William T. Freeman

Test-Time Training Done Right

MathNet: A Global Multimodal Benchmark for Mathematical Reasoning and Retrieval

HyperBatch: Scaling Contrastive Learning Batch Sizes by Two Orders of Magnitude

GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Spatiotemporal Texture

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Single-pass Adaptive Image Tokenization for Minimum Program Search

I-Con: A Unifying Framework for Representation Learning

Test-Time Training Done Right

Adaptive Length Image Tokenization via Recurrent Allocation