Search papers, labs, and topics across Lattice.
Hacettepe University
3
0
6
30
Hyperspherical latent spaces unlock better 3D scene understanding from vision transformers, especially when bandwidth is constrained.
Forget scaling laws: teaching models *how* to think like a cartoonist unlocks expert-level humor understanding, even surpassing larger black-box models.
Instruction-tuned MLLMs, despite excelling in zero-shot scenarios, surprisingly fail to leverage few-shot examples or chain-of-thought prompting, suggesting a fundamental limitation in their ability to learn from demonstrations.
