A training framework that adds a removable image-generation branch to multimodal LLMs improves visual understanding benchmarks with zero inference-time cost.
Why are visually-grounded language models bad at image classification? Advances in Neural Information Processing Systems, 37:51727–51753, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction
A training framework that adds a removable image-generation branch to multimodal LLMs improves visual understanding benchmarks with zero inference-time cost.