Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
-
Updated
May 17, 2025 - Python
#
scaling-law
Here are 11 public repositories matching this topic...
[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
imitation-learning robot-learning quadruped visual-navigation video-learning outdoor-navigation embodied-ai embodied-navigation urban-navigation scaling-law point-goal-navigation cvpr2025
-
Updated
Sep 19, 2025 - Python
Implements the paper "Wukong: Towards a Scaling Law for Large-Scale Recommendation" from Meta.
-
Updated
Dec 19, 2024 - Python
Navigating Model Phase Transitions to Enable Extreme Lossless Compression: A Perspective
nlp quantization model-compression pruning-optimization llm scaling-law low-rank-decomposition model-phase-transitions
-
Updated
Feb 9, 2026
This is an official repository for "Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources" (NeurIPS 2023).
-
Updated
Oct 26, 2023 - Python
(NeurIPS 2025) Official Code for L²M: Mutual Information Scaling Law for Long-Context Language Modeling
-
Updated
Nov 9, 2025 - Python
Scaling Law of Neural Koopman Operators
-
Updated
Mar 2, 2026 - C++
Theory-derived PyTorch optimizer matching Adam with zero tuning. τ* = κ√(σ²/λ) — validated on CIFAR-10 and CIFAR-100
machine-learning deep-learning neural-network optimizer pytorch cifar10 adam-optimizer cifar100 adaptive-learning-rate scaling-law
-
Updated
Feb 17, 2026 - Jupyter Notebook
Scaling laws for positron production in laser–electron-beam collisions
-
Updated
Jul 12, 2024 - Jupyter Notebook
Optimize learning rates dynamically with the Syntonic optimizer, enhancing performance beyond Adam without the need for hyperparameter tuning.
machine-learning deep-learning neural-network optimizer pytorch cifar10 adam-optimizer cifar100 adaptive-learning-rate scaling-law
-
Updated
Jul 17, 2025
Bond Order Scaling Law: 100% accurate molecular vs crystalline prediction for binary compounds. Cascade classifier L4→L5→L6 covering 76K JARVIS-DFT materials. No DFT required.
chemistry crystal-structure materials-science periodic-table cascade-classifier interpretable-ml dimensionality molecular-prediction scaling-law oxidation-state binary-compounds jarvis-dft bond-order staircase-method
-
Updated
Apr 13, 2026 - Python
Improve this page
Add a description, image, and links to the scaling-law topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the scaling-law topic, visit your repo's landing page and select "manage topics."