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
Energy-Structured Low-Rank Adaptation for Continual Learning
arXiv cs.AI Security & Safety
Grimlock: Guarding High-Agency Systems with eBPF and Attested Channels
arXiv cs.AI Research & Papers
On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note
arXiv cs.AI Research & Papers
The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level En…
arXiv cs.AI Research & Papers
ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
arXiv cs.AI Research & Papers
Eliot: Interactively $\underline{E}$xploring Fast-Changing Scientific $\underline{Li}$ter…
arXiv cs.AI Research & Papers
Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers
arXiv cs.AI Research & Papers
How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
arXiv cs.AI Research & Papers
Worker Disagreement Reveals Sharp Directions in Local SGD
arXiv cs.AI Research & Papers
Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdo…
arXiv cs.AI Research & Papers
Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detec…
arXiv cs.AI Research & Papers
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
arXiv cs.AI Research & Papers
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
arXiv cs.AI Research & Papers
Turning Video Models into Generalist Robot Policies
arXiv cs.AI Research & Papers
Hallucination Behavior in Multimodal LLMs Across Agricultural Image Interpretation and Ge…
arXiv cs.AI Research & Papers
Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines
arXiv cs.AI Security & Safety
Symmetry Defeats Auditing
arXiv cs.AI Research & Papers
Score Based Error Correcting Code Decoder
arXiv cs.AI Research & Papers
Fine-Tuned LLM as a Complementary Predictor Improving Ads System
arXiv cs.AI Research & Papers
From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Inter…
arXiv cs.AI Research & Papers
MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryM…
arXiv cs.AI Research & Papers
Architecture-driven Shift: towards a lightweight selector for capturing the trends of log…
arXiv cs.AI Research & Papers
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
arXiv cs.AI Research & Papers
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of…
arXiv cs.AI Research & Papers
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
arXiv cs.AI Research & Papers
Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking
arXiv cs.AI Research & Papers
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Decep…
arXiv cs.AI Research & Papers
Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration…
arXiv cs.AI Research & Papers
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
arXiv cs.AI Research & Papers
KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evalua…