Gao Huang, Ziyi Wang, Xiu Li, Yifan Pu, Dongchen Han, Xiaochen Wang, Tianzhu Ye, Qixiu Li, Jixuan Ying, Xinyu Shao
1 of 2 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, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), 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/2511.00833.json · badge: /api/ran/2511.00833.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.
| Repository | Role | Ran |
|---|---|---|
| LeapLabTHU/LinearDiff | community Papers with Code archive |
1 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| RMSNorm | Ran ran on a synthesized input |
LeapLabTHU/LinearDiff/image_classification/models/vca_deit.py pointer only (licence: NONE) · get_code("af5816548ff50622") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, LeapLabTHU/LinearDiff 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. |
| VisualContrastAttention | Not yet run unverified (harvested, no recorded run) |
LeapLabTHU/LinearDiff/image_classification/models/vca_deit.py pointer only (licence: NONE) · get_code("dd29f958b05b63d8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, LeapLabTHU/LinearDiff 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. |
Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce Visual-Contrast Attention (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from O(N 2 C) to O(N nC) with n ≪ N . VCA first distils each head's dense query field into a handful of spatially pooled visual-contrast tokens, then splits them into a learnable positive and negative stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than 0.3 M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from 72.2% to 75.6% (+3.4) and improves three strong hierarchical ViTs by up to 3.1%, while in class-conditional ImageNet generation it lowers FID-50K by 2.1 to 5.2 points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at https://github.com/LeapLabTHU/LinearDiff.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2511.00833")
get_code_for_paper("2511.00833")
have("2511.00833")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2511.00833.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2511.00833)
Connect an agent — have() is free.