Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Cli…
arXiv cs.AI Research & Papers
The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinica…
arXiv cs.AI Research & Papers
The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents
arXiv cs.AI Research & Papers
SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
arXiv cs.AI Research & Papers
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs
arXiv cs.AI Research & Papers
TaRA: Training-Aware Low-Rank Adaptation Initialization
arXiv cs.AI Research & Papers
Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Patt…
arXiv cs.AI Research & Papers
Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supe…
arXiv cs.AI Research & Papers
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
arXiv cs.AI Research & Papers
UTP-Bench: Uncertainty-aware Travel Planning Benchmark
arXiv cs.AI Research & Papers
Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
arXiv cs.AI Research & Papers
Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?
arXiv cs.AI Research & Papers
LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails
arXiv cs.AI Research & Papers
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in…
arXiv cs.AI Research & Papers
When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent R…
arXiv cs.AI Research & Papers
Induction and Inquiry via Probabilistic Reasoning over Language and Code
arXiv cs.AI Research & Papers
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
arXiv cs.AI Research & Papers
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compi…
arXiv cs.AI Research & Papers
A Survey of Transformer-based Language Models with Focus on Efficiency
arXiv cs.AI Research & Papers
AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transf…
arXiv cs.AI Research & Papers
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
arXiv cs.AI Research & Papers
Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents
arXiv cs.AI Research & Papers
Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grou…
arXiv cs.AI Research & Papers
VoRTeC: Taming Foundation Flow for One-step Real time Video Compression
arXiv cs.AI Research & Papers
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
arXiv cs.AI Research & Papers
hLLM: Single Pass Decoding for Generative Reranking
arXiv cs.AI Research & Papers
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fi…
arXiv cs.AI Research & Papers
PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
arXiv cs.AI Research & Papers
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Tra…
arXiv cs.AI Research & Papers
Can Coding Agents Reproduce Findings in Computational Materials Science?