Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised framework for learning hierarchical manipulation concepts that encode these invariant patterns through cross-modal sensory correlations and multilevel temporal abstractions without requiring human annotation. Our approach combines a cross-modal correlation network that identifies persistent patterns across sensory modalities with a multi-horizon predictor that organizes representations hierarchically across temporal scales. Manipulation concepts learned through this dual structure enable policies to focus on transferable relational patterns while maintaining awareness of both immediate actions and longer-term goals. Empirical evaluation across simulated benchmarks and real-world deployments demonstrates significant performance improvements with our concept-enhanced policies. Analysis reveals that the learned concepts resemble human-interpretable manipulation primitives despite receiving no semantic supervision. This work advances both the understanding of representation learning for manipulation and provides a practical approach to enhancing robotic performance in complex scenarios. Code is available at: https://github.com/zrllrz/HiMaCon.

Scientific embodied agents play a crucial role in modern laboratories by automating complex experimental workflows. Compared to typical household environments, laboratory settings impose significantly higher demands on perception of physicalchemical transformations and long-horizon planning, making them an ideal testbed for advancing embodied intelligence. However, its development has been long hampered by the lack of suitable simulator and benchmarks. In this paper, we address this gap by introducing LabUtopia, a comprehensive simulation and benchmarking suite designed to facilitate the development of generalizable, reasoning-capable embodied agents in laboratory settings.

Scaling up executable code data is significant for improving language models' software engineering capability. The intricate nature of the process makes it labor-intensive, time-consuming, and expert-knowledge-dependent to build a large number of executable code repositories, limiting the scalability of existing work based on running tests. The primary bottleneck lies in the automated building of test environments for different repositories, which is an essential yet underexplored task. To mitigate the gap, we introduce Repo2Run, the first LLM-based agent aiming at automating the building of executable test environments for any repositories at scale. Specifically, given a code repository, Repo2Run iteratively builds the Docker image, runs unit tests based on the feedback of the building, and synthesizes the Dockerfile until the entire pipeline is executed successfully. The resulting Dockerfile can then be used to create Docker container environments for running code and tests. We created a benchmark containing 420 Python repositories with unit tests for evaluation. The results illustrate that Repo2Run achieves an 86.0%

The tall container was almost certainly used for distillation experiments. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. The ceramic container is over 1.5 feet tall. Breakthroughs, discoveries, and DIY tips sent six days a week. By signing up, you confirm you are 16+, will receive newsletters and promotional content and agree to our Terms of Use and acknowledge the data practices in our Privacy Policy .

Trump's hidden five-tap code in handshake with Xi... and the tell-tale'bullfrog smile' that betrayed the president How Kylie Kelce REALLY feels about Taylor Swift after her foul-mouthed wedding rant: Insiders reveal stark'differences' between the sisters-in-law... and truth about'feud' What REALLY goes on in some Equinox steam rooms: Gym insiders reveal eye-popping indecency... secret towel signals used by experimental married men... and clubs with most'aggressive' locker rooms Xi greets Trump with ominous warning about risk of war between US and China: 'Beware the Thucydides Trap' Inside Eric Swalwell's marriage implosion: Disgraced Democrat nowhere in sight at family home as his furious wife appears without her ring and delivers ultimate insult Home Depot and Lowe's use sneaky cameras in theft crackdown - but honest customers are the real victims Buster Murdaugh's explosive reaction as his father's murder conviction is overturned: Insiders reveal all about his secret new life... and jailhouse calls with Alex Inside Carrie Underwood's'grounded' and'traditional' home life on her 400-acre Tennessee farm Grotesque new Michael Jackson allegations raise questions about his accusers so taboo they're almost impossible to ask... but we must: MAUREEN CALLAHAN Kylie Jenner and Timothee Chalamet's mortifying relationship secrets exposed: Her'jealousy'... his pleas for'space'... and why he's now finally'on board' with a proposal Beautiful young mom appeared to have it all. Now her two toddlers are dead after falling into a pool while on COCAINE... and her own parents allegedly made very troubling comments about her Walmart axes 1,000 workers as white-collar jobs bloodbath reaches America's biggest private employer Grief author Kouri Richins gives 40-minute rant about love and calls husband's poisoning murder a'tragedy' as she learns fate in Moscow Mule slaying... and sends deranged message to her sons This miracle drug rapidly reversed my balding. It wrecked my sex life... but a microdosing hack gave me my libido and my hair back Whether it's a rogue chicken breast or the last of a lasagna, many of us regularly pop our leftovers in the freezer. But it turns out you've probably been doing it wrong this entire time. While plastic containers are the go-to for many Brits, experts now say that these should be avoided.

The exploit, dubbed CopyFail and tracked as CVE-2026-31431, allows hackers to take over PCs and data center servers. The Linux vulnerabilities have been patched--but many machines remain at risk. Publicly released exploit code for an effectively unpatched vulnerability that gives root access to virtually all releases of Linux is setting off alarm bells as defenders scramble to ward off severe compromises inside data centers and on personal devices. The vulnerability and exploit code that exploits it were released Wednesday evening by researchers from security firm Theori, five weeks after privately disclosing it to the Linux kernel security team. The critical flaw, tracked as CVE-2026-31431 and the name CopyFail, is a local privilege escalation, a vulnerability class that allows unprivileged users to elevate themselves to administrators.

Do not open until July 4, 2276: U.S. buries a'zombie-proof' time capsule The durable stainless steel container will be buried in Philadelphia for the country's 250th birthday. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. The time capsule will include items from all 50 states and six territories. Breakthroughs, discoveries, and DIY tips sent six days a week. It's been 250 years since the United States decided it was no longer interested in being part of Great Britain.

Embed to control: A locally linear307 latent dynamics model for control from raw images.

Given a visual scene, humans have strong intuitions about how a scene can evolve over time under given actions. The intuition, often termed visual intuitive physics, is a critical ability that allows us to make effective plans to manipulate the scene to achieve desired outcomes without relying on extensive trial and error. In this paper, we present a framework capable of learning 3D-grounded visual intuitive physics models from videos of complex scenes. Our method is composed of a conditional Neural Radiance Field (NeRF)-style visual frontend and a 3D point-based dynamics prediction backend, using which we can impose strong relational and structural inductive bias to capture the structure of the underlying environment. Unlike existing intuitive point-based dynamics works that rely on the supervision of dense point trajectory from simulators, we relax the requirements and only assume access to multi-view RGB images and (imperfect) instance masks acquired using color prior.

Table 5: All task variations except shape used in VLMbench. The shape variation of each task can be found in the detail descriptions of each task category. Variations Totals Values Color 25 seen:red, maroon, lime, green, blue,navy, yellow, cyan, magenta, silver, gray, olive, purple, teal, azure, violet, rose, black, white unseen: brown, gold, pink, chocolate, coral Size 5 larger, smaller, large, medium, small Relative Position 5 top, front, rear, left, right Level 3 top, middle, bottom Amount 2 fully, slightly Action Type 2 open, close Table 6: All object models used in VLMbench. The number behind the object class indicate the instance number of that class. Here, we list variations used for these tasks in Table. 5. For each demonstration, all things in the scene will change the pose at the beginning. When building an instance-level task with one variation, the other variations will also randomly change. For example, in the demonstrations of "Pick & Place objects" with "size" variation, all objects' color and relative positions, including targets and distractors, will randomly change. In the dataset, we have five types of objects, shown in Table 6. We will explain each task in detail as follows. Visualizations can be found on the project website. A.1 Pick & Place Objects Task Definition: The agent needs to distinguish the specific object to grasp and then place it into a particular container. The object can be placed anywhere with any orientation inside the container.