Search: “applications”

Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge

arXiv:2510.04772v2 Announce Type: replace-cross Abstract: Developing generalizable surgical AI requires multi-institutional data, yet patient privacy constraints preclude direct data sharing, making F

Model Releases

From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media

DGX agent

arXiv:2604.21786v1 Announce Type: new Abstract: Social media platforms have become primary arenas for climate communication, generating millions of images and posts that - if systematically analysed -

model-releasesarxiv-cs-cv

24 Apr 2026

Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction

arXiv:2604.21479v1 Announce Type: new Abstract: Large language models (LLMs) have recently demonstrated strong reasoning capabilities and attracted increasing research attention in the field of autono

local-aiarxiv-cs-cv

Tools

GPT 5.5 on AI Gateway

Vercel announced the availability of GPT-5.5 through its AI Gateway service, expanding the model options developers can access through the platform. This integration allows developers to leverage Open

toolsvercel-blog

Graph Neural Network-Informed Predictive Flows for Faster Ford-Fulkerson and PAC-Learnability

arXiv:2604.21175v1 Announce Type: new Abstract: We propose a learning-augmented framework for accelerating max-flow computation and image segmentation by integrating Graph Neural Networks (GNNs) with

tutorialsarxiv-cs-lg

Tools

@jsconfeu @cramforce talk now live! @vercel is doing incredible AI engineering work and it comes direct from the C-suite, this should be mor…

@jsconfeu @cramforce talk now live! @vercel is doing incredible AI engineering work and it comes direct from the C-suite, this should be more common but it is not, even today https://x.com/cramforce/s

toolsswyx--x

Klein 9B Distilled vs. five different cloud API models

local-air-stablediffusion

The Klein 9B Distilled is a distilled image generation model enabling sub-second image generation with text-to-image and image-to-image editing capabilities in a single unified model, designed for rea

Large-Scale Data Parallelization of Product Quantization and Inverted Indexing Using Dask

arXiv:2604.21645v1 Announce Type: new Abstract: Large-scale Nearest Neighbor (NN) search, though widely utilized in the similarity search field, remains challenged by the computational limitations inh

Learning Linear Regression with Low-Rank Tasks in-Context

arXiv:2510.04548v2 Announce Type: replace-cross Abstract: In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It

tutorialsarxiv-cs-lg

Linear Image Generation by Synthesizing Exposure Brackets

arXiv:2604.21008v1 Announce Type: new Abstract: The life of a photo begins with photons striking the sensor, whose signals are passed through a sophisticated image signal processing (ISP) pipeline to

researcharxiv-cs-cv

LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval

model-releasesarxiv-cs-cv

arXiv:2505.15269v2 Announce Type: replace Abstract: Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance.

Materialistic RIR: Material Conditioned Realistic RIR Generation

arXiv:2604.21119v1 Announce Type: cross Abstract: Rings like gold, thuds like wood! The sound we hear in a scene is shaped not only by the spatial layout of the environment but also by the materials o

researcharxiv-cs-ai

Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs

arXiv:2510.20064v2 Announce Type: replace Abstract: Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection

PREVENT-JACK: Context Steering for Swarms of Long Heavy Articulated Vehicles

model-releasesarxiv-cs-ro

arXiv:2604.21337v1 Announce Type: new Abstract: In this paper, we aim to extend the traditional point-mass-like robot representation in swarm robotics and instead study a swarm of long Heavy Articulat

Product Quantization for Surface Soil Similarity

arXiv:2506.03374v2 Announce Type: replace Abstract: The use of machine learning (ML) techniques has allowed rapid advancements in many scientific and engineering fields. One of these problems is that

Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction

arXiv:2604.21203v1 Announce Type: cross Abstract: We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as p

safetyarxiv-cs-lg

Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts

arXiv:2604.20851v1 Announce Type: cross Abstract: Modern video-text retrieval (VTR) models excel on in-distribution benchmarks but are highly vulnerable to real-world query shifts, where the distribut

RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting

arXiv:2604.21355v1 Announce Type: new Abstract: Humanoid robots have demonstrated impressive motor skills in a wide range of tasks, yet whole-body control for humanlike long-time, dynamic fighting rem

safetyarxiv-cs-ro

SLAM as a Stochastic Control Problem with Partial Information: Optimal Solutions and Rigorous Approximations

arXiv:2604.21693v1 Announce Type: new Abstract: Simultaneous localization and mapping (SLAM) is a foundational state estimation problem in robotics in which a robot accurately constructs a map of its

tutorialsarxiv-cs-ro

Industry

SpaceX is developing a next-generation gateway station to boost @Starlink speeds after securing approval to upgrade the satellite internet s…

SpaceX is developing a next-generation gateway station to boost @Starlink speeds after securing approval to upgrade the satellite internet service with gigabit connectivity, according to a new FCC fil

industryelon-musk--x

Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture

arXiv:2604.21284v1 Announce Type: new Abstract: MemPalace is an open-source AI memory system that applies the ancient method of loci (memory palace) spatial metaphor to organize long-term memory for l

Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction

model-releasesarxiv-cs-lg

arXiv:2604.21094v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) excel on relational data, but standard benchmarks unrealistically assume the graph is centrally available. In practice, set

Agents

Stratified Topological Autonomy for Long-Range Coordination (STALC)

arXiv:2503.10475v4 Announce Type: replace Abstract: In this paper, we present Stratified Topological Autonomy for Long-Range Coordination (STALC), a hierarchical planning approach for multi-robot coor

agentsarxiv-cs-ro

Survey on Evaluation of LLM-based Agents

arXiv:2503.16416v2 Announce Type: replace Abstract: LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environ

safetyarxiv-cs-ai

TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval

model-releasesarxiv-cs-cv

arXiv:2604.21806v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) is an important image retrieval paradigm that enables users to retrieve a target image using a multimodal query that cons

Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics

arXiv:2604.21456v1 Announce Type: new Abstract: We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design a

safetyarxiv-cs-lg

To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning

arXiv:2604.21632v1 Announce Type: new Abstract: We investigate the ability of decoder-only transformer models to perform abstract symbolic reasoning; specifically solving propositional logic reasoning

Transferable Physics-Informed Representations via Closed-Form Head Adaptation

arXiv:2604.21761v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have garnered significant interest for their potential in solving partial differential equations (PDEs) that go

tutorialsarxiv-cs-lg

Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation

arXiv:2512.08216v3 Announce Type: replace-cross Abstract: Accurate segmentation of lung tumors from 3D computed tomography (CT) scans is essential for automated treatment planning and response assessm

safetyarxiv-cs-cv

UbiQVision: Quantifying Uncertainty in XAI for Image Recognition

arXiv:2512.20288v2 Announce Type: replace-cross Abstract: Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is drive

researcharxiv-cs-ai

Ufil: A Unified Framework for Infrastructure-based Localization

arXiv:2604.21471v1 Announce Type: new Abstract: Infrastructure-based localization enhances road safety and traffic management by providing state estimates of road users. Development is hindered by fra

local-aiarxiv-cs-ro

Unbiased Prevalence Estimation with Multicalibrated LLMs

arXiv:2604.21549v1 Announce Type: new Abstract: Estimating the prevalence of a category in a population using imperfect measurement devices (diagnostic tests, classifiers, or large language models) is

safetyarxiv-cs-ai

Weighted quantization using MMD: From mean field to mean shift via gradient flows

arXiv:2502.10600v4 Announce Type: replace-cross Abstract: Approximating a probability distribution using a set of particles is a fundamental problem in machine learning and statistics, with applicatio

You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes

model-releasesarxiv-cs-cv

arXiv:2604.21400v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has revolutionized neural rendering, yet existing methods remain predominantly research prototypes ill-suited for productio

ZipFold: Modular Actuators for Scaleable Adaptive Robots

arXiv:2604.05260v2 Announce Type: replace Abstract: There is a growing need for robots that can change their shape, size and mechanical properties to adapt to evolving tasks and environments. However,

researcharxiv-cs-ro

Industry

3,000 people are testing the ml-intern!

Hugging Face's ml-intern project has reached a testing milestone with 3,000 people actively participating in its evaluation. This suggests significant community interest in what is likely an open-sour

industryclem-delangue--x

A Kinematic Framework for Evaluating Pinch Configurations in Robotic Hand Design without Object or Contact Models

arXiv:2604.20692v1 Announce Type: new Abstract: Evaluating the pinch capability of a robotic hand is important for understanding its functional dexterity. However, many existing grasp evaluation metho

researcharxiv-cs-ro

Adaptive Multi-task Learning for Multi-sector Portfolio Optimization

arXiv:2507.16433v2 Announce Type: replace-cross Abstract: Accurate transfer of information across multiple sectors to enhance model estimation is both significant and challenging in multi-sector portf

Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems

arXiv:2604.20795v1 Announce Type: new Abstract: This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory

Automations

OpenAI's Automations documentation covers tools and techniques for automating repetitive tasks using AI models, likely including practical examples of how to use their APIs to create automated workflo

tutorialsopenai

Agents

Built a community catalog of real-world Hermes Agent use cases

A community catalog documenting practical use cases for Hermes Agent, a self-improving AI agent built by Nous Research that features automatic skill creation, cross-session memory, and 70+ built-in sk

agentsr-ollama

Calibrating conditional risk

arXiv:2604.20409v1 Announce Type: new Abstract: We introduce and study the problem of calibrating conditional risk, which involves estimating the expected loss of a prediction model conditional on inp

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment

arXiv:2510.18471v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between the

safetyarxiv-cs-ai

Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging

arXiv:2604.19750v1 Announce Type: cross Abstract: Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly re

Context Attribution with Multi-Armed Bandit Optimization

arXiv:2506.19977v2 Announce Type: replace Abstract: Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable a

researcharxiv-cs-ai

Tools

Customer Experience Automation First try: 2018: Google Duplex Today: 2026: Google Agents ~8 years to mature and work

Google Duplex, introduced in 2018, represented an early attempt at customer experience automation through AI-powered phone conversations, while Google Agents (expected circa 2026) represents a more ma

toolsitamar-friedman--x

Databricks partners with OpenAI on GPT-5.5

Databricks has announced a partnership with OpenAI to integrate GPT-5.5, OpenAI's latest language model, into its data and AI platform. This collaboration enables Databricks customers to leverage GPT-

model-releasesdatabricks

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

arXiv:2604.20447v1 Announce Type: new Abstract: Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughp

local-aiarxiv-cs-cl