Español

Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
arXiv cs.AI Research & Papers
Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal
arXiv cs.AI Research & Papers
Using LLMs for Explainable, Data-Driven Insight Generation from Time Series
arXiv cs.AI Research & Papers
Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles
arXiv cs.AI Research & Papers
State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation
arXiv cs.AI Research & Papers
Beyond-Diagonal RIS Under Non-Idealities: Learning-Based Architecture Discovery and Optim…
arXiv cs.AI Research & Papers
MUX: Continuous Reasoning via Multiplexed Tokens
arXiv cs.AI Research & Papers
Regime-Aware Physics-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Using Th…
arXiv cs.AI Research & Papers
FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration
arXiv cs.AI Research & Papers
Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
arXiv cs.AI Research & Papers
ProbSPARQL: Querying Knowledge Graphs with Multi-dimensional, Uncertain Numeric Data
arXiv cs.AI Research & Papers
FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis
arXiv cs.AI Research & Papers
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
arXiv cs.AI Research & Papers
PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language
arXiv cs.AI Research & Papers
Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Deri…
arXiv cs.AI Research & Papers
MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers
arXiv cs.AI Research & Papers
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
arXiv cs.AI Research & Papers
RAMP: Recognition parametrisation by Amortised Message Passing
arXiv cs.AI Research & Papers
Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre…
arXiv cs.AI Research & Papers
From Agent Failure Paths to Quantified Residual Risk: A Compositional Framework for Resil…
arXiv cs.AI Research & Papers
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
arXiv cs.AI Research & Papers
Robust Belief-State Policy Learning for Quantum Network Routing Under Decoherence and Tim…
arXiv cs.AI Research & Papers
Variational meta-learning inference for low dimensional neural system identification
arXiv cs.AI Research & Papers
BatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data
arXiv cs.AI Research & Papers
Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit…
arXiv cs.AI Research & Papers
Attacking Graph Foundation Models Through Their Shared Representation
arXiv cs.AI Research & Papers
Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization
arXiv cs.AI Research & Papers
Circuit Claims Depend on What Is Extracted and How It Is Compared
arXiv cs.AI Research & Papers
AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LL…
arXiv cs.AI Research & Papers
Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Re…