AI News Archive: July 7, 2026 — Part 18
Sourced from 500+ daily AI sources, scored by relevance.
- Learning When to Automate: Queue Control in Human-AI Service Systems
We study a human-AI service system in which tasks arrive sequentially and are processed through a two-stage architecture: an automated chatbot followed, when necessary, by a human agent. We consider $T$ sequentially arriving tasks, each belonging to one of $K$ heterogeneous types. For each task the ...
- Auditing of Unlearning Algorithms
Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes data-dependent lower bounds on the unlearning parameter $\varepsilon$ using membership inference attacks. Evaluating multiple unlearning algorithms, w...
- RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time to specific hardware and workspaces. We introduce digital teleoperation, a paradigm that decouples data collection from ...
- LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation
Real-world learning for dexterous hands remains brittle because high-dimensional hand actions amplify imitation errors and make reinforcement-learning exploration prone to contact-breaking motion. While combining imitation learning (IL) with online reinforcement learning (RL) can reduce manual super...
- Optimal Transport Q-Learning for Flow Policy Steering and Acceleration
Diffusion and flow policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions, especially in the context of vision language action (VLA) models. However, high quality policy performance also requires fast infer...
- Why does Deep Learning Improve Visual SLAM?
Visual SLAM is a well-established technology utilized in a wide range of real-world applications. However, its performance still degrades under challenging visual conditions, such as low texture, severe motion blur, and poor illumination. Systems based on deep learning outperform classical geometry-...
- Delay-Aware Active Triangulation with Uncertainty-Driven Multi-Agent Reinforcement Learning for Counter-UAS
Multi-agent active visual triangulation enables precise 3D localization of aerial targets by coordinating mobile observers with controllable cameras. However, existing methods assume instantaneous state feedback, ignoring cumulative latency from detection, communication, and decision propagation. We...
- Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning
This article presents a solution to intercept an agile drone by a team of agile drone carrying catching nets. We formulate the problem as a competitive Multi-Agent Reinforcement Learning (MARL) task. To address the problem of nonstationarity and catastrophic forgetting of agents overfitting to the c...
- TRIG: Trajectory-Rig Decoupled Metric Geometry Learning
Vision-centric autonomous driving requires accurate metric geometry and ego-motion estimation from synchronized multi-camera observations. Recent visual geometry models show strong performance in pose estimation, depth prediction, and 3D reconstruction, but are not tailored to rigid multi-camera dri...
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
Embodied navigation aims to build agents that interpret multimodal goals, reason in 3D space, and reach target destinations reliably in the real world. However, progress remains constrained by the lack of scalable, high-fidelity, and physically grounded interactive environments. Although real-world ...
- Embodied Human-Robot Interaction via Acoustics: A MARL Approach with AcoustoBots for Spatial Data Physicalization
Traditional data physicalization is often static and disconnected from real environments, limiting its ability to convey embodied spatial dynamics and engage users. To address this limitation, we present AcoustoBots, a mobile acoustophoretic data-physicalization platform in which TurtleBot3 robots c...
- RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under interaction. We argue that synchronized RGB, depth, and optical flow, namely RGB-DF, provide a physically grounded representation that captures the und...
- UniLM-Nav: A Unified Framework for Zero-Shot Last-Mile Navigation
Mobile manipulation requires a robot to navigate to a target object or receptacle and then perform intended manipulation. However, reaching the vicinity of the target does not guarantee a manipulation-ready base pose, a problem known as last-mile navigation. Prior methods for last-mile navigation ei...
- Neural-ESO: A Dual-Pathway Architecture for Provably Robust Learning-Based Control
A learning-enabled disturbance-rejection framework based on a Neural Extended State Observer (Neural-ESO) is presented in this letter. Unlike existing learning-based control methods that largely rely on the learned model once deployed, Neural-ESO adopts a dual-pathway architecture: a predictive path...
- Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning
We consider an open-world planning setting in which service robots must operate in unknown environments with incomplete knowledge of objects and actions. Traditional closed-world approaches with pre-programmed knowledge bases fail when robots encounter unexpected situations and tasks, posing a funda...
- Clustering-Embedded Model Predictive Path Integral Control: Avoiding Averaging-Induced Failure and Enabling Efficient Cluster Selection for Dynamic Obstacles
With the widespread availability of parallel computing hardware, sampling-based motion planning methods such as Model Predictive Path Integral (MPPI) control have become increasingly powerful for complex nonlinear systems in non-smooth task spaces. However, the sampling and forward-simulation pipeli...
- Hilti-Trimble-Oxford Dataset: 360 Visual-Inertial Benchmark with Floor Plan Priors for SLAM and Localization
Automated progress monitoring on construction sites is an active area of research and development. Robot and human-carried mapping systems have been developed to build 3D maps of building and infrastructure projects. While LiDAR-based mapping systems achieve high accuracy, the cost of LiDAR can be p...
- SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models
Vision-Language-Action (VLA) models are typically trained by imitation learning on large-scale robot demonstration datasets, but more data does not necessarily yield better policies due to redundancy, noise, and uneven coverage. Existing data selection methods often assess demonstrations at either t...
- From Foundation to Application: Improving VLA Models in Practice
Despite recent progress of VLA foundation models, the disparity between laboratory conditions and real-world applications continues to impede their practical implementation. To bridge this gap, we present LingBot-VLA 2.0, which advances LingBot-VLA through improvements in three functional domains. (...
- Towards Real-World Applications with an Autonomous Powered Wheelchair
Wheelchair users call for assistive mobility systems that provide active support, adapt to dynamic environments, and are intuitive and user-friendly. However, powered wheelchairs typically still provide limited autonomy and lack effective integration with advanced perception and navigation capabilit...
- Diagnosing Semantic Handoff Failures in Agent-Orchestrated Vision-Language-Action Skill Composition
Long-horizon household tasks require robots to compose many language-conditioned skills, yet the boundary between consecutive skills is rarely explicit. A skill may satisfy its own postcondition while leaving the robot, objects, or camera views in a state from which the next skill cannot reliably st...
- RoboVAST: Automated Scenario-Based Validation of Robots at Scale
Validation of robotic systems critically depends on the operating conditions under which they are assessed. Scenario selection and variation are often manual, experience-driven, and difficult to scale, which harms reproducibility and weakens validation conclusions. We propose a scenario-based method...
- APVI-SLAM: Real-Time Acoustic-Pressure-Visual-Inertial Localization and Photorealistic Mapping System in Complex Underwater Environment
Extreme subsea environments often cause severe feature de-gradation and estimator divergence in underwater visual-inertial SLAM. Although sensors like Doppler Velocity Logs (DVL) and pressure gauges provide auxiliary constraints, robust multi-sensor fusion during intermittent visual failure remains ...
- Calf-Integrated Arms for Bimanual Quadruped Loco-Manipulation
Most quadruped loco-manipulation designs trade manipulation capability against stance. A trunk-mounted arm sits high and usually carries a single arm; using the legs as manipulators lifts the manipulating leg off the ground; and even leg-mounted grippers reach two-handed tasks only by rearing onto t...
- EAGOR: Embodied Reasoning in Omni-direction
Omni-directional (360°) cameras provide embodied agents with a holistic view of their surroundings, making them suited for directional reasoning in tasks such as navigation and object search. Existing Vision Language Models (VLMs) project 360° observations to 2D equirectangular projection (ERP) imag...
- Kuberns
The AI agent that deploys and manages your cloud
- RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a result, these models can be difficult to use for planning or policy extraction. To address these limitations, we pr...
- Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure
Long-horizon failure in world models is conventionally attributed to compounding error, a generic framing that does not distinguish what kind of error compounds. We propose a kinematic-vs-dynamic reframing: world models tend to imagine kinematically rather than dynamically. We operationalize this as...
- Prior-First, Condition-Second: Scalable and Controllable Hand Motion Completion
Synthesizing hand motion that matches the full body motion and the semantic labels is a difficult task due to their high degrees of freedom and the lack of semantic labels. To cope with this issue, we propose a prior-first, condition-second framework for body-conditioned hand motion completion. Our ...
- GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation
Robust robotic grasping of novel objects requires datasets that simultaneously provide photorealistic RGB-D observations, physically validated grasp quality annotations, and a principled bridge between simulation and the real world, which existing datasets lack to provide jointly. \textbf{GraspIT} a...
- FORGE: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning
While humans readily repurpose a book, a stone, or a shoe to drive a nail, robots trained on specific tools fail to transfer the same function to novel ones -- a gap we formalize as functional generalization. Such tools share a common functional intent that is visually recognizable, yet this percept...
- Factor-Augmented Machine Learning Panel Regressions
This paper develops the asymptotic theory for high-dimensional panel data regressions in settings with cross-sectionally dependent errors driven by common shocks. We consider a factor-augmented sparse-group LASSO estimator that combines MIDAS aggregation with latent factors. The estimator can take a...
- Width-Robust Learnability in Mean-Field Bayesian Neural Networks
Infinite-width limits are a standard way to reason about neural networks, but it is not automatic that the limiting learner has the same complexity-theoretic inductive bias as large finite networks. We study this question for Bayesian neural networks at the mean-field, or critical feature-learning, ...
- Feature Learning for the High Dimensional Stationary Schödinger Equation with Deep Ritz Method
This paper investigates feature learning within the framework of the deep Ritz method for solving the stationary Schrödinger equation with Neumann boundary conditions. We first analyze the convergence of Riemannian gradient descent in an agnostic setting, where the hypothesis function is restricted ...
- A unified perspective of Gaussian process approximation for differential equations
The use of Gaussian processes for approximating differential equations has expanded rapidly, leading to a growing, diverse, and fragmented body of numerical methods. We present a unified Bayesian perspective that places these techniques within a common probabilistic framework, based on a derivative ...
- No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
Memory-efficient optimizers such as GaLore train large language models by projecting gradients onto a rank-r subspace recomputed every T steps, assuming this subspace is a slowly drifting object that can be tracked. We show that beyond a small reproducible core, there is no such object. Two estimate...
- Boosting with List-Decodable Codes
Boosting is a fundamental technique for generically improving the accuracy of learning algorithms (Schapire 1989). Existing boosting algorithms construct a strong learner using $O(\log(\frac{1}ε)/γ^2)$ calls to a $γ$-advantage weak learner, and this round complexity is known to be optimal for generi...
- Badge
AI agents collect peer reviews to generate proof of work
- Half-Dose Ticagrelor Monotherapy Versus Standard Dual Antiplatelet Therapy in Chronic Coronary Syndrome After Percutaneous Coronary Intervention: A Randomized Pilot Trial With PRU-Guided Pharmacodynamic Assessment
Background: Aspirin-free P2Y12-inhibitor monotherapy after percutaneous coronary intervention (PCI) is an alternative to dual antiplatelet therapy (DAPT), but the evidence rests largely on full-dose ticagrelor in acute coronary syndrome and on designs retaining a DAPT run-in; East-Asian patients may not require the same antithrombotic intensity. We compared standard DAPT, DAPT with half-dose ticagrelor, and aspirin-free half-dose ticagrelor monotherapy initiated on the day of PCI in chronic coronary syndrome (CCS). Methods: Sixty-one East-Asian patients with CCS scheduled for elective PCI were randomized 1:1:1 to Control (aspirin plus clopidogrel), Experimental A (aspirin plus ticagrelor 45 mg twice daily), or Experimental B (ticagrelor 45 mg monotherapy, aspirin discontinued at day 2). DAPT arms continued for six months; Experimental B continued indefinitely. P2Y12 reaction units (PRU) were measured at baseline and at a median of 17 days. Results: PRU reduction was three-fold greater in both ticagrelor arms than in Control ({Delta}PRU -188 and -181 versus -60.5; P<0.001), with no difference between ticagrelor arms (P=0.772). At 12 months, major adverse cardiovascular events (MACE) and clinically relevant bleeding each occurred in 1 of 17 Experimental B patients (5.9%) and in neither other arm. One Experimental A patient crossed over for ticagrelor-induced dyspnea; no stent thrombosis or cardiac death occurred. Conclusions: In East-Asian patients with CCS, half-dose ticagrelor produced markedly greater platelet inhibition than standard DAPT, with an identical effect whether given with or without aspirin. It merits evaluation in an adequately powered randomized trial. Clinical Trial Registration. URL: https://www.clinicaltrials.gov; Unique Identifier: NCT07622056
- KarmaScout
Surface the best opportunities in your target communities
- Platform
The cloud platform you run by talking to it
- ShipSafe AI
Pre-launch security audits for vibe-coded apps
- Kelsa
Your Twitter/X growth workspace, built into Chrome
- Rheo
Ship and test app funnels without App Store reviews
- Influencer Studio
Create owned AI influencers for UGC videos, ads, and content
- DataCrawlPro
AI web scraping, OCR extraction, and site risk audits
- Detector de IA
Review AI signals in text and documents
- BatchEdits
Create daily videos faster with AI batch editing
- BoardQ.io
Gamify Your Team’s Daily Performance
- Morphic CMS
Modern, Edge-Ready Headless CMS