ESCROW: Guarded and Dual-Objective Continual Maintenance for Agents in Policy-Governed Enterprise Workflows
Research
Research News
New papers, breakthroughs and academic AI research
Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
Research
Debias Anything: Fairness with Diversity without Supervision in Diffusion Models
Research
What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives
Research
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
Research
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Research
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
Research
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization
Research
Generalized Design Choices for Deepfake Detectors
Research
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
Research
MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration
Research
MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection
Research