Español

Explorar

Noticias de IA

22115 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
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question …
arXiv cs.AI Research & Papers
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
arXiv cs.AI Research & Papers
Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
arXiv cs.AI Research & Papers
CITRAS: Covariate-Informed Transformer for Time Series Forecasting
arXiv cs.AI Research & Papers
Provenance Tracking in AI Compilers through the Lens of Coalgebra
arXiv cs.AI Research & Papers
Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Fea…
arXiv cs.AI Research & Papers
Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diag…
arXiv cs.AI Research & Papers
T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains
arXiv cs.AI Research & Papers
Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision…
arXiv cs.AI Research & Papers
Unifying Local Communications and Local Updates for LLM Pretraining
arXiv cs.AI Research & Papers
PhantomBench: Benchmarking the Non-existential Threat of Language Models
arXiv cs.AI Research & Papers
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
arXiv cs.AI Research & Papers
Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation
arXiv cs.AI Research & Papers
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
arXiv cs.AI Research & Papers
Benchmarking Knowledge Editing using Logical Rules
arXiv cs.AI Research & Papers
ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark
arXiv cs.AI Research & Papers
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogat…
arXiv cs.AI Research & Papers
Quantifying Perception-Based Student Success with Generative AI: An Exploratory Monte Car…
arXiv cs.AI Research & Papers
GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning
arXiv cs.AI Research & Papers
Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection
arXiv cs.AI Research & Papers
Learning Evidence Highlighting for Frozen LLMs
arXiv cs.AI Research & Papers
Does Normalization Choice Matter for Causal Large Time-Series Models?
arXiv cs.AI Research & Papers
LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts
arXiv cs.AI Research & Papers
Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
arXiv cs.AI Research & Papers
MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
arXiv cs.AI Research & Papers
ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents
arXiv cs.AI Research & Papers
Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feat…
arXiv cs.AI Research & Papers
Mix, Don't Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Mode…
arXiv cs.AI Research & Papers
RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
arXiv cs.AI Research & Papers
GRAU: Generic Reconfigurable Activation Unit Design for Neural Network Hardware Accelerat…