Español

Explorar

Noticias de IA

29670 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
6G Communication Networks Enabling Embodied Agents: Architecture and Prototype
arXiv cs.AI Research & Papers
When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Paramete…
arXiv cs.AI Research & Papers
Convergence Without Understanding: When Language Models Agree on Representations but Disa…
arXiv cs.AI Research & Papers
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
arXiv cs.AI Research & Papers
CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs
arXiv cs.AI Research & Papers
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
arXiv cs.AI Research & Papers
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
arXiv cs.AI Research & Papers
Learning Individual Dynamics from Sparse Cross-Sectional Snapshots
arXiv cs.AI Research & Papers
Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dim…
arXiv cs.AI Research & Papers
Multimodal Distribution Matching for Vision-Language Dataset Distillation
arXiv cs.AI Research & Papers
DrawVideo: Generating Long Video from Storyboard Keyframe Sketches
arXiv cs.AI Research & Papers
Cost-Effective Model Evaluation with Meta-Learning
arXiv cs.AI Research & Papers
EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video…
arXiv cs.AI Research & Papers
DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in O…
arXiv cs.AI Research & Papers
CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Ima…
arXiv cs.AI Research & Papers
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
arXiv cs.AI Research & Papers
Human Decision-Making with Persuasive and Narrative LLM Explanations
arXiv cs.AI Research & Papers
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memor…
arXiv cs.AI Research & Papers
Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
arXiv cs.AI Research & Papers
VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
arXiv cs.AI Research & Papers
AI Evaluation Should Require Standardized Item-Level Data Releases
arXiv cs.AI Research & Papers
QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems
arXiv cs.AI Research & Papers
Model Spec Midtraining: Improving How Alignment Training Generalizes
arXiv cs.AI Research & Papers
Representational Alignment with Chemical Induced Fit for Molecular Relational Learning
arXiv cs.AI Research & Papers
Spectral-inspired Operator Learning with Limited Data and Unknown Physics
arXiv cs.AI Security & Safety
Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
arXiv cs.AI Research & Papers
A drone-based framework for coral habitat mapping via weakly supervised segmentation
arXiv cs.AI Research & Papers
Controlled Personalization in Legacy Media Online Services: A Case Study in News Recommen…
arXiv cs.AI Research & Papers
LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Mani…
arXiv cs.AI Research & Papers
Patterns vs. Patients: Evaluating LLMs against Mental Health Professionals on Personality…