Views
No views yet
| File | Description | Status |
|---|---|---|
light-mer-teacher-qwen3-8b.pth | Qwen3-8B teacher checkpoint for Stage 1 SWD-H distillation | Released |
stage1-swdh-qwen3-0.6b/checkpoint_000060_loss_1.291.pth | Recommended Qwen3-0.6B student checkpoint after Stage 1 SWD-H distillation | Released |
stage1-swdh-qwen3-0.6b/checkpoint_*.pth | Stage 1 SWD-H checkpoint trajectory from epoch 5 to epoch 60 | Released |
stage1-swdh-qwen3-0.6b/config.yaml | Stage 1 SWD-H training config used for the released checkpoints | Released |
stage2-mgrpo-qwen3-0.6b/checkpoint_*.pth | Stage 2 M-GRPO checkpoint sweep for steps 50, 500, ..., 5000 | Released |
stage2-mgrpo-qwen3-0.6b/config.yaml | Stage 2 M-GRPO training config used for the released checkpoint sweep | Released |
checkpoints/light-mer-teacher-qwen3-8b.pth1CONDA_ENV_NAME=swdh-stage1 \
2TEACHER_CKPT=checkpoints/light-mer-teacher-qwen3-8b.pth \
3bash scripts/train_stage1_swdh.shcheckpoints/light-mer-stage1-swdh-qwen3-0.6b.pthstage1-swdh-qwen3-0.6b/checkpoint_000060_loss_1.291.pthstage2-mgrpo-qwen3-0.6b/STAGE2_CKPT_ROOT in the GitHub codebase.1@misc{zheng2026lightmer,
2 title = {Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?},
3 author = {Zheng, Kaiwen and Fu, Junchen and Deng, Wenhao and Han, Hu and Jose, Joemon M. and Ge, Xuri},
4 year = {2026},
5 eprint = {2607.12787},
6 archivePrefix = {arXiv},
7 primaryClass = {cs.AI},
8 url = {https://arxiv.org/abs/2607.12787},
9 note = {Accepted by ACM MM 2026}
10}