Question about paper on Qwen3-VL

Open
#1 15 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Documentation
Clarity
Needs clarification
Activity status
Quiet
Tech stack
machine-learning
Domain
machine-learning

Research direction

Start with the discussion on page 16 of the paper and the Qwen3-VL, SFT, and VTG questions in this issue. No repository file, test, or entry point is identified; the issue would be complete when the Qwen3-VL SFT settings and the meaning of “common scenario” are clarified, ideally with experiment results.

Written by the indexing model from the issue text.

Description

Woderful work! Thank you for your contributions, though I have some questions to be solved.
I noticed that you mentioned :

We observed that directly applying RL training on Qwen3-VL fails to yield improvements, likely because Qwen3-VL has undergone large-scale multi-task RL training that includes VTG data, preventing the model from generating rollouts with sufficient diversity on VTG task during our continual RL.Therefore, we first perform a small SFT stage to, in a sense, revert the model back to the “base model” state before RL. This is merely a workaround specific to Qwen3-VL, a model that has already acquired strong VTG capabilities through an RL stage similar to that proposed in this paper. In the common scenario, our recipes are designed to enhance the VTG capabilities of a “base MLLM”, where this trick is not required.

in page 16 of your paper.
My question:

  1. Is this strategy necessary when evaluating Qwen3-VL?
  2. Could you briefly introduce the SFT configuration/settings for Qwen3-VL?
  3. What do you mean by “common scenario”? Can I understand it as: this step may not be required for other tasks (e.g., VQA), but it is necessary when fine-tuning Qwen3-VL on our own VTG dataset?

These questions are intended purely for discussion. I will also run my own experiments to validate the points above. I hope we can have a pleasant, in-depth discussion, and thank you again for your contribution.
Wishing you all the best.

Dominant language
Python
Stars
179
Forks
14
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from TencentARC/TimeLens

All issues in TencentARC/TimeLens

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.