Español

Explorar

Noticias de IA

30239 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 Developer Tooling
MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
arXiv cs.AI Research & Papers
Federated Causal Inference from Multi-Site Observational Data via Propensity Score Aggreg…
arXiv cs.AI Research & Papers
DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
arXiv cs.AI Research & Papers
UltraSketchLLM: Sub-1-Bit LLM Compression via Sketch and Hardware-Friendly Operators
arXiv cs.AI Research & Papers
Fusion of Pervasive RF Data with Spatial Images via Vision Transformers for Enhanced Mapp…
arXiv cs.AI Research & Papers
Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforce…
arXiv cs.AI Research & Papers
Q-Net: Queue Length Estimation via Kalman-based Neural Networks
arXiv cs.AI Research & Papers
Chronological Thinking in Full-Duplex Spoken Dialogue Language Models
arXiv cs.AI Research & Papers
The Journal of Prompt-Engineered (Moral) Philosophy Or: Why AI-Assisted Ethics Research R…
arXiv cs.AI Research & Papers
An interpretable unsupervised representation learning for high precision measurement in p…
arXiv cs.AI Security & Safety
COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
arXiv cs.AI Research & Papers
Schr\"odinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigati…
arXiv cs.AI Research & Papers
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
arXiv cs.AI Research & Papers
Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Que…
arXiv cs.AI Research & Papers
SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer…
arXiv cs.AI Research & Papers
Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-I…
arXiv cs.AI Research & Papers
Residual Context Diffusion Language Models
arXiv cs.AI Research & Papers
Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and …
arXiv cs.AI Research & Papers
Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-preci…
arXiv cs.AI Research & Papers
Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling
arXiv cs.AI Research & Papers
FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
arXiv cs.AI Research & Papers
C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Though…
arXiv cs.AI Research & Papers
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
arXiv cs.AI Research & Papers
Did You Forget What I Asked? Prospective Memory Failures in Large Language Models
arXiv cs.AI Research & Papers
X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
arXiv cs.AI Research & Papers
The Shrinking Lifespan of LLMs in Science
arXiv cs.AI Research & Papers
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
arXiv cs.AI Research & Papers
LEPO: Latent Reasoning Policy Optimization for Large Language Models
arXiv cs.AI Research & Papers
Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs
arXiv cs.AI Research & Papers
EmoMind: Decoding Affective Captions from Human Brain fMRI