Español

Explorar

Noticias de IA

29348 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
Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning
arXiv cs.AI Research & Papers
Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-…
arXiv cs.AI Research & Papers
VidMsg: A Benchmark for Implicit Message Inference in Short Videos
arXiv cs.AI Research & Papers
ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization
arXiv cs.AI Research & Papers
CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benc…
arXiv cs.AI Research & Papers
FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on N…
arXiv cs.AI Research & Papers
Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning
arXiv cs.AI Research & Papers
Introduction to optimization methods for training SciML models
arXiv cs.AI Research & Papers
When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics
arXiv cs.AI Research & Papers
Test-Time Optimization of Physical Query Plans with LLMs
arXiv cs.AI Research & Papers
Causal Neural Probabilistic Circuits
arXiv cs.AI Research & Papers
Learned Non-Maximum Suppression for 3D Object Detection
arXiv cs.AI Research & Papers
Crystal: Characterizing Relative Impact of Scholarly Publications
arXiv cs.AI Research & Papers
Efficient Hyperparameter Optimization for LLM Reinforcement Learning
arXiv cs.AI Research & Papers
\textsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentati…
arXiv cs.AI Research & Papers
$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy R…
arXiv cs.AI Research & Papers
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative …
arXiv cs.AI Research & Papers
Towards Robust Sequential Decomposition for Complex Image Editing
arXiv cs.AI Research & Papers
Scalable On-Hardware Training of Quantum Neural Networks and Application to Clinical Data…
arXiv cs.AI Security & Safety
Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You …
arXiv cs.AI Research & Papers
PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization
arXiv cs.AI Research & Papers
P\textsuperscript{2}-DPO: Grounding Hallucination in Perceptual Processing via Calibratio…
arXiv cs.AI Research & Papers
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation
arXiv cs.AI Research & Papers
Evaluating LLMs' Effectiveness on Real-World Consumer Device Repair Questions
arXiv cs.AI Research & Papers
Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters…
arXiv cs.AI Research & Papers
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
arXiv cs.AI Research & Papers
Learn When and Where to Connect: Adaptive Virtual Nodes for Dynamic Message Passing on Gr…
arXiv cs.AI Research & Papers
Rethinking Molecular Text Representations for LLMs: An Empirical Study
arXiv cs.AI Research & Papers
MUSE: A Unified Agentic Harness for MLLMs
arXiv cs.AI Research & Papers
Pretraining Language Models on Historical Text