Español

Explorar

Noticias de IA

22318 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
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
arXiv cs.AI Research & Papers
Reinforcement Learning: From Algorithms To Foundation Models
arXiv cs.AI Research & Papers
A Dual-Hypothesis Reasoning Framework for LLM Guardrails
arXiv cs.AI Research & Papers
Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Age…
arXiv cs.AI Research & Papers
FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models
arXiv cs.AI Research & Papers
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orienta…
arXiv cs.AI Research & Papers
Is Progressive Disclosure All You Need for Long-Context Agents?
arXiv cs.AI Research & Papers
LaT: LLM-as-Trainer for Multi-Task Vehicle Routing Solvers
arXiv cs.AI Research & Papers
Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Att…
arXiv cs.AI Research & Papers
SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategies Refinement i…
arXiv cs.AI Research & Papers
Semantically Similar, Logically Distinct: Diagnosing the Semantic-Answerability Gap in Ta…
arXiv cs.AI Research & Papers
Financial Audit Assistance using Misinformation Detection and Explanation
arXiv cs.AI Research & Papers
PGN: Design and Implementation of a Vision-Language Navigation System Based on Pangu Mult…
arXiv cs.AI Research & Papers
A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deployment
arXiv cs.AI Research & Papers
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
arXiv cs.AI Research & Papers
Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Check…
arXiv cs.AI Research & Papers
OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs
arXiv cs.AI Research & Papers
SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning
arXiv cs.AI Research & Papers
PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcem…
arXiv cs.AI Research & Papers
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective
arXiv cs.AI Research & Papers
AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models
arXiv cs.AI Research & Papers
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse S…
arXiv cs.AI Research & Papers
Judge-dependent safety gains and model-specific helpfulness costs of evidence-sufficiency…
arXiv cs.AI Research & Papers
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steer…
arXiv cs.AI Research & Papers
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
arXiv cs.AI Research & Papers
Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Pref…
arXiv cs.AI Research & Papers
What Makes Linguistic Representations Good Models of High-Level Visual Perception in the …
arXiv cs.AI Research & Papers
Fully-sensorized smart-eyewear platform for on-device Machine Learning
arXiv cs.AI Research & Papers
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
arXiv cs.AI Research & Papers
RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deplo…