ProToMEx: Rapid, Interpretable Explanations via Structured Representations
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference
Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented G…
CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification
The Internal Anatomy of Strategic Choice in Large Language Models
Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding
Human-like moral judgments conceal divergent motive attributions in large language models
Personalizing LLM Agent Memory Using Biometrics
Weakly supervised neural network: segmentation of complex structures in X-ray microCT
SkillAlign: Aligning Skill Interfaces for LLM-based Agents
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Rep…
RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavior…
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
Application of curiosity driven exploration methods for hardware interference identificat…
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
The Surprising Effectiveness of Approximate Value Iteration in Self-Play
Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to …
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis …
Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpretin…
Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow P…
Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive …
zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring
An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orche…
Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement …
A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
Analysis of Respiratory Sinus Arrhythmia with Neural Networks
Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in Ea…
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training