Image de couverture de livre

Speeding Up MACE: Low-Precision Tricks for Equivarient Force Fields

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Benoit, Alexandre
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Diagnosing Spectral Ceilings in Equivariant Neural Force Fields
par: Kim, Hyunmog
Publié: (2026)

MARA: Continuous SE(3)-Equivariant Attention for Molecular Force Fields
par: Leonardi, Francesco, et autres
Publié: (2026)

Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction
par: Xu, Zhao, et autres
Publié: (2024)

Speed-up of Data Analysis with Kernel Trick in Encrypted Domain
par: Yoo, Joon Soo, et autres
Publié: (2024)

Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields
par: Liao, Yi-Lun, et autres
Publié: (2024)

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
par: Ramesh, Aditya A., et autres
Publié: (2024)

Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments
par: Du, Yipeng, et autres
Publié: (2025)

Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments
par: Andres, Alain, et autres
Publié: (2023)

Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
par: García-Castellanos, Alejandro, et autres
Publié: (2026)

LLaDA2.1: Speeding Up Text Diffusion via Token Editing
par: Bie, Tiwei, et autres
Publié: (2026)

MACE: Mass Concept Erasure in Diffusion Models
par: Lu, Shilin, et autres
Publié: (2024)

Enhancing LLM Evaluations: The Garbling Trick
par: Bradley, William F.
Publié: (2024)

Teach Me to Trick: Exploring Adversarial Transferability via Knowledge Distillation
par: Pradhan, Siddhartha, et autres
Publié: (2025)

Transformer Based Planning in the Observation Space with Applications to Trick Taking Card Games
par: Rebstock, Douglas, et autres
Publié: (2024)

Teach Old SAEs New Domain Tricks with Boosting
par: Koriagin, Nikita, et autres
Publié: (2025)

STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization
par: Federici, Marco, et autres
Publié: (2025)

Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics
par: Benoit, Alexandre, et autres
Publié: (2025)

Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen Estimator
par: Watanabe, Shuhei, et autres
Publié: (2022)

Neural Force Field: Few-shot Learning of Generalized Physical Reasoning
par: Li, Shiqian, et autres
Publié: (2025)

Improving the Stability of GNN Force Field Models by Reducing Feature Correlation
par: Zeng, Yujie, et autres
Publié: (2025)

Equivariant Symmetry Breaking Sets
par: Xie, YuQing, et autres
Publié: (2024)

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
par: Wang, Kai, et autres
Publié: (2024)

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
par: Legate, Gwen, et autres
Publié: (2025)

Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
par: Jin, Dian, et autres
Publié: (2025)

Field Assessment of Force Torque Sensors for Planetary Rover Navigation
par: Gerdes, Levin, et autres
Publié: (2024)

Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities
par: Hao, Zhiwei, et autres
Publié: (2025)

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
par: Qiu, Haiquan, et autres
Publié: (2025)

Algebraic Priors for Approximately Equivariant Networks
par: Ali, Riccardo, et autres
Publié: (2025)

Separation Power of Equivariant Neural Networks
par: Pacini, Marco, et autres
Publié: (2024)

Symbol-Equivariant Recurrent Reasoning Models
par: Freinschlag, Richard, et autres
Publié: (2026)

Contrastive Learning Via Equivariant Representation
par: Song, Sifan, et autres
Publié: (2024)

Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments
par: Yang, Yuzhe, et autres
Publié: (2024)

Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection
par: Kelodjou, Gwladys, et autres
Publié: (2023)

Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
par: Emadi, Seyed Morteza
Publié: (2026)

Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference
par: Ding, Yifu, et autres
Publié: (2026)

Learning Equivariant Functions via Quadratic Forms
par: Karjol, Pavan, et autres
Publié: (2025)

Mathematical Foundation of Interpretable Equivariant Surrogate Models
par: Colombini, Jacopo Joy, et autres
Publié: (2025)

Equivariant Spherical Transformer for Efficient Molecular Modeling
par: An, Junyi, et autres
Publié: (2025)

Controlled Generation with Equivariant Variational Flow Matching
par: Eijkelboom, Floor, et autres
Publié: (2025)

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
par: Kim, Jinwoo, et autres
Publié: (2023)