MatRIS-10M-MP

Version: v1 Added: 2025-10-29 Published: 2025-10-29 10.4M parameters Missing preds: 25 (0.01%)
Repo Paper Docs DOI Files PR Checkpoint
Predictions
κSRMEGeometry OptimizationDiscovery

Convex hull distance prediction errors projected onto elements

1 H 0.18
2 He 0.00
3 Li 0.03
4 Be 0.05
5 B 0.08
6 C 0.07
7 N 0.10
8 O 0.11
9 F 0.12
10 Ne 0.00
11 Na 0.04
12 Mg 0.05
13 Al 0.08
14 Si 0.08
15 P 0.07
16 S 0.09
17 Cl 0.11
18 Ar 0.00
19 K 0.05
20 Ca 0.05
21 Sc 0.05
22 Ti 0.05
23 V 0.07
24 Cr 0.10
25 Mn 0.13
26 Fe 0.12
27 Co 0.07
28 Ni 0.06
29 Cu 0.05
30 Zn 0.05
31 Ga 0.07
32 Ge 0.07
33 As 0.07
34 Se 0.11
35 Br 0.09
36 Kr 0.00
37 Rb 0.05
38 Sr 0.05
39 Y 0.05
40 Zr 0.06
41 Nb 0.07
42 Mo 0.07
43 Tc 0.07
44 Ru 0.09
45 Rh 0.08
46 Pd 0.07
47 Ag 0.05
48 Cd 0.05
49 In 0.08
50 Sn 0.07
51 Sb 0.07
52 Te 0.13
53 I 0.08
54 Xe 0.03
55 Cs 0.05
56 Ba 0.05
57 La 0.05
58 Ce 0.05
59 Pr 0.05
60 Nd 0.04
61 Pm 0.04
62 Sm 0.05
63 Eu 0.07
64 Gd 0.06
65 Tb 0.05
66 Dy 0.05
67 Ho 0.05
68 Er 0.05
69 Tm 0.05
70 Yb 0.05
71 Lu 0.05
72 Hf 0.06
73 Ta 0.09
74 W 0.07
75 Re 0.07
76 Os 0.08
77 Ir 0.10
78 Pt 0.09
79 Au 0.08
80 Hg 0.05
81 Tl 0.05
82 Pb 0.07
83 Bi 0.05
84 Po 0.00
85 At 0.00
86 Rn 0.00
87 Fr 0.00
88 Ra 0.00
89 Ac 0.05
90 Th 0.07
91 Pa 0.08
92 U 0.08
93 Np 0.15
94 Pu 0.36
95 Am 0.00
96 Cm 0.00
97 Bk 0.00
98 Cf 0.00
99 Es 0.00
100 Fm 0.00
101 Md 0.00
102 No 0.00
103 Lr 0.00
104 Rf 0.00
105 Db 0.00
106 Sg 0.00
107 Bh 0.00
108 Hs 0.00
109 Mt 0.00
110 Ds 0.00
111 Rg 0.00
112 Cn 0.00
113 Nh 0.00
114 Fl 0.00
115 Mc 0.00
116 Lv 0.00
117 Ts 0.00
118 Og 0.00
57-71 La-Lu Lanthanides
89-103 Ac-Lr Actinides

Model Authors

  1. Yuanchang Zhou  Institute of Computing Technology, Chinese Academy of Sciences    
  2. Siyu Hu  Institute of Computing Technology, Chinese Academy of Sciences    
  3. Guangming Tan  Institute of Computing Technology, Chinese Academy of Sciences    
  4. Weile Jia  Institute of Computing Technology, Chinese Academy of Sciences    

Trained By

  1. Yuanchang Zhou (Institute of Computing Technology, Chinese Academy of Sciences)

Model Info

  • Model Version v1
  • Model Type UIP
  • Targets EFSGM
  • Openness OSOD
  • Train Task S2EFSM
  • Test Task IS2RE-SR
  • Trained for Benchmark Yes

Training Set

MPtrj: 1.58M structures from 146k materials

Description

MatRIS is a foundation model for materials representation and interaction simulation.

Hyperparameters

  • max_force: 0.05
  • max_steps: 500
  • ase_optimizer: "FIRE"
  • optimizer: "AdamW(wd=1e-2)"
  • cell_filter: "FrechetCellFilter"
  • loss: "MAE/L2MAE"
  • loss_weights: {"energy":5,"force":5,"stress":0.1,"magmom":0.1}
  • batch_size: 512
  • initial_learning_rate: 0.0003
  • learning_rate_schedule: "CosineAnnealingLR(T_max=100)"
  • n_layers: 10
  • graph_construction_radius: 6
  • three_body_cutoff: 4.5
  • max_neighbors: null

Dependencies