QuantVLA is the first post-training quantization framework for VLA models that quantizes the diffusion transformer action head and reports higher task success rates than full-precision baselines with roughly 70% memory savings on the quantized components.
Awq: Activation-aware weight quantization for on-device llm compression and accelera- tion.Proceedings of machine learning and systems, 6:87– 100, 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Permutation-COMQ is a new post-training quantization algorithm that reorders weights within layers and uses only dot-product and rounding steps to deliver the highest reported accuracy for 2-, 4-, and 8-bit medical foundation models.
A data-driven adaptive policy for KV-cache bit-width selection based on token importance features reduces decoding latency by ~18% and improves accuracy over static quantization while staying near FP16 levels on SmolLM models.
citing papers explorer
-
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
QuantVLA is the first post-training quantization framework for VLA models that quantizes the diffusion transformer action head and reports higher task success rates than full-precision baselines with roughly 70% memory savings on the quantized components.
-
Weight Group-wise Post-Training Quantization for Medical Foundation Model
Permutation-COMQ is a new post-training quantization algorithm that reorders weights within layers and uses only dot-product and rounding steps to deliver the highest reported accuracy for 2-, 4-, and 8-bit medical foundation models.
-
Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs
A data-driven adaptive policy for KV-cache bit-width selection based on token importance features reduces decoding latency by ~18% and improves accuracy over static quantization while staying near FP16 levels on SmolLM models.