- Rating
- 4(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces Humanoid-LLA, which aims to turn free-form language instructions into executable humanoid motions. The authors build a unified human–humanoid motion vocabulary, train a vocabulary-directed controller, and fine-tune the language model using motion CoT and RL with physical feedback.
Critical strengths
- The paper provides fairly comprehensive comparisons, including existing methods, ablation studies and real-world experiments.
- The authors learn a shared human–humanoid motion vocabulary and train a controller to execute motion tokens directly, avoiding online retargeting. They also use physical-feedback RL to improve motion generation and execution.
Critical weaknesses
- Some vector symbols in the equations appear to be in bold upright rather than bold italic. I guess the authors may have used \mathbf for these symbols. They might consider using \bm or other appropriate LaTeX commands instead, following the mathematical notation conventions in [1] and ISO 80000-2 [2].
- The experimental analysis of the loss functions is somewhat limited. Additional figures or tables would help clarify the contributions of individual loss terms.
References: [1] https://www.nist.gov/pml/special-publication-811/nist-guide-si-chapter-10-more-printing-and-using-symbols-and-numbers [2] https://www.iso.org/standard/64973.html (not open access)
Questions for authors
- The real-world experiments include only 10 trials per task(table10). Could the authors increase the number of trials and include more quantitative Sim2Real results in the main text?
- In Table 2, removing has only a small impact on the first four values (table 2) but leads to a noticeable drop in success rate. Could the authors further analyze the reasons for this difference, particularly the failure cases?
3 comments
I have no further questions. It would be nice to include the Q2 explanation in the main text, the current response is OK.
I will raise my rating from 3 to 4.
Thank you for your constructive feedback. We will incorporate the analysis of Q2 into the ablation study discussion in the main text of our next revised PDF version.
We sincerely appreciate your positive assessment of our work and the clarifications provided in our rebuttal, as well as the decision to increase your rating from 3 to 4. Thank you again for your time and consideration.
We thank the reviewer for recognizing the comprehensiveness of our evaluation and the merits of our token-conditioned control design. We also appreciate the constructive suggestions for further strengthening our experimental analysis. We address these points and the notation concern below.
A: We thank the reviewer for pointing out this inconsistency. We have corrected the affected vector symbols in the main text and appendix from bold upright to bold italic notation, following the suggested conventions. The corrections are highlighted in blue in our revised PDF.
A: We agree that the roles of individual objectives should be presented more clearly. Existing experiments provide direct objective-level evidence for Lcross (Appendix, Tables 12–14) and rdist and rtrack (Table 2). Appendix Table 16 evaluates the controller architecture, prior, and goal masking.
To strengthen analysis of different loss terms, we have added a dedicated stage-wise summary in Appendix Table 17, covering: (1) Unified Tokenizer: Lintra, Lcross, Lcommit, and Lreg; (2) Controller Distillation: action imitation and KL regularization; and (3) LLM Fine-tuning: SFT/GRPO objectives, rformat, rdist, and rtrack=rpos+racc. The table clarifies each term's purpose. We have also added references to this summary in all three corresponding main-text sections (revised PDF, lines 238–239, 298, and 376-377, highlighted in blue).
A: We have expanded the real-world evaluation from 10 to 20 trials per task across seven tasks, while keeping the evaluation protocol unchanged. We have also moved the quantitative Sim2Real evaluation from the original Appendix Table 10 into Section 4.5 and Table 4 of the revised main text (revised PDF, lines 486-505, highlighted in blue). The updated results are presented below.
Table R1. Expanded quantitative Sim2Real evaluation.
A: The key distinction lies in distribution-level motion quality versus sequence-level physical robustness. The first four metrics primarily measure overall motion distribution and semantic alignment, whereas Success requires the tracking deviation in Eq. 26 to remain below 0.5,m throughout execution. Thus, even brief tracking failures can cause an entire sequence to fail without substantially affecting aggregate generation metrics. Importantly, removing rtrack retains rollout-based distributional feedback through rdist, but eliminates explicit optimization for position and acceleration tracking accuracy. Consequently, Success drops from 87.6% to 76.72%, while MPJPE increases from 56.43 to 66.42 mm, velocity error from 8.92 to 10.89, and acceleration error from 8.74 to 9.77.
Representative failures involve balance- and contact-critical transitions, such as prolonged single-leg support, repeated high kicks, or rapid rotations, where localized tracking deviations can cause falls or exceed the sequence-level success threshold. Such failures can substantially reduce Success while leaving aggregate distributional and semantic metrics largely unchanged.