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
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
arXiv cs.AI Research & Papers
Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank
arXiv cs.AI Security & Safety
MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
arXiv cs.AI Research & Papers
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustn…
arXiv cs.AI Research & Papers
LieSolver: PDE-Constrained Learning for IBVPs via Lie Symmetries
arXiv cs.AI Research & Papers
Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-…
arXiv cs.AI Research & Papers
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
arXiv cs.AI Research & Papers
Psychometric Comparability of LLM-Based Digital Twins
arXiv cs.AI Research & Papers
A Primer on SO(3) Action Representations in Deep Reinforcement Learning
arXiv cs.AI Research & Papers
Reasoning-Enhanced Rare-Event Prediction with Balanced Outcome Correction
arXiv cs.AI Research & Papers
Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting
arXiv cs.AI Research & Papers
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing …
arXiv cs.AI Research & Papers
Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees…
arXiv cs.AI Research & Papers
HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
arXiv cs.AI Research & Papers
Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasti…
arXiv cs.AI Research & Papers
MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
arXiv cs.AI Research & Papers
Measuring the Redundancy of Decoder Layers in SpeechLLMs
arXiv cs.AI Research & Papers
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
arXiv cs.AI Research & Papers
From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Sc…
arXiv cs.AI Research & Papers
LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
arXiv cs.AI Research & Papers
Optimizing Teacher-Student Partitioning for Scalable Knowledge Distillation on HPC Systems
arXiv cs.AI Research & Papers
GenMatter: Perceiving Physical Objects with Generative Matter Models
arXiv cs.AI Research & Papers
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their …
arXiv cs.AI Research & Papers
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics …
arXiv cs.AI Research & Papers
EAGT: Echocardiography Augmentation for Generalisability and Transferability
arXiv cs.AI Research & Papers
Position Bias Correction is Insufficient for One-Pass Attention Sorting
arXiv cs.AI Research & Papers
Mitigating LLM-based p-Hacking by Preregistering for the Next LLM
arXiv cs.AI Research & Papers
MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
arXiv cs.AI Research & Papers
Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinem…
arXiv cs.AI Research & Papers
Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing