Español

Explorar

Noticias de IA

29335 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
Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Comput…
arXiv cs.AI Research & Papers
Query Timing Produces Opposite Positional Biases Between LLMs and Humans
arXiv cs.AI Research & Papers
SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
arXiv cs.AI Research & Papers
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
arXiv cs.AI Research & Papers
Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories
arXiv cs.AI Research & Papers
From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks
arXiv cs.AI Research & Papers
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
arXiv cs.AI Research & Papers
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
arXiv cs.AI Research & Papers
ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs
arXiv cs.AI Research & Papers
PROVE-RT: Generating Mechanized Theorem Prover Scripts for Real-Time Systems using LLMs
arXiv cs.AI Research & Papers
Multi-Layer Context Camouflaging: A Semantic Superposition and Contextual Lamination Fram…
arXiv cs.AI Research & Papers
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Si…
arXiv cs.AI Research & Papers
Cat-DPO: Category-Adaptive Safety Alignment
arXiv cs.AI Research & Papers
FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving
arXiv cs.AI Research & Papers
Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Inde…
arXiv cs.AI Research & Papers
Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
arXiv cs.AI Research & Papers
From Observation to Intervention: Memory in Brains and Large Language Models
arXiv cs.AI Research & Papers
AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-…
arXiv cs.AI Research & Papers
Steering the Language Axis: From Linear Decodability to Causal Control
arXiv cs.AI Research & Papers
Cueless EEG imagined speech for subject identification: dataset and benchmarks
arXiv cs.AI Research & Papers
Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
arXiv cs.AI Research & Papers
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
arXiv cs.AI Research & Papers
Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Ne…
arXiv cs.AI Research & Papers
Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses
arXiv cs.AI Security & Safety
TopoIntent: Compiling Security Intent into Executable, Compliance-Checked Network Topolog…
arXiv cs.AI Research & Papers
LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Obs…
arXiv cs.AI Research & Papers
BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving D…
arXiv cs.AI Research & Papers
Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of …
arXiv cs.AI Research & Papers
DMDIntel: Interpreting Large Language Models via Dynamic Mode Decomposition
arXiv cs.AI Research & Papers
Polish Medical Visual Question Answering: Vision-Language Models Underutilize Visual Evid…