VLA language backbones show high redundancy on manipulation benchmarks, with half the LLM blocks removable and even two blocks sufficient to recover baseline performance after fine-tuning, unlike vision and action pathways.
Gradpruner: Gradient-guided layer pruning enabling efficient fine-tuning and inference for llms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
GHOST is a geometry-hierarchical token eviction framework that halves the KV cache size in monocular video 3D reconstruction while maintaining quality and achieving 1.75x faster inference.
citing papers explorer
-
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
VLA language backbones show high redundancy on manipulation benchmarks, with half the LLM blocks removable and even two blocks sufficient to recover baseline performance after fine-tuning, unlike vision and action pathways.
-
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
GHOST is a geometry-hierarchical token eviction framework that halves the KV cache size in monocular video 3D reconstruction while maintaining quality and achieving 1.75x faster inference.