Español

Explorar

Noticias de IA

21272 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
On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning
arXiv cs.AI Research & Papers
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
arXiv cs.AI Research & Papers
Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert …
arXiv cs.AI Research & Papers
Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Sy…
arXiv cs.AI Research & Papers
SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for…
arXiv cs.AI Research & Papers
Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration
arXiv cs.AI Research & Papers
Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation
arXiv cs.AI Research & Papers
Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertai…
arXiv cs.AI Research & Papers
BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classif…
arXiv cs.AI Research & Papers
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
arXiv cs.AI Research & Papers
Identifying Explicit Parsimonious Piece-wise Polynomial Relationships in Industrial time-…
arXiv cs.AI Research & Papers
Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models
arXiv cs.AI Research & Papers
Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardw…
arXiv cs.AI Research & Papers
Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Named
arXiv cs.AI Research & Papers
Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in State…
arXiv cs.AI Research & Papers
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment …
arXiv cs.AI Research & Papers
Pruning and Distilling Mixture-of-Experts into Dense Language Models
arXiv cs.AI Research & Papers
Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation
arXiv cs.AI Research & Papers
QuITE: Query-Based Irregular Time Series Embedding
arXiv cs.AI Research & Papers
Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
arXiv cs.AI Research & Papers
The Computational Boundary of Inference: Capability Internalization, Training, and the Tu…
arXiv cs.AI Research & Papers
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
arXiv cs.AI Research & Papers
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Mo…
arXiv cs.AI Research & Papers
An LLM-Based Assistance System for Intuitive and Flexible Capability-Based Planning
arXiv cs.AI Research & Papers
LACUNA: Safe Agents as Recursive Program Holes
arXiv cs.AI Research & Papers
Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
arXiv cs.AI Research & Papers
Learning to Assign Prediction Tasks to Agents with Capacity Constraints
arXiv cs.AI Research & Papers
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
arXiv cs.AI Research & Papers
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
arXiv cs.AI Research & Papers
Efficient Pre-Training of LLMs through Truncated SVD Layers