Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VL…
arXiv cs.AI Research & Papers
ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
arXiv cs.AI Research & Papers
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
arXiv cs.AI Research & Papers
Refinement-based Flow Policy Optimization
arXiv cs.AI Research & Papers
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Re…
arXiv cs.AI Research & Papers
Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks
arXiv cs.AI Research & Papers
Attention Is All You Need (to Avoid Spurious Oscillations)
arXiv cs.AI Research & Papers
Thought without systematicity? Evaluating reasoning models on rule induction tasks
arXiv cs.AI Research & Papers
Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Coll…
arXiv cs.AI Research & Papers
Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LL…
arXiv cs.AI Research & Papers
Adaptive Phase-Switching for Communication-Efficient Federated LoRA Fine-Tuning
arXiv cs.AI Research & Papers
LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM Inferen…
arXiv cs.AI Research & Papers
Signatures of Steerability in Activation Space of Language Models
arXiv cs.AI Research & Papers
A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation i…
arXiv cs.AI Research & Papers
Predictive audio representations for early detection and tracking of hidden dynamic objec…
arXiv cs.AI Research & Papers
Lightweight Generalized DeepFake Face Detection with WAVIE: Wavelet Augmented Vision Inte…
arXiv cs.AI Research & Papers
Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning
arXiv cs.AI Research & Papers
NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass
arXiv cs.AI Research & Papers
Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding
arXiv cs.AI Research & Papers
Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Em…
arXiv cs.AI Research & Papers
Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum …
arXiv cs.AI Research & Papers
Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the …
arXiv cs.AI Research & Papers
OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise
arXiv cs.AI Research & Papers
A property-registry contract for retrieve-or-refuse thermal-mechanical lattice search
arXiv cs.AI Research & Papers
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
arXiv cs.AI Research & Papers
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Imag…
arXiv cs.AI Research & Papers
Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of…
arXiv cs.AI Research & Papers
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
arXiv cs.AI Research & Papers
Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizi…
arXiv cs.AI Research & Papers
Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized …