Chain Visualization: Reading the Trace Waterfall The spans from the last section don't mean much as a raw list.

In this article, you will learn how to add a lightweight temporal reasoning layer to a Graph-RAG system so that it can distinguish fresh facts...

Multi-node GPU clusters with RDMA, gang scheduled from Modal's shared capacity pool and billed by the second, behind a single decorator.

Discussion | Link

The following article originally appeared on Robert Englander’s blog site and is being reposted here with the author’s permission. The software industry has become deeply focused on autonomous AI systems. Agents that can replace workers. Agents that can write software. Agents that can operate applications on our behalf. Entire startups are now built around the […]

Benefitting from the Bitter Lesson

Discussion | Link

Discussion | Link

Discussion | Link

Guardian tested chatbots after French far-right politician stripped a Muslim woman of her hijab in a photo When prompted, AI chat bots will edit images to remove the hijabs from Muslim women, a violation of one of the world’s most common and visible expressions of faith. The Guardian asked ChatGPT, Grok, Gemini and Claude to take the veil off an AI-generated image of a woman wearing a hijab. Both OpenAI’s ChatGPT and xAI’s Grok bots complied with the prompt. Anthropic’s Claude responded that it does not have an image-editing or generating feature but that it would not alter a photo to remove someone’s hijab. Continue reading...

Discussion | Link

The risks of AI aren’t what we think they are, as a recent security incident between China and the United States reveals Amid a barrage of news stories warning about superintelligent machines rendering humanity extinct, a CNN story describing the opposite scenario – one in which the US military’s reliance on brittle chatbots almost brought the US into war with China – went mostly unnoticed by the public. The biggest international AI news of the past three weeks was Anthropic engineer Jacob Coxon’s resignation. According to him, OpenAI and Anthropic are “racing straight towards self-improving superintelligence and gambling with our lives”. Coxon’s description of a “terminator” scenario, a machine becoming much smarter than humanity and deciding to wipe us out, captured the public, journali…

Every dev team has repeatable setup tasks: spinning up a new project, running a deployment checklist, generating a file structure, or typing the same instructions into Claude again and again. Claude Code helps reduce that friction with slash commands, including built-in commands and custom commands you can define for your own workflows. These commands turn […] The post Claude Code Custom Commands & Skills: Automate Your Workflow appeared first on Analytics Vidhya.

Discussion | Link

Discussion | Link

Time magazine list includes Australian communications minister after her efforts to take on big tech The federal communications minister, Anika Wells, has been named as one of Time magazine’s “world’s most influential rising stars” in recognition of her work on Australia’s under-16 social media ban and taking on big tech companies. Australia’s world-leading restrictions on social media for children, which came into force last year, have garnered international attention, with governments across Europe and Asia, and in some American states, enacting or proposing similar measures. Continue reading...

NVIDIA has released Kumo Tabular, a new family of tabular foundation models (TFMs) for classification and regression. If you have followed TabPFN or TabICL, the setup will look familiar. The model takes labeled rows as context and predicts new rows in one forward pass. There is no training, no hyperparameter tuning, and no feature engineering. […] The post NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass appeared first on MarkTechPost.

... but you can’t try it yet unless you are “government users and trusted cyber defenders in the Fairwind Program”

[...] Put these pieces together and you have the two halves of a worm: a payload that hijacks the agent, and an agent that will carry the payload to the next agent. Agents in separately-isolated sandboxes discovered that they could leave instructions for each other in a shared package cache, and those instructions changed what the recipients did. Replace the package cache with email, Slack and shared documents or WhatsApp, and replace independently-sandboxed training runs with independently-deployed personal agents like Muse, and you have exactly the ingredients that a worm needs. — Matthew Green, Is sandboxing sufficient to contain rogue agents? Tags: accidental-cyberattacks, ai-misuse, generative-ai, ai-security-research, sandboxing, ai, llms

The candidates running to replace Gavin Newsom sparred over taxes, immigration and regulating AI Xavier Becerra and Steve Hilton, the candidates running to be California’s next governor, clashed on Wednesday over taxes, immigration and regulating artificial intelligence in a testy debate held days before voters begin receiving their ballots in the heavily Democratic state. Hilton, the former Fox News host endorsed by Donald Trump, used the hourlong matchup, hosted by CNN, to argue that Becerra, a former congressman who served as the US health and human services secretary during the Biden administration, was not actively campaigning and instead taking voters for granted. Continue reading...

arXiv:2609.38421v1 Announce Type: new Abstract: Dynamical Systems (DS) are reactive motion policies representing vector fields trained with theoretical guarantees of stability and convergence. To ensure safety during deployment in unknown environments they must be locally reshaped, either through modulation or geometric control barrier function strategies. However, depending on the geometry of the obstacles and the complexity of the DS, these local strategies can lead the system to unavoidable collisions or spurious attractors. In this work, we certify safety with a value function drawn from the notion of backward reachability tube, which measures the worst-case safety along a rollout trajectory of the nominal DS. Usually, such a value function is intractable for a controlled system due t…

arXiv:2609.38418v1 Announce Type: new Abstract: Soft robots and tactile sensors have demonstrated great potential in delicate manipulation tasks. Soft pneumatic robots enable safe contact through compliance, and vision-based tactile sensors offer high-resolution touch perception. However, learning tactile manipulation with compliant robots has been challenging, bottlenecked by the lack of efficient simulation. Existing simulators typically model them in isolation, and exhibit large calibration gaps that are difficult to overcome efficiently. We present PneuTac, a unified framework for tactile-feedback manipulation with soft pneumatic robots. We leverage the material point method (MPM) for modelling the dynamics of the soft robot and the deformable tactile membrane, and 3D Gaussian splatti…

arXiv:2609.38405v1 Announce Type: new Abstract: Robot performance is often limited by the cost of iterating on morphology and control together, since every computer-aided design (CAD) change has to be carried into a simulation-ready model before control work begins. Co-design methods attempt to close this gap, but each uses a model generator written for a single platform or lack the use of real-world data to suggest that designs are plausible. We present Draft, a parametric generation tool whose generalized engine compiles any parametric tree of serial chains into a simulation-ready MJCF model, without CAD. It allows engineers to explore design tradeoffs through easily adjustable models and evaluate how changes influence controller performance. Draft grounds the free parameters of each de…

arXiv:2609.38401v1 Announce Type: new Abstract: Training data variation, whether through designing a domain randomization (DR) scheme in simulation or curating demonstrations for imitation learning, is a primary lever for improving the robustness of robotic manipulation policies. Yet its underlying mechanisms remain poorly understood, and practitioners typically select randomization parameters through expensive trial and error. We investigate these mechanisms through a series of case studies, randomizing object size, color, and type as well as scene lighting and linguistic prompts across settings including pick-and-place RL in ManiSkill and fine-tuning of vision-language-action (VLA) models on LIBERO and RoboTwin. We examine both model behavior and internal representations, using the empi…

arXiv:2609.38400v1 Announce Type: new Abstract: Co-speech gestures for robots must adapt not only to speech and embodiment, but also to the workspace available for performing the motion. Since the same speech can be accompanied by different gestures, a robot can respond to workspace constraints, e.g., gestures for speech next to a wall. In these scenarios, the robot should gesture in a suitable motion rather than simply correcting an unconstrained one. To achieve this goal, we present GestAdapt, a workspace-conditioned framework that conditions co-speech gesture generation on a prescribed wrist workspace. The GestAdapt framework learns from six complementary co-speech corpora through a shared motion representation and supports retargeting to different robot embodiments. Quantitative evalu…

arXiv:2609.38371v1 Announce Type: new Abstract: Existing LLM-driven robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focused. However, when interacting with real-world users, especially those experiencing cognitive impairments, such as people living with dementia (PLWD), the planners often make mistakes and even pose physical safety risks. We proposed TALK-Dem (Talking Attributes and Linguistic Knowledge in Dementia), the first benchmark for evaluating LLM-driven robot task planning under dementia-associated verbal communication. TALK-Dem contains 4,800 instructions and covers five typical communication patterns, including Referential Imprecision, Object Substitution, Empty Speech, Topic Drift, and Intrusion, at t…

arXiv:2609.38227v1 Announce Type: new Abstract: We introduce the two-echelon covering tour vehicle routing problem (2E-CTVRP) for the distribution of relief supplies after a disaster. In the first echelon, a fleet of trucks transports supplies and drones from a central depot to satellites at the periphery of the affected area. In the second echelon, drones launched in parallel from the satellites deliver the supplies to the centroids of victim clusters, which are obtained by clustering the victim locations, and each truck waits at a satellite until its drones have returned. The problem combines the assignment of satellites to trucks, the sequencing of the truck routes, and the assignment of clusters to satellites, and minimizes the sum of the arrival times of the trucks at the satellites…

arXiv:2609.38225v1 Announce Type: new Abstract: Imitation learning enables robots to acquire complex skills directly from massive demonstration datasets, but its performance degrades severely when datasets are contaminated with suboptimal or noisy demonstrations. While prior quality-assessment methods attempt to filter or reweight data, they typically rely on manual pre-selection of expert reference data or task-specific heuristics, limiting scalability. To address this challenge, we introduce SynIL (Synergy-based Imitation Learning), a novel framework for automated, label-free demonstration quality assessment in offline reinforcement learning. Grounded in neuroscientific evidence that motor synergy, a low-dimensional coordinated structure in movement, correlates directly with motor profi…

arXiv:2609.38216v1 Announce Type: new Abstract: Existing benchmarks evaluate tabletop manipulation, flat-floor household activity, or humanoid locomotion and manipulation as separate task groups; none scores vertical mobility and dexterous work on a fragile payload in one long-horizon episode. We present Fiatlux, a light-bulb replacement benchmark built on NVIDIA Isaac Lab. In one episode, a Unitree G1 humanoid positions a step ladder under a ceiling or wall fixture, climbs it, exchanges a spent bulb in a socket for a fresh one, and leaves the spent one in a disposal crate. We decompose the episode into twelve subtask environments scored on difficulty-weighted gates. The goal is a successful replacement, with the fresh bulb seated, the spent one disposed of, neither dropped, and a fragili…

arXiv:2609.38202v1 Announce Type: new Abstract: Soft continuum robots can exploit distributed compliance for whole-body manipulation, but synthesizing behavior through changing contacts remains difficult. We address whole-body grasping and pick-and-throw from an initially ungrasped state through outcome-based actuation-space optimization. Grasping is quantified by tip angular sweep and body-object enclosure, while throwing further incorporates release-direction alignment and minimum release speed. These objectives allow grasping, acceleration, and release to emerge from compliant interaction without prescribing contact forces, contact locations, or body configurations. Because the resulting actuation-to-outcome mapping is nonsmooth, we utilize derivative-free CMA-ES within an optimize-lea…