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
Self-Specialized Teachers for Domain Post-Training
arXiv cs.AI Research & Papers
Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twi…
arXiv cs.AI Security & Safety
Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents
arXiv cs.AI Research & Papers
Training-Free Action Correction for VLA Model Failures via Language Feedback
arXiv cs.AI Research & Papers
Balance of Benchmarks: Semantic Density Reweighting for Benchmark Multiplicity and Task-C…
arXiv cs.AI Research & Papers
TPR-Attention for Combinatorial Generalization
arXiv cs.AI Research & Papers
Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Compet…
arXiv cs.AI Research & Papers
Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval
arXiv cs.AI Research & Papers
Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation…
arXiv cs.AI Research & Papers
IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and…
arXiv cs.AI Research & Papers
Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered Wi…
arXiv cs.AI Research & Papers
LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientifi…
arXiv cs.AI Research & Papers
Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines
arXiv cs.AI Research & Papers
Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextuali…
arXiv cs.AI Research & Papers
Interpretable Predictability-Based AI Text Detection: A Replication Study
arXiv cs.AI Research & Papers
When Less is More: Understanding When Token Filtering Helps and Fails in AI-generated Tex…
arXiv cs.AI Research & Papers
Reviving our data foundations is the most disruptive step to data maturity
arXiv cs.AI Research & Papers
Evaluating Tiny Recursive Models Across Training for Code Generation
arXiv cs.AI Research & Papers
Ideation Arena: Evaluating LLM Generated Research Ideas with Battle-style Human Expert As…
arXiv cs.AI Research & Papers
Toward Latent Language Model Skills Steering and Optimization: An Empirical Study
arXiv cs.AI Research & Papers
Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued …
arXiv cs.AI Research & Papers
Cross-Relational Preference Learning for Better LLM Instruction Following
arXiv cs.AI Research & Papers
Plant-Inspired AI: Plants as Inspiration for Novel Problem Formulations, and Two Case Stu…
arXiv cs.AI Research & Papers
TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcemen…
arXiv cs.AI Research & Papers
Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilizat…
arXiv cs.AI Research & Papers
SynCrash: A Multi-Stage Pipeline for Zero-Shot Accident Detection and Localization in Tra…
arXiv cs.AI Research & Papers
Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look L…
arXiv cs.AI Research & Papers
REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Len…
arXiv cs.AI Research & Papers
The reach of a verification tool decides its value: A controlled study of verification su…
arXiv cs.AI Research & Papers
Formal Concept Analysis with Three Types of Negation