Español

Explorar

Noticias de IA

29675 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
Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
arXiv cs.AI Research & Papers
Effective Reasoning Chains Reduce Intrinsic Dimensionality
arXiv cs.AI Research & Papers
A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agen…
arXiv cs.AI Research & Papers
HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Lang…
arXiv cs.AI Research & Papers
DTBench: A Synthetic Benchmark for Document-to-Table Extraction
arXiv cs.AI Research & Papers
Position: Evaluation of ECG Representations Must Be Fixed
arXiv cs.AI Policy & Regulation
The Global Landscape of Environmental AI Regulation: From the Cost of Reasoning to a Righ…
arXiv cs.AI Security & Safety
From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
arXiv cs.AI Research & Papers
NGDBench: Towards Neural Graph Data Management
arXiv cs.AI Security & Safety
Prompt Injection as Role Confusion
arXiv cs.AI Research & Papers
Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Tran…
arXiv cs.AI Research & Papers
SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs
arXiv cs.AI Research & Papers
Empirical Characterization of Inference-Time Elicited Probability Transformations in Larg…
arXiv cs.AI Research & Papers
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
arXiv cs.AI Research & Papers
Functorial Neural Architectures from Higher Inductive Types
arXiv cs.AI Research & Papers
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
arXiv cs.AI Research & Papers
Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE…
arXiv cs.AI Research & Papers
SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
arXiv cs.AI Research & Papers
Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
arXiv cs.AI Research & Papers
Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection
arXiv cs.AI Research & Papers
Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Ro…
arXiv cs.AI Research & Papers
Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
arXiv cs.AI Research & Papers
OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implici…
arXiv cs.AI Research & Papers
Towards a holistic understanding of Selection Bias for Causal Effect Identification
arXiv cs.AI Research & Papers
Block-Based Double Decoders
arXiv cs.AI Research & Papers
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement …
arXiv cs.AI Research & Papers
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Sea…
arXiv cs.AI Research & Papers
Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
arXiv cs.AI Research & Papers
Efficient Learning of Deep State Space Models via Importance Smoothing
arXiv cs.AI Research & Papers
SWIM: Single-Instance Whole-Body Imitation for swiMming