Content Feed

The latest content from across the network

Ranked Latest Top this week
[2510.18342] ShortcutBreaker: Low-Rank Noisy Bottleneck and Frequency Filtering Block for Multi-Class Unsupervised Anomaly Detection
Machine Learning

[2510.18342] ShortcutBreaker: Low-Rank Noisy Bottleneck and Frequency Filtering Block for Multi-Class Unsupervised Anomaly Detection

Abstract page for arXiv paper 2510.18342: ShortcutBreaker: Low-Rank Noisy Bottleneck and Frequency Filtering Block for Multi-Class Unsupervised Anomaly Detection

arXiv - AI · 4 min ·
[2510.08847] What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
Llms

[2510.08847] What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment

Abstract page for arXiv paper 2510.08847: What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment

arXiv - AI · 4 min ·
[2510.14035] GammaZero: Learning To Guide POMDP Belief Space Search With Graph Representations
Nlp

[2510.14035] GammaZero: Learning To Guide POMDP Belief Space Search With Graph Representations

Abstract page for arXiv paper 2510.14035: GammaZero: Learning To Guide POMDP Belief Space Search With Graph Representations

arXiv - AI · 3 min ·
[2510.04116] Searching Meta Reasoning Skeleton to Guide LLM Reasoning
Llms

[2510.04116] Searching Meta Reasoning Skeleton to Guide LLM Reasoning

Abstract page for arXiv paper 2510.04116: Searching Meta Reasoning Skeleton to Guide LLM Reasoning

arXiv - AI · 4 min ·
[2509.23392] Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
Machine Learning

[2509.23392] Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking

Abstract page for arXiv paper 2509.23392: Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking

arXiv - AI · 4 min ·
[2509.00761] L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search
Nlp

[2509.00761] L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search

Abstract page for arXiv paper 2509.00761: L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search

arXiv - AI · 4 min ·
[2508.11524] Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models
Llms

[2508.11524] Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models

Abstract page for arXiv paper 2508.11524: Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language...

arXiv - AI · 4 min ·
[2507.17988] Synthesis of timeline-based planning strategies avoiding determinization
Machine Learning

[2507.17988] Synthesis of timeline-based planning strategies avoiding determinization

Abstract page for arXiv paper 2507.17988: Synthesis of timeline-based planning strategies avoiding determinization

arXiv - AI · 3 min ·
[2504.06188] SkillFlow: Scalable and Efficient Agent Skill Retrieval System
Machine Learning

[2504.06188] SkillFlow: Scalable and Efficient Agent Skill Retrieval System

Abstract page for arXiv paper 2504.06188: SkillFlow: Scalable and Efficient Agent Skill Retrieval System

arXiv - AI · 4 min ·
[2412.14019] Retrieving Classes of Causal Orders with Inconsistent Knowledge Bases
Llms

[2412.14019] Retrieving Classes of Causal Orders with Inconsistent Knowledge Bases

Abstract page for arXiv paper 2412.14019: Retrieving Classes of Causal Orders with Inconsistent Knowledge Bases

arXiv - AI · 4 min ·
[2603.28731] SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability
Llms

[2603.28731] SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability

Abstract page for arXiv paper 2603.28731: SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability

arXiv - AI · 4 min ·
[2603.28737] ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Machine Learning

[2603.28737] ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Abstract page for arXiv paper 2603.28737: ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

arXiv - AI · 3 min ·
[2603.28735] RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Machine Learning

[2603.28735] RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems

Abstract page for arXiv paper 2603.28735: RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems

arXiv - AI · 4 min ·
[2603.28707] A Convex Route to Thermomechanics: Learning Internal Energy and Dissipation
Machine Learning

[2603.28707] A Convex Route to Thermomechanics: Learning Internal Energy and Dissipation

Abstract page for arXiv paper 2603.28707: A Convex Route to Thermomechanics: Learning Internal Energy and Dissipation

arXiv - AI · 4 min ·
[2603.28625] Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing
Robotics

[2603.28625] Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing

Abstract page for arXiv paper 2603.28625: Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing

arXiv - AI · 4 min ·
[2603.28696] AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Llms

[2603.28696] AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding

Abstract page for arXiv paper 2603.28696: AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding

arXiv - AI · 4 min ·
[2603.28610] ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
Llms

[2603.28610] ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning

Abstract page for arXiv paper 2603.28610: ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning

arXiv - AI · 4 min ·
[2603.28622] Trust-Aware Routing for Distributed Generative AI Inference at the Edge
Machine Learning

[2603.28622] Trust-Aware Routing for Distributed Generative AI Inference at the Edge

Abstract page for arXiv paper 2603.28622: Trust-Aware Routing for Distributed Generative AI Inference at the Edge

arXiv - AI · 4 min ·
[2603.28613] TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark
Generative Ai

[2603.28613] TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark

Abstract page for arXiv paper 2603.28613: TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark

arXiv - AI · 4 min ·
[2603.28596] Moving Beyond Review: Applying Language Models to Planning and Translation in Reflection
Llms

[2603.28596] Moving Beyond Review: Applying Language Models to Planning and Translation in Reflection

Abstract page for arXiv paper 2603.28596: Moving Beyond Review: Applying Language Models to Planning and Translation in Reflection

arXiv - AI · 4 min ·