A wavelet-based multi-level factorized blendshape representation with distillation achieves ultra-detailed animatable avatars at 2000X lower cost and 10X smaller size, running at 24 FPS natively on Meta Quest 3.
Lora: Low-rank adaptation of large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Weight Patching localizes capabilities to specific parameter modules in LLMs by replacing weights from a behavior-specialized model into a base model and validating recovery via a vector-anchor interface, revealing a hierarchy of source, routing, and execution components.
citing papers explorer
-
MUA: Mobile Ultra-detailed Animatable Avatars
A wavelet-based multi-level factorized blendshape representation with distillation achieves ultra-detailed animatable avatars at 2000X lower cost and 10X smaller size, running at 24 FPS natively on Meta Quest 3.
-
Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
Weight Patching localizes capabilities to specific parameter modules in LLMs by replacing weights from a behavior-specialized model into a base model and validating recovery via a vector-anchor interface, revealing a hierarchy of source, routing, and execution components.