Explorar

Noticias de IA

21861 elementos — filtrados, clasificados y sin duplicados

Hugging Face Daily Papers Research & Papers
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign a…
Hugging Face Daily Papers Research & Papers
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
Hugging Face Daily Papers Research & Papers
Self-Supervised Representation-Guided Generative Dataset Distillation
Hugging Face Daily Papers Research & Papers
On the Implicit Flatness Bias of Sharpness-Aware Minimization: A Linear Stability Analysi…
Hugging Face Daily Papers Research & Papers
Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning
Hugging Face Daily Papers Research & Papers
SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retri…
Hugging Face Daily Papers Research & Papers
Double Descent in Gradient Boosting Decision Trees via Split-Candidate Scaling
Hugging Face Daily Papers Research & Papers
Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language…
Hugging Face Daily Papers Research & Papers
A Unified Resolution-Conditioned Framework for Orthogonal Line-Scanning Image Fusion
Hugging Face Daily Papers Research & Papers
FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepf…
Hugging Face Daily Papers Research & Papers
Scalable Frequency- and Length-Aware Subdocument Deduplication for Large Language Model P…
Hugging Face Daily Papers Research & Papers
SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation
arXiv cs.AI Research & Papers
MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents
arXiv cs.AI Research & Papers
Cost-Effective Automated Judging of Natural-Language Mathematical Proofs
arXiv cs.AI Research & Papers
Width, Memory, and Delay: A Resource Accounting for the Limits of Flat Multi-Agent Systems
arXiv cs.AI Research & Papers
Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response
arXiv cs.AI Research & Papers
Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiab…
arXiv cs.AI Research & Papers
MechGeo: Autoformalizing and Proving Euclidean Geometry in Lean 4
arXiv cs.AI Research & Papers
Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit
arXiv cs.AI Research & Papers
SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
arXiv cs.AI Research & Papers
What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs
arXiv cs.AI Research & Papers
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Bas…
arXiv cs.AI Research & Papers
Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating
arXiv cs.AI Research & Papers
Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability
arXiv cs.AI Research & Papers
From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized L…
arXiv cs.AI Research & Papers
Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation
arXiv cs.AI Research & Papers
PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with…
arXiv cs.AI Research & Papers
Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies
arXiv cs.AI Research & Papers
SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agents
arXiv cs.AI Research & Papers
MonitrLLM: A Community-Centered Evaluation Infrastructure for Large Language Models