Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
The Kalman Evolve: Closing the Gap in Kalman Filtering via Interpretable Algorithm Discov…
arXiv cs.AI Research & Papers
Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
arXiv cs.AI Research & Papers
APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented…
arXiv cs.AI Research & Papers
Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU
arXiv cs.AI Research & Papers
HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML
arXiv cs.AI Research & Papers
SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation …
arXiv cs.AI Research & Papers
Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Exper…
arXiv cs.AI Research & Papers
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
arXiv cs.AI Research & Papers
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository …
arXiv cs.AI Research & Papers
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
arXiv cs.AI Research & Papers
VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes
arXiv cs.AI Research & Papers
Natural Language Query to Configuration for Retrieval Agents
arXiv cs.AI Research & Papers
2-ASP(Q) programs with weak constraints: Complexity and efficient implementation
arXiv cs.AI Research & Papers
Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
arXiv cs.AI Research & Papers
L2Rec: Towards Dual-View Understanding of LLMs for Personalized Recommendation
arXiv cs.AI Research & Papers
Governed Evolution of Agent Runtimes through Executable Operational Cognition
arXiv cs.AI Research & Papers
Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Mu…
arXiv cs.AI Research & Papers
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
arXiv cs.AI Research & Papers
Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation
arXiv cs.AI Research & Papers
FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentat…
arXiv cs.AI Research & Papers
JobBench: Aligning Agent Work With Human Will
arXiv cs.AI Research & Papers
DEI: Diversity in Evolutionary Inference for Quality-Diversity Search
arXiv cs.AI Research & Papers
Trust Region Q Adjoint Matching
arXiv cs.AI Research & Papers
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
arXiv cs.AI Research & Papers
Post-training makes large language models less human-like
arXiv cs.AI Research & Papers
Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs
arXiv cs.AI Research & Papers
Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination
arXiv cs.AI Research & Papers
AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
arXiv cs.AI Research & Papers
Governed Metaprogramming for Intelligent Systems: Reclassifying Eval as a Governed Effect
arXiv cs.AI Research & Papers
The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection