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
Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with …
arXiv cs.AI Research & Papers
The Bioelectrical Information Theory: Investigating the theoretical compression limit of …
arXiv cs.AI Research & Papers
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference
arXiv cs.AI Research & Papers
IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent…
arXiv cs.AI Research & Papers
The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reser…
arXiv cs.AI Research & Papers
Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retr…
arXiv cs.AI Research & Papers
When Attribution Patching Lies: Diagnosis and a Second-Order Correction
arXiv cs.AI Research & Papers
Representation Curriculum: Stagewise Training for Robust Ranking and Allocation
arXiv cs.AI Research & Papers
SocraticPO: Policy Optimization via Interactive Guidance
arXiv cs.AI Research & Papers
SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs
arXiv cs.AI Research & Papers
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
arXiv cs.AI Research & Papers
Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoni…
arXiv cs.AI Research & Papers
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Fed…
arXiv cs.AI Research & Papers
EstRTL: Functional Estimation Guided RTL Code Generation
arXiv cs.AI Research & Papers
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
arXiv cs.AI Research & Papers
Blurry Window Attention
arXiv cs.AI Research & Papers
Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting w…
arXiv cs.AI Research & Papers
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy M…
arXiv cs.AI Research & Papers
Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models
arXiv cs.AI Research & Papers
Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained…
arXiv cs.AI Research & Papers
LLM-Based Code Documentation Generation and Multi-Judge Evaluation
arXiv cs.AI Research & Papers
The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans
arXiv cs.AI Research & Papers
An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 M…
arXiv cs.AI Research & Papers
Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS
arXiv cs.AI Research & Papers
CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks
arXiv cs.AI Research & Papers
AI-Driven Analytics of Team-Teaching Talk: Acoustic Patterns across Experience, Cohorts a…
arXiv cs.AI Research & Papers
More Human or More AI? Visualizing Human-AI Collaboration Disclosures in Journalistic New…
arXiv cs.AI Research & Papers
The Role of Feedback Alignment in Self-Distillation
arXiv cs.AI Research & Papers
ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
arXiv cs.AI Research & Papers
A History-Aware Visually Grounded Critic for Computer Use Agents