- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents SP-QAT, a QAT framework for extreme low-bit quantization of VLA models, with a particular focus on fixed 2-bit weight quantization of the LLM backbone. The paper first analyzes why directly applying standard LSQ to VLA models causes severe performance degradation at 2-bit precision. The authors attribute the failure to distortion of the singular spectrum of the LLM’s cognition features, especially the loss of energy in the action-sensitive subspace. Based on this diagnosis, SP-QAT introduces three components: Prior-Anchored Low-Rank Quantization, which freezes the pretrained weights and constrains QAT-induced weight updates to a low-rank subspace; Soft-Mask Gradients with Severity-Aware Scale Regulation, which provides non-zero pull-back gradients for clipped outliers and modifies the step-size gradient to alleviate outlier-driven quantization-resolution collapse; and Difficulty-Aware Curriculum Learning with SNR-Guided Static Reweighting, which emphasizes low-noise timesteps and quantization-sensitive hard samples. The method is evaluated on CogACT and π0 using SimplerEnv, including in-domain and cross-domain settings, together with component ablations and real-world Franka Panda experiments. The paper reports a success-rate drop of at most 2.6% in the main in-domain setting; cross-domain and real-world W2A16 results show larger drops (5–6%). It also reports 75%–84% memory savings and a 1.6× inference speedup.
Critical strengths
1.A systematic analysis of why standard QAT fails under extreme low-bit VLA quantization. Through theoretical and experimental analysis, the authors identify that preserving the cognition-feature spectral subspace, particularly the concentration of action-sensitive energy in the singular spectrum, is critical for extreme low-bit quantization of the VLA LLM backbone. The analysis shows that W2A16-LSQ causes spectral flattening of cognition features, with energy leaking from a few dominant directions into many tail directions, while the action-sensitive subspace is selectively degraded. The authors further trace this distortion to three possible causes. These observations provide a coherent motivation for the three corresponding components of SP-QAT. 2.Strong empirical performance across multiple evaluation settings. The empirical results are compelling, particularly under the challenging W2A16 setting. SP-QAT is evaluated on two VLA policies with different action-generation mechanisms, CogACT and π0, and the paper includes in-domain evaluation, zero-shot cross-embodiment evaluation, extensive component/hyperparameter ablations, and real-world Franka Panda experiments. The W2A16 models remain close to their FP16 counterparts in several settings where the evaluated conventional PTQ/QAT methods degrade severely or collapse. The real-world results additionally show that W2A16 CogACT retains a 60% average success rate compared with 65% for FP16 while reducing the reported inference latency from 241 ms to 151 ms.
Critical weaknesses
The paper’s central claim that preserving action-sensitive energy in the cognition-feature spectrum is key to extreme low-bit VLA quantization is well motivated, but the current evidence is not yet sufficient. First, the construction of the action-sensitive subspace is insufficiently described in the main text. Second, the experiments mainly show a correlation between SP-QAT, improved spectral preservation, and improved success, rather than isolating the mechanism. It would strengthen the claim to report action-sensitive energy preservation and effective rank after progressively adding each component, and to examine whether these metrics consistently track the corresponding success-rate improvements.
Questions for authors
1.Clarification on the action-sensitive subspace and spectral evidence. The authors could provide a precise definition and implementation procedure for constructing the action-sensitive subspace.
2.Given that the real-world experiments perform inference on a remote NVIDIA A100 GPU, could the authors provide measurements on a representative edge platform, or otherwise clarify the scope of the edge-deployment claim.
- The related-work discussion identifies ActQuant as a sub-4-bit VLA quantization approach and BitVLA as a native 1.58-bit model, but the main empirical comparison focuses on GPTQ, Ω-QVLA, LSQ, and SQIL. A comparison or at least a controlled discussion with ActQuant at comparable BPW would be useful.
4.The Figure 1 caption and the main text are run together “...with ω-QVLA.” is immediately followed by “in one shot without task-level dynamic adjustment...” making the boundary between caption and body text unclear. Please separate them.
- The abstract claim of “at most 2.6%” should be scoped to the main in-domain setting, since the cross-domain and real-world W2A16 results in Tables 2 and 4 show larger drops (6.1%, 5.3%, and 5.0%). The authors should clarify the scope of this claim.
3 comments
Q6: Effective Rank and Action-Sensitive Energy Preservation across Components.
A6: Thank you for your suggestion. We have revised Sec.4.3 in the main text by reporting the action-sensitive energy preservation and effective rank after progressively adding each component. Partial results from Tab.3 are reproduced below:
| Method | Avg. | R_s | ||
|---|---|---|---|---|
| LSQ (Baseline) | 0% | — | 122.2 | 0.142 |
| + PA-LoQ | 17.5% | +17.5% | 102.7 | 0.354 |
| + SMG-SASR (w/o SMG) | 33.1% | +33.1% | 84.3 | 0.472 |
| + SMG-SASR (w/o SASR) | 35.2% | +35.2% | 78.9 | 0.512 |
| + SMG-SASR | 44.0% | +44.0% | 61.8 | 0.708 |
| + DACL-SNR (w/o DACL) | 46.5% | +46.5% | 57.5 | 0.877 |
| + DACL-SNR (SP-QAT) | 52.3% | +52.3% | 54.8 | 0.908 |
It shows that progressive integration of our components reduces the effective rank while raising the action-sensitive energy preservation , along with the increase in success rate. Thus these metrics consistently track the corresponding success rate improvements.
Hope this message finds you well. Thank you again for your constructive comments on our paper. We have posted our point-by-point responses and revised the manuscript accordingly. With the discussion period closing in less than two days, we would like to ensure we have addressed all your concerns.
For quick reference, the key changes are:
-
Provided a precise definition and implementation procedure for constructing the action-sensitive subspace in Sec.3.2.
-
Clarified the scope of the edge-deployment claim in Abstract, Introduction and Appendix H.
-
Added visualization of spectral changes and damage to action-sensitive directions on in Appendix J.
-
Added a comparison with ActQuant and BitVLA in Q3.
-
Fixed this formatting issue and incorporate the restriction “under in-domain setting”.
-
Added additional results on effective rank and action-sensitive energy preservation across components in Sec. 4.3.
Your insights are valuable to us, and we hope that our responses and the revised manuscript have addressed your concerns. Thank you again for your time, effort and help in improving the quality of our paper.
Thanks for your deep and constructive comments!
Q1: Clarification on the action-sensitive subspace and spectral evidence. The authors could provide a precise definition and implementation procedure for constructing the action-sensitive subspace.
A1: The action-sensitive subspace is defined as the span of the top-k right singular vectors of the Jacobian matrix of the action output with respect to the cognition feature: Ja=∂h∂a, where a denotes the action output by the action head, and h is the cognitive feature fed as the input to the action head. It identifies the cognition feature directions most critical to action prediction. In practice, we project both FP16 and quantized cognition features onto this subspace to compute the energy preservation ratio. We have already included the precise definition and implementation procedure in the paper (Sec.3.2).
Q2: Given that the real-world experiments perform inference on a remote NVIDIA A100 GPU, could the authors provide measurements on a representative edge platform, or otherwise clarify the scope of the edge-deployment claim.
A2: We thank the reviewer for this valuable comment. Due to hardware access constraints, we are currently unable to provide end-to-end inference latency measurements on physical edge platforms. Nevertheless, our method produces fixed-bit quantized weights conforming to the standard GPTQ packing format. This design guarantees compatibility with many widely adopted inference backends and hardware accelerators, and cleanly decouples our quantization training algorithm from low-level kernel implementations. We have revised the manuscript to clarify this scope.
Q3: The related-work discussion identifies ActQuant as a sub-4-bit VLA quantization approach and BitVLA as a native 1.58-bit model, but the main empirical comparison focuses on GPTQ, Ω-QVLA, LSQ, and SQIL. A comparison or at least a controlled discussion with ActQuant at comparable BPW would be useful.
A3: We have added controlled comparisons against ActQuant and BitVLA for π0.5 on LIBERO. We evaluate our fixed 2-bit quantized variant alongside ActQuant at 2 bpw and BitVLA, where only the LLM backbone is quantized for all methods. Since BitVLA builds upon BitNet and natively supports only 1.58-bit quantization without flexible bitwidth adjustment, we report its published results from the original work.
The results show that our SP-QAT maintains strong task performance without relying on mixed-precision layouts. It outperforms ActQuant by 4.9% in average success rate and exceeds BitVLA by 0.4%. Unlike BitVLA, which demands an expensive 14-day multi-stage pre-training before robotic fine-tuning, our pipeline does not require heavy dedicated pre-training and finishes training in roughly 4 hours on only two H100 GPUs. In addition, our method imposes no hard restriction on quantization bitwidth and theoretically flexibly supports arbitrary uniform bitwidth configurations.
Q4: The Figure 1 caption and the main text are run together “...with ω-QVLA.” is immediately followed by “in one shot without task-level dynamic adjustment...” making the boundary between caption and body text unclear. Please separate them.
A4: We have fixed this formatting issue in the revised version.
Q5: The abstract claim of “at most 2.6%” should be scoped to the main in-domain setting, since the cross-domain and real-world W2A16 results in Tables 2 and 4 show larger drops (6.1%, 5.3%, and 5.0%). The authors should clarify the scope of this claim.
A5: We incorporate the restriction “under in-domain setting” in the revised version to bound this statement.