CLOOPD: Closing the Learner Loop in On-Policy Distillation
Research
Research News
New papers, breakthroughs and academic AI research
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
Research
Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents
Research
PAGE: Partition-Aware Gated KV-Cache Eviction
Research
Pretrained Persona Mixture Models and Tandem Models for Human Simulation
Research
MoSAT: Human Motion Generation from Spatial Audio and Textual Description
Research
HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
Research
The Ups and Downs of Backprop Weights
Research
Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective
Research
Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets
Research
PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems
Research
Ev-YOLO: Uncertainty-Aware Object Detection via a Unified Evidential Formulation
Research