Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing Fal…
arXiv cs.AI Research & Papers
Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models
arXiv cs.AI Research & Papers
Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction
arXiv cs.AI Research & Papers
Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models
arXiv cs.AI Research & Papers
Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
arXiv cs.AI Research & Papers
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Conc…
arXiv cs.AI Research & Papers
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters
arXiv cs.AI Security & Safety
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
arXiv cs.AI Research & Papers
Tracing Audio Grounding and Answer Selection in Audio LLMs
arXiv cs.AI Research & Papers
Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets
arXiv cs.AI Research & Papers
Hakken: Predicting future discoveries to fill the gaps in today's knowledge
arXiv cs.AI Research & Papers
Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Soft…
arXiv cs.AI Research & Papers
A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual …
arXiv cs.AI Research & Papers
Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language…
arXiv cs.AI Research & Papers
A Roadmap for MEG Foundation Models
arXiv cs.AI Research & Papers
What Moves? Localized Motion Representations for Compositional Scene Control
arXiv cs.AI Security & Safety
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
arXiv cs.AI Research & Papers
Scalable Context Orchestration for Serving LLMs Over Voice
arXiv cs.AI Research & Papers
Evidence Integration in Large Language Models
arXiv cs.AI Research & Papers
A Deep Generative Model for Synthesizing Labeled Wireless Signals
arXiv cs.AI Research & Papers
Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based F…
arXiv cs.AI Research & Papers
Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents
arXiv cs.AI Research & Papers
Abstraction Agent
arXiv cs.AI Research & Papers
Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Di…
arXiv cs.AI Research & Papers
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence
arXiv cs.AI Research & Papers
Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Th…
arXiv cs.AI Research & Papers
CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review
arXiv cs.AI Research & Papers
ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs
arXiv cs.AI Research & Papers
Substrate-Aware AI Agents: Execution Context as a First-Class Input
arXiv cs.AI Research & Papers
Building a research-software catalog with a coding agent: from hackathon prototype to pub…