Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Worker Disagreement Reveals Sharp Directions in Local SGD
arXiv cs.AI Research & Papers
Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detec…
arXiv cs.AI Research & Papers
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
arXiv cs.AI Research & Papers
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
arXiv cs.AI Research & Papers
Turning Video Models into Generalist Robot Policies
arXiv cs.AI Research & Papers
Score Based Error Correcting Code Decoder
arXiv cs.AI Research & Papers
LASER: Learning Active Sensing for Continuum Field Reconstruction
arXiv cs.AI Research & Papers
Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering
arXiv cs.AI Research & Papers
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendati…
arXiv cs.AI Research & Papers
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
arXiv cs.AI Research & Papers
The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic V…
arXiv cs.AI Research & Papers
Differential syntactic and semantic encoding in LLMs
arXiv cs.AI Research & Papers
Fine-Tuned LLM as a Complementary Predictor Improving Ads System
arXiv cs.AI Research & Papers
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex…
arXiv cs.AI Research & Papers
Optimal and Diffusion Transports in Machine Learning
arXiv cs.AI Research & Papers
From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Inter…
arXiv cs.AI Research & Papers
MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryM…
arXiv cs.AI Research & Papers
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
arXiv cs.AI Research & Papers
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
arXiv cs.AI Research & Papers
ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process…
arXiv cs.AI Research & Papers
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
arXiv cs.AI Research & Papers
Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Soko…
arXiv cs.AI Research & Papers
STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation
arXiv cs.AI Research & Papers
GradientStabilizer:Fix the Norm, Not the Gradient
arXiv cs.AI Research & Papers
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM A…
arXiv cs.AI Research & Papers
Text2Model: Modeling Copilots for Text-to-Model Translation
arXiv cs.AI Research & Papers
DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision…
arXiv cs.AI Research & Papers
Heterogeneous Causal Discovery of Repeated Undesirable Health Outcomes
arXiv cs.AI Research & Papers
Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Mod…
arXiv cs.AI Research & Papers
Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking