The spectral edge transitions from a gradient-driven functional direction before grokking to a perturbation-flat, ablation-critical compression axis at grokking, forming three universality classes predicted by a gap flow equation.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Vim is a bidirectional Mamba vision backbone that outperforms DeiT in accuracy on standard tasks while being substantially faster and more memory-efficient for high-resolution images.
TabPack packs MLPs with diverse sampled hyperparameters into one vectorized model, selects ensemble members online during training, and matches tuned baselines at a fraction of the compute cost.
GXPO approximates longer local lookahead in GRPO training via gradient extrapolation from two optimizer steps using three backward passes total, improving pass@1 accuracy by 1.65-5.00 points over GRPO and delivering up to 4x step speedup.
UDM-GRPO integrates reinforcement learning with Uniform Discrete Diffusion Models by treating the final clean sample as the action and reconstructing trajectories via the forward process, achieving state-of-the-art text-to-image performance.
citing papers explorer
-
The Lifecycle of the Spectral Edge: From Gradient Learning to Weight-Decay Compression
The spectral edge transitions from a gradient-driven functional direction before grokking to a perturbation-flat, ablation-critical compression axis at grokking, forming three universality classes predicted by a gap flow equation.
-
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Vim is a bidirectional Mamba vision backbone that outperforms DeiT in accuracy on standard tasks while being substantially faster and more memory-efficient for high-resolution images.
-
TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning
TabPack packs MLPs with diverse sampled hyperparameters into one vectorized model, selects ensemble members online during training, and matches tuned baselines at a fraction of the compute cost.
-
Gradient Extrapolation-Based Policy Optimization
GXPO approximates longer local lookahead in GRPO training via gradient extrapolation from two optimizer steps using three backward passes total, improving pass@1 accuracy by 1.65-5.00 points over GRPO and delivering up to 4x step speedup.
-
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
UDM-GRPO integrates reinforcement learning with Uniform Discrete Diffusion Models by treating the final clean sample as the action and reconstructing trajectories via the forward process, achieving state-of-the-art text-to-image performance.