A Network Science Perspective on Evaluating Deep Graph Generative Models
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
StainPresetNet: Stain Preset Network for Fast Multi-to-Multi Stain Normalization
Medical Causal Hypothesis Verification with Large Language Models
Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
Agentic programs: an emerging form of scientific software in computational materials scie…
Semi-Supervised Virtual Staining via Morphology Preservation and Histopathological Realis…
Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architec…
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant…
ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Reca…
Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Mode…
Solaris: Towards Interfaces That Are Generated, Not Coded
A Study of Hidden-State Optimization Order in Predictive Coding Networks
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Pro…
SARTM: Segment Any RGB Thermal Model with Language aided Distillation
Towards Effective Structured Context Modeling for Conversational Recommender Systems via …
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Pro…
Visual Framing for News Stance Detection via Image Generation
Building Expressive and Tractable Probabilistic Generative Models: A Review
Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion
ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthet…
VoiceLongMemEval: Do Assistants Remember How You Sounded?
Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and Englis…
EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
Towards a Belief-Based World Model for LLM Agents
In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privile…
A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System…
Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Har…
CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Lan…
DualStake: Dual-Path Confidence Calibration in Deep Research Agents