Content Feed

The latest content from across the network

Ranked Latest Top this week
[2603.27624] Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling
Machine Learning

[2603.27624] Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

Abstract page for arXiv paper 2603.27624: Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

arXiv - AI · 4 min ·
[2603.27593] STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
Llms

[2603.27593] STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

Abstract page for arXiv paper 2603.27593: STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

arXiv - AI · 3 min ·
[2603.27563] InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection
Ai Agents

[2603.27563] InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection

Abstract page for arXiv paper 2603.27563: InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection

arXiv - AI · 4 min ·
[2603.27557] A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators
Machine Learning

[2603.27557] A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators

Abstract page for arXiv paper 2603.27557: A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based G...

arXiv - AI · 4 min ·
[2603.27550] Drag or Traction: Understanding How Designers Appropriate Friction in AI Ideation Outputs
Machine Learning

[2603.27550] Drag or Traction: Understanding How Designers Appropriate Friction in AI Ideation Outputs

Abstract page for arXiv paper 2603.27550: Drag or Traction: Understanding How Designers Appropriate Friction in AI Ideation Outputs

arXiv - AI · 4 min ·
[2603.27541] A Novel Immune Algorithm for Multiparty Multiobjective Optimization

[2603.27541] A Novel Immune Algorithm for Multiparty Multiobjective Optimization

Abstract page for arXiv paper 2603.27541: A Novel Immune Algorithm for Multiparty Multiobjective Optimization

arXiv - AI · 4 min ·
[2603.27539] Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness
Llms

[2603.27539] Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness

Abstract page for arXiv paper 2603.27539: Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination P...

arXiv - AI · 4 min ·
[2603.27513] Understanding Semantic Perturbations on In-Processing Generative Image Watermarks
Machine Learning

[2603.27513] Understanding Semantic Perturbations on In-Processing Generative Image Watermarks

Abstract page for arXiv paper 2603.27513: Understanding Semantic Perturbations on In-Processing Generative Image Watermarks

arXiv - AI · 4 min ·
[2603.27524] Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs
Ai Agents

[2603.27524] Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

Abstract page for arXiv paper 2603.27524: Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

arXiv - AI · 4 min ·
[2603.27533] Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation
Machine Learning

[2603.27533] Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation

Abstract page for arXiv paper 2603.27533: Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation

arXiv - AI · 3 min ·
[2603.27517] A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework
Llms

[2603.27517] A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework

Abstract page for arXiv paper 2603.27517: A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework

arXiv - AI · 4 min ·
[2603.27494] Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs
Llms

[2603.27494] Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Abstract page for arXiv paper 2603.27494: Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gap...

arXiv - AI · 4 min ·
[2603.27492] Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding
Machine Learning

[2603.27492] Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding

Abstract page for arXiv paper 2603.27492: Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding

arXiv - AI · 4 min ·
[2603.27490] AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Llms

[2603.27490] AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

Abstract page for arXiv paper 2603.27490: AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

arXiv - AI · 4 min ·
[2603.27460] Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development
Llms

[2603.27460] Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Abstract page for arXiv paper 2603.27460: Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model ...

arXiv - AI · 5 min ·
[2603.27482] Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning
Llms

[2603.27482] Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

Abstract page for arXiv paper 2603.27482: Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Lear...

arXiv - AI · 3 min ·
[2603.27441] Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste Disassembly
Machine Learning

[2603.27441] Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste Disassembly

Abstract page for arXiv paper 2603.27441: Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste ...

arXiv - AI · 4 min ·
[2603.27451] Multi-Agent Dialectical Refinement for Enhanced Argument Classification
Llms

[2603.27451] Multi-Agent Dialectical Refinement for Enhanced Argument Classification

Abstract page for arXiv paper 2603.27451: Multi-Agent Dialectical Refinement for Enhanced Argument Classification

arXiv - AI · 3 min ·
[2603.27435] Improving Attributed Long-form Question Answering with Intent Awareness
Llms

[2603.27435] Improving Attributed Long-form Question Answering with Intent Awareness

Abstract page for arXiv paper 2603.27435: Improving Attributed Long-form Question Answering with Intent Awareness

arXiv - AI · 3 min ·
[2603.27416] Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped Locomotion
Robotics

[2603.27416] Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped Locomotion

Abstract page for arXiv paper 2603.27416: Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadr...

arXiv - AI · 4 min ·