cover

Why Judgmental Equality Fails Under Defunctionalization

4 Mar 2026

Exploring how defunctionalization breaks judgmental and eta equality—and the naming-based solution that preserves type safety.

cover

The Proof Expression Problem, Reimagined Through Object-Oriented Lenses

4 Mar 2026

A case study showing how dependently typed OOP enables modular web servers, extensible routes, and type-level enforcement of HTTP properties.

cover

Rethinking OOP Through Dependent Types and Codata

4 Mar 2026

A deep dive into dependently typed object-oriented programming, codata design, self-parameters, and verified interfaces.

cover

Deriving Dependently-Typed OOP from First Principles

4 Mar 2026

A new calculus unifies functional and object-oriented paradigms in dependently typed languages using duality and defunctionalization.

cover

Concatenated Masked Autoencoders as Spatial-Temporal Learner: Conclusion & References

27 Feb 2024

In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning.

cover

Concatenated Masked Autoencoders as Spatial-Temporal Learner: Experiments

27 Feb 2024

In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning.

cover

Concatenated Masked Autoencoders as Spatial-Temporal Learner: Method

27 Feb 2024

In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning.

cover

Concatenated Masked Autoencoders as Spatial-Temporal Learner: Related Work

27 Feb 2024

In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning.

cover

Concatenated Masked Autoencoders as Spatial-Temporal Learner: Abstract & Intro

27 Feb 2024

In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning.