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
Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States
arXiv cs.AI Research & Papers
Subliminal Learning is a LoRA Artifact
arXiv cs.AI Research & Papers
DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for D…
arXiv cs.AI Research & Papers
Computation-Aware Kalman Filtering with Model Selection for Neural Dynamics
arXiv cs.AI Research & Papers
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
arXiv cs.AI Research & Papers
IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesi…
arXiv cs.AI Research & Papers
Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue
arXiv cs.AI Research & Papers
pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirements
arXiv cs.AI Research & Papers
When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
arXiv cs.AI Research & Papers
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
arXiv cs.AI Research & Papers
MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention fo…
arXiv cs.AI Research & Papers
Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation …
arXiv cs.AI Research & Papers
ProductWebGen: Benchmarking Multimodal Product Webpage Generation
arXiv cs.AI Research & Papers
Dive into Waves: Morlet Spectral Transformer for Cross-Subject Emotion Decoding from EEG
arXiv cs.AI Research & Papers
Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and…
arXiv cs.AI Research & Papers
Extending Causal Metamodeling to a non-Markovian Queue
arXiv cs.AI Research & Papers
Behavior-Invariant Task Representation Learning with Transformer-based World Models for O…
arXiv cs.AI Research & Papers
SORA: Free Second-Order Attacks in Fast Adversarial Training
arXiv cs.AI Research & Papers
Information-Theoretic Lower Bounds for Bit-Constrained Stochastic Optimization via a Redu…
arXiv cs.AI Research & Papers
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Sh…
arXiv cs.AI Research & Papers
Demystifying the Optimal Fair Classifier in Multi-Class Classification
arXiv cs.AI Research & Papers
LinguIUTics at PsyDefDetect: Iterative Imbalance-Aware Fine-tuning of Qwen3-8B for Psycho…
arXiv cs.AI Research & Papers
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answe…
arXiv cs.AI Research & Papers
Improving Visual Representation Alignment Generation with GRPO
arXiv cs.AI Research & Papers
Interpretable Policy Distillation for Power Grid Topology Control
arXiv cs.AI Research & Papers
CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action…
arXiv cs.AI Research & Papers
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
arXiv cs.AI Research & Papers
Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
arXiv cs.AI Research & Papers
(HB-ARFM) History-Bootstrapped Flow Matching for Inverse Boiling Reconstruction
arXiv cs.AI Research & Papers
Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Lear…