Español

Explorar

Noticias de IA

27413 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
Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs
arXiv cs.AI Research & Papers
ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention…
arXiv cs.AI Research & Papers
Multimodal Model Diffing for Feature Discovery and Control
arXiv cs.AI Research & Papers
Carnot: Interpretable, Interactive, and Optimized Execution of Deep Research Queries
arXiv cs.AI Research & Papers
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Resea…
arXiv cs.AI Research & Papers
Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs
arXiv cs.AI Research & Papers
From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UA…
arXiv cs.AI Research & Papers
Illusion or Integrity? Geometrical Consistency Metric for AIGC Video Quality Evaluation
arXiv cs.AI Research & Papers
Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks
arXiv cs.AI Research & Papers
Communication-efficient distributed hazard difference estimation for heterogeneous multi-…
arXiv cs.AI Research & Papers
DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation
arXiv cs.AI Research & Papers
Predictive safety filter enhanced curriculum learning control for efficient vehicle dynam…
arXiv cs.AI Research & Papers
Evaluating Generative Time-Series Models on Data with Point Masses
arXiv cs.AI Research & Papers
How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Perso…
arXiv cs.AI Research & Papers
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
arXiv cs.AI Research & Papers
Sign Language Recognition Using Original and Synthetic Depth Image Based Point Cloud Data…
arXiv cs.AI Research & Papers
Flow-by-Flow:Content-Judgment Bypass for Governing AI Output in High-Loss Domains
arXiv cs.AI Research & Papers
Automating Deception: Scalable Multi-Turn LLM Jailbreaks
arXiv cs.AI Research & Papers
In-context superposition: human-like working memory interference in large language models
arXiv cs.AI Research & Papers
Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks
arXiv cs.AI Research & Papers
Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders
arXiv cs.AI Research & Papers
FoMoH: A clinically meaningful foundation model evaluation for structured electronic heal…
arXiv cs.AI Research & Papers
Beyond Pixels: Benchmarking and Reward-Based Assessing Framework for Visual Spatial Aesth…
arXiv cs.AI Research & Papers
PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
arXiv cs.AI Research & Papers
Adversarial Latent-State Training for Robust Policies in Partially Observable Domains
arXiv cs.AI Research & Papers
X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid Imitation
arXiv cs.AI Research & Papers
SuperCoder: Assembly Program Superoptimization with Large Language Models
arXiv cs.AI Research & Papers
Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithm…
arXiv cs.AI Research & Papers
Attn-QAT: 4-Bit Attention With Quantization-Aware Training
arXiv cs.AI Research & Papers
SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer