Español

Explorar

Noticias de IA

30294 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
PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers
arXiv cs.AI Research & Papers
Target-Agnostic Calibration under Distribution Shift with Frequency-Aware Gradient Rectif…
arXiv cs.AI Research & Papers
Human Psychometric Questionnaires Mischaracterize LLM Behavior
arXiv cs.AI Research & Papers
LLM Bias Evaluation: Gender, Racial, and Age Disparities in Occupational and Crime Scenar…
arXiv cs.AI Research & Papers
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
arXiv cs.AI Research & Papers
SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor D…
arXiv cs.AI Research & Papers
Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
arXiv cs.AI Research & Papers
Conditional Coverage Diagnostics for Conformal Prediction
arXiv cs.AI Research & Papers
SpectralTrain: A Universal Framework for Hyperspectral Image Classification
arXiv cs.AI Research & Papers
If LLMs Have Human-Like Attributes, Then So Does Age of Empires II
arXiv cs.AI Research & Papers
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Poli…
arXiv cs.AI Research & Papers
Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus
arXiv cs.AI Research & Papers
The Refutability Gap: Challenges in Validating Reasoning by Large Language Models
arXiv cs.AI Research & Papers
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Languag…
arXiv cs.AI Research & Papers
Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
arXiv cs.AI Research & Papers
Pull Requests as a Training Signal for Repo-Level Code Editing
arXiv cs.AI Security & Safety
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
arXiv cs.AI Research & Papers
Plain Transformers are Surprisingly Powerful Link Predictors
arXiv cs.AI Research & Papers
The Information Geometry of Softmax: Probing and Steering
arXiv cs.AI Research & Papers
Biases in the Blind Spot: Detecting What LLMs Fail to Mention
arXiv cs.AI Research & Papers
Neuro-symbolic Syntactic Parsing: Shaping a Neural Network with the CYK Algorithm
arXiv cs.AI Research & Papers
MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networ…
arXiv cs.AI Research & Papers
Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcemen…
arXiv cs.AI Research & Papers
HistCAD: A Constraint-Aware Parametric History-Based CAD Representation, Dataset, and Ben…
arXiv cs.AI Research & Papers
Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
arXiv cs.AI Research & Papers
Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection
arXiv cs.AI Research & Papers
Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech
arXiv cs.AI Research & Papers
Aligning Dense Retrievers with LLM Utility via Distillation
arXiv cs.AI Research & Papers
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
arXiv cs.AI Research & Papers
Autoregressive Visual Generation Needs a Prologue