Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
Geometry of Ordinal Representations in Language Models
Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersec…
Broken Ergodicity and the Violation of the Fluctuation-Dissipation Theorem Lead to Genera…
Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers
Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming
Efficient Discovery of Conditional Dependencies with Desbordante
How your smartwatch and AI might detect early signs of illness
MANCE: Manifold Aware Concept Erasure
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generat…
Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-r…
ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration
An Interpretable Deep Learning Framework for Discovery and Clinical Validation of Deep Ra…
AI saves about 3% of your hours, and almost none of it reaches the money
Google DeepMind and A24 announce first-of-its-kind research partnership
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Inter…
LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional…
Gravity-Awareness: Deep Learning Models and LLM Simulation of Human Awareness in Altered …
Locality-Aware Continual Unlearning for Diffusion Models
Spanning Tree Autoregressive Visual Generation
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-L…
Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training
Towards Cellular-Scale Interpretability in Pathology Foundation Models for Biomarker Asse…
SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment
UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement
Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation
Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Effici…
MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning