Search papers, labs, and topics across Lattice.
Rutgers University
2
0
4
0
Forget opaque embeddings: Cross-Layer Transcoders reveal how ViT layers contribute to the final representation, pinpointing the critical few that drive performance.
Domain-specific visual tasks get a 13.51% performance boost in LVLMs thanks to a new codebook-anchored adaptation method that decouples vision encoder tuning from the language model.
