Four Ways to Grow a Classifier and Why One of Them Cannot Learn
Research
Research News
New papers, breakthroughs and academic AI research
Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping
Research
Constant-Memory Recall: Learned Associations in a Fixed Matrix State
Research
How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds
Research
Ontology-Based Contextual AI Evaluations (OB-CAIE) Methodology
Research
A Low Grounding Score Is Not an Ungrounded Judge: Identifying the Perceptibility Confound in Multimodal Oversight
Research
Query Independent Variable Rate Visual Token Coding
Research
Beyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents
Research
Rules Amortize, Pairings Don't: Linguistic Structure Determines What Latent Task Representations Can Replace In-Context Learning
Research
LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation
Research
Assessing the Impact of Language Disparity on Multilingual Linguistic Ability in Large Language Models
Research
Vmem-$\varphi$: Low-Compute Out-of-Distribution Detection in Spiking Neural Networks from Membrane-Potential Statistics
Research