Automated Detection and Classification of Delusion-related Content in Naturalistic Audio …
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
PRIMA: Operational Patterns for Resilient Multi-Agent Research with Verifiable Identity a…
TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents
Noise-Robust Financial Numerical Entity Attribute Tagging
Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention…
An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation
Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat
RECTOR: Priority-Aware Rule-Based Reranking for Compliance-Aware Autonomous Driving Traje…
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking
FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Opt…
AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems
Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis
CODESKILL: Learning Self-Evolving Skills for Coding Agents
A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Rout…
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Ag…
PHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecas…
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of A…
A Deep Dive into Axiomatic Design -- Part I: Problem Formulation
$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing
Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modaliti…
VeriTrace: Evolving Mental Models for Deep Research Agents
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's D…
Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Tex…