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
TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Lang…
arXiv cs.AI Research & Papers
GSPRec: On Improving Item Representations in Graph Signal Processing for Collaborative Fi…
arXiv cs.AI Research & Papers
Parameter-Efficient Continual Fine-Tuning: A Survey
arXiv cs.AI Research & Papers
Soft-TransFormers for Continual Learning
arXiv cs.AI Research & Papers
MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clini…
arXiv cs.AI Research & Papers
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
arXiv cs.AI Research & Papers
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
arXiv cs.AI Research & Papers
Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in G…
arXiv cs.AI Research & Papers
FormGym: Doing Paperwork with Agents
arXiv cs.AI Research & Papers
Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evide…
arXiv cs.AI Research & Papers
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
arXiv cs.AI Research & Papers
From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-A…
arXiv cs.AI Research & Papers
Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale
arXiv cs.AI Research & Papers
GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based M…
arXiv cs.AI Research & Papers
They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trus…
arXiv cs.AI Research & Papers
Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agent…
arXiv cs.AI Research & Papers
PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Patho…
arXiv cs.AI Research & Papers
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instructi…
arXiv cs.AI Research & Papers
Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs
arXiv cs.AI Research & Papers
MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical …
arXiv cs.AI Research & Papers
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
arXiv cs.AI Research & Papers
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
arXiv cs.AI Research & Papers
Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoni…
arXiv cs.AI Research & Papers
Attacking Graph Foundation Models Through Their Shared Representation
arXiv cs.AI Research & Papers
DWM: Separating World Effects from Actions in Latent World Models
arXiv cs.AI Research & Papers
SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval
arXiv cs.AI Research & Papers
NaviAIS: A Scenario-Level Vessel Trajectory Prediction Dataset withVectorized Lane Priors…
arXiv cs.AI Research & Papers
OntoBook: Ontology-Grounded Synthetic Textbooks for Medical Encoder Pretraining
arXiv cs.AI Research & Papers
AI Tool Discovery at Scale: All You Need is DNS
arXiv cs.AI Research & Papers
SAAG: Structured Agent Assessment and Grounding