Content Feed

The latest content from across the network

Ranked Latest Top this week
[2603.26731] Contextual inference from single objects in Vision-Language models
Llms

[2603.26731] Contextual inference from single objects in Vision-Language models

Abstract page for arXiv paper 2603.26731: Contextual inference from single objects in Vision-Language models

arXiv - AI · 4 min ·
[2603.26729] Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion
Nlp

[2603.26729] Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion

Abstract page for arXiv paper 2603.26729: Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-base...

arXiv - AI · 4 min ·
[2603.26728] SEAR: Schema-Based Evaluation and Routing for LLM Gateways
Llms

[2603.26728] SEAR: Schema-Based Evaluation and Routing for LLM Gateways

Abstract page for arXiv paper 2603.26728: SEAR: Schema-Based Evaluation and Routing for LLM Gateways

arXiv - AI · 3 min ·
[2603.26727] The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating
Computer Vision

[2603.26727] The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating

Abstract page for arXiv paper 2603.26727: The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating

arXiv - AI · 4 min ·
[2603.26726] A Multimodal Deep Learning Framework for Edema Classification Using HCT and Clinical Data
Machine Learning

[2603.26726] A Multimodal Deep Learning Framework for Edema Classification Using HCT and Clinical Data

Abstract page for arXiv paper 2603.26726: A Multimodal Deep Learning Framework for Edema Classification Using HCT and Clinical Data

arXiv - AI · 4 min ·
[2603.26725] Capability Safety as Datalog: A Foundational Equivalence
Nlp

[2603.26725] Capability Safety as Datalog: A Foundational Equivalence

Abstract page for arXiv paper 2603.26725: Capability Safety as Datalog: A Foundational Equivalence

arXiv - AI · 3 min ·
[2603.26722] Brain-inspired AI for Edge Intelligence: a systematic review
Machine Learning

[2603.26722] Brain-inspired AI for Edge Intelligence: a systematic review

Abstract page for arXiv paper 2603.26722: Brain-inspired AI for Edge Intelligence: a systematic review

arXiv - AI · 3 min ·
[2603.26720] SutureAgent: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space
Robotics

[2603.26720] SutureAgent: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space

Abstract page for arXiv paper 2603.26720: SutureAgent: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space

arXiv - AI · 4 min ·
[2603.26718] Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems
Machine Learning

[2603.26718] Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems

Abstract page for arXiv paper 2603.26718: Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems

arXiv - AI · 3 min ·
[2603.26712] On the Carbon Footprint of Economic Research in the Age of Generative AI
Machine Learning

[2603.26712] On the Carbon Footprint of Economic Research in the Age of Generative AI

Abstract page for arXiv paper 2603.26712: On the Carbon Footprint of Economic Research in the Age of Generative AI

arXiv - AI · 4 min ·
[2603.26710] Agentic AI for Human Resources: LLM-Driven Candidate Assessment
Llms

[2603.26710] Agentic AI for Human Resources: LLM-Driven Candidate Assessment

Abstract page for arXiv paper 2603.26710: Agentic AI for Human Resources: LLM-Driven Candidate Assessment

arXiv - AI · 4 min ·
[2603.26707] The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop
Llms

[2603.26707] The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop

Abstract page for arXiv paper 2603.26707: The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedb...

arXiv - AI · 4 min ·
[2603.26704] Deep Learning Multi-Horizon Irradiance Nowcasting: A Comparative Evaluation of Three Methods for Leveraging Sky Images
Machine Learning

[2603.26704] Deep Learning Multi-Horizon Irradiance Nowcasting: A Comparative Evaluation of Three Methods for Leveraging Sky Images

Abstract page for arXiv paper 2603.26704: Deep Learning Multi-Horizon Irradiance Nowcasting: A Comparative Evaluation of Three Methods fo...

arXiv - AI · 4 min ·
[2603.26697] Physicochemical-Neural Fusion for Semi-Closed-Circuit Respiratory Autonomy in Extreme Environments

[2603.26697] Physicochemical-Neural Fusion for Semi-Closed-Circuit Respiratory Autonomy in Extreme Environments

Abstract page for arXiv paper 2603.26697: Physicochemical-Neural Fusion for Semi-Closed-Circuit Respiratory Autonomy in Extreme Environments

arXiv - AI · 4 min ·
[2603.26692] Degrees, Levels, and Profiles of Contextuality

[2603.26692] Degrees, Levels, and Profiles of Contextuality

Abstract page for arXiv paper 2603.26692: Degrees, Levels, and Profiles of Contextuality

arXiv - AI · 3 min ·
[2603.26690] SpatialPoint: Spatial-aware Point Prediction for Embodied Localization

[2603.26690] SpatialPoint: Spatial-aware Point Prediction for Embodied Localization

Abstract page for arXiv paper 2603.26690: SpatialPoint: Spatial-aware Point Prediction for Embodied Localization

arXiv - AI · 4 min ·
[2603.26687] Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain
Robotics

[2603.26687] Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain

Abstract page for arXiv paper 2603.26687: Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain

arXiv - AI · 3 min ·
[2603.26683] LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval
Machine Learning

[2603.26683] LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval

Abstract page for arXiv paper 2603.26683: LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval

arXiv - AI · 4 min ·
[2603.26682] Operationalizing Perceptions of Agent Gender: Foundations and Guidelines
Robotics

[2603.26682] Operationalizing Perceptions of Agent Gender: Foundations and Guidelines

Abstract page for arXiv paper 2603.26682: Operationalizing Perceptions of Agent Gender: Foundations and Guidelines

arXiv - AI · 3 min ·
[2603.26680] AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment
Llms

[2603.26680] AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment

Abstract page for arXiv paper 2603.26680: AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Align...

arXiv - AI · 4 min ·