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
Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns
arXiv cs.AI Research & Papers
CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition
arXiv cs.AI Research & Papers
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
arXiv cs.AI Research & Papers
Pass the Baton: Trajectory-Relayed On-Policy Distillation
arXiv cs.AI Research & Papers
DSevolve: Enabling Real-Time Adaptive Scheduling on Dynamic Flexible Job Shop with LLM-Ev…
arXiv cs.AI Research & Papers
MusiChat: Vibe Composing for Music Creation
arXiv cs.AI Research & Papers
Localized Anomaly Detection via Differentiable D-vine Copulas
arXiv cs.AI Research & Papers
Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visua…
arXiv cs.AI Research & Papers
Personalization, Personas, and Forecasting in Value Alignment
arXiv cs.AI Research & Papers
Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies…
arXiv cs.AI Research & Papers
A Control System, a Dataset, and a Recipe for Making Frozen LLM Agents Learn a Domain
arXiv cs.AI Research & Papers
TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation
arXiv cs.AI Research & Papers
OmniQEC: discovering practical quantum error-correcting codes by an AI scientist
arXiv cs.AI Research & Papers
A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks
arXiv cs.AI Research & Papers
Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prio…
arXiv cs.AI Research & Papers
Do Models Fake Alignment Without Clear Consequences?
arXiv cs.AI Research & Papers
EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff
arXiv cs.AI Research & Papers
FFNet: MetaMixer-based Efficient Convolutional Mixer Design
arXiv cs.AI Research & Papers
Localizing Persona Representations in LLMs
arXiv cs.AI Research & Papers
GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models
arXiv cs.AI Research & Papers
Fairness Is Not Enough: Auditing Competence and Intersectional Bias in AI-powered Resume …
arXiv cs.AI Research & Papers
Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook
arXiv cs.AI Research & Papers
RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Compre…
arXiv cs.AI Research & Papers
AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
arXiv cs.AI Research & Papers
scMIR: a vision-language foundation model for single-cell light microscopy image represen…
arXiv cs.AI Research & Papers
Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA
arXiv cs.AI Research & Papers
Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical …
arXiv cs.AI Research & Papers
Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?
arXiv cs.AI Research & Papers
Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT
arXiv cs.AI Research & Papers
ScalableRAG: High-Quality RAG at Zero Ingestion Cost