Search papers, labs, and topics across Lattice.
Email:
3
0
5
Two consistent dissociations between representation-level alignment and behavioral expression are reported, plus a common failure under position perturbations, characterize representation-behavior dissociation in a high-signal setting rather than establishing universality across models or persona pairs.
Video-ToC drastically improves video understanding by forcing Video LLMs to focus on relevant visual cues, leading to state-of-the-art performance and reduced hallucinations.
VLMs can achieve 7.8x faster prefilling speeds with only a minor accuracy drop by intelligently pruning redundant visual tokens *without* retraining.
