Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation
Explorar
Noticias de IA
22065 elementos — filtrados, clasificados y sin duplicados
CrowdMath: A Dataset of Crowdsourced Mathematical Research Discussions
A Study of Parallel Continuous Local Search
A Geometric Account of Activation Steering through Angle-Norm Decomposition
SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust…
OpenSkill: Open-World Self-Evolution for LLM Agents
AdMem: Advanced Memory for Task-solving Agents
Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Lan…
Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows
Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothe…
Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents
Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Gro…
Online Pandora's Box for Contextual LLM Cascading
Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harn…
When Does Multi-Agent Collaboration Help? An Entropy Perspective
Trading Engagement for Sustainability: Carbon-Aware Re-ranking for E-commerce Recommendat…
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foun…
Attention-Guided Autoencoder Fusion for Insulator Defect Detection Using UAV Transmission…
Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local T…
P-Cast Precision in FP8 Attention: Sink-Induced Collapse and the Optimality of S=2^8
Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestrati…
Didact: A Cross-Domain Capability Discovery System for Defence
Geometric Second-Order Feature Correlation Learning for Self-Supervised Speech Emotion Re…
IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spok…
AI-Driven Test Case Generation from Natural Language Requirements: A Survey of Techniques…
Generative Models Erode Human Temporal Learning Through Market Selection