SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.01426 · ICML · 2025

Unifying Specialized Visual Encoders for Video Language Models

Olga Russakovsky, Juan Niebles, Tyler Zhu, Jihoon Chung, Max Gonzalez Saez-Diez, Honglu Zhou

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; 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/2501.01426.json · badge: /api/ran/2501.01426.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
princetonvisualai/merv canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
initialize_overwatch Ran
ran; our contract draft was wrong, not the code
princetonvisualai/merv/merv/overwatch/overwatch.py
code served (permissive licence) · get_code("febfbebb4e9a35a4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned PureOverwatch. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import logging
import os
from typing import Union

# Set up minimal logging configuration
logging.basicConfig(level=logging.INFO)

# The function takes one parameter: name
# We need to provide a string name for the logger

ARGS = {
    'name': 'test_overwatch_logger'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
accelerate — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PureOverwatch — a PureOverwatch output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PureOverwatch output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

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 (1 with at least one paper dated earlier, 0 the same month, 0 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.

FunctionAlso present inEarliest-datedOthers named
initialize_overwatch 2 other papers
2 dated earlier
2402.07865 (2024-02)
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
2403.14520 (2024-03)
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

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

Recent advances in vision backbones have yielded powerful and diverse visual and video encoders. Yet, current Video Large Language Models encode visual inputs using an encoder from a single backbone family, limiting the amount and type of visual information they can process. We propose MERV, a Multi-Encoder Video Representation, which utilizes multiple encoders for a comprehensive video representation. To optimize heterogeneous features from a broad spectrum of encoders and ensure efficient and coherent feature integration, MERV first aligns encoder features spatio-temporally, then projects them into a unified structure, and finally fuses them through cross-attention. Under fair comparison, MERV achieves up to 4.62% higher accuracy than its base model, while introducing minimal extra parameters and training faster than equivalent singleencoder methods after parallelizing visual processing. Qualitative analysis shows MERV successfully captures and integrates domain knowledge from each encoder, opening new possibilities for scaling enhanced video understanding.

For agents

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

get_harvested_code_for_paper("2501.01426")
get_code_for_paper("2501.01426")
have("2501.01426")

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

curl https://syntology.ai/api/ran/2501.01426.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.01426.svg)](https://syntology.ai/paper/2501.01426)

Connect an agent — have() is free.