SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.30992 · ICML · 2026

Eigenvectors of Experts are Training-free Non-collapsing Routers

Hung Le, Truyen Tran, Giang Do

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2605.30992.json · badge: /api/ran/2605.30992.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
giangdip2410/SSMoE canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_deepseek.py
pointer only (licence: NONE) · get_code("30d7eec482ebf6b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_deepseek.py
pointer only (licence: NONE) · get_code("d61c483a3c2b3156")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_rotary_pos_emb Ran
ran; our contract draft was wrong, not the code
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_olmoe.py
pointer only (licence: NONE) · get_code("bac65c3dafaec040")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_gpus_max_memory Ran
ran; our contract draft was wrong, not the code
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/eval_mteb.py
pointer only (licence: NONE); the stored copy get_code serves, from tianyi-lab/moe-embedding, is pointer only (licence: NONE) · get_code("aecadcaa2ac48b1b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gritlm_instruction_format Ran
ran; our contract draft was wrong, not the code
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/eval_mteb.py
pointer only (licence: NONE); the stored copy get_code serves, from tianyi-lab/moe-embedding, is pointer only (licence: NONE) · get_code("62866964865efbd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_balancing_loss_func Ran
ran, violated the contract we drafted
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_olmoe.py
pointer only (licence: NONE); the stored copy get_code serves, from tianyi-lab/moe-embedding, is pointer only (licence: NONE) · get_code("d0725ff0666ee959")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_balancing_loss_func Ran
ran, violated the contract we drafted
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_gritlm8x7b.py
pointer only (licence: NONE) · get_code("e566aca3f6f9392e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_balancing_loss_func Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
giangdip2410/SSMoE/SSMoE/Vision/CLIP-SSMoE/clipmoe/model_clipmoe.py
pointer only (licence: NONE) · get_code("25b8549e7bd56c7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rotate_half Ran
ran; our contract draft was wrong, not the code
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_deepseek.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

zephyr_instruction_format Ran
ran; our contract draft was wrong, not the code
giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/eval_mteb.py
pointer only (licence: NONE); the stored copy get_code serves, from tianyi-lab/moe-embedding, is pointer only (licence: NONE) · get_code("a591f38d473d9770")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_model Not yet run
unverified (harvested, no recorded run)
giangdip2410/SSMoE/SSMoE/Vision/CLIP-SSMoE/clipmoe/model_clipmoe.py
pointer only (licence: NONE) · get_code("640bc7cbe2f90309")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, giangdip2410/SSMoE when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 4 the same month, 4 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
rotate_half 360 other papers
340 dated earlier, 5 the same month, 12 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv 243 other papers
228 dated earlier, 4 the same month, 9 later, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb 94 other papers
84 dated earlier, 1 the same month, 6 later, 3 undated · 6 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
2309.11674 (2023-09)
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
and 91 more not named here
apply_rotary_pos_emb 75 other papers
73 dated earlier, 1 the same month, 1 later · 2 only as an assembly brick
2309.11499 (2023-09)
DreamLLM: Synergistic Multimodal Comprehension and Creation
2312.02051 (2023-12)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
2312.03414 (2023-12)
Compressed Context Memory For Online Language Model Interaction
and 72 more not named here
get_gpus_max_memory 4 other papers
4 dated earlier
2402.09906 (2024-02)
Generative Representational Instruction Tuning
2408.09121 (2024-08)
Selective Prompt Anchoring for Code Generation
2410.10814 (2024-10)
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
and 1 more not named here
gritlm_instruction_format 2 other papers
2 dated earlier
2402.09906 (2024-02)
Generative Representational Instruction Tuning
2410.10814 (2024-10)
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
load_balancing_loss_func 2 other papers
2 dated earlier
2410.10814 (2024-10)
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
2506.13585 (2025-06)
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
load_balancing_loss_func 2 other papers
2 dated earlier
2404.15574 (2024-04)
Retrieval Head Mechanistically Explains Long-Context Factuality
2503.06881 (2025-03)
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
zephyr_instruction_format 2 other papers
2 dated earlier
2402.09906 (2024-02)
Generative Representational Instruction Tuning
2410.10814 (2024-10)
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sparse Mixture of Experts (SMoE) architectures improve the training efficiency of Large Language Models (LLMs) by routing input tokens to a selected subset of specialized experts. Despite their remarkable success, both training and inference in SMoE models suffer from the expert collapse issue (Chi et al., 2022), which degrades model performance. Prior studies primarily focus on improving the router; however, such methods rely on training from scratch or fine-tuning, which requires high computational and data-processing costs. Furthermore, we demonstrate that, despite these efforts, the issue persists when advancing well-pretrained SMoE models, as evidenced by both theoretical and empirical results. To fill that gap, we analyze the advanced SMoE models and observe that the eigenvectors of expert weight matrices encode rich semantic information, pointing to an effective alternative to conventional routing strategies. Building on this insight, we propose Singular Value Decomposition SMoE (SS-MoE), a novel and training-free framework that leverages spectral properties of the expert weights to address the collapse issue and enhance model performance. Extensive experiments across diverse language and vision tasks, under both clean and corrupt data settings, demonstrate the strong generalization and robustness of SSMoE. Our findings highlight how a deeper understanding of model internals can guide the development of more effective SMoE architectures. Our implementation is publicly available at https: //github.com/giangdip2410/SSMoE.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.30992")
get_code_for_paper("2605.30992")
have("2605.30992")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2605.30992.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2605.30992.svg)](https://syntology.ai/paper/2605.30992)

Connect an agent — have() is free.