Entity · paper

On Subquadratic Architectures: From Applications to Principles

paperactiveon-subquadratic-architectures-from-applications-to-principles-1d849fe9·1 events·first seen Jun 11, 2026

Aliases: On Subquadratic Architectures: From Applications to Principles

Co-occurring entities

More like this (12)

Subquadratic Braun et al. 2025 Compressed Computation Goedel-Architect Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures OpenSCAD Architectural 3D LLM Benchmark Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth Extractable Memorization From First Principles From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs Sparse Circuits Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs

Recent events (1)

5arXiv · cs.LG·Jun 11, 2026·source ↗

Comparative study finds xLSTM outperforms Mamba-2 and Gated DeltaNet on complex sequence tasks

A new arXiv paper compares three subquadratic sequence modeling architectures — xLSTM, Mamba-2, and Gated DeltaNet — across code model pre-training, LLM distillation, and time-series foundation model pre-training. xLSTM consistently delivers the strongest performance, which the authors attribute to more flexible and stable memory correction via its gating scheme. The paper provides a unified formulation and analysis of state tracking and memory dynamics across the three architectures, with corroborating results on synthetic length-generalization tasks.

Training Infrastructure Evaluation and Benchmarking Mamba On Subquadratic Architectures: From Applications to Principles Gated DeltaNet-2 +1 more