Matthieu Cord, Jayneel Parekh, Mustafa Shukor, Pegah Khayatan, Alasdair Newson
None of the 1 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (1 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2406.08074.json · badge: /api/ran/2406.08074.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 |
|---|---|---|
| mshukor/xl-vlms | canonical (classifier label) classifier basis: classifier_2025 |
0 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| decompose_activations | Not yet run unverified (harvested, no recorded run) |
mshukor/xl-vlms/src/analysis/feature_decomposition.py code served (permissive licence) · get_code("da0e1909987d2150") How it ranno invocation recorded. |
Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| decompose_activations brick of this paper's assembly: entry |
1 other paper 1 later |
2501.03012 (2025-01) Analyzing Fine-tuning Representation Shift for Multimodal LLMs Steering |
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs remains largely a mystery. In this paper, we present a novel framework for the interpretation of LMMs. We propose a dictionary learning based approach, applied to the representation of tokens. The elements of the learned dictionary correspond to our proposed concepts. We show that these concepts are well semantically grounded in both vision and text. Thus we refer to these as "multimodal concepts". We qualitatively and quantitatively evaluate the results of the learnt concepts. We show that the extracted multimodal concepts are useful to interpret representations of test samples. Finally, we evaluate the disentanglement between different concepts and the quality of grounding concepts visually and textually. Our implementation is publicly available. 1 Understanding VLM/LMM representations There has been an increasing interest in understanding internal representations of visual-language models (VLM) through the lens of multimodality. Shukor and Cord [42] analyse multimodal tokens and shows that despite being different, visual and perceptual tokens are implicitly aligned inside LLMs. Goh et al. [18] discover neurons termed
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.08074")
get_code_for_paper("2406.08074")
have("2406.08074")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.08074.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.08074)
Connect an agent — have() is free.