Partial AUC Maximization from Positive-unlabeled Data
Research
Research News
New papers, breakthroughs and academic AI research
ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality
Research
Enterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AI
Research
Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping
Research
Closing the Loop: Practical Training Recipes for Looped Language Models
Research
Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow
Research
VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision
Research
PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
Research
Towards Robust Numerical Claim Verification
Research
Harnessing Vision-Language Models for Perceptual Quality Assessment and Autonomous Content Adjustment in Augmented Reality
Research
FedMAD: Modulation-Aware Directional Aggregation for Federated Learning in Remote Sensing Image Classification
Research
What Builds the Scene? Luminance Dominates Geometry Formation in 3D Gaussian Splatting
Research