Search: “applications”

Differential-Integral Neural Operator for Long-Term Turbulence Forecasting

model-releasesarxiv-cs-cv

arXiv:2509.21196v3 Announce Type: replace-cross Abstract: Accurately forecasting the long-term evolution of turbulence represents a grand challenge in scientific computing and is crucial for applicati

Safety

Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance

DGX agent

arXiv:2605.18793v1 Announce Type: cross Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing met

safetyarxiv-cs-ai

20 May 2026

Distilling Linearized Behavior for Effective Task Arithmetic

arXiv:2605.18993v1 Announce Type: cross Abstract: Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning thr

Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study

arXiv:2605.20049v1 Announce Type: cross Abstract: As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. Thi

Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance

arXiv:2512.23461v2 Announce Type: replace-cross Abstract: Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values

Entry-level guide to the use of large language models for medical research

arXiv:2410.18856v4 Announce Type: replace Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools c

Fast Tensorization of Neural Networks via Slice-wise Feature Distillation

arXiv:2605.19842v1 Announce Type: new Abstract: We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomp

researcharxiv-cs-lg

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models

arXiv:2410.15362v2 Announce Type: replace-cross Abstract: Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks t

safetyarxiv-cs-ai

FedBiCross: A Bi-Level Optimization Framework to Tackle Non-IID Challenges in Data-Free One-Shot Federated Learning on Medical Data

arXiv:2601.01901v2 Announce Type: replace Abstract: Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, m

researcharxiv-cs-lg

Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings

model-releasesarxiv-cs-cl

arXiv:2507.03122v2 Announce Type: replace-cross Abstract: This study investigates the feasibility and performance of federated learning (FL) for multi-label ICD code classification using clinical note

Hardware

FiLark: a streaming-first software framework for end-to-end exploration, annotation, and algorithm integration in distributed acoustic sensing

arXiv:2605.20132v1 Announce Type: cross Abstract: Distributed acoustic sensing (DAS) systems generate continuous, ultra-high-channel-count data streams at rates that exceed the capabilities of convent

hardwarearxiv-cs-lg

Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG

arXiv:2605.19224v1 Announce Type: new Abstract: Neuroscientists have recently turned to intracranial brain recording methods, like electrocorticography (ECoG), for human experiments because of the fin

researcharxiv-cs-cl

FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding

arXiv:2605.19846v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained

FormalASR: End-to-End Spoken Chinese to Formal Text

arXiv:2605.19266v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems are typically optimized for verbatim transcription, which preserves disfluencies, filler words, and informa

local-aiarxiv-cs-ai

Tutorials

FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

arXiv:2601.18993v2 Announce Type: replace-cross Abstract: Camera redirection aims to replay a dynamic scene from a single monocular video under a user-specified camera trajectory. However, large-angle

tutorialsarxiv-cs-ai

Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation

arXiv:2605.19629v1 Announce Type: cross Abstract: In this paper, we establish Berry-Esseen-type bounds for federated linear stochastic approximation (LSA). Our results provide the first federated Gaus

local-aiarxiv-cs-lg

GenAI-FDIA: Physics-Informed Generative Models for False Data Injection Attacks

arXiv:2605.18873v1 Announce Type: cross Abstract: Training and evaluating false data injection attack (FDIA) detectors for power systems is constrained by data scarcity. Operational grid measurements

General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions

model-releasesarxiv-cs-lg

arXiv:2605.19813v1 Announce Type: new Abstract: We prove a general lower bound for differentially private federated learning protocols with arbitrary public-transcript interactions. The protocol may u

Generative Auto-Bidding with Unified Modeling and Exploration

arXiv:2605.19457v1 Announce Type: new Abstract: Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approa

safetyarxiv-cs-ai

Agents

High-quality generation of dynamic game content via small language models: A proof of concept

arXiv:2601.23206v2 Announce Type: replace Abstract: Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and

agentsarxiv-cs-ai

Industry

How Databricks Genie improves retail personalization

Databricks Genie is a tool designed to enhance personalized retail experiences by leveraging data analytics and AI capabilities. The resource likely explains how retailers can use Genie to analyze cus

industrydatabricks

How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines

model-releasesarxiv-cs-lg

arXiv:2605.18814v1 Announce Type: new Abstract: Trajectory-based data attribution methods estimate the influence of training samples on model predictions by unrolling the training trajectory. They are

How Ramp engineers accelerate code review with Codex

Ramp engineers use OpenAI's Codex to streamline and accelerate their code review process, leveraging AI-assisted code understanding and analysis. The implementation likely demonstrates how Codex helps

model-releasesopenai

Industry

How telecom CFOs can make smarter network capex decisions with AI

Databricks discusses how artificial intelligence can help telecommunications CFOs optimize capital expenditure decisions for network infrastructure by enabling data-driven analysis and predictive mode

industrydatabricks

Hardware

Hyrax: An Extensible Framework for Rapid ML Experimentation and Unsupervised Discovery in the Era of Rubin, Roman, and Euclid

arXiv:2605.18959v1 Announce Type: cross Abstract: The NSF-DOE Vera C. Rubin Observatory, Roman Space Telescope, Euclid, and other next-generation surveys will deliver imaging, spectroscopic, and time-

hardwarearxiv-cs-lg

Agents

Informatica expands agentic AI strategy with headless data services and unified agent governance

In its first major announcement since being acquired by Salesforce Inc., data management vendor Informatica today unveiled a “headless” version of its flagship Intelligent Data Management Cloud, posit

agentssiliconangle

Interpretable Computer Vision for Defect Detection in X-ray Tomography of Aerospace SiC/SiC Composites

arXiv:2605.20159v1 Announce Type: new Abstract: Non-destructive testing of aerospace SiC/SiC composites via X-ray computed tomography (XCT) relies on expert visual assessment, with current workflows o

researcharxiv-cs-cv

Introducing skill bundles:

Nous Research announced a new feature called 'skill bundles,' which likely refers to packaged collections of AI capabilities or competencies that can be grouped together for more efficient deployment

researchnous-research--x

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters

arXiv:2605.19523v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire

Industry

Just tap the Grok logo

This post likely references a user interface feature or instruction related to Grok, the AI assistant developed by xAI (Elon Musk's AI company). The phrase 'just tap the Grok logo' suggests a simple i

industryelon-musk--x

KoRe: Compact Knowledge Representations for Large Language Models

arXiv:2605.20170v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvemen

researcharxiv-cs-cl

Hardware

Lambda partners with Hudson River Trading to power quantitative research and development

Lambda Labs announced a partnership with Hudson River Trading (HRT), a quantitative trading firm, to provide computational infrastructure and GPU resources for HRT's quantitative research and developm

hardwarelambda-labs

Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions

model-releasesarxiv-cs-lg

arXiv:2605.19562v1 Announce Type: cross Abstract: This paper presents a learning-augmented trajectory planning framework for cooperative unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV)

LTX 2.3 IC LoRAs (LipDub and Video Utilities) https://x.com/i/broadcasts/1qKDzPZeLjVJV

LTX 2.3 IC introduces specialized LoRA (Low-Rank Adaptation) modules for video generation, including LipDub functionality for synchronized lip movements and Video Utilities for enhanced video processi

local-aicomfyui--x

MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training

model-releasesarxiv-cs-cl

arXiv:2510.18830v2 Announce Type: replace Abstract: The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their

MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

model-releasesarxiv-cs-cv

arXiv:2511.14159v2 Announce Type: replace Abstract: Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-wo

Neural Operators for Design-Space Surrogate Modeling of Tendon-Actuated Continuum Robots

arXiv:2605.19104v1 Announce Type: cross Abstract: Continuum robots enable dexterous manipulation in constrained environments, but require accurate and efficient models for real-time manipulation and c

OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments

arXiv:2605.18758v1 Announce Type: cross Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction rout

patches allow for trust boundaries > patches separate 'system wants to change state' from 'change is now accepted policy determines what hap…

Patches represent a mechanism for establishing trust boundaries in systems by decoupling the intent to change state from the acceptance and policy-driven implementation of that change. This separation

safetyyohei-nakajima--x

Agents

Personally incredibly exciting at LangChain Labs to lead a focused, applied research effort into Continual Learning. A big prior is in treat…

Personally incredibly exciting at LangChain Labs to lead a focused, applied research effort into Continual Learning. A big prior is in treating the long horizon agent optimization problem as one that

agentsharrison-chase--x

Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise

arXiv:2605.18832v1 Announce Type: cross Abstract: The Transformer is the foundational building block of modern AI, yet offers no principled handling of uncertainty, which is prevalent in real applicat

PRISM-SLAM: Probabilistic Ray-Grounded Inference for Scale-aware Metric SLAM

arXiv:2605.19257v1 Announce Type: new Abstract: Monocular SLAM historically suffers from scale ambiguity and tracking failure in dynamic environments. While recent vision foundation models (VFMs) prov

local-aiarxiv-cs-ro

ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation

model-releasesarxiv-cs-cv

arXiv:2506.05317v3 Announce Type: replace Abstract: Neural rendering has advanced significantly in 3D reconstruction and novel view synthesis, and integrating physics into these frameworks opens new a

Retrieval-Augmented Generation for Natural Language Processing: A Survey

model-releasesarxiv-cs-cl

arXiv:2407.13193v4 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that stor

SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation

arXiv:2605.18913v1 Announce Type: cross Abstract: The U.S. financial system processes approximately 1.3 million interbank transactions daily, yet no system in the reviewed literature models fraud prop

Tools

Scaling Reinforcement Learning at Applied Compute

This article discusses how Applied Compute leverages Modal's infrastructure to scale reinforcement learning workloads, likely covering the technical implementation of distributed RL training, computat

toolsmodal-blog

Set-Valued Policy Learning

arXiv:2605.19830v1 Announce Type: new Abstract: Conventional treatment policies map patient covariates to a single recommended intervention in order to maximize expected clinical outcomes. Although a

safetyarxiv-cs-lg

StableGrad: Backward Scale Control without Batch Normalization

arXiv:2605.19856v1 Announce Type: cross Abstract: Training very deep neural networks requires controlling the propagation of magnitudes across depth. Without such control, activations and gradients ma

local-aiarxiv-cs-ai