Theoretical AI

7papers
1.7viability
-25%30d

State of the Field

Recent theoretical advancements in AI are increasingly focused on understanding the underlying mechanics of model behavior and improving their efficiency. Work on spectral superposition is revealing how neural networks manage feature representation, emphasizing the geometric relationships between features, which could enhance interpretability and diagnostics in complex models. Meanwhile, research on rectified flow models is demonstrating significant improvements in sample complexity, offering a more efficient alternative to traditional generative models, which could streamline applications in data generation and simulation. The exploration of self-rewarding language models is shedding light on their iterative alignment capabilities, providing theoretical guarantees that explain their success in improving performance without external feedback. This shift toward rigorous theoretical frameworks not only clarifies existing methodologies but also suggests new pathways for developing AI systems that are both more efficient and interpretable, addressing commercial needs for reliable and understandable AI applications across various industries.

Last updated Mar 3, 2026

Papers

1–7 of 7
Research Paper·Feb 2, 2026

Spectral Superposition: A Theory of Feature Geometry

Neural networks represent more features than they have dimensions via superposition, forcing features to share representational space. Current methods decompose activations into sparse linear features...

2.0 viability
Research Paper·Jan 28, 2026

Order-Optimal Sample Complexity of Rectified Flows

Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport trajectories to be linear f...

2.0 viability
Research Paper·Jan 30, 2026

Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models

Self-Rewarding Language Models (SRLMs) achieve notable success in iteratively improving alignment without external feedback. Yet, despite their striking empirical progress, the core mechanisms driving...

2.0 viability
Research Paper·Jan 20, 2026

Self-Improvement as Coherence Optimization: A Theoretical Account

Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surprising feat, even matching golden finet...

2.0 viability
Research Paper·Feb 26, 2026

The logic of KM belief update is contained in the logic of AGM belief revision

For each axiom of KM belief update we provide a corresponding axiom in a modal logic containing three modal operators: a unimodal belief operator $B$, a bimodal conditional operator $>$ and the unimod...

2.0 viability
Research Paper·Feb 17, 2026

Common Belief Revisited

Contrary to common belief, common belief is not KD4. If individual belief is KD45, common belief does indeed lose the 5 property and keep the D and 4 properties -- and it has none of the other commo...

1.0 viability
Research Paper·Feb 11, 2026

The Manifold of the Absolute: Religious Perennialism as Generative Inference

This paper formalizes religious epistemology through the mathematics of Variational Autoencoders. We model religious traditions as distinct generative mappings from a shared, low-dimensional latent sp...

1.0 viability