Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Cli…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinica…
The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents
SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs
TaRA: Training-Aware Low-Rank Adaptation Initialization
Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Patt…
Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supe…
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
UTP-Bench: Uncertainty-aware Travel Planning Benchmark
Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?
LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in…
When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent R…
Induction and Inquiry via Probabilistic Reasoning over Language and Code
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compi…
A Survey of Transformer-based Language Models with Focus on Efficiency
AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transf…
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents
Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grou…
VoRTeC: Taming Foundation Flow for One-step Real time Video Compression
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
hLLM: Single Pass Decoding for Generative Reranking
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fi…
PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Tra…
Can Coding Agents Reproduce Findings in Computational Materials Science?