MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation
Research
Research News
New papers, breakthroughs and academic AI research
Mobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian Splatting
Research
ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
Research
From Token-Max to Outcome-Max: How You Use AI Determines Its Productivity
Research
Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes
Research
Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery
Research
F$^2$ SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAM
Research
Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning
Research
Hybrid-Basis Feature Forecasting for Diffusion Sampling Acceleration
Research
When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA
Research
Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems
Research
FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis
Research