A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
hub
nature , volume=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
representative citing papers
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
Neural networks possess a propagation field of trajectories and Jacobians whose quality can be measured and optimized independently of endpoint loss, yielding better unseen-path generalization and reduced forgetting in continual learning.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
A pre-activation regularizer seeds more affine regions near data in piecewise affine networks, increasing local region count and improving early training performance.
Gemma introduces open 2B and 7B LLMs derived from Gemini technology that beat comparable open models on 11 of 18 text tasks and come with safety assessments.
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
-
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
-
Convergence of difference inclusions via a diameter criterion
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
-
The Propagation Field: A Geometric Substrate Theory of Deep Learning
Neural networks possess a propagation field of trajectories and Jacobians whose quality can be measured and optimized independently of endpoint loss, yielding better unseen-path generalization and reduced forgetting in continual learning.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
-
PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.
-
Are Candidate Models Really Needed for Active Learning?
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
-
Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks
A pre-activation regularizer seeds more affine regions near data in piecewise affine networks, increasing local region count and improving early training performance.
-
Gemma: Open Models Based on Gemini Research and Technology
Gemma introduces open 2B and 7B LLMs derived from Gemini technology that beat comparable open models on 11 of 18 text tasks and come with safety assessments.
-
Gemma 2: Improving Open Language Models at a Practical Size
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.