Español

Explorar

Noticias de IA

21863 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
When Model Merging Breaks Routing: Training-Free Calibration for MoE
arXiv cs.AI Research & Papers
Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Ge…
arXiv cs.AI Research & Papers
scTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation
arXiv cs.AI Research & Papers
PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy…
arXiv cs.AI Research & Papers
SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts
arXiv cs.AI Research & Papers
Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in M…
arXiv cs.AI Research & Papers
When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillat…
arXiv cs.AI Research & Papers
When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming
arXiv cs.AI Research & Papers
Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks
arXiv cs.AI Research & Papers
CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery
arXiv cs.AI Research & Papers
PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models
arXiv cs.AI Research & Papers
How Quantization Changes Interpretable Features: A Sparse Autoencoder Analysis of Languag…
arXiv cs.AI Research & Papers
Are we really tilting? The mechanics of reward guidance in flow and diffusion models
arXiv cs.AI Research & Papers
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
arXiv cs.AI Research & Papers
Building Reliable Long-Form Generation via Hallucination Rejection Sampling
arXiv cs.AI Research & Papers
TurtleAI: Benchmarking Multimodal Models for Visual Programming in Turtle Graphics
arXiv cs.AI Research & Papers
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Context…
arXiv cs.AI Research & Papers
Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism
arXiv cs.AI Research & Papers
Staying Alive: Uncensored Survival Analysis with Tabular Foundation Models
arXiv cs.AI Research & Papers
AUGUSTE: Online-Learning dApp for Predictive URLLC Scheduling
arXiv cs.AI Research & Papers
MemVerse: Multimodal Memory for Lifelong Learning Agents
arXiv cs.AI Research & Papers
PURGE: Projected Unlearning via Retain-Guided Erasure
arXiv cs.AI Research & Papers
Trading Human Curation for Synthetic Augmentation in RLVR
arXiv cs.AI Research & Papers
Signed Spiking Neuron Enabled by an Orthogonal-Easy-Axis Magnetic Tunnel Junction
arXiv cs.AI Research & Papers
E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments
arXiv cs.AI Research & Papers
FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collabo…
arXiv cs.AI Research & Papers
VeRO: A Harness for Agents to Optimize Agents
arXiv cs.AI Research & Papers
Conditional Latent Diffusion Model with Fourier-based Motion Modelling for Virtual Popula…
arXiv cs.AI Research & Papers
Consistency Training Can Entrench Misalignment
arXiv cs.AI Research & Papers
Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM…