Search papers, labs, and topics across Lattice.
5
0
6
9
Unlearning can inadvertently reinforce biases if demographic requests are imbalanced, but FAUN ensures fairness while effectively removing sensitive data from MLLMs.
Textual refusal directions can be harnessed to enhance multimodal safety without the need for unsafe multimodal data, revealing a powerful alignment strategy.
Data mixing, especially with instruction-heavy data, emerges as the crucial factor for optimizing VLM training, challenging traditional filtering approaches.
Unlocking fairer vision-language models may be as simple as intervening in the sparse latent space of a sparse autoencoder, enabling targeted bias removal without harming performance.
Forget specialized classifiers鈥擫MMs, enhanced with in-context learning and a novel iterative refinement method (CIRCLE), can outperform even fine-tuned VLMs in both closed and open-world classification.
