All entries

A Comparative Study of Rule-Based and Data-Driven Approaches in Industrial Monitoring

arXiv:2509.15848v2 Announce Type: replace Abstract: Industrial monitoring systems, especially when deployed in Industry 4.0 environments, are experiencing a shift in paradigm from traditional rule-bas

safetyarxiv-cs-ai

Research

A Conflict-Aware Penalty and Statistical Loss Framework for Balancing Modalities and Enhancing Stability in Multimodal Sentiment Analysis

DGX agent

arXiv:2605.28575v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) fuses text, acoustic, and visual streams to infer sentiment. Because pre-trained text encoders are far more expressi

researcharxiv-cs-ai

28 May 2026

A Digital Twin Framework for Virtual Visuo-Haptic Teleoperation of Complex-Shaped Optical Microrobots

arXiv:2605.28448v1 Announce Type: new Abstract: Optical tweezers (OT) provide piconewton-scale manipulation for delicate biomedical tasks, where visuo-haptic feedback can improve operator awareness by

researcharxiv-cs-ro

A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons

arXiv:2605.27461v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies have shown promising manipulation capabilities, yet their practical impact is often limited by the reliability dem

safetyarxiv-cs-ro

A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test

arXiv:2605.27789v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems are often compared by asking a large language model (LLM) judge which answer is better. For multi-hop RAG,

A Fresh Look at Lamarckian Evolution and the Baldwin Effect

arXiv:2605.28703v1 Announce Type: cross Abstract: Baldwinian and Lamarckian evolution have existed for a long time in evolutionary algorithms (EAs) without ever dominating the academic literature or p

A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks

arXiv:2605.28578v1 Announce Type: new Abstract: We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which

local-aiarxiv-cs-lg

Agents

a hot (cold at this point?) take that lead us to build this: every agent in the future will need a sandbox to connect to writing/executing c…

a hot (cold at this point?) take that lead us to build this: every agent in the future will need a sandbox to connect to writing/executing code is not just for coding agents! is useful for all sorts o

agentsharrison-chase--x

Tools

A humanist view of the computer user, and a presumption that computers should enhance our abilities!

This post presents a humanist perspective on human-computer interaction, arguing that computers should be designed as tools to augment and enhance human capabilities rather than replace or diminish th

toolslinus-lee--x

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

arXiv:2605.28556v1 Announce Type: new Abstract: As agent capabilities advance, existing benchmarks, such as au^2-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remain

A Methodology to Assess Power Modeling in Energy-Aware Federated Learning on Heterogeneous Mobile Devices

arXiv:2605.27601v1 Announce Type: cross Abstract: Estimating CPU power on heterogeneous ARM-based commodity devices is challenging due to limited access to CPU's voltage domains. As a result, state-of

researcharxiv-cs-lg

A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models

arXiv:2605.28563v1 Announce Type: cross Abstract: Evaluating foundation models under appropriate adaptation settings is essential for understanding the quality and transferability of the learned repre

A Multiscale Kinetic Framework for Image Segmentation: From Particle Systems to Continuum Models

arXiv:2605.28619v1 Announce Type: new Abstract: In this work, we present a multiscale kinetic framework for consensus-based image segmentation. By interpreting an image as a system of interacting part

A New Era of Innovation: Google Research at I/O 2026

Google Research at I/O 2026 showcased new Gemini AI models including Gemini Omni, which can create content from any input starting with video, and Gemini 3.5 Flash, combining frontier intelligence wit

researchgoogle-research

A new semantically annotated corpus with syntactic-semantic and cross-lingual senses

arXiv:2605.28494v1 Announce Type: new Abstract: We describe a new sense-tagged corpus for word sense disambiguation. The corpus is constituted of instances of 20 French polysemous verbs. Each verb ins

researcharxiv-cs-cl

A novel ordinal multi-view aggregation scheme for oak defoliation

arXiv:2605.28151v1 Announce Type: new Abstract: Forest decline driven by climate and biotic stressors threatens ecosystem functioning, making accurate monitoring of tree health essential. In this work

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving

arXiv:2605.27763v1 Announce Type: new Abstract: Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment

local-aiarxiv-cs-lg

A Patient-Specific Pulmonary Arterial Tree Digital Twin to Extract Pulmonary Embolism Biomarkers

arXiv:2605.28217v1 Announce Type: new Abstract: Pulmonary embolism, the obstruction of a pulmonary artery by a blood clot, is one of the leading causes of acute cardiovascular syndrome. In clinical pr

A Policy-Driven Runtime Layer for Agentic LLM Serving

arXiv:2605.27744v1 Announce Type: new Abstract: Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agen

safetyarxiv-cs-ai

A Query Engine for the Agents

arXiv:2605.27785v1 Announce Type: new Abstract: The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it,

Industry

A respectable port of Age of Empires II: Definitive Edition invades macOS

Age of Empires II: Definitive Edition became available on Steam for macOS on May 28, 2026. The port by Feral Interactive includes three expansions and 4K visuals, with Apple Silicon required. Feral In

industryars-technica

A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learning

arXiv:2605.27884v1 Announce Type: new Abstract: City-wide traffic forecasting is important for congestion management, route guidance, and intelligent transportation systems, but accurate prediction re

Applications

A self-supervised learning approach to deep filter banks for texture recognition

arXiv:2605.27843v1 Announce Type: new Abstract: An important challenge in texture recognition is the limited amount of data for training frequently found in real-world applications. In computer vision

applicationsarxiv-cs-cv

Applications

A Sheaf-Theoretic and Topological Perspective on Complex Network Modeling and Attention Mechanisms in Graph Neural Models

arXiv:2601.21207v3 Announce Type: replace-cross Abstract: Combinatorial and topological structures, such as graphs, simplicial complexes, and cell complexes, form the foundation of geometric and topol

applicationsarxiv-cs-ai

A Simple State Space Model Excels at Multivariate Time Series Classification

model-releasesarxiv-cs-lg

arXiv:2605.27406v1 Announce Type: new Abstract: Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating

A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control

arXiv:2511.02398v2 Announce Type: replace Abstract: We present a novel decentralized algorithm for coverage control in unknown spatial environments modeled by Gaussian Processes (GPs). To trade-off be

local-aiarxiv-cs-lg

A Structural Theory of Position Bias in Transformers

arXiv:2602.16837v2 Announce Type: replace Abstract: Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This

safetyarxiv-cs-lg

A Surveillance Evasion Game with Continuous Sensor Redeployment via Bilevel Optimization

arXiv:2605.27917v1 Announce Type: new Abstract: Uncrewed Aerial Systems (UASs) have become a growing threat to the security of critical infrastructure, exploiting spatiotemporal gaps in sensor perimet

researcharxiv-cs-ro

A Survey on Event-based Optical Marker Systems

arXiv:2504.20736v2 Announce Type: replace-cross Abstract: The advent of event-based cameras, with their low latency, high dynamic range, and reduced power consumption, marked a turning point in machin

A Systematic Evaluation of Retrieval-Augmented Generation and Language Models for Space Operations

arXiv:2605.27444v1 Announce Type: cross Abstract: The rapid expansion of space activities has led to an unprecedented accumulation of technical documentation, operational guidelines, and scientific li

Agents

A TLDR on LangSmith Sandboxes: ✅ Hardware-virtualized microVM ✅ Kernel-isolated from your services + other sandboxes. ✅ Same SDK and API key…

A TLDR on LangSmith Sandboxes: ✅ Hardware-virtualized microVM ✅ Kernel-isolated from your services + other sandboxes. ✅ Same SDK and API key as the rest of LangSmith ✅ Any framework or custom code ✅ N

agentsharrison-chase--x

A tree interpretation of arc standard dependency derivation

arXiv:2603.27459v2 Announce Type: replace Abstract: Arc-standard derivations over projective dependency trees can be interpreted as the incremental construction of lexicalized ordered trees with conti

researcharxiv-cs-cl

A Unified Framework for the Evaluation of LLM Agentic Capabilities

arXiv:2605.27898v1 Announce Type: new Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores

Hardware

A Unified Structured Query Understanding Framework for Industrial Semantic Search

arXiv:2605.27441v1 Announce Type: cross Abstract: Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components. While indiv

hardwarearxiv-cs-lg

A very cool model for the GPU poor bros Trained on an ungodly amount of tokens for a 8b a1b model Gonna be super fast excited to try this ou…

This post announces an 8-9 billion parameter language model optimized for efficiency and speed, trained on a very large token dataset, and positioned as accessible for users with limited GPU resources

local-aiclem-delangue--x

Applications

A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG

arXiv:2605.28112v1 Announce Type: cross Abstract: Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because raw data remain local. As a result, routing

applicationsarxiv-cs-cl

ABot-OCR Technical Report

arXiv:2605.27978v1 Announce Type: new Abstract: We introduce ABot-OCR, an end-to-end vision-language model that transcribes a page image directly into clean Markdown in a single forward pass. By doing

Industry

Abundance is coming. Actual, ridiculous, post scarcity abundance. The bottleneck was always (not enough) intelligence. That bottleneck just …

Elon Musk posits that technological abundance and post-scarcity economics are forthcoming, with artificial intelligence advancement being the primary limiting factor that is now being overcome. He arg

industryelon-musk--x

Accelerating Diffusion Sampling via Exploiting Local Transition Coherence

arXiv:2503.09675v3 Announce Type: replace Abstract: Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the

Accelerating Natural Gradient Descent for PINNs with Randomized Numerical Linear Algebra

arXiv:2505.11638v4 Announce Type: replace-cross Abstract: Natural Gradient Descent (NGD) has emerged as a promising optimization algorithm for training neural network-based solvers for partial differe

researcharxiv-cs-lg

Accelerating Reinforcement Learning Training Using Simulation Surrogate Models

arXiv:2605.27556v1 Announce Type: cross Abstract: High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of

researcharxiv-cs-lg

Accelerating Robot Path Planning via Connectivity-Preserving Region Proposal Network

arXiv:2605.28362v1 Announce Type: new Abstract: Mobile robot path planning methods are often constrained by vast search spaces, resulting in latency in samplingbased algorithms. Learning-based approac

local-aiarxiv-cs-ro

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection

arXiv:2605.28664v1 Announce Type: cross Abstract: Safety detection models require examples of HHH (Helpful, Harmless, Honest)-violating outputs for robust generalization, however such examples are sca

safetyarxiv-cs-cl

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates

model-releasesarxiv-cs-cl

arXiv:2605.28440v1 Announce Type: new Abstract: DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loo

AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning

arXiv:2410.04498v2 Announce Type: replace Abstract: In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on

safetyarxiv-cs-lg

AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers

arXiv:2605.27465v1 Announce Type: cross Abstract: The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant

Adapting, Fast and Slow: On Few-Shot Transportability of Compositions

arXiv:2512.22777v2 Announce Type: replace-cross Abstract: Generalization across domains requires stable structure that links the source and target distributions. Building on causal transportability th

Agents

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

arXiv:2605.22166v2 Announce Type: replace Abstract: LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feed

agentsarxiv-cs-ai