TorchUMM is the first unified codebase and benchmark suite for multimodal understanding, generation, and editing across varied UMM models and datasets.
Do instruction-tuned models always perform better than base models? evidence from math and domain-shifted benchmarks.arXiv preprint arXiv:2601.13244
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
TorchUMM is the first unified codebase and benchmark suite for multimodal understanding, generation, and editing across varied UMM models and datasets.