Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document…
arXiv cs.AI Research & Papers
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignme…
arXiv cs.AI Research & Papers
Agentic Proving for Program Verification
arXiv cs.AI Research & Papers
One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
arXiv cs.AI Research & Papers
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
arXiv cs.AI Research & Papers
RAG4Outcome: A Retrieval-Augmented Multimodal Framework for Prognostic Prediction in Chro…
arXiv cs.AI Research & Papers
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self …
arXiv cs.AI Research & Papers
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic V…
arXiv cs.AI Research & Papers
Staging by the Book: Automatic Sleep Stage Classification Using Scoring Rules
arXiv cs.AI Research & Papers
Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learned
arXiv cs.AI Research & Papers
Socially fluent AI decouples conversational signals from source identity in online intera…
arXiv cs.AI Research & Papers
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Mul…
arXiv cs.AI Research & Papers
STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction
arXiv cs.AI Research & Papers
Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Ap…
arXiv cs.AI Research & Papers
V-VLAPS: Value-Guided Planning for Vision-Language-Action Models
arXiv cs.AI Research & Papers
The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small…
arXiv cs.AI Research & Papers
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
arXiv cs.AI Research & Papers
Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?
arXiv cs.AI Research & Papers
Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework fo…
arXiv cs.AI Research & Papers
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
arXiv cs.AI Research & Papers
Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Op…
arXiv cs.AI Research & Papers
A mathematical theory of balancing relational generalization and memorization
arXiv cs.AI Research & Papers
A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptiv…
arXiv cs.AI Research & Papers
Ontological Knowledge Blocks: Executable Compliance and Profile-Based Validation for Trus…
arXiv cs.AI Research & Papers
Parallel Context Compaction for Long-Horizon LLM Agent Serving
arXiv cs.AI Research & Papers
Anatomy-Guided Vision-Language Learning with Angular Prototype Separation for Multi-Label…
arXiv cs.AI Research & Papers
ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation
arXiv cs.AI Research & Papers
Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype V…
arXiv cs.AI Research & Papers
Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Liv…
arXiv cs.AI Research & Papers
LLM Code Smells: A Taxonomy and Detection Approach