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
SemPIC: Learning Semantic Position-Independent KV Caches
arXiv cs.AI Research & Papers
RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Mode…
arXiv cs.AI Research & Papers
Visual Distortion Detection in UGC Images Using Large Multimodal Models
arXiv cs.AI Research & Papers
Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent G…
arXiv cs.AI Research & Papers
When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution
arXiv cs.AI Research & Papers
Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adap…
arXiv cs.AI Research & Papers
How Far Do Foundation Models Transfer to Infant Signals? A Cross-Dataset Transfer Audit w…
arXiv cs.AI Research & Papers
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based …
arXiv cs.AI Research & Papers
PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue
arXiv cs.AI Research & Papers
SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment
arXiv cs.AI Research & Papers
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
arXiv cs.AI Research & Papers
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Conti…
arXiv cs.AI Research & Papers
CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting
arXiv cs.AI Research & Papers
SpikeWorld: Fast-State Adaptation for Frozen Spiking World Models
arXiv cs.AI Research & Papers
LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs
arXiv cs.AI Research & Papers
SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation
arXiv cs.AI Research & Papers
Complete, Scalable, and Robust Prioritized Planning for Multi-Robot Ordered Storage and R…
arXiv cs.AI Research & Papers
Multi-Task Consistency-based Detection of Adversarial Attacks
arXiv cs.AI Research & Papers
The Anatomy of a Prompt Injection: A Component Model for Structured Analysis
arXiv cs.AI Research & Papers
From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
arXiv cs.AI Research & Papers
Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reason…
arXiv cs.AI Research & Papers
Vision-Language Grounding as Bidirectional Concept Correspondence
arXiv cs.AI Research & Papers
Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compr…
arXiv cs.AI Research & Papers
Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset…
arXiv cs.AI Research & Papers
Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-o…
arXiv cs.AI Research & Papers
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models
arXiv cs.AI Research & Papers
Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
arXiv cs.AI Research & Papers
Efficient Cross-View Localization in 6G Space-Air-Ground Integrated Network
arXiv cs.AI Research & Papers
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
arXiv cs.AI Research & Papers
Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via…