mlsanityData to 14 Oct 2026

Late Breaking Results: Quamba-SE: Soft-edge Quantizer for Activations in State Space Models

arXiv 2601.09451 ↗First posted 14 Jan 2026cs.LG cs.AI cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose Quamba-SE, a soft-edge quantizer for State Space Model (SSM) activation quantization. Unlike existing methods, using standard INT8 operation, Quamba-SE employs three adaptive scales: high-precision for small values, standard scale for normal values, and low-precision for outliers. This preserves outlier information instead of hard clipping, while maintaining precision for other values. We evaluate on Mamba- 130M across 6 zero-shot benchmarks. Results show that Quamba- SE consistently outperforms Quamba, achieving up to +2.68% on individual benchmarks and up to +0.83% improvement in the average accuracy of 6 datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 10 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

8 of 10 references.

References · 8

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  3. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  4. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
  5. 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methodscited by 29
  6. 2024Quamba: A Post-Training Quantization Recipe for Selective State Space Modelscited by 28
  7. 2025Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Modelscited by 16
  8. 2024Mamba-PTQ: Outlier Channels in Recurrent Large Language Modelscited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Quantizing Small-Scale State-Space Models for Edge AI
  2. 2023Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
  3. 2025QMamba: Post-Training Quantization for Vision State Space Models
  4. 2026Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models
  5. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
  6. 2024Q-S5: Towards Quantized State Space Models
  7. 2025Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLMs
  8. 2026MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference