UniMod: mitigating shortcut learning in multi-modal medical diagnosis via cross-modality and within-modality alignment (ACM MM 2026)
-
Updated
Aug 12, 2026 - Python
#
acm-multimedia-2026
Here are 4 public repositories matching this topic...
Official implementation of SCOPE (ACM MM 2026): selective computation and predictive extrapolation for autoregressive video diffusion.
video-generation diffusion-models inference-acceleration autoregressive-models training-free acm-multimedia-2026
-
Updated
Jul 11, 2026 - Python
Official implementation of PrediT (ACM MM 2026): training-free linear multistep feature forecasting for efficient diffusion transformers.
-
Updated
Jul 11, 2026 - Python
5th-place system for MER2026 Track 3 (MER-Prefer), MRAC 2026 @ ACM MM. LoRA post-training on Qwen2.5-Omni-7B, with per-sample scores that recompute every number in the paper on CPU in one minute.
lora reproducibility emotion-recognition preference-learning peft multimodal reward-model qwen acm-multimedia-2026
-
Updated
Aug 7, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the acm-multimedia-2026 topic, visit your repo's landing page and select "manage topics."