Español

Explorar

Noticias de IA

22318 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
When Synthetic Speech Is All You Have: Better Call GRPO
arXiv cs.AI Research & Papers
Predicting Male Fertility Using Machine Learning: A Semen Parameters Based Analysis with …
arXiv cs.AI Research & Papers
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
arXiv cs.AI Research & Papers
TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Per…
arXiv cs.AI Research & Papers
ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access
arXiv cs.AI Research & Papers
Retrieval of Scientific and Technological Resources for Experts and Scholars
arXiv cs.AI Research & Papers
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Mod…
arXiv cs.AI Research & Papers
Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring
arXiv cs.AI Research & Papers
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
arXiv cs.AI Research & Papers
XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
arXiv cs.AI Research & Papers
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Predi…
arXiv cs.AI Research & Papers
A Practical Investigation of Training-free Relaxed Speculative Decoding
arXiv cs.AI Research & Papers
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
arXiv cs.AI Research & Papers
StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
arXiv cs.AI Research & Papers
Robust Weighted Triangulation of Causal Effects Under Model Uncertainty
arXiv cs.AI Research & Papers
Spectral Analysis of Dueling Q-Learning
arXiv cs.AI Research & Papers
GitLake: Git-for-data for the agentic lakehouse
arXiv cs.AI Research & Papers
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
arXiv cs.AI Research & Papers
Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal L…
arXiv cs.AI Research & Papers
VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Token…
arXiv cs.AI Research & Papers
Spatio-Temporal Scheduling Prediction Under Backhaul Delay for Resilient Coordinated Beam…
arXiv cs.AI Research & Papers
EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
arXiv cs.AI Research & Papers
TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Ag…
arXiv cs.AI Research & Papers
From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
arXiv cs.AI Research & Papers
Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting
arXiv cs.AI Research & Papers
The complexities of patient-centred conversational artificial intelligence
arXiv cs.AI Research & Papers
SHAP-Weighted Cross-Modal Expert Fusion for Emotion and Sentiment Recognition: Evidence a…
arXiv cs.AI Research & Papers
Drift-Aware Temporal Graph Rewiring (DATGR) for Adaptive Semantic Modeling in Biomedical …
arXiv cs.AI Research & Papers
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Larg…
arXiv cs.AI Research & Papers
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models