applications

As everyone knows, the internet has millions of images of art galleries filled with paintings of otters sitting on airplanes, which is the o…

As everyone knows, the internet has millions of images of art galleries filled with paintings of otters sitting on airplanes, which is the only reason these stochastic parrot AIs can produce outputs l

Applications

AutoAdapt: Automated domain adaptation for large language models

DGX agent

Deploying large language models (LLMs) in real-world, high-stakes settings is harder than it should be. In high-stakes settings like law, medicine, and cloud incident response, performance and reliabi

applicationsmicrosoft-research

22 Apr 2026

Bayesian Event-Based Model for Disease Subtype and Stage Inference

arXiv:2512.03467v2 Announce Type: replace Abstract: Chronic diseases often progress differently across patients. Rather than randomly varying, there are typically a small number of subtypes for how a

Benign Overfitting in Adversarial Training for Vision Transformers

arXiv:2604.19724v1 Announce Type: cross Abstract: Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulner

Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models

arXiv:2604.18751v1 Announce Type: cross Abstract: Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs

Bridging the High-Frequency Data Gap: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models

arXiv:2603.16497v2 Announce Type: replace-cross Abstract: Time series foundation models (TSFMs) require diverse, real-world datasets to adapt across varying domains and temporal frequencies. However,

Budgeted Online Influence Maximization

arXiv:2604.19672v1 Announce Type: new Abstract: We introduce a new budgeted framework for online influence maximization, considering the total cost of an advertising campaign instead of the common car

Build your own finance app with Replit using @plaid Plaid is now natively integrated into Replit, giving you secure, real-time access to you…

Build your own finance app with Replit using @plaid Plaid is now natively integrated into Replit, giving you secure, real-time access to your financial data. Connect your accounts → prompt what you wa

applicationsreplit--x

CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation

arXiv:2604.19488v1 Announce Type: new Abstract: Large language models (LLMs) have achieved substantial advances in logical reasoning, yet they continue to lag behind human-level performance. In-contex

Collaborative Contextual Bayesian Optimization

arXiv:2604.18912v1 Announce Type: new Abstract: Discovering optimal designs through sequential data collection is essential in many real-world applications. While Bayesian Optimization (BO) has achiev

Conditional Diffusion Modeling with Attention for Probabilistic Battery Capacity Prediction under Real-World Condition

arXiv:2510.17414v2 Announce Type: replace Abstract: Accurate prediction of lithium-ion battery capacity and its associated uncertainty is essential for reliable battery management but remains challeng

Contrast Security integrates ADR with Google Security Operations for runtime app visibility in the SOC

Application security startup Contrast Security Inc. today announced a new integration that pipes runtime application telemetry from its Application Detection and Response platform directly into Google

applicationssiliconangle

Courier Health, which develops an AI-powered biopharma platform for managing the end-to-end patient experience, raised a $50M Series B led by Oak HC/FT (Heather Landi/Fierce Healthcare)

Heather Landi / Fierce Healthcare: Courier Health, which develops an AI-powered biopharma platform for managing the end-to-end patient experience, raised a $50M Series B led by Oak HC/FT — Oak HC/FT N

applicationstechmeme

Enabling Vibration-Based Gesture Recognition on Everyday Furniture via Energy-Efficient FPGA Implementation of 1D Convolutional Networks

arXiv:2510.23156v2 Announce Type: replace-cross Abstract: The growing demand for smart home interfaces has increased interest in non-intrusive sensing methods like vibration-based gesture recognition.

Evaluating Histogram Matching for Robust Deep learning-Based Grapevine Disease Detection

arXiv:2604.19510v1 Announce Type: new Abstract: Variability in illumination is a primary factor limiting deep learning robustness for field-based plant disease detection. This study evaluates Histogra

applicationsarxiv-cs-cv

Every system that was regulated, either explicitly or implicitly, by the fact that they were effortful for humans (letters of recommendation…

Every system that was regulated, either explicitly or implicitly, by the fact that they were effortful for humans (letters of recommendation, lawsuits, government filings, essays) will break. 🚨New pre

Excited to share our work on production-ready W4A8 inference, now integrated in vLLM! By combining 4-bit weights (low memory) with 8-bit act…

Excited to share our work on production-ready W4A8 inference, now integrated in vLLM! By combining 4-bit weights (low memory) with 8-bit activations (high compute), we hit the sweet spot for both deco

applicationscohere--x

Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation

arXiv:2604.19678v1 Announce Type: new Abstract: Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that

applicationsarxiv-cs-cl

FG^2-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control

arXiv:2604.19021v1 Announce Type: new Abstract: Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advanc

Formally Verified Patent Analysis via Dependent Type Theory: Machine-Checkable Certificates from a Hybrid AI + Lean 4 Pipeline

arXiv:2604.18882v1 Announce Type: new Abstract: We present a formally verified framework for patent analysis as a hybrid AI + Lean 4 pipeline. The DAG-coverage core (Algorithm 1b) is fully machine-ver

From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems

arXiv:2604.19663v1 Announce Type: cross Abstract: Counterfactual explanations (CEs) provide an intuitive way to understand recommender systems by identifying minimal modifications to user-item interac

GPT-ImageGen-2 did this in one shot, with just the prompt 'turn all of Tennyson's Ulysses into a comic, across as many pages as needed. make…

GPT-ImageGen-2 did this in one shot, with just the prompt 'turn all of Tennyson's Ulysses into a comic, across as many pages as needed. make it great, include the full text' 10 pages, though it did us

Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

arXiv:2512.00716v2 Announce Type: replace-cross Abstract: Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common

Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling

arXiv:2604.18753v1 Announce Type: cross Abstract: An active challenge in developing multimodal machine learning (ML) models for healthcare is handling missing modalities during training and deployment

How Sabre turned x86 efficiency into AI investment

As AI inference demand surges and enterprise compute budgets buckle under expanding workloads, x86 efficiency has emerged as one of the most powerful — and underutilized — levers in cloud financial ma

applicationssiliconangle

Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning

arXiv:2604.18862v1 Announce Type: cross Abstract: Bug reports, encompassing a wide range of bug types, are crucial for maintaining software quality. However, the increasing complexity and volume of bu

IMPACT: Importance-Aware Activation Space Reconstruction

arXiv:2507.03828v4 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance across diverse domains but remain difficult to deploy in resource-constrained environments d

Implicit Neural Field-Based Process Planning for Multi-Axis Manufacturing: Direct Control over Collision Avoidance and Toolpath Geometry

arXiv:2511.17578v2 Announce Type: replace Abstract: Existing curved-layer-based process planning methods for multi-axis manufacturing address collisions only indirectly and generate toolpaths in a pos

applicationsarxiv-cs-ro

InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement

arXiv:2604.19673v1 Announce Type: new Abstract: Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, ye

applicationsarxiv-cs-cv

IoT in Manufacturing: Strategy, Components, Use Cases, and Challenges

This article explores the implementation of Internet of Things technology in manufacturing environments, covering strategic approaches, key hardware and software components, practical applications acr

applicationsdatabricks

Joint Magnetometer-IMU Calibration via Maximum A Posteriori Estimation

arXiv:2505.16662v4 Announce Type: replace Abstract: This paper presents a new method for jointly calibrating a magnetometer and inertial measurement unit (IMU), focusing on balancing calibration accur

applicationsarxiv-cs-ro

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

arXiv:2604.19028v1 Announce Type: new Abstract: One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face

Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects

arXiv:2601.03442v4 Announce Type: replace-cross Abstract: Inspired by the success of performing multiple local optimization steps between communication rounds in federated learning, incorporating such

Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes

arXiv:2604.19318v1 Announce Type: new Abstract: Multi-view crowd tracking estimates each person's tracking trajectories on the ground of the scene. Recent research works mainly rely on CNNs-based mult

applicationsarxiv-cs-cv

Multimodal Data Integration: Production Architectures for Healthcare AI

This Databricks resource discusses production-ready architectural approaches for integrating multimodal data (structured, unstructured, images, text, etc.) in healthcare AI systems. It likely covers b

applicationsdatabricks

Nearly perfect (if unnerving). This is first shot, and the only real issue is the double hour hand.

This post discusses an AI-generated image that is remarkably realistic with only minor flaws, specifically noting that the most noticeable error is a doubled hour hand on a clock face. Ethan Mollick u

New court ruling blocks many of the government's anti-renewable policies

A federal judge in Massachusetts struck down several Trump administration actions slowing down clean energy development, including a requirement that all solar and wind projects on federal lands and w

applicationsars-technica

New Technical Report from @EkagraRanjan: Contrary to what you might expect, MoE-based LLMs make speculative decoding even more effective. Re…

New Technical Report from @EkagraRanjan: Contrary to what you might expect, MoE-based LLMs make speculative decoding even more effective. Read more on our blog: Ever wondered how Speculative Decoding

applicationscohere--x

On Temperature-Constrained Non-Deterministic Machine Translation: Potential and Evaluation

arXiv:2601.13729v2 Announce Type: replace Abstract: In recent years, the non-deterministic properties of language models have garnered considerable attention and have shown a significant influence on

applicationsarxiv-cs-cl

ParamBoost: Gradient Boosted Piecewise Cubic Polynomials

arXiv:2604.18864v1 Announce Type: new Abstract: Generalized Additive Models (GAMs) can be used to create non-linear glass-box (i.e. explicitly interpretable) models, where the predictive function is f

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption

arXiv:2510.18333v2 Announce Type: replace-cross Abstract: Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap st

applicationsarxiv-cs-cl

Position: No Retroactive Cure for Infringement during Training

arXiv:2604.18649v1 Announce Type: cross Abstract: As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on post-hoc mitigation -- especially mach

PREF-XAI: Preference-Based Personalized Rule Explanations of Black-Box Machine Learning Models

arXiv:2604.19684v1 Announce Type: new Abstract: Explainable artificial intelligence (XAI) has predominantly focused on generating model-centric explanations that approximate the behavior of black-box

Prompt to Pwn: Automated Exploit Generation for Smart Contracts

arXiv:2508.01371v3 Announce Type: replace-cross Abstract: Smart contracts are important for digital finance, yet they are hard to patch once deployed. Prior work has mainly explored LLMs for smart con

Quantum Non-Linear Bandit Optimization

arXiv:2503.03023v2 Announce Type: replace Abstract: We study non-linear bandit optimization where the learner maximizes a black-box function with zeroth order function oracle, which has been successfu

Reduced-Order Surrogates for Forced Flexible Mesh Coastal-Ocean Models

arXiv:2602.05416v2 Announce Type: replace-cross Abstract: While proper orthogonal decomposition (POD)-based surrogates are widely explored for hydrodynamic applications, the use of Koopman autoencoder

RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian

arXiv:2604.19593v1 Announce Type: cross Abstract: The importance of clear and correct text in legal documents cannot be understated, and, consequently, a grammatical error correction tool meant to ass

S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

arXiv:2604.19072v1 Announce Type: cross Abstract: Semi-supervised learning with manifold regularization is a classical framework for jointly learning from both labeled and unlabeled data, where the ke