Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
arXiv cs.AI Research & Papers
Co-Evolving Structured Knowledge and Reasoning in Language Models
arXiv cs.AI Research & Papers
Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinfor…
arXiv cs.AI Research & Papers
C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning
arXiv cs.AI Research & Papers
Do Language Models Follow Occam's Razor? An Evaluation of Parsimony in Inductive and Abdu…
arXiv cs.AI Research & Papers
LoRA as Oracle
arXiv cs.AI Research & Papers
Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Pr…
arXiv cs.AI Research & Papers
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
arXiv cs.AI Research & Papers
A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Ans…
arXiv cs.AI Research & Papers
Decoupling Planning and Control for Instructable Agents
arXiv cs.AI Research & Papers
Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execu…
arXiv cs.AI Research & Papers
Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detecti…
arXiv cs.AI Research & Papers
High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
arXiv cs.AI Research & Papers
How Language Models Organize and Structure Moral Knowledge
arXiv cs.AI Research & Papers
Stageboost: Recommending Signals Based on Counterfactual Estimation
arXiv cs.AI Research & Papers
Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision T…
arXiv cs.AI Research & Papers
Categorizer Automata for Discounted-Sum Payoffs
arXiv cs.AI Research & Papers
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
arXiv cs.AI Research & Papers
Compositional Online Learning for Semantic Data Processing Systems
arXiv cs.AI Research & Papers
TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection
arXiv cs.AI Research & Papers
STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Coll…
arXiv cs.AI Research & Papers
RCMN: Understanding Misleadingness in Influential Public Discourse
arXiv cs.AI Research & Papers
PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference
arXiv cs.AI Research & Papers
When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue
arXiv cs.AI Research & Papers
Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents
arXiv cs.AI Research & Papers
Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence …
arXiv cs.AI Research & Papers
MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-F…
arXiv cs.AI Research & Papers
Learning Transverse Momentum Distributions from Raw Scattering Events via Conditional Dif…
arXiv cs.AI Research & Papers
Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transfor…
arXiv cs.AI Research & Papers
Active sensing to characterize the heterogeneity of plant stress