion a mass as heavy as the ocean. The nervous system, of all the parts that make up the human organism, is the part most sensitive to atmospheric variations, as the slightest variation in temperature, humidity or dryness can have serious effects upon it. The moon therefore, given the important power that its trajectory exerts on the atmosphere, is likely to act most on people whose nervous fibres are particularly delicate:
“Madness is an exclusively nervous condition, and the brain of a madman must therefore be infinitely more susceptible to the influence of the atmosphere, which itself undergoes considerable changes of intensity as a result of the different positions of the moon relative to the earth.” [Daquin, Philosophie de la folie, Paris, 1792]
"""
(Michel Foucault, History of Madness)

How popular media gets love wrong
Now a bit of background about why I have this "engineered" model of love:
First, I'm a white straight cis man. I've got a few traits that might work against my relationship chances (e.g., neurodivergence; I generally fit pretty well into the "weird geek" stereotype), but as I was recently reminded, it's possible my experience derives more from luck than other factors, and since things are tilted more in my favor than most people on the planet, my advice could be worse than useless if it leads people towards strategies that would only have worked for someone like me. I don't *think* that's the case, but it's worth mentioning explicitly.
When I first started dating my now-wife, we were both in graduate school. I was 26, and had exactly zero dating/romantic experience though that point in my life. In other words, a pretty stereotypical "incel" although I definitely didn't subscribe to incel ideology at all. I felt lonely, and vaguely wanted a romantic relationship (I'm neither aromantic nor asexual), but had never felt socially comfortable enough to pursue one before. I don't drink and dislike most social gatherings like parties or bars; I mostly hung around the fringes of the few college parties I attended, and although I had a reasonable college social life in terms of friends, I didn't really do anything to pursue romance, feeling too awkward to know where to start. I had the beginnings of crushes in both high school and college, but never developed a really strong crush, probably correlated with not putting myself in many social situations outside of close all-male friend gatherings. I never felt remotely comfortable enough to act on any of the proto-crushes I did have. I did watch porn and masturbate, so one motivation for pursuing a relationship was physical intimacy, but loneliness was as much of a motivating factor, and of course the social pressure to date was a factor too, even though I'm quite contrarian.
When I first started dating my now-wife, we were both in graduate school. I was 26, and had exactly zero dating/romantic experience though that point in my life. In other words, a pretty stereotypical "incel" although I definitely didn't subscribe to incel ideology at all. I felt lonely, and vaguely wanted a romantic relationship (I'm neither aromantic nor asexual), but had never felt socially comfortable enough to pursue one before. I don't drink and dislike most social gatherings like parties or bars; I mostly hung around the fringes of the few college parties I attended, and although I had a reasonable college social life in terms of friends, I didn't really do anything to pursue romance, feeling too awkward to know where to start. I had the beginnings of crushes in both high school and college, but never developed a really strong crush, probably correlated with not putting myself in many social situations outside of close all-male friend gatherings. I never felt remotely comfortable enough to act on any of the proto-crushes I did have. I did watch porn and masturbate, so one motivation for pursuing a relationship was physical intimacy, but loneliness was as much of a motivating factor, and of course the social pressure to date was a factor too, even though I'm quite contrarian.
I'm lucky in that I had some mixed-gender social circles already like intramural soccer and a graduate-student housing potluck. Graduate school makes a *lot* more of these social spaces accessible, so I recognize that those not in school of some sort have a harder time of things, especially if like me they don't feel like they fit in in typical adult social spaces like bars.
However, at one point I just decided that my desire for a relationship would need action on my part and so I'd try to build a relationship and see what happened. I worked up my courage and asked one of the people in my potluck if she'd like to go for a hike (pretty much clearly a date but not explicitly one; in retrospect not the best first-date modality in a lot of ways, but it made a little more sense in our setting where we could go for a hike from our front door). To emphasize this point: I was not in love with (or even infatuated with) my now-wife at that point. I made a decision to be open to building a relationship, but didn't follow the typical romance story formula beyond that. Now of course, in real life as opposed to popular media, this isn't anything special. People ask each other out all the time just because they're lonely, and some of those relationships turn out fine (although many do not).
I was lucky in that some aspects of who I am and what I do happened to be naturally comforting to my wife (natural advantage in the "appeal" model of love) but of course there are some aspects of me that annoy my wife, and we negotiate that. In the other direction, there's some things I instantly liked about my wife, and other things that still annoy me. We've figured out how to accept a little, change a little, and overall be happy with each other (though we do still have arguments; it's not like the operation/construction/maintenance of the "love mechanism" is always perfectly smooth). In particular though, I approached the relationship with the attitude of "I want to try to build a relationship with this person," at first just because of my own desires for *any* relationship, and then gradually more and more through my desire to build *this specific* relationship as I enjoyed the rewards of companionship.
So for example, while I think my wife is objectively beautiful, she's also *subjectively* very beautiful *to me* because having decided to build a relationship with her, I actively tried to see her as beautiful, rather than trying to judge whether I wanted a relationship with her based on her beauty. In other words, our relationship is more causative of her beauty-to-me than her beauty-to-me is causative of our relationship. This is the biggest way I think the "engineered" model of love differs from the "fire" and "appeal" models: you can just decide to build love independent of factors we typically think of as engendering love (NOT independent of your partner's willingness to participate, of course), and then all of those things like "thinking your partner is beautiful" can be a result of the relationship you're building. For sure those factors might affect who is willing to try building a relationship with you in the first place, but if more people were willing to jump into relationship building (not necessarily with full commitment from the start) without worrying about those other factors, they might find that those factors can come out of the relationship instead of being prerequisites for it. I think this is the biggest failure of the "appeal" model in particular: yes you *do* need to do things that appeal to your partner, but it's not just "make myself lovable" it's also: is your partner putting in the effort to see the ways that you are beautiful/lovable/etc., or are they just expecting you to become exactly some perfect person they've imagined (and/or been told to desire by society)? The former is perfectly possible, and no less satisfying than the latter.
To cut off my rambling a bit here, I'll just add that in our progress from dating through marriage through staying-married, my wife and I have both talked at times explicitly about commitment, and especially when deciding to get married, I told her that I knew I couldn't live up to the perfect model of a husband that I'd want to be, but that if she wanted to deepen our commitment, I was happy to do that, and so we did. I also rearranged my priorities at that point, deciding that I knew I wanted to prioritize this relationship above things like my career or my research interests, and while I've not always been perfect at that in my little decisions, I've been good at holding to that in my big decisions at least. In the end, *once we had built a somewhat-committed relationship*, we had something that we both recognized was worth more than most other things in life, and that let us commit even more, thus getting even more out of it in the long term. Obviously you can't start the first date with an expectation of life-long commitment, and you need to synchronize your increasing commitment to a relationship so that it doesn't become lopsided, which is hard. But if you take the commitment as an active decision and as the *precursor* to things like infatuation, attraction, etc., you can build up to something that's incredibly strong and rewarding.
I'll follow this up with one more post trying to distill some advice from my ramblings.
#relationships #love

Could? This has been happening for a long, long time. It's not a new phenomenon!
@… - Older Australian women could retire in poverty, new report says http…

Looming crisis for older Australian women who will retire into poverty if no urgent action taken, new report finds
Women’s super balances are disproportionately impacted by events later in life, in addition to childcare duties, which could mean serious financial problems, research from Super Members Council (SMC) has found. 

This renowned climate scientist says this is the most difficult time for climate science he’s ever seen
https://www.fastcompany.com/91347103/this-

This renowned climate scientist says this is the most difficult time for climate science he’s ever seen
Benjamin Santer has faced pushback on climate research in the past. But this environment feels different ‘because it's so targeted.’

Optimal Messaging Strategy for Incentivizing Agents in Dynamic Systems
Renyan Sun, Ashutosh Nayyar
https://arxiv.org/abs/2508.00188 https://arxiv.org/pdf/2…

Optimal Messaging Strategy for Incentivizing Agents in Dynamic Systems
We consider a finite-horizon discrete-time dynamic system jointly controlled by a designer and one or more agents, where the designer can influence the agents' actions through selective information disclosure. At each time step, the designer sends a message to the agent(s) from a prespecified message space. The designer may also take an action that directly influences system dynamics and rewards. Each agent uses its received message (and its own information) to choose its action. We are interes…

Impact of the Social Action, Responsibility and Heroism Act 2015
"If a standard of care in relation to risk assessment which is too high is imposed [...], people may be put off contributing for free or at all. Insurance premiums will rise. Volunteers are not looking to be sued, they are looking to help others"

Law firm hails "important judgement" for local cycling events after judge throws out claim club was liable for driver seriously injuring time trial participant
High Court judge rules negligent driver solely at fault and club's risk assessment was carried out "properly and sufficiently", the ruling said to provide reassurance and "sensible guidance for those who give their free time to help organise events"

Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning
Xiefeng Wu, Jing Zhao, Shu Zhang, Mingyu Hu
https://arxiv.org/abs/2509.21126 https://…

Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning
Online reinforcement learning in complex tasks is time-consuming, as massive interaction steps are needed to learn the optimal Q-function.Vision-language action (VLA) policies represent a promising direction for solving diverse tasks; however, their performance on low-level control remains limited, and effective deployment often requires task-specific expert demonstrations for fine-tuning. In this paper, we propose \textbf{VARL} (\textbf{V}LM as \textbf{A}ction advisor for online \textbf{R}einf…

Slow convergence almost everywhere of ergodic averages
Valery V. Ryzhikov
https://arxiv.org/abs/2508.00463 https://arxiv.org/pdf/2508.00463

Slow convergence almost everywhere of ergodic averages
For an ergodic action of the group $Z^n$ on a probability space and a given arbitrarily slowly decreasing to zero sequence, there exists an integrable function such that the standard ergodic time averages for it converge almost everywhere to the spatial average of the function at a rate that is not asymptotically majorized by this sequence. This generalizes the Krengel effect about the absence of universal estimates for the rate of convergence in Birkhoff's ergodic theorem. The proof uses a wea…

Quantum Simulation of Random Unitaries from Clebsch-Gordan Transforms
Dmitry Grinko, Satoshi Yoshida
https://arxiv.org/abs/2509.26623 https://arxiv.org/pdf…

Quantum Simulation of Random Unitaries from Clebsch-Gordan Transforms
We present a general method for simulating an action of $t$ copies of a Haar random unitary for arbitrary compact groups. This construction can be viewed as a representation-theoretic generalization of Zhandry's compressed function oracle technique. It is conceptually simple, exact and utilizes Clebsch-Gordan transforms as main building blocks. In particular, for the unitary group, our method is efficient in space and time. Finally, our general oracle for forward queries can be easily modified …

wow cool did Sentry just fucking HALF the spans included in our plan!?
gotta love when a company introduces a feature you never asked for and doubles the price on a feature you care about
cool cool cool, no action required indeed

A Fundamental Convergence Rate Bound for Gradient Based Online Optimization Algorithms with Exact Tracking
Alex Xinting Wu, Ian R. Petersen, Iman Shames
https://arxiv.org/abs/2508.21335

A Fundamental Convergence Rate Bound for Gradient Based Online Optimization Algorithms with Exact Tracking
In this paper, we consider algorithms with integral action for solving online optimization problems characterized by quadratic cost functions with a time-varying optimal point described by an $(n-1)$th order polynomial. Using a version of the internal model principle, the optimization algorithms under consideration are required to incorporate a discrete time $n$-th order integrator in order to achieve exact tracking. By using results on an optimal gain margin problem, we obtain a fundamental co…

SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Murayyiam Parvez, Annus Zulfiqar, Roman Beltiukov, Shir Landau Feibish, Walter Willinger, Arpit Gupta, Muhammad Shahbaz
https://arxiv.org/abs/2509.00397

SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network decision-making. Decision trees (DTs) are particularly well-suited for these tasks due to their interpretability and compatibility with data-plane architectures, i.e., match-action tables (MATs). However, existing in-network DT implementations are constrained by the need to compute all input features upfront, forcing …

💸 Agency for college athlete payment deals agrees to loosen third-party restrictions
https://www.theguardian.com/sport/2025/jul/31/agency-for-college-athlete-payment-deals-agrees-to-loosen-third-party-restrictio…

Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment
Fengshun Wang, Qiurui Wang, Peilin Zhao
https://arxiv.org/abs/2508.16291

Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment
Technical Element Score (TES) and Program Component Score (PCS) evaluations in figure skating demand precise assessment of athletic actions and artistic interpretation, respectively. Existing methods face three major challenges. Firstly, video and audio cues are regarded as common features for both TES and PCS predictions in previous works without considering the prior evaluation criterion of figure skating. Secondly, action elements in competitions are separated in time, TES should be derived …

I think I need to clarify some shit for (white) liberals.
How many times have you wondered if someone you're talking to in an informant sent to entrap you? How many times have you or a friend of yours been hit by a car, intentionally? How many friends have been hit, or almost hit? Ever been stabbed? Know anyone who has? Has the FBI ever knocked on a friend's door? Have police ever kicked down your door? Have you ever been arrested? Pepper sprayed? Does the sound or smell or blast balls give you flashbacks? Do you ever wonder what all the CS exposure is doing to your body? How many times have you been shot or shot at? Do you wonder every day if this is the day they'll come to kill you? Would anyone in your social circle answer these questions differently?
When you vote, you risk nothing (big asterisk, but if I'm talking to you then it doesn't apply to you). What you get out of voting is exactly what you put into it. Direct action is the same.
If you aren't worried about someone murdering you, then you probably aren't actually threatening the system. That's the difference between voting, and doing something useful. If they had to murder all the liberals in order to keep going, fascism would end. If they're only murdering radicals and marginalized people, then you're just like all the "good Germans" who hated Hitler but did essentially nothing.
It's already that bad for some people. How much are you willing to risk? How many people are you willing to sacrifice for your comfort? These are the questions we're all thinking about every time you tell us to vote.
(I'm tagging this #USPol so it's easy for folks to filter out if they're already well acquaintaned with the horror. I'm not CW, because USPol is just expected to be triggering.)

A proposed class action suit against Amazon filed August 22 claims it misleads customers, who think they own content they bought when they only have a license (Winston Cho/The Hollywood Reporter)
https://www.hollywoodreporter.com/business

You Don’t Actually Own That Movie You Just “Bought.” A New Class Action Lawsuit Targets Amazon
A suit challenges Prime Video telling people they can "buy" a movie when they're purchasing a license to watch it for a period of time.

On a Differential Model for Sandpiles Growing in a Silo
Graziano Crasta, Annalisa Malusa
https://arxiv.org/abs/2509.24618 https://arxiv.org/pdf/2509.24618

On a Differential Model for Sandpiles Growing in a Silo
We discuss some features of a boundary value problem for a system of PDEs that describes the growth of a sandpile in a container under the action of a vertical source. In particular, we characterize the long-term behavior of the profiles, and we provide a sufficient condition on the vertical source that guarantees the convergence to the equilibrium in a finite time. We show by counterexamples that a stable configuration may not be reached in a finite time, in general, even if the source is time…

DoubleFine are giving Brutal Legend away for free on itch.io, for a limited time to honor Ozzy's passing. I got this when it launched back in the day on PS3, I quite enjoyed it (I still have it). So go get it. Even available for Linux.
#Gaming #VideoGames

Perfect way to end the middle of summer: at the same time, an interesting parcours for the final TdF stage (with the usual scenic Paris shots), and a *gripping* cricket match finale. Very little comes close to a 5th day rearguard action: the excitement of a game that has no result! (Maybe.)

INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models
Ulas Berk Karli, Ziyao Shangguan, Tesca FItzgerald
https://arxiv.org/abs/2510.01389

INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models
Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning framework for leveraging token-level uncertainty signals to predict when a VLA should request help. Using $π_0$-FAST as the underlying model, we extract per-token \emph{entropy}, \emph{log-probability}, and Dirichlet-based estimates of \emph{aleatoric and epistemi…

I wonder how Nazi Germany handled climate issues during the Holocaust. Do you think it was widely discussed at the time? https://mastodon.social/@Snoro/115179873107637672

Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II
Weiyu Ma, Dongyu Xu, Shu Lin, Haifeng Zhang, Jun Wang
https://arxiv.org/abs/2508.16580 https://…

Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II
We present Adaptive Command, a novel framework integrating large language models (LLMs) with behavior trees for real-time strategic decision-making in StarCraft II. Our system focuses on enhancing human-AI collaboration in complex, dynamic environments through natural language interactions. The framework comprises: (1) an LLM-based strategic advisor, (2) a behavior tree for action execution, and (3) a natural language interface with speech capabilities. User studies demonstrate significant impr…

Interpretable Modeling of Articulatory Temporal Dynamics from real-time MRI for Phoneme Recognition
Jay Park, Hong Nguyen, Sean Foley, Jihwan Lee, Yoonjeong Lee, Dani Byrd, Shrikanth Narayanan
https://arxiv.org/abs/2509.15689

Interpretable Modeling of Articulatory Temporal Dynamics from real-time MRI for Phoneme Recognition
Real-time Magnetic Resonance Imaging (rtMRI) visualizes vocal tract action, offering a comprehensive window into speech articulation. However, its signals are high dimensional and noisy, hindering interpretation. We investigate compact representations of spatiotemporal articulatory dynamics for phoneme recognition from midsagittal vocal tract rtMRI videos. We compare three feature types: (1) raw video, (2) optical flow, and (3) six linguistically-relevant regions of interest (ROIs) for articula…

@…: Reform is spewing more lies. This time it’s using attacks against women as a cover for attacks on migrants. We can’t let it stand. Email Reform. #Goodlawproject

Tell Reform to stop exploiting women’s safety to fuel attacks on migrants
Reform UK is pushing racist claims that migrants are a threat to women’s safety. This toxic narrative paints an entire group of people as inherently dangerous. But there’s no credible evidence to back it up. Reform MP Sarah Pochin suggested that migrants have a “warped view of their right to sexually assault women”. She claimed that men from “predominantly Muslim countries like Afghanistan” hold a “medieval view of women’s rights” and that “women are at risk of sexual assaul…

"Brazil implores businesses to attend major climate summit, despite 'second thoughts' amid Trump backlash"
#Brazil #ClimateSummit

Brazil implores businesses to attend major climate summit, despite 'second thoughts' amid Trump backlash
November's COP30 summit comes at a precarious time for climate action, as companies back away from environmental initiatives, and attacks on green energy by President Trump.

Potential Trade Has Raiders Landing Big-Time Wide Receiver https://www.si.com/nfl/raiders/las-vegas-san-francisco-49ers-jauan-jennings-pete-carroll-geno-smith

Emergence of General Relativity from Cosmological Constant Via Ghost Condensation
Ichiro Oda
https://arxiv.org/abs/2509.23648 https://arxiv.org/pdf/2509.23…

Emergence of General Relativity from Cosmological Constant Via Ghost Condensation
We show that starting with a cosmological constant in a curved space-time, the Einstein-Hilbert term of general relativity is generated through a ghost condensation. We fix Weyl symmetry, or equivalently local scale symmetry by a gauge condition $R = 0$ à la BRST formalism, and see that the condensation of the Faddeev-Popov ghosts, $\langle \bar c c \rangle \neq 0$ leads to a generation of the Einstein-Hilbert action of general relativity. This dynamical mechanism of symmetry breakdown for a g…

Similarity-Based Supervised User Session Segmentation Method for Behavior Logs
Yongzhi Jin, Kazushi Okamoto, Kei Harada, Atsushi Shibata, Koki Karube
https://arxiv.org/abs/2508.16106

Similarity-Based Supervised User Session Segmentation Method for Behavior Logs
In information recommendation, a session refers to a sequence of user actions within a specific time frame. Session-based recommender systems aim to capture short-term preferences and generate relevant recommendations. However, user interests may shift even within a session, making appropriate segmentation essential for modeling dynamic behaviors. In this study, we propose a supervised session segmentation method based on similarity features derived from action embeddings and attributes. We com…

Stop spinning your wheels trying to understand those complex Excel formulas.
Seriously. Let AI do it for you. 🤖
Microsoft Copilot now gives instant, plain English explanations right inside your spreadsheet. It’s a massive time-saver for anyone working with complex data... Or even just someone new to Excel altogether.
Could this be the best Excel update in years?
See the game-changing feature in action in my new video:

$R^2$ corrections to Complexity Growth with a Probe String
Wen-Bin Chang
https://arxiv.org/abs/2507.20841 https://arxiv.org/pdf/2507.20841

$R^2$ corrections to Complexity Growth with a Probe String
We investigate the effect of $R^2$ corrections on holographic complexity growth within the framework of the Complexity=Action(CA) conjecture. By introducing a probe string into Gauss-Bonnet(GB) $AdS$ black brane background, we analyze the time derivative of the Nambu-Goto(NG) action as the holographic dual to complexity growth. Our results indicate that the complexity growth is maximized for a stationary string and is suppressed by its motion. Significantly, we identify a crossover point at spe…

Tell Congress: NO Funding for Primate Breeding! #AnimalRights

URGENT: Tell Congress NO to Funding Primate Breeding!
Right now, Congress is working on the 2025 federal budget, and the Senate Appropriations Committee has allocated a staggering $30 million to expand primate breeding and research at National Primate Research Centers. This funding will support invasive, unethical experiments on primates—causing unimaginable suffering while advancing unreliable science that fails over 90% of the time in human clinical trials. 🔬 Despite these facts, the NIH asked for $10 million, but the Senate has tripled th…

Choose Your Battles: Distributed Learning Over Multiple Tug of War Games
Siddharth Chandak, Ilai Bistritz, Nicholas Bambos
https://arxiv.org/abs/2509.20147 https://

Choose Your Battles: Distributed Learning Over Multiple Tug of War Games
Consider N players and K games taking place simultaneously. Each of these games is modeled as a Tug-of-War (ToW) game where increasing the action of one player decreases the reward for all other players. Each player participates in only one game at any given time. At each time step, a player decides the game in which they wish to participate in and the action they take in that game. Their reward depends on the actions of all players that are in the same game. This system of K games is termed `M…

A continuity equation compatible basis for Effective Field Theory of Dark Energy
Federico Armato, Edoardo Martinelli, Marco Raveri
https://arxiv.org/abs/2507.18526 https://

A continuity equation compatible basis for Effective Field Theory of Dark Energy
The Effective Field Theory (EFT) of Dark Energy (DE) is a model independent framework that allows for the description of a wide class of dark energy and modified gravity models. This is achieved by extending the Hilbert Einstein action through the introduction of time dependent functions. However, the choice of these functions and thus the operator basis is not unique. In this paper, we propose a physically motivated constraint based on the continuity equation, leading to a continuity equation …

A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains
Antonio Finocchiaro, Alessandro Sebastiano Catinello, Michele Mazzamuto, Rosario Leonardi, Antonino Furnari, Giovanni Maria Farinella
https://arxiv.org/abs/2507.13326

A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains
Hand-object interaction detection remains an open challenge in real-time applications, where intuitive user experiences depend on fast and accurate detection of interactions with surrounding objects. We propose an efficient approach for detecting hand-objects interactions from streaming egocentric vision that operates in real time. Our approach consists of an action recognition module and an object detection module for identifying active objects upon confirmed interaction. Our Mamba model with …

From David Suzuki Foundation
The Suzuki Sessions: Resistance and Solidarity in the Face of LNG
Together, they’ll dive into the most pressing issues of our time, from climate to environmental justice, and explore real opportunities for collective action. Expect lively, thought-provoking discussions that spark ideas and fuel hope for a better future.
The first session will feature the voices and perspectives of front-line land defenders resisting fossil fuel expansion on thei…

"At 6 months in, I think it’s time for food and nutrition advocates, scientists and professionals to call out the MAHA agenda for what it is - it’s a movement with the right vibes, the wrong priorities and solutions, headed up by someone with dangerous thoughts on public health who is not going to improve the health of Americans, nutritional or otherwise."
6 Months of MAHA

6 Months of MAHA
A Reflection and Call to Action

Towards 6G Intelligence: The Role of Generative AI in Future Wireless Networks
Muhammad Ahmed Mohsin, Junaid Ahmad, Muhammad Hamza Nawaz, Muhammad Ali Jamshed
https://arxiv.org/abs/2508.19495

Towards 6G Intelligence: The Role of Generative AI in Future Wireless Networks
Ambient intelligence (AmI) is a computing paradigm in which physical environments are embedded with sensing, computation, and communication so they can perceive people and context, decide appropriate actions, and respond autonomously. Realizing AmI at global scale requires sixth generation (6G) wireless networks with capabilities for real time perception, reasoning, and action aligned with human behavior and mobility patterns. We argue that Generative Artificial Intelligence (GenAI) is the crea…

Six-dimensional cosmological models with conformal extensions
Daniel Muller, Sergey G. Rubin, Ilya L. Shapiro, Alexey Toporensky
https://arxiv.org/abs/2510.01534 https://…

Six-dimensional cosmological models with conformal extensions
We consider the background cosmological solutions in the $6D$ (six-dimensional) model with one time and five space coordinates. The theory of our interest has the action composed by the Einstein term, cosmological constant, and two conformal terms constructed from the third powers of the Weyl tensor. It is shown how the highest derivative terms in the equations of motion can be isolated that opens the way for their numerical integration. There are flat anisotropic solutions which make one of th…

Normative Moral Pluralism for AI: A Framework for Deliberation in Complex Moral Contexts
David-Doron Yaacov
https://arxiv.org/abs/2508.08333 https://arxiv.…

Normative Moral Pluralism for AI: A Framework for Deliberation in Complex Moral Contexts
The conceptual framework proposed in this paper centers on the development of a deliberative moral reasoning system - one designed to process complex moral situations by generating, filtering, and weighing normative arguments drawn from diverse ethical perspectives. While the framework is rooted in Machine Ethics, it also makes a substantive contribution to Value Alignment by outlining a system architecture that links structured moral reasoning to action under time constraints. Grounded in norm…

UK would rather arrest almost 500 people rather than admit or cease its complicity in Israel’s genocide of the Palestinian people.
So I guess the next step is a 5,000-person protest.
They arrest 5,000? Time for 50,000.
Overwhelm the system until the system stops committing genocide.

UK police arrest at least 466 people at Palestine Action protest in London
Critics say ban on activist group stifles freedom of speech and assembly and aims to curb pro-Palestine demonstrations.

OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities
Mary Tonwe
https://arxiv.org/abs/2508.12943

OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities
Public service systems in many African regions suffer from delayed emergency response and spatial inequity, causing avoidable suffering. This paper introduces OPTIC-ER, a reinforcement learning (RL) framework for real-time, adaptive, and equitable emergency response. OPTIC-ER uses an attention-guided actor-critic architecture to manage the complexity of dispatch environments. Its key innovations are a Context-Rich State Vector, encoding action sub-optimality, and a Precision Reward Function, wh…

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
Jiahang Cao, Yize Huang, Hanzhong Guo, Rui Zhang, Mu Nan, Weijian Mai, Jiaxu Wang, Hao Cheng, Jingkai Sun, Gang Han, Wen Zhao, Qiang Zhang, Yijie Guo, Qihao Zheng, Chunfeng Song, Xiao Li, Ping Luo, Andrew F. Luo
https://

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale interaction datasets. This work introduces an alternative paradigm for enhancing policy performance without additional model training. Perhaps surprisingly, we demonstrate that the composed policies can exceed the performance of either parent policy. Our contr…

Before you spend $59 on that iPhone strap, consider giving the same amount to the World Central Kitchen. They help feed people in a humanitarian crisis around the world.
Many thanks for considering my request.
https://wck.org/

What TV channel is Cowboys vs. Rams on today? Time, TV schedule for NFL preseason game https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/08/09/where-to-watch-cowboys-vs-rams-today-tv-channel-…

Pointwise purity, derived Satake, and Symplectic duality
Victor Ginzburg
https://arxiv.org/abs/2508.15958 https://arxiv.org/pdf/2508.15958

Pointwise purity, derived Satake, and Symplectic duality
It has been known for a long time that Ext's between IC-sheaves may often be expressed in terms of Hom's between cohomology groups. We prove a more general result under weaker assumptions. The result is used to describe the action of the derived Satake equivalence on !-pure objects and show that the equivalence enjoys a new kind of functoriality with respect to morphisms of reductive groups. We find and prove normality of the symplectic dual X^! for many smooth affine Hamiltonian G-varieties X,…

Angular Linearization and Quantitative Convergence of Statistical Ensembles for Weighted Integrable Hamiltonian Systems
Xinyu Liu, Yong Li
https://arxiv.org/abs/2509.21412 https…

Angular Linearization and Quantitative Convergence of Statistical Ensembles for Weighted Integrable Hamiltonian Systems
Within the framework of weighted integrable Hamiltonian systems, we study the long-time behavior of the associated statistical ensembles. We construct an action-dependent angular conjugacy that rectifies the nonuniform angular flow into a constant-speed linear flow, thereby reducing the ensemble dynamics to oscillatory integrals over the action domain. Using integration by parts along a tailored vector field and \(W^{1,1}\) approximations with controlled boundary terms, we derive inverse-in-tim…

Good Morning #Canada
Summer is over, and this morning, approximately 5.5 million primary and secondary Canadian students go back to school. Lunches are packed, stylish new backpacks have a light load, and sneakers are fashionably untied. Stay alert for school busses, crosswalks, and that speed camera newly installed outside your local school. Yes, it's hectic today as you relearn how to get your kids out the door on time. Enjoy the change of pace because soon you'll be shoveling snow.
#CanadaIsAwesome #BackToSchool #WinterIsComing
https://www150.statcan.gc.ca/t1/tbl1/en/tv.action?pid=3710010901

Exact kinetic propagators for coherent state complex Langevin simulations
Thomas G. Kiely, Ethan C. McGarrigle, Glenn H. Fredrickson
https://arxiv.org/abs/2508.11057 https://

Exact kinetic propagators for coherent state complex Langevin simulations
We introduce and benchmark an improved algorithm for complex Langevin simulations of bosonic coherent state path integrals. Our approach utilizes a Strang splitting of the imaginary-time propagator rather than the conventional linear-order Taylor expansion, allowing us to construct an action that incorporates higher-order terms at negligible computational cost. The resulting algorithm enjoys guaranteed linear stability independent of the imaginary-time discretization, enabling more resource-eff…

The average undergrad tuition fee in the 1974/75 academic year in Canada, across all disciplines, was $547 ($3445 adjusted to 2025)
Fees 50 years later in 2024/25 were $7360 ($7496 adjusted)
That is more than double. 117%.
And I *know* from personal experience this is a low ball average. If I could find a breakdown by discipline or by length of study for today, some would be even more obscene.
What has changed? Any occupation outside a minimum wage paying job demands a 2-4yr undergraduate diploma or degree, if not more.
Think about the 1970s and how common it was for people to get good paying jobs, leading to careers, without even high school education. Our free education stops with high school.
My family is a good example.
Mom and Step Dad: teacher college/degree. One got a Masters mid career.
Dad: didn’t complete HS
Father in law: didn’t complete HS
Mother in law: completed HS mid-career
Leadership positions and full careers demand a Masters or PhD requiring 5-10 years of study after HS!
Add in the cost of food and housing and the massive cuts happening at all colleges and universities because of the loss of international student tuition and I am going to go out on a limb and say our students today are going to pay double the price for a far worse experience than possibly any time since the Second World War.
Public education should be free.
Food and Housing should be controlled.
If the only thing government cares about is the economy, then they are setting us up for failure, and have been for decades.
(Don’t get me started on the kinds of “values” Canadian governments demonstrate when International student tuitions are 5x more than domestic students, let alone the inherent revenue risk in that funding strategy that has now come home to roost)
#canpoli #cdnpoli #education #university #college #canada
(
74/75 Source Stats Can: https://www150.statcan.gc.ca/t1/tbl1/en/tv.action?pid=3710015001&pickMembers[0]=1.1&cubeTimeFrame.startYear=1972 / 1973&cubeTimeFrame.endYear=2006 / 2007&referencePeriods=19720101,20060101
24/25 source stats can: https://www150.statcan.gc.ca/t1/tbl1/en/tv.action?pid=3710004501
cc: @… @…

AEGIS: An Agent for Extraction and Geographic Identification in Scholarly Proceedings
Om Vishesh, Harshad Khadilkar, Deepak Akkil
https://arxiv.org/abs/2509.09470 https://

AEGIS: An Agent for Extraction and Geographic Identification in Scholarly Proceedings
Keeping pace with the rapid growth of academia literature presents a significant challenge for researchers, funding bodies, and academic societies. To address the time-consuming manual effort required for scholarly discovery, we present a novel, fully automated system that transitions from data discovery to direct action. Our pipeline demonstrates how a specialized AI agent, 'Agent-E', can be tasked with identifying papers from specific geographic regions within conference proceedings and then …

Statistical Inference for Misspecified Contextual Bandits
Yongyi Guo, Ziping Xu
https://arxiv.org/abs/2509.06287 https://arxiv.org/pdf/2509.06287

Statistical Inference for Misspecified Contextual Bandits
Contextual bandit algorithms have transformed modern experimentation by enabling real-time adaptation for personalized treatment and efficient use of data. Yet these advantages create challenges for statistical inference due to adaptivity. A fundamental property that supports valid inference is policy convergence, meaning that action-selection probabilities converge in probability given the context. Convergence ensures replicability of adaptive experiments and stability of online algorithms. In…

VITA: Vision-to-Action Flow Matching Policy
Dechen Gao, Boqi Zhao, Andrew Lee, Ian Chuang, Hanchu Zhou, Hang Wang, Zhe Zhao, Junshan Zhang, Iman Soltani
https://arxiv.org/abs/2507.13231

VITA: Vision-to-Action Flow Matching Policy
We present VITA, a Vision-To-Action flow matching policy that evolves latent visual representations into latent actions for visuomotor control. Traditional flow matching and diffusion policies sample from standard source distributions (e.g., Gaussian noise) and require additional conditioning mechanisms like cross-attention to condition action generation on visual information, creating time and space overheads. VITA proposes a novel paradigm that treats latent images as the flow source, learnin…

It's Robert Reich.
Never have I seen a president or Congress do so much harm to so many people in so little time.
Trump and his MAGA stooges in Congress have:
- Stripped health care from 10 million people;
- Cut food stamp benefits for 40 million, half of them children;
- Slashed $8 billion from foreign aid programs;
- Defunded public radio and TV;
- Handed $4.5 trillion in tax breaks to Trump and his billionaire friends.
It's our job to ho…

Get Robert Reich's new book, Coming Up Short, and enter to win a signed copy!
When you get Robert Reich's new book through Inequality Media Civic Action, you'll be entered to win 1 of 75 signed copies!

What TV channel is Cowboys vs. Rams on today? Time, TV schedule for NFL preseason game https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/08/09/where-to-watch-cowboys-vs-rams-today-tv-channel-…

Admission Control for Inelastic Traffic on a Link Shared by Deadline-Driven Elastic Traffic
Patrick Kreidl
https://arxiv.org/abs/2509.08135 https://arxiv.o…

Admission Control for Inelastic Traffic on a Link Shared by Deadline-Driven Elastic Traffic
Consider a (logical) link between two distributed data centers with available bandwidth designated for both deadline-driven elastic traffic, such as for scheduled synchronization services, and profitable inelastic traffic, such as for real-time streaming services. Admission control in this setting is cast as a stochastic shortest path problem, with state space derived from (discretization of) the elastic flow's size/deadline and action space corresponding to alternative subsets of admitted inel…

Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning
Daechul Ahn, San Kim, Jonghyun Choi
https://arxiv.org/abs/2508.06042 https…

Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning
Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents need to manage resource constraints and adapt to evolving battlefield situations in a partially observable environment. This often overwhelms exisiting LLM-based approaches. To address these challenges, we propose a hierarchical multi-agent framework that emplo…

Vanishing of the $H^3$ obstruction for time-reversal symmetry in (2 1)D abelian bosonic TQFTs
Ippo Orii
https://arxiv.org/abs/2509.07368 https://arxiv.org/…

Vanishing of the $H^3$ obstruction for time-reversal symmetry in (2+1)D abelian bosonic TQFTs
In $(2+1)$-dimensional topological quantum field theories (TQFTs), the action of a global symmetry group on the anyon system is one of the central topics of research. Owing to the subtle categorical nature of anyons, such group actions do not automatically satisfy associativity. The obstruction is captured by a cohomology class, known as the $H^3$ obstruction, whose presence signals a failure of group associativity. In these cases, the symmetry structure is no longer described by an ordinary gr…

Diffeomorphic Neural Operator Learning
Seth Taylor, Alex Bihlo, Jean-Christophe Nave
https://arxiv.org/abs/2508.06690 https://arxiv.org/pdf/2508.06690

Diffeomorphic Neural Operator Learning
We present an operator learning approach for a class of evolution operators using a composition of a learned lift into the space of diffeomorphisms of the domain and the group action on the field space. In turn, this transforms the semigroup structure of the evolution operator into a corresponding group structure allowing time stepping be performed through composition on the space of diffeomorphisms rather than in the field space directly. This results in a number of structure-preserving proper…

Gaussian concentration bounds for probabilistic cellular automata
Jean-Ren\'e Chazottes, Frank Redig, Edgardo Ugalde
https://arxiv.org/abs/2507.05431 h…

Gaussian concentration bounds for probabilistic cellular automata
We study lattice spin systems and analyze the evolution of Gaussian concentration bounds (GCB) under the action of probabilistic cellular automata (PCA), which serve as discrete-time analogues of Markovian spin-flip dynamics. We establish the conservation of GCB and, in the high-noise regime, demonstrate that GCB holds for the unique stationary measure. Additionally, we prove the equivalence of GCB for the space-time measure and its spatial marginals in the case of contractive probabilistic cel…

Lagrangian controllability in perforated domains
Mitsuo Higaki, Jiajiang Liao, Franck Sueur
https://arxiv.org/abs/2509.14913 https://arxiv.org/pdf/2509.149…

Lagrangian controllability in perforated domains
The question at stake in Lagrangian controllability is whether one can move a patch of fluid particles to a target location by means of remote action in a given time interval. In the last two decades, positive results have been obtained both for the incompressible Euler and Navier-Stokes equations. However, for the latter, the case where the fluid is contained within domains bounded by solid boundaries with the no-slip condition has not been addressed, with respect to the difficulty caused by v…

A gravitational spin-orbit interaction in Poincar\'e gauge theory
Sebastian Bahamonde, Jorge Gigante Valcarcel
https://arxiv.org/abs/2508.20035 https://

A gravitational spin-orbit interaction in Poincaré gauge theory
We show a gravitational spin-orbit interaction that can potentially modify the space-time geometry naturally emerges in the framework of Poincaré gauge theory. For this purpose, we derive the field equations of a particular model with cubic order invariants and demonstrate the existence of analytical solutions which display an interaction between the intrinsic and extrinsic angular momentum parameters in the gravitational action, in analogy to the spin-orbit interaction arising from atomic and…

SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation
Haoyuan Deng, Wenkai Guo, Qianzhun Wang, Zhenyu Wu, Ziwei Wang
https://arxiv.org/abs/2508.18268

SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation
Bimanual manipulation has been widely applied in household services and manufacturing, which enables the complex task completion with coordination requirements. Recent diffusion-based policy learning approaches have achieved promising performance in modeling action distributions for bimanual manipulation. However, they ignored the physical safety constraints of bimanual manipulation, which leads to the dangerous behaviors with damage to robots and objects. To this end, we propose a test-time tr…

A Dynamic Programming Framework for Vehicular Task Offloading with Successive Action Improvement
Qianren Li, Yuncong Hong, Bojie Lv, Rui Wang
https://arxiv.org/abs/2509.05907 ht…

A Dynamic Programming Framework for Vehicular Task Offloading with Successive Action Improvement
In this paper, task offloading from vehicles with random velocities is optimized via a novel dynamic programming framework. Particularly, in a vehicular network with multiple vehicles and base stations (BSs), computing tasks of vehicles are offloaded via BSs to an edge server. Due to the random velocities, the exact locations of vehicles versus time, namely trajectories, cannot be determined in advance. Hence, instead of deterministic optimization, the cell association, uplink time, and through…

Self-Guided Action Diffusion
Rhea Malhotra, Yuejiang Liu, Chelsea Finn
https://arxiv.org/abs/2508.12189 https://arxiv.org/pdf/2508.12189

Self-Guided Action Diffusion
Recent works have shown the promise of inference-time search over action samples for improving generative robot policies. In particular, optimizing cross-chunk coherence via bidirectional decoding has proven effective in boosting the consistency and reactivity of diffusion policies. However, this approach remains computationally expensive as the diversity of sampled actions grows. In this paper, we introduce self-guided action diffusion, a more efficient variant of bidirectional decoding tailor…

Scaling invariance for the diffusion coefficient in a billiard system
Anne K\'etri P. da Fonseca, Diego F. M. Oliveira, Edson D. Leonel
https://arxiv.org/abs/2507.06395

Scaling invariance for the diffusion coefficient in a billiard system
We investigated the unbounded diffusion observed in a time-dependent oval-shaped billiard and its suppression owing to inelastic collisions with the boundary. The main focus is on the behavior of the diffusion coefficient, which plays a key role in describing the scaling invariance characteristic of this transition. For short times, the low-action regime is characterized by a constant diffusion coefficient, which begins to decay after a crossover iteration, thereby suppressing the unlimited gro…

SimCoachCorpus: A naturalistic dataset with language and trajectories for embodied teaching
Emily Sumner, Deepak E. Gopinath, Laporsha Dees, Patricio Reyes Gomez, Xiongyi Cui, Andrew Silva, Jean Costa, Allison Morgan, Mariah Schrum, Tiffany L. Chen, Avinash Balachandran, Guy Rosman
https://arxiv.org/abs/2509.14548

SimCoachCorpus: A naturalistic dataset with language and trajectories for embodied teaching
Curated datasets are essential for training and evaluating AI approaches, but are often lacking in domains where language and physical action are deeply intertwined. In particular, few datasets capture how people acquire embodied skills through verbal instruction over time. To address this gap, we introduce SimCoachCorpus: a unique dataset of race car simulator driving that allows for the investigation of rich interactive phenomena during guided and unguided motor skill acquisition. In this dat…

Bianchi-I cosmology with scale dependent $G$ and $\Lambda$ in asymptotically safe gravity
Chiang-Mei Chen, Akihiro Ishibashi, Rituparna Mandal, Nobuyoshi Ohta
https://arxiv.org/abs/2509.09759

Bianchi-I cosmology with scale dependent $G$ and $Λ$ in asymptotically safe gravity
We study anisotropic Bianchi-I (BI) cosmology, incorporating quantum gravitational corrections into the Einstein equation through the scale-dependent Newton coupling and cosmological term, as determined by the flow equation of the effective action for gravity. For the cosmological term $Λ_0=0$, we derive the quantum-corrected power-series solution for a general equation-of-state parameter $w$ in the range $-1

Mutual Information Tracks Policy Coherence in Reinforcement Learning
Cameron Reid, Wael Hafez, Amirhossein Nazeri
https://arxiv.org/abs/2509.10423 https://…

Mutual Information Tracks Policy Coherence in Reinforcement Learning
Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms to detect and diagnose these failures. We present an information-theoretic framework that reveals both the fundamental dynamics of RL and provides practical methods for diagnosing deployment-time anomalies. Through analysis of state-action mutual information patterns in a robotic control task, we first demonstrate that…

ADPro: a Test-time Adaptive Diffusion Policy for Robot Manipulation via Manifold and Initial Noise Constraints
Zezeng Li, Rui Yang, Ruochen Chen, ZhongXuan Luo, Liming Chen
https://arxiv.org/abs/2508.06266

ADPro: a Test-time Adaptive Diffusion Policy for Robot Manipulation via Manifold and Initial Noise Constraints
Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action generation as an unconstrained denoising process, ignoring valuable a priori knowledge about geometry and control structure. In this work, we propose the Adaptive Diffusion Policy (ADP), a test-time adaptation method that introduces two key inductive biases into the …

Scalar quasinormal modes of magnetically charged black holes in a quintessence field
Ali Hasnain
https://arxiv.org/abs/2509.08845 https://arxiv.org/pdf/250…

Scalar quasinormal modes of magnetically charged black holes in a quintessence field
We investigate the quasinormal mode (QNM) spectrum for scalar perturbations of static, magnetically charged black holes in the presence of a quintessence field. The background geometry is obtained from the Einstein-Power-Maxwell action with a Kiselev-type contribution for quintessence. The associated master wave equation is solved using complementary numerical approaches, including high-order WKB expansions, the asymptotic iteration method, and time-domain integration, with cross-validation to …

The least I can do. After you write YOUR letter, post a picture!
#disney #boycottdisney
#uspol #JimmyKimmel

Charged Proca Stars
Yahir Mio, Miguel Alcubierre
https://arxiv.org/abs/2508.09081 https://arxiv.org/pdf/2508.09081

Charged Proca Stars
We consider self-gravitating stationary configurations of a charged massive complex Proca field, also known as charged Proca stars, in the particular case of spherical symmetry. We first present a general 3+1 decomposition of the Einstein--Maxwell--Proca system, starting from the action and field equations. We then restrict our system to the case of spherical symmetry and, after imposing a harmonic time dependence ansatz for the Proca field, we construct families of charged Proca stars for diff…

Good Morning #Canada
Today is World Population Day, established by United Nations as a result of the massive interest people had in Five Billion Day in 1987. It's a good day to get an update on Canada’s population growth, which was aggressive in 2023 when we hit 40M, and then hit 41M just a few months into 2024. The #StatsCan Real Time Tracker is not working for some reason, but we still have their Quarterly Estimates data. At the end of June, there were 41,548,787 of us strolling around Canada, with every province and territory showing growth.
#CanadaIsAwesome #INeedMySpace
https://www150.statcan.gc.ca/t1/tbl1/en/tv.action?pid=1710000901

Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
Xiatao Sun, Yuxuan Wang, Shuo Yang, Yinxing Chen, Daniel Rakita
https://arxiv.org/abs/2507.05695

Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
Diffusion policies have become increasingly popular in robot learning due to their reliable convergence in motion generation tasks. At a high level, these policies learn to transform noisy action trajectories into effective ones, conditioned on observations. However, each time such a model is trained in a robotics context, the network must relearn fundamental spatial representations and operations, such as translations and rotations, from scratch in order to ground itself and operate effectivel…