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
Mode-Dependent Rectification for Stable PPO Training
arXiv cs.AI Research & Papers
VisAdj: Learning Adjacency Matrices from Node-Link Images
arXiv cs.AI Research & Papers
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
arXiv cs.AI Research & Papers
Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap
arXiv cs.AI Research & Papers
Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddings
arXiv cs.AI Research & Papers
AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language…
arXiv cs.AI Research & Papers
Diagnosing Capability Preservation and Task Sensitivity in Memory Augmented Document Clas…
arXiv cs.AI Research & Papers
Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Mo…
arXiv cs.AI Research & Papers
Prime Agent: A Self-Improving RLM Harness
arXiv cs.AI Research & Papers
The Measurement Revolution? Credible Measurement and Inference in the Age of AI
arXiv cs.AI Research & Papers
Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality
arXiv cs.AI Research & Papers
The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybr…
arXiv cs.AI Research & Papers
Search Broadly, Seek Evidence on Both Sides, Decide Narrowly: Evidence-Admissible GraphRA…
arXiv cs.AI Research & Papers
Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents
arXiv cs.AI Research & Papers
Molecular LLM Agents: From Architectural Design to Scientific Autonomy
arXiv cs.AI Research & Papers
DeMixPert: Decomposed Response Modeling with Gaussian Mixtures for OOD Single-Cell Pertur…
arXiv cs.AI Research & Papers
Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual …
arXiv cs.AI Research & Papers
Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems
arXiv cs.AI Research & Papers
SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing
arXiv cs.AI Research & Papers
Constructing Predictive Surgical Path for AI-based Capsulorhexis Skill Transfer
arXiv cs.AI Research & Papers
Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners…
arXiv cs.AI Research & Papers
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
arXiv cs.AI Research & Papers
Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators
arXiv cs.AI Research & Papers
HiMA-MDD: A Hierarchical Multi-Agent Harness for Interpretable Multimodal Depression Dete…
arXiv cs.AI Research & Papers
Evaluating SAT Solver Metrics as Predictors of Human-Perceived Nonogram Difficulty
arXiv cs.AI Research & Papers
SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale
arXiv cs.AI Research & Papers
What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When…
arXiv cs.AI Research & Papers
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
arXiv cs.AI Research & Papers
A Scalable Vector Graphics Latent Space
arXiv cs.AI Research & Papers
ReWorld: An Interactive World Model with Long-Horizon Memory