Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
arXiv cs.AI Research & Papers
Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference
arXiv cs.AI Research & Papers
Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
arXiv cs.AI Research & Papers
Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented G…
arXiv cs.AI Research & Papers
CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification
arXiv cs.AI Research & Papers
The Internal Anatomy of Strategic Choice in Large Language Models
arXiv cs.AI Research & Papers
Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding
arXiv cs.AI Research & Papers
Human-like moral judgments conceal divergent motive attributions in large language models
arXiv cs.AI Research & Papers
Personalizing LLM Agent Memory Using Biometrics
arXiv cs.AI Research & Papers
Weakly supervised neural network: segmentation of complex structures in X-ray microCT
arXiv cs.AI Research & Papers
SkillAlign: Aligning Skill Interfaces for LLM-based Agents
arXiv cs.AI Research & Papers
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Rep…
arXiv cs.AI Research & Papers
RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavior…
arXiv cs.AI Research & Papers
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
arXiv cs.AI Research & Papers
Application of curiosity driven exploration methods for hardware interference identificat…
arXiv cs.AI Research & Papers
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
arXiv cs.AI Research & Papers
The Surprising Effectiveness of Approximate Value Iteration in Self-Play
arXiv cs.AI Research & Papers
Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to …
arXiv cs.AI Research & Papers
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis …
arXiv cs.AI Research & Papers
Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpretin…
arXiv cs.AI Research & Papers
Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow P…
arXiv cs.AI Research & Papers
Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive …
arXiv cs.AI Research & Papers
zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring
arXiv cs.AI Research & Papers
An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orche…
arXiv cs.AI Research & Papers
Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement …
arXiv cs.AI Research & Papers
A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
arXiv cs.AI Research & Papers
Analysis of Respiratory Sinus Arrhythmia with Neural Networks
arXiv cs.AI Research & Papers
Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in Ea…
arXiv cs.AI Research & Papers
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
arXiv cs.AI Research & Papers
Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training