Search: “applications”

Flatness Preserves Instruction Following in Vision-Language-Action Models

arXiv:2606.23641v1 Announce Type: new Abstract: Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained vision-language representations, yet downs

Applications

FLFL: Federated Latent Factor Learning for Private Recovery of Spatio-Temporal Signals

DGX agent

arXiv:2606.23091v1 Announce Type: new Abstract: Wireless sensor network (WSNs) stands out as a burgeoning and promising domain in intelligent sensing. Owing to various factors such as sudden sensor ma

applicationsarxiv-cs-lg

23 Jun 2026

Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation

arXiv:2606.23090v1 Announce Type: new Abstract: Cross-embodiment data have become central to training robotic foundation models. To leverage such heterogeneous data, we focus on flow-based object mani

FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation

arXiv:2606.22424v1 Announce Type: new Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes. While Large

FlowTrain: Flow-Based Decoupled Training for Industrial-Grade Vision-Language Models

arXiv:2606.23087v1 Announce Type: new Abstract: Industrial-grade distributed training of vision-language models (VLMs) remains far less efficient than that of unimodal LLMs. Existing solutions either

Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents

arXiv:2606.23085v1 Announce Type: new Abstract: Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underexplored. Detecting failures in long-

From Complaint Narratives to Monetary Relief: A Hybrid Machine Learning Framework for CFPB Consumer Complaints

arXiv:2606.22664v1 Announce Type: cross Abstract: Consumer financial complaints provide a valuable source of information for identifying service failures, dispute frictions, and operational deficienci

GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation

arXiv:2411.18276v3 Announce Type: replace Abstract: Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mai

Generative Robust Optimisation

arXiv:2606.22536v1 Announce Type: new Abstract: Classical uncertainty sets for robust optimisation impose fixed geometric shapes that cannot represent the complex dependencies present in real-world da

GraphPFN: A Prior-Data Fitted Graph Foundation Model

arXiv:2509.21489v3 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into que

I know they are pivoting to health care(?!) but there is still nothing like Midjourney for making strange and atmospheric images and short a…

applicationsethan-mollick--x

I know they are pivoting to health care(?!) but there is still nothing like Midjourney for making strange and atmospheric images and short animations in ways no other AI image generator can do. Here a

Integrated cloud-based architecture for robot-robot and human-robot collaboration using ROS 2--MQTT in Mediterranean Greenhouses

arXiv:2606.22682v1 Announce Type: new Abstract: The imperative to develop more sustainable agriculture demands a transition from isolated automation toward the deployment of multi-robot systems (MRS)

Interpretable Machine Learning for Predicting Startup Funding, Patenting, and Exits

arXiv:2510.09465v2 Announce Type: replace Abstract: This study develops an interpretable machine learning framework to forecast startup outcomes, including funding, patenting, and exit. A firm-quarter

ISOPoT: Imaging Sonar Odometry by Point Tracking

arXiv:2606.23006v1 Announce Type: new Abstract: Reliable navigation in underwater environments remains a key challenge in marine robotics. In such scenarios, forward-looking sonars are a natural choic

It’s all fake and gay. Government and media manufactured the “class war” then pivoted to race war to absolve the state of blame for the 2008…

It’s all fake and gay. Government and media manufactured the “class war” then pivoted to race war to absolve the state of blame for the 2008 crisis, sideline the Tea Party with racist media attacks, a

applicationselon-musk--x

KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies

arXiv:2606.23589v1 Announce Type: new Abstract: Long-horizon robot manipulation remains challenging because similar observations may occur at different execution stages, while the appropriate action d

Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri

arXiv:2606.23144v1 Announce Type: new Abstract: Optical Character Recognition (OCR) for low-resource languages is often constrained by the lack of annotated training data and the complexity of script-

L-SR1: Learned Symmetric-Rank-One Preconditioning

arXiv:2508.12270v2 Announce Type: replace-cross Abstract: End-to-end deep learning has achieved impressive results but remains limited by its reliance on large labeled datasets, poor generalization to

Lessons from the Field: A Case Study of Robotic Intervention in an Industrial Emergency

arXiv:2606.23246v1 Announce Type: new Abstract: Incidents in chemical plants can pose a high level of risk and harsh environments for first responders. Contamination and explosion hazards can deny hum

low hanging fruit everywhere with those with the arms to pick them

applicationsethan-mollick--x

This post likely discusses opportunities for significant gains or improvements that are readily available and easy to capitalize on for those with the capability or resources to act on them. The 'low

Safety

Measuring Model-Induced Discrimination via Efficient Fairness Approximation

arXiv:2405.09251v2 Announce Type: replace Abstract: Providing various machine learning (ML) applications in the real world, concerns about discrimination hidden in ML models are growing, particularly

safetyarxiv-cs-lg

MS-rPPG: Multi-spectral State Space Model for Remote Photoplethysmography in Driver Monitoring Systems

arXiv:2606.21115v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) is a camera-based technique for measuring physiological signals, particularly cardiac activity. From the remotely mea

NAC: Neural Action Codec for Vision-Language-Action Models

arXiv:2606.21372v1 Announce Type: cross Abstract: Vision-language-action (VLA) models rely on discrete action tokenizers to bridge continuous robot control and autoregressive sequence modeling, yet ex

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings

arXiv:2507.07532v4 Announce Type: replace Abstract: While Prover-Verifier Games (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to

OSOG: A Differentiable, Physics-Informed Synthetic Data Engine for Micro-Optical Environments

arXiv:2606.21381v1 Announce Type: new Abstract: Deep learning in computational microscopy is severely constrained by the scarcity of densely annotated datasets. While synthetic data generation has bri

Parametrized Power-Iteration Clustering for Directed Graphs

arXiv:2210.00310v3 Announce Type: replace Abstract: Vertex-level clustering for directed graphs (digraphs) remains challenging as edge directionality breaks the key assumptions underlying popular spec

Physics-Informed Eikonal Caging for Whole-Arm Manipulation Planning

arXiv:2606.22143v1 Announce Type: cross Abstract: Planning contact-rich whole-arm manipulation is challenging because interactions that involve extended robot geometry give rise to complex contact dyn

Physics-Informed Modeling for Wood Thermal Analysis and Prediction

arXiv:2606.23402v1 Announce Type: new Abstract: Wood materials exhibit complex, spatially varying thermal properties that challenge traditional architectural assumptions of material homogeneity. Altho

Predictive Repair Management Using a Multi-Head Attention Transformer and Online Learning

arXiv:2606.21364v1 Announce Type: new Abstract: Accurate prediction of repair duration is an important challenge in product maintenance due to its implications for resource allocation, customer satisf

Prosper AI nabs $30M to help healthcare providers streamline patient interactions

Prosper AI Inc., a provider of artificial intelligence software for healthcare organizations, today announced that it has raised 30 million in funding. The Series A round was led by Andreessen Horowit

applicationssiliconangle

PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support

arXiv:2606.23673v1 Announce Type: cross Abstract: Mental health assessment commonly relies on isolated screening instruments or data-driven models that often lack interpretability and multi-dimensiona

RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation

arXiv:2606.22027v1 Announce Type: new Abstract: Reinforcement learning for robot manipulation is often bottlenecked by reward design, especially in long-horizon tasks: sparse success rewards provide w

Reference-Free Assessment of Physical Consistency in World Model-based Video Generation

arXiv:2606.22363v1 Announce Type: cross Abstract: We introduce reference-free measures for evaluating the physical consistency of generated videos, combining relative and absolute approaches to assess

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic

arXiv:2606.20734v1 Announce Type: new Abstract: Open Vocabulary Action Recognition (OVAR) enables the recognition of novel actions by leveraging vision-language representations, overcoming the limitat

Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats

arXiv:2606.21753v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physi

Sharing a love for calculus

applicationsmit-tech-review

The national conversation about the value of education is currently dominated by speculation about the risks and positive potential of AI. Whatever your own perspective on that debate, I hope you’ll b

Signed Evidence Flow: Conflict-Aware and Stability-Calibrated Data Analysis

arXiv:2606.21875v1 Announce Type: cross Abstract: Modern data analysis usually gives a prediction without showing whether the evidence behind it is clear, conflicting, or stable. Two cases can have th

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

arXiv:2606.23444v1 Announce Type: cross Abstract: Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertai

Sources: Hadrian, which is building AI-powered factories to produce space and defense parts, is in talks to raise ~1B at a ~7.5B post-money valuation (Bloomberg)

Bloomberg: Sources: Hadrian, which is building AI-powered factories to produce space and defense parts, is in talks to raise ~1B at a ~7.5B post-money valuation — Company runs AI-powered factories tha

applicationstechmeme

Stand Up for Research, Innovation, and Education

applicationsmit-tech-review

Right now, MIT alumni and friends are voicing their support for: America’s scientific and technological leadership Merit-based admissions and affordable education Advances that increase US health, sec

Statistical Matching via Schrodinger Bridge beyond Conditional Independence

arXiv:2606.22770v1 Announce Type: new Abstract: Statistical matching combines partially overlapping datasets that share covariates X but observe the target Y and auxiliary variables Z separately. Clas

Structure-Aware Graph Multi-Task Learning for Dynamic Sparse OD Demand Prediction

arXiv:2606.21022v1 Announce Type: new Abstract: Origin-Destination (OD) demand prediction is fundamental to intelligent transportation systems, yet real-world OD flows are often dynamically sparse, lo

Subsampling for supervised learning in reproducing kernel Hilbert spaces

arXiv:2606.21260v1 Announce Type: cross Abstract: In the era of big data, subsampling became a common practice in statistical learning. By selecting a subgroup of individuals based on which the learne

SURE: Safe Uncertainty-Aware Robot-Environment Interaction using Trajectory Optimization

arXiv:2602.06864v2 Announce Type: replace Abstract: Robotic tasks involving contact interactions pose significant challenges for trajectory optimization due to discontinuous dynamics. Conventional for

TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel

arXiv:2606.22975v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) are widely used in many real-world domains, and learning on TAGs requires jointly modeling text semantics and graph struct

Temporal logics and formal synthesis for robot planning and control

arXiv:2606.21438v1 Announce Type: new Abstract: As robots move from controlled environments into real-world settings, it becomes increasingly crucial to ensure that they perform as expected. A key ste

The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production

arXiv:2606.22959v1 Announce Type: cross Abstract: Latent diffusion approaches to sign language production (SLP) rely on an initial stage that learns an encoding of sign pose sequences, enabling genera

THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion

arXiv:2606.21792v1 Announce Type: new Abstract: Manipulation in confined environments, such as threading a manipulator through narrow apertures, remains a fundamental challenge, especially for convent