MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting
Research
Research News
New papers, breakthroughs and academic AI research
Beyond the Good, the Bad, and the Ugly: Colormap Assessment through Data-Aware Perceptual Metric
Research
Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
Research
SUAVE: Unified Video-Action Models via Masked Diffusion
Research
OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies
Research
TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel
Research
EpicWorldModel: Exploration-driven Planning with Latent World Models
Research
Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?
Research
Feature identification for parameter extraction and defect detection using machine learning
Research
ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning
Research
Runaway Reaction: When Benign Skills Compose into Malicious Behavior
Research
AgentSpy: Making AI Agent Behavior Observable
Research