Español

Explorar

Noticias de IA

37834 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
PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech …
arXiv cs.AI Research & Papers
GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
arXiv cs.AI Research & Papers
Computing Actual Causes for Neural Network Predictions under Structured Causal Inputs
arXiv cs.AI Research & Papers
NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Me…
arXiv cs.AI Research & Papers
Can Training Logs Make Model Comparisons More Precise?
arXiv cs.AI Research & Papers
Designing a Good Virtual Node: Addressable and Cardinality-Preserving Global Memory for M…
arXiv cs.AI Research & Papers
Evading Chain-of-Thought Monitoring Through Model Poisoning
arXiv cs.AI Research & Papers
BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?
arXiv cs.AI Research & Papers
When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index
arXiv cs.AI Models & Releases
dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
arXiv cs.AI Research & Papers
A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varyi…
arXiv cs.AI Research & Papers
Optimal Liability Design for Medical AI
arXiv cs.AI Research & Papers
Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds
arXiv cs.AI Research & Papers
Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation
arXiv cs.AI Research & Papers
A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Con…
arXiv cs.AI Research & Papers
PACE: Adaptive Budget Allocation for Time-Efficient Embodied Planning
arXiv cs.AI Research & Papers
Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for…
arXiv cs.AI Research & Papers
CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dy…
arXiv cs.AI Research & Papers
Distilled Roads: Generalisable Road Network Extraction Across Sensors, Resolutions, and R…
arXiv cs.AI Research & Papers
SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling
arXiv cs.AI Research & Papers
ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonom…
arXiv cs.AI Research & Papers
HyperFL: Query-Adaptive Representation Learning for Software Fault Localization
arXiv cs.AI Research & Papers
AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Rev…
arXiv cs.AI Research & Papers
Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampli…
arXiv cs.AI Research & Papers
UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space
arXiv cs.AI Research & Papers
SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
arXiv cs.AI Research & Papers
Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning
arXiv cs.AI Research & Papers
Patient-centered data science: an integrative framework for evaluating and predicting cli…
arXiv cs.AI Research & Papers
LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation
arXiv cs.AI Research & Papers
Can LLMs Test Terminal User Interfaces?