Search papers, labs, and topics across Lattice.
Princeton University
3
0
7
0
Even the top-performing MLLMs struggle with visual reasoning, achieving only 64% accuracy on a benchmark designed to reflect real-world diversity.
Massive activation spikes in LLMs are structural biases that can be eliminated to enable high-fidelity low-bit quantization across modalities.
Fine-tuning can unexpectedly break safety guardrails because alignment concentrates in brittle, low-dimensional subspaces, causing gradient descent to steer models into alignment-sensitive regions despite initial orthogonality.
