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 Security & Safety
FORGE: Multi-Agent Graduated Exploitation and Detection Engineering
arXiv cs.AI Research & Papers
Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Ge…
arXiv cs.AI Research & Papers
When Model Merging Breaks Routing: Training-Free Calibration for MoE
arXiv cs.AI Research & Papers
Causal Evidence of Stack Representations in Modeling Counter Languages Using Transformers
arXiv cs.AI Research & Papers
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation…
arXiv cs.AI Research & Papers
The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Co…
arXiv cs.AI Research & Papers
Multi-Modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinic…
arXiv cs.AI Research & Papers
dstack-capsule: Pod-Level Remote Attestation for Confidential Workloads on Kubernetes
arXiv cs.AI Research & Papers
Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective
arXiv cs.AI Research & Papers
Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
arXiv cs.AI Research & Papers
Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vect…
arXiv cs.AI Research & Papers
GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond
arXiv cs.AI Research & Papers
AirDreamer: Generalist Drone Navigation with World Models
arXiv cs.AI Research & Papers
Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large …
arXiv cs.AI Research & Papers
Reinforcement Learning from Cross-domain Videos with Video Prediction Model
arXiv cs.AI Research & Papers
AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Foll…
arXiv cs.AI Research & Papers
Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregati…
arXiv cs.AI Research & Papers
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Si…
arXiv cs.AI Research & Papers
Libra: Efficient Resource Management for Agentic RL Post-Training
arXiv cs.AI Research & Papers
Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
arXiv cs.AI Research & Papers
Constitutional On-Policy Safe Distillation
arXiv cs.AI Research & Papers
ROBUST-WT: Robust Uncertainty-aware Segmentation Transform via Whitening and Training Enh…
arXiv cs.AI Research & Papers
ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without B…
arXiv cs.AI Research & Papers
Spike-Aware C++ INT8 Inference for Sparse Spiking Language Models on Commodity CPUs
arXiv cs.AI Research & Papers
Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified C…
arXiv cs.AI Research & Papers
Capability Advertisement as a Market for Lemons: A Trust Layer for Heterogeneous Agent Ne…
arXiv cs.AI Research & Papers
Exact equivariance, kept through training, buys zero-shot generalisation across the symme…
arXiv cs.AI Research & Papers
Patcher: Post-Hoc Patching of Backdoored Large Language Models
arXiv cs.AI Research & Papers
Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
arXiv cs.AI Research & Papers
Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries