Español

Explorar

Noticias de IA

30934 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
Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in…
arXiv cs.AI Research & Papers
Adaptive Reinforcement Learning for Unobservable Random Delays
arXiv cs.AI Research & Papers
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
arXiv cs.AI Research & Papers
Can Argus Judge Them All? Comparing VLMs Across Domains
arXiv cs.AI Research & Papers
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
arXiv cs.AI Research & Papers
Beyond Na\"ive Prompting: Strategies for Improved Context-aided Forecasting with LLMs
arXiv cs.AI Research & Papers
TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation
arXiv cs.AI Research & Papers
Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge
arXiv cs.AI Research & Papers
Toward Autonomous Soft Robotic Endovascular Navigation via Imitation Learning
arXiv cs.AI Research & Papers
People use fast and flat simulation to reason about new games
arXiv cs.AI Research & Papers
Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COV…
arXiv cs.AI Research & Papers
Enabling Agents to Communicate Entirely in Latent Space
arXiv cs.AI Research & Papers
SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation
arXiv cs.AI Research & Papers
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Le…
arXiv cs.AI Research & Papers
Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertaint…
arXiv cs.AI Research & Papers
Emotion Recognition in Signers
arXiv cs.AI Research & Papers
MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
arXiv cs.AI Research & Papers
BiasLab: A Multilingual Dual-Framing Framework for LLM Bias Measurement, Applied to Workp…
arXiv cs.AI Research & Papers
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
arXiv cs.AI Research & Papers
Referential Regimes: Transformation-Invariant Identity for Neutral Substrates
arXiv cs.AI Research & Papers
Ideological Bias in LLMs' Economic Causal Reasoning
arXiv cs.AI Research & Papers
Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling S…
arXiv cs.AI Research & Papers
Research on Cross-media Science and Technology Information Data Retrieval
arXiv cs.AI Research & Papers
Safety from Honesty in a Disinterested AI Predictor
arXiv cs.AI Research & Papers
SFO: Learning PDE Operators via Spectral Filtering
arXiv cs.AI Research & Papers
Understanding Persuasive Interactions between Generative Social Agents and Humans: The Kn…
arXiv cs.AI Research & Papers
SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data
arXiv cs.AI Research & Papers
Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Sca…
arXiv cs.AI Research & Papers
Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers
arXiv cs.AI Research & Papers
A General Equilibrium Theory of Orchestrated AI Agent Systems