Search: “models”

GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback

arXiv:2502.18414v2 Announce Type: replace Abstract: Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabe

applicationsarxiv-cs-cl

Safety

Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting

DGX agent

arXiv:2605.03163v1 Announce Type: new Abstract: Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlin

safetyarxiv-cs-lg

6 May 2026

Governing What the EU AI Act Excludes: Accountability for Autonomous AI Agents in Smart City Critical Infrastructure

arXiv:2605.01091v1 Announce Type: cross Abstract: When a traffic signal controller adjusts green phases and a grid manager curtails power on the same corridor, each system may comply with its own obli

HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness

arXiv:2605.02396v1 Announce Type: new Abstract: Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarka

Human-in-the-Loop Uncertainty Analysis in Self-Adaptive Robots Using LLMs

arXiv:2605.02983v1 Announce Type: new Abstract: Self-adaptive robots operate in dynamic, unpredictable environments where unaddressed uncertainties can lead to safety violations and operational failur

safetyarxiv-cs-ro

Industry

Inside IBM Think: theCUBE’s analyst-led coverage airs May 12

When it comes to artificial intelligence, enterprises want speed, lower cost and security. For IBM Corp., these are the value points it wants to provide for its hybrid AI customers. The computing gian

industrysiliconangle

Instance-Level Costs for Nuanced Classifier Evaluation

arXiv:2605.03135v1 Announce Type: new Abstract: Standard classification treats all errors equally, but in content moderation, medical screening, and safety-critical applications, mistakes on clear-cut

safetyarxiv-cs-lg

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy

arXiv:2507.02974v3 Announce Type: replace-cross Abstract: As major progress in LLM-based long-form text generation enables paradigms such as retrieval-augmented generation (RAG) and inference-time sca

KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation

arXiv:2605.01582v1 Announce Type: cross Abstract: Authoritative competency frameworks such as ESCO, ROME, and O*NET are essential for aligning education with labor market needs, yet their technical co

applicationsarxiv-cs-ai

Learning Generalizable Action Representations via Pre-training AEMG

arXiv:2605.03462v1 Announce Type: new Abstract: A fundamental role in decoding human motor intent and enabling intuitive human-computer interaction is played by electromyography (EMG). However, its ge

LLMs Should Not Yet Be Credited with Decision Explanation

arXiv:2605.01164v1 Announce Type: new Abstract: This position paper argues that LLMs should not yet be credited with decision explanation. This matters because recent work increasingly treats accurate

researcharxiv-cs-ai

Logic-Constrained Shortest Paths for Flight Planning

arXiv:2412.13235v4 Announce Type: replace Abstract: The logic-constrained shortest path problem (LCSPP) combines a one-to-one shortest path problem with satisfiability constraints imposed on the routi

MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding

arXiv:2605.03398v1 Announce Type: new Abstract: Video Temporal Grounding (VTG) faces a cross-modal semantic gap that often leads to background features being incorrectly aligned with the query, while

local-aiarxiv-cs-cv

MindMelody: A Closed-Loop EEG-Driven System for Personalized Music Intervention

arXiv:2605.01235v1 Announce Type: cross Abstract: Driven by the escalating global burden of mental health conditions, music-based interventions have attracted significant attention as a non-invasive,

local-aiarxiv-cs-ai

Tutorials

Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items

arXiv:2507.22268v3 Announce Type: replace-cross Abstract: We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purcha

tutorialsarxiv-cs-ai

NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science

arXiv:2605.02092v1 Announce Type: new Abstract: The automation of scientific research workflows has emerged as a transformative frontier in artificial intelligence, yet existing autonomous research ag

NucEval: A Robust Evaluation Framework for Nuclear Instance Segmentation

arXiv:2605.03144v1 Announce Type: new Abstract: In computational pathology, nuclear instance segmentation is a fundamental task with many downstream clinical applications. With the advent of deep lear

researcharxiv-cs-cv

Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback

arXiv:2506.14067v4 Announce Type: replace Abstract: As interactive generative systems are increasingly deployed in real-world applications, their tendency to generate unreliable or false responses rai

applicationsarxiv-cs-lg

Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes

arXiv:2605.03921v1 Announce Type: new Abstract: We study the (arepsilon, elta)-PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finit

safetyarxiv-cs-lg

Industry

Our team cares. A lot.

industrycristobal-valenzuela--x

Our team cares. A lot. Appreciation post for @runwayml. In their Creative Partner Program. Not paid to post. Genuine respect for what they hand creators every month: → Solid monthly credit allotment →

Partial Effective Information Decomposition for Synergistic Causality

arXiv:2605.03267v1 Announce Type: cross Abstract: Causality is a central topic in scientific inquiry, yet for complex systems, the identification and analysis of synergistic causation remain a challen

PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics

arXiv:2605.03548v1 Announce Type: new Abstract: Reconstructing PDE-governed fields from sparse and irregular measurements is challenging due to their ill-posed nature. Deterministic surrogates are tra

Tutorials

Physically Guided Visual Mass Estimation from a Single RGB Image

arXiv:2601.20303v2 Announce Type: replace Abstract: Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of

tutorialsarxiv-cs-cv

Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics

arXiv:2605.01280v1 Announce Type: cross Abstract: This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic founda

researcharxiv-cs-ai

Practical Limits of Autonomous Test Repair: A Multi-Agent Case Study with LLM-Driven Discovery and Self-Correction

arXiv:2605.01471v1 Announce Type: cross Abstract: Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study o

PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework

arXiv:2605.02940v1 Announce Type: new Abstract: The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation.

agentsarxiv-cs-lg

psifx -- Psychological and Social Interactions Feature Extraction Package

arXiv:2407.10266v5 Announce Type: replace Abstract: psifx is a plug-and-play multi-modal feature extraction toolkit, aiming to facilitate and democratize the use of state-of-the-art machine learning t

really cool work by the Harvey team, excited to partner with them to push forward research on designing + understanding agents across Long H…

applicationsharrison-chase--x

really cool work by the Harvey team, excited to partner with them to push forward research on designing + understanding agents across Long Horizon Legal work the first peak I got at LAB was 'woah this

Refining Compositional Diffusion for Reliable Long-Horizon Planning

arXiv:2605.03075v1 Announce Type: cross Abstract: Compositional diffusion planning generates long-horizon trajectories by stitching together overlapping short-horizon segments through score compositio

local-aiarxiv-cs-lg

Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning

arXiv:2605.01834v1 Announce Type: cross Abstract: Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, relianc

researcharxiv-cs-ai

Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence

arXiv:2605.03650v1 Announce Type: new Abstract: The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object repres

researcharxiv-cs-cv

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

arXiv:2605.02900v1 Announce Type: cross Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, saf

safetyarxiv-cs-cv

Sheaf-Theoretic Planning: A Categorical Foundation for Resilient Multi-Agent Autonomous Systems

arXiv:2605.01879v1 Announce Type: new Abstract: The challenge of engineering autonomous agents capable of navigating the stochastic and adversarial nature of the physical world has historically reside

Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization

arXiv:2512.16504v3 Announce Type: replace Abstract: The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition usin

researcharxiv-cs-cv

SOAR: Real-Time Joint Optimization of Order Allocation and Robot Scheduling in Robotic Mobile Fulfillment Systems

arXiv:2605.03842v1 Announce Type: cross Abstract: Robotic Mobile Fulfillment Systems (RMFS) rely on mobile robots for automated inventory transportation, coordinating order allocation and robot schedu

agentsarxiv-cs-ro

Sovereign cloud reshapes enterprise AI deployment strategies

Enterprises are entering a new phase of cloud adoption where flexibility, control and performance are no longer trade-offs but requirements. As AI workloads become more distributed and data-intensive,

applicationssiliconangle

Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention

arXiv:2604.00754v2 Announce Type: replace Abstract: The whole-brain connectome of a fruit fly comprises over 130K neurons connected with a probability of merely 0.02%, yet achieves an average shortest

local-aiarxiv-cs-cl

TabSurv: Adapting Modern Tabular Neural Networks to Survival Analysis

arXiv:2605.03944v1 Announce Type: new Abstract: Survival analysis on tabular data is a well-studied problem. However, existing deep learning methods are often highly task-specific, which can limit the

applicationsarxiv-cs-lg

The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence

arXiv:2408.12622v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet resea

safetyarxiv-cs-lg

Hardware

The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm

arXiv:2505.16932v5 Announce Type: replace-cross Abstract: Computing the polar decomposition and the related matrix sign function has been a well-studied problem in numerical analysis for decades. Rece

hardwarearxiv-cs-cl

Toggling stiffness via multistability

arXiv:2510.09511v2 Announce Type: replace-cross Abstract: Variable stiffness is a key capability in biological and robotic systems, enabling adaptive interaction across tasks and environments. Mechani

researcharxiv-cs-ro

Tracing Like a Clinician: Anatomy-Guided Spatial Priors for Cephalometric Landmark Detection

arXiv:2605.03358v1 Announce Type: new Abstract: When orthodontists trace cephalometric radiographs, they follow a structured workflow: identify the soft tissue profile, partition the skull into anatom

safetyarxiv-cs-cv

Transformers with Selective Access to Early Representations

arXiv:2605.03953v1 Announce Type: cross Abstract: Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low

Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents

arXiv:2605.01329v1 Announce Type: new Abstract: In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social coope

Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference

arXiv:2605.03379v1 Announce Type: cross Abstract: Repeated sampling is a standard way to spend test-time compute, but its benefit is controlled by the latent distribution of correctness across example

Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration

arXiv:2605.01257v1 Announce Type: new Abstract: Large-scale GPS trajectory data offer rich observations of human mobility, yet assigning trip purposes to detected stops remains challenging due to the

Uncovering and Understanding FPR Manipulation Attack in Industrial IoT Networks

arXiv:2601.14505v2 Announce Type: replace-cross Abstract: In the network security domain, due to practical issues -- including imbalanced data and heterogeneous legitimate network traffic -- adversari

Unsupervised Monocular Road Segmentation for Autonomous Driving via Scene Geometry

arXiv:2510.16790v2 Announce Type: replace Abstract: This paper presents a fully unsupervised approach for binary road segmentation (road vs. non-road), eliminating the reliance on costly manually labe

local-aiarxiv-cs-cv