Content Feed

The latest content from across the network

Ranked Latest Top this week
[2603.28583] Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
Llms

[2603.28583] Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering

Abstract page for arXiv paper 2603.28583: Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering

arXiv - AI · 4 min ·
[2603.28594] Detection of Adversarial Attacks in Robotic Perception
Machine Learning

[2603.28594] Detection of Adversarial Attacks in Robotic Perception

Abstract page for arXiv paper 2603.28594: Detection of Adversarial Attacks in Robotic Perception

arXiv - AI · 3 min ·
[2603.28561] Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems
Llms

[2603.28561] Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems

Abstract page for arXiv paper 2603.28561: Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aeri...

arXiv - AI · 4 min ·
[2603.28555] Domain-Invariant Prompt Learning for Vision-Language Models
Llms

[2603.28555] Domain-Invariant Prompt Learning for Vision-Language Models

Abstract page for arXiv paper 2603.28555: Domain-Invariant Prompt Learning for Vision-Language Models

arXiv - AI · 3 min ·
[2603.28498] MRI-to-CT synthesis using drifting models
Machine Learning

[2603.28498] MRI-to-CT synthesis using drifting models

Abstract page for arXiv paper 2603.28498: MRI-to-CT synthesis using drifting models

arXiv - AI · 4 min ·
[2603.28488] Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification
Llms

[2603.28488] Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification

Abstract page for arXiv paper 2603.28488: Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Cl...

arXiv - AI · 3 min ·
[2603.28371] Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure
Llms

[2603.28371] Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure

Abstract page for arXiv paper 2603.28371: Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure

arXiv - AI · 4 min ·
[2603.28474] CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains
Computer Vision

[2603.28474] CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains

Abstract page for arXiv paper 2603.28474: CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on...

arXiv - AI · 4 min ·
[2603.28431] GeoHCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting
Machine Learning

[2603.28431] GeoHCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

Abstract page for arXiv paper 2603.28431: GeoHCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting

arXiv - AI · 3 min ·
[2603.28429] AceleradorSNN: A Neuromorphic Cognitive System Integrating Spiking Neural Networks and DynamicImage Signal Processing on FPGA
Machine Learning

[2603.28429] AceleradorSNN: A Neuromorphic Cognitive System Integrating Spiking Neural Networks and DynamicImage Signal Processing on FPGA

Abstract page for arXiv paper 2603.28429: AceleradorSNN: A Neuromorphic Cognitive System Integrating Spiking Neural Networks and DynamicI...

arXiv - AI · 3 min ·
[2603.28251] DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
Llms

[2603.28251] DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning

Abstract page for arXiv paper 2603.28251: DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reaso...

arXiv - AI · 4 min ·
[2603.28421] Learning unified control of internal spin squeezing in atomic qudits for magnetometry
Ai Infrastructure

[2603.28421] Learning unified control of internal spin squeezing in atomic qudits for magnetometry

Abstract page for arXiv paper 2603.28421: Learning unified control of internal spin squeezing in atomic qudits for magnetometry

arXiv - AI · 4 min ·
[2603.28405] EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
Machine Learning

[2603.28405] EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

Abstract page for arXiv paper 2603.28405: EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

arXiv - AI · 4 min ·
[2603.28378] Membership Inference Attacks against Large Audio Language Models
Llms

[2603.28378] Membership Inference Attacks against Large Audio Language Models

Abstract page for arXiv paper 2603.28378: Membership Inference Attacks against Large Audio Language Models

arXiv - AI · 3 min ·
[2603.28376] Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Machine Learning

[2603.28376] Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

Abstract page for arXiv paper 2603.28376: Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

arXiv - AI · 4 min ·
[2603.28333] Integrating Multimodal Large Language Model Knowledge into Amodal Completion
Llms

[2603.28333] Integrating Multimodal Large Language Model Knowledge into Amodal Completion

Abstract page for arXiv paper 2603.28333: Integrating Multimodal Large Language Model Knowledge into Amodal Completion

arXiv - AI · 4 min ·
[2603.28345] Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Boundary in LLM-Integrated Code
Llms

[2603.28345] Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Boundary in LLM-Integrated Code

Abstract page for arXiv paper 2603.28345: Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Boundary in LLM-Integrate...

arXiv - AI · 4 min ·
[2603.28325] Building evidence-based knowledge graphs from full-text literature for disease-specific biomedical reasoning
Llms

[2603.28325] Building evidence-based knowledge graphs from full-text literature for disease-specific biomedical reasoning

Abstract page for arXiv paper 2603.28325: Building evidence-based knowledge graphs from full-text literature for disease-specific biomedi...

arXiv - AI · 3 min ·
[2603.28317] Mapping data literacy trajectories in K-12 education

[2603.28317] Mapping data literacy trajectories in K-12 education

Abstract page for arXiv paper 2603.28317: Mapping data literacy trajectories in K-12 education

arXiv - AI · 3 min ·
[2603.28306] Self++: Co-Determined Agency for Human--AI Symbiosis in Extended Reality
Ai Agents

[2603.28306] Self++: Co-Determined Agency for Human--AI Symbiosis in Extended Reality

Abstract page for arXiv paper 2603.28306: Self++: Co-Determined Agency for Human--AI Symbiosis in Extended Reality

arXiv - AI · 4 min ·