Search: “applications”

Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation

arXiv:2601.22679v2 Announce Type: replace-cross Abstract: Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, the

Statistical Inference for Misspecified Contextual Bandits

DGX agent

arXiv:2606.22639v1 Announce Type: cross Abstract: Contextual bandit algorithms have transformed modern experimentation by enabling real-time adaptation for personalized treatment. Yet these advantages

safetyarxiv-cs-lg

23 Jun 2026

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models

arXiv:2603.07307v2 Announce Type: replace Abstract: Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-atten

Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans

arXiv:2510.10779v5 Announce Type: replace Abstract: With the growing volume of CT examinations, there is an increasing demand for automated tools such as organ segmentation, abnormality detection, and

Local Ai

SuperCond-GNN: Scalable Graph Neural Network Surrogate for Superconducting Circuit Simulations

arXiv:2606.23548v1 Announce Type: cross Abstract: This paper presents SuperCond-GNN, a graph neural network-based surrogate model for predicting the voltage distribution in high-temperature supercondu

local-aiarxiv-cs-lg

Surgical Anatomy Recognition with Context Learning using Foundation Representations

arXiv:2606.22124v1 Announce Type: new Abstract: Accurate recognition of anatomical structures is essential for safe and effective minimally invasive surgery (MIS), yet it remains underexplored in surg

TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild

model-releasesarxiv-cs-lg

arXiv:2603.21478v2 Announce Type: replace-cross Abstract: Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limi

Tensor Train Decomposition-based 3D Implicit Full Waveform Inversion with Multi-scale Structural Similarity

arXiv:2606.22867v1 Announce Type: cross Abstract: Three-dimensional full waveform inversion (3DFWI) is a powerful technique for reconstructing high-resolution subsurface velocity models. However, its

Industry

Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design

model-releasesarxiv-cs-lg

arXiv:2606.22782v1 Announce Type: new Abstract: The proliferation of IoT devices has fueled distributed edge systems to collect vast amounts of sensitive data, creating fertile ground for on-device ma

TriMotion: Modality-Agnostic Camera Control for Video Generation

arXiv:2606.20774v1 Announce Type: new Abstract: Camera motion control is essential for directing viewpoint changes in generative systems. However, existing methods typically condition the generation p

Trustworthy MRI Reconstruction via Bayesian Uncertainty Quantification with Sparsity Prior Models

arXiv:2606.17343v2 Announce Type: replace Abstract: We propose a novel Bayesian framework for joint image reconstruction and uncertainty quantification from compressed sensing magnetic resonance imagi

UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models

arXiv:2606.22794v1 Announce Type: new Abstract: Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for ef

researcharxiv-cs-ro

Unlimited OCR Works

model-releasesarxiv-cs-cv

arXiv:2606.23050v1 Announce Type: new Abstract: Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a larg

Agents

VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation

arXiv:2512.11061v2 Announce Type: replace Abstract: Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack in

agentsarxiv-cs-cv

Hardware

We were honored to welcome His Royal Highness Crown Prince Al Hussein bin Abdullah II and Her Royal Highness Princess Rajwa Al Hussein to Re…

We were honored to welcome His Royal Highness Crown Prince Al Hussein bin Abdullah II and Her Royal Highness Princess Rajwa Al Hussein to Replit in Silicon Valley. It was a privilege to share how AI i

hardwarereplit--x

Industry

What is Vector Search?

Vector search is a retrieval method that converts unstructured data (text, images, audio) into numerical vector representations and finds similar items by comparing vectors in high-dimensional space,

industrydatabricks

When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations

arXiv:2606.16196v2 Announce Type: replace-cross Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributio

Industry

With Starfall, SpaceX eyes an edge in global cargo delivery from orbit

Starfall is a proposed reentry vehicle designed by SpaceX to provide uncrewed, point-to-point cargo delivery from orbit by safely returning payloads to Earth. The design focuses on precision delivery

industryars-technica

You can try it out on your own images here (~1.3GB model download in your browser) https://simonw.github.io/moebius-web/

This post highlights an interactive web-based demo of the Moebius model, which users can test directly in their browser with approximately 1.3GB of model data downloaded locally. The tool appears to b

toolssimon-willison--x

A mirror facing a mirror creates the illusion of depth. A prediction machine directed towards itself creates the illusion of direction.

researchfrancois-chollet--x

Chollet draws an analogy between visual recursion and self-referential AI systems, suggesting that just as mirrors facing each other create a false sense of infinite depth, a prediction machine analyz

Hardware

Enable Real-Time AI for High-Speed Data Acquisition with DAQIRI

DAQIRI (Data Acquisition for Integrated Real-time Instruments) is a high-performance networking library that streams data from fast detectors . DAQIRI keeps up by handling the stream as it arrives , e

hardwarenvidia-developer

Explore next-gen quantum algorithms with IBM Quantum Credits

IBM Quantum Credits is a program that provides researchers and developers with access to IBM's quantum computing systems to explore and develop advanced quantum algorithms. The initiative enables user

researchibm-research

GLM-5.2 is the step change for open agents

GLM-5.2 represents a significant advancement in open-source AI agent capabilities, marking a notable improvement over previous versions in terms of performance and functionality. The article from Inte

researchinterconnects

Hardware

HPE and Kamiwaza rethink AI infrastructure for the inference era

As AI factories evolve into “data centers of the future,” the infrastructure stack must also transform into a mix of CPU and GPU platforms that can deliver a full set of AI computing solutions. This r

hardwaresiliconangle

Nvidia introduces Halos for Robotics to bridge the physical AI safety gap

Nivida Corp. today announced Halos for Robotics, the industry’s first full framework for robotic safety systems that encompasses building, testing and managing complete artificial intelligence robotic

safetysiliconangle

Sakana Fugu Ultra now available on AI Gateway

Sakana Fugu Ultra, a new AI model, is now available through Vercel's AI Gateway, expanding the selection of models developers can access via the platform. This addition allows users to integrate Sakan

toolsvercel-blog

Unpacking sandbox startup latency: why started ≠ ready

This article examines the gap between when a sandbox container reports as 'started' versus when it's actually ready to handle requests, exploring the technical reasons for latency during startup on Mo

toolsmodal-blog

Vercel Flags: Platform-native feature flags

Vercel Flags is a platform-native feature flagging system integrated directly into Vercel's deployment platform, enabling developers to control feature rollouts and perform A/B testing without externa

toolsvercel-blog

WebSocket support is now in Public Beta

Vercel announced that WebSocket support has entered public beta, enabling developers to use WebSocket connections on the Vercel platform. This feature allows for real-time, bidirectional communication

toolsvercel-blog

yes in case you missed it we are doing 'poaster' sessions at AIE for the first time ever no papers, no posters. only poasters. we are lookin…

yes in case you missed it we are doing 'poaster' sessions at AIE for the first time ever no papers, no posters. only poasters. we are looking for people who physically print out their hottest takes an

toolsswyx--x

Flesh-eating maggots.

Flesh-eating maggots, scientifically known as larvae of blow flies and flesh flies, are used in medical settings for debridement therapy to treat infected or necrotic wounds by consuming dead tissue w

safetygary-marcus--x

Local Ai

GLM-5.2 is really, really good.

GLM-5.2 is a language model that has garnered positive reception, likely referring to improvements in performance, capabilities, or user experience compared to previous versions. The post appears to b

local-aiollama--x

Agents

In the meantime, for parsing human-native documents, check out LlamaParse: https://cloud.llamaindex.ai/

LlamaParse is a document parsing tool from LlamaIndex designed to extract and process data from human-readable documents with high accuracy. The tool is available as a cloud service and represents Lla

agentsjerry-liu--x

Two days. One playground. Countless things built. That was Vibecon. Thank you, New York, for proving that code is the new creative medium.

Vibecon was a two-day event held in New York where participants used Replit's coding platform to build projects in a playground-style environment, demonstrating code as a creative medium. The event br

toolsreplit--x

also hearing from other customers that GLM 5.2 approaches GPT 5.5 on their evals + use cases

Fireworks AI reports that GLM 5.2, their language model, demonstrates performance comparable to GPT 5.5 across various evaluation benchmarks and real-world use cases. This claim suggests GLM 5.2 is co

toolsfireworks-ai--x

19 Jun 2026

3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling

arXiv:2606.11446v1 Announce Type: new Abstract: This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures to address the inherent 'semant

A Comprehensive Ecosystem for Open-Domain Customized Video Generation

model-releasesarxiv-cs-cv

arXiv:2606.11783v1 Announce Type: new Abstract: Recent progress in video generation has shown impressive visual synthesis capabilities. However, open-domain customized video generation remains limited

A PubMed-Scale Dataset of Structured Biomedical Abstracts

model-releasesarxiv-cs-cl

arXiv:2606.11361v1 Announce Type: cross Abstract: Structured abstracts are important for biomedical literature processing, by facilitating information retrieval, text mining, and knowledge synthesis.

A Resource for Enthymeme Detection in Controversial Political Discourse

arXiv:2606.12186v1 Announce Type: new Abstract: Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse, yet their annotation remains notoriously subjective.

researcharxiv-cs-cl

Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels

arXiv:2606.11626v1 Announce Type: new Abstract: Understanding multi-label images remains a challenging task in computer vision. With the rapid progress of vision-language multimodal learning, vision-l

Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

model-releasesarxiv-cs-cl

arXiv:2606.12203v1 Announce Type: new Abstract: Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged

Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems

arXiv:2606.12337v1 Announce Type: cross Abstract: Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based opt

AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents

arXiv:2606.12142v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, mos

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

model-releasesarxiv-cs-cl

arXiv:2606.11435v1 Announce Type: new Abstract: The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evalua

AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory

arXiv:2602.02285v2 Announce Type: replace-cross Abstract: We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-e

researcharxiv-cs-cl

Analytic Bijections for Smooth and Interpretable Normalizing Flows

arXiv:2601.10774v2 Announce Type: replace Abstract: A key challenge in normalizing flows is finding expressive invertible scalar bijections. Existing approaches face trade-offs: affine transformations

Bergson: An Open Source Library for Data Attribution

arXiv:2606.11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applicati