← Back to all news
arXiv AI By Allex Kan, Ji Zhang, Hao Yin, Hao Li, Owen Fu, Xunxing Chen, Lin Huang, Zion Wang, Lucas Li, Jiajun Cheng, Arthur Jiang, Junping Zhao, Jia Zhang

Ab Initio Accuracy Beyond the Cutoff: Distributed Message-Passing Equivariant Attention at Tens-of-Millions-of-Atom Scale

Read the original on arXiv AI →

The paper introduces Tessera, a distributed runtime that enables equivariant message‑passing Transformers to simulate molecular dynamics at ab initio accuracy for tens of millions of atoms. By sorting atoms along a space‑filling curve and maintaining consistent workload shapes, Tessera achieves near‑linear scaling on 512 GPUs, sustaining 30.7 million atoms with high weak‑scaling efficiency and low energy drift in large‑scale simulations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 9

ASPIRE: Saddle-Point Discovery through Set Prediction and Physical Refinement

ASPIRE (Atomistic Saddle-Point Inference with Refinement for Events) is a new framework that predicts multiple saddle-point candidates from a single atomic environment and refines them using Dimer searches on the original interatomic potential. Its equivariant set predictor, Ev-Quiformer, generates proposals via geometry-conditioned scalar‑vector event slots and decodes them into full atomic displacement fields. The authors provide two new datasets—BCCFE4VACAV‑4000 and BCCFE‑1TO4VAC—and demonstrate that ASPIRE achieves 77.20 % reference‑event coverage, outperforming a conventional Dimer baseline while halving the number of force evaluations and reducing wall‑time per configuration from 478.8 s to 176.3 s.

By Yucheng Zhao, Quanyou Zhang, Shaoxiang Qin, Haixuan Xu, Xiongye Xiao
diffusionbenchmarks
More like this →
arXiv AI
Oct 1

TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training

arXiv:2604.09107v2 Announce Type: replace-cross Abstract: Modern LLM reinforcement learning (RL) workloads require a high-performance weight transfer system to scale training across heterogeneous com...

By Chenhao Ye, Huaizheng Zhang, Mingcong Han, Baoquan Zhong, Xiang Li, Qixiang Chen, Xinyi Zhang, Weidong Zhang, Kaihua Jiang, Wang Zhang, He Sun, Wencong Xiao, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
llmsreinforcement-learning
More like this →
arXiv Machine Learning
Oct 12

Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On

The paper examines the commonly used structure‑disjoint split for evaluating molecular machine learning models, which relies on single‑linkage clustering with the Maximum Common Edge Subgraph (MCES) distance at a threshold of 10. The authors show that this criterion, originally calibrated on 29,000 molecules, has never been tested on the current public libraries of 227,690 molecules due to its NP‑hard complexity. They propose an optimized algorithm that reduces the number of required integer programs from $2.6 imes10^{10}$ to $1.15 imes10^{7}$, enabling lossless partitioning at scale, and reveal that the resulting graph percolates—over 95 % of the library lies in a single component, making held‑out compounds systematically larger and more complex than training ones. "whyItMatters":"The study highlights that large‑library benchmarks using the traditional split conflate structural novelty with extrapolation to larger, more complex chemistry, potentially misleading assessments of model generalization."

By Tomo Oga, Devesh Shah, Cailum M. K. Stienstra, Gabriel Asher, Antonio H. de O. Fonseca, Niall O'Connor, Michael Widrich
benchmarks
More like this →