Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Imag…
arXiv cs.AI Research & Papers
MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal…
arXiv cs.AI Research & Papers
Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents
arXiv cs.AI Research & Papers
Dissociating performance from compositional feature learning
arXiv cs.AI Research & Papers
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
arXiv cs.AI Research & Papers
Calibrating Interpretability Instruments Before Trusting Their Verdicts
arXiv cs.AI Research & Papers
A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-A…
arXiv cs.AI Research & Papers
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic…
arXiv cs.AI Research & Papers
Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of…
arXiv cs.AI Research & Papers
LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents
arXiv cs.AI Research & Papers
Neural-Network Solutions to Real-Space Charge Density and Generalization
arXiv cs.AI Research & Papers
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Mo…
arXiv cs.AI Research & Papers
The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
arXiv cs.AI Research & Papers
Towards Evolving Context Parameterization for Large Language Models
arXiv cs.AI Research & Papers
Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coor…
arXiv cs.AI Research & Papers
Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repe…
arXiv cs.AI Research & Papers
RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction
arXiv cs.AI Research & Papers
Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Lear…
arXiv cs.AI Research & Papers
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
arXiv cs.AI Research & Papers
AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?
arXiv cs.AI Research & Papers
Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete R…
arXiv cs.AI Research & Papers
SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable mach…
arXiv cs.AI Research & Papers
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-T…
arXiv cs.AI Research & Papers
Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment
arXiv cs.AI Research & Papers
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
arXiv cs.AI Research & Papers
Legislating World-Model-Based Planning with Legal Reasoning
arXiv cs.AI Research & Papers
Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation
arXiv cs.AI Research & Papers
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
arXiv cs.AI Research & Papers
LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Fi…
arXiv cs.AI Research & Papers
MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving