SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13009 · CVPR · 2023

MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models

Hyunwoo Kim, Byungseok Roh, Hyeong Choi, Joonmyung Choi, Dohwan Ko, Kyoung-Woon On

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 (1 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; 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/2303.13009.json · badge: /api/ran/2303.13009.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
mlvlab/MELTR marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
MELTR Ran
ran on a synthesized input · constructed an object; no result was computed
mlvlab/MELTR/univl/modules/meltr.py
code served (permissive licence) · get_code("a3964b84fb27d6e4")
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 an instance of its own class, MELTR: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Analyze the MELTR forward method to understand dimensions:
# - x: input to loss_fc1 (i_dim -> h1_dim)
# - loss_fc2 output: h1_dim -> h2_dim
# - task_embedding.weight: (t_dim, h2_dim)
# - encoder: d_model=h2_dim, nhead=8, dim_feedforward=f_dim
# - fc1: h2_dim -> o_dim
# - encoder input shape: (1, t_dim, h2_dim) after unsqueeze
# - encoder output: (1, t_dim, h2_dim)
# - final output: (1, o_dim)

# For nhead=8 to work, h2_dim must be divisible by 8
# Let's use h2_dim=16 (divisible by 8)

t_dim = 5      # number of tasks
f_dim = 32     # feedforward dimension in transformer
i_dim = 8      # input dimension
h1_dim = 12    # first hidden dimension
h2_dim = 16    # second hidden dimension (must be divisible by nhead=8)
o_dim = 4      # output dimension

# Create a small input tensor
x = torch.randn(2, i_dim)

ARGS = {
    "t_dim": t_dim,
    "f_dim": f_dim,
    "i_dim": i_dim,
    "h1_dim": h1_dim,
    "h2_dim": h2_dim,
    "o_dim": o_dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MELTR — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MELTR 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, 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 1 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.

Repositories linked to this paper

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

Abstract

Foundation models have shown outstanding performance and generalization capabilities across domains. Since most studies on foundation models mainly focus on the pretraining phase, a naive strategy to minimize a single task-specific loss is adopted for fine-tuning. However, such fine-tuning methods do not fully leverage other losses that are potentially beneficial for the target task. Therefore, we propose MEta Loss TRansformer (MELTR), a plug-in module that automatically and non-linearly combines various loss functions to aid learning the target task via auxiliary learning. We formulate the auxiliary learning as a bi-level optimization problem and present an efficient optimization algorithm based on Approximate Implicit Differentiation (AID). For evaluation, we apply our framework to various video foundation models (UniVL, Violet and All-in-one), and show significant performance gain on all four downstream tasks: text-to-video retrieval, video question answering, video captioning, and multimodal sentiment analysis. Our qualitative analyses demonstrate that MELTR adequately 'transforms' individual loss functions and 'melts' them into an effective unified loss. Code is available at https://github.com/mlvlab/ MELTR.

For agents

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

get_harvested_code_for_paper("2303.13009")
get_code_for_paper("2303.13009")
have("2303.13009")

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

curl https://syntology.ai/api/ran/2303.13009.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.13009.svg)](https://syntology.ai/paper/2303.13009)

Connect an agent — have() is free.