- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In the paper, the authors propose Interaction Latents as Actions for combining motion, contact, and forces and using those latents as generation targets for different robot policy types. They evalute the proposed method on real-world contact rich task and show that their method is superior to the proposed baselines.
Critical strengths
Relevant tasks are addressed using a proposed, intuitive approach that results in its good perfomance.
Critical weaknesses
It is is not clear how much novel is the proposed method, as the new algorithmic additions are common in field as the authors state in the introduction.
Evaluation using methods that consider the same training data is lacking. Comparison to baselines that are outside the related families should be added for complete picture of the performance of the method.
Questions for authors
- Could you explain in more detail how does the proposed work differ from the existing works? Can you clearly state what is novel in this work?
- Have you considered other methods that learn from the the multiple data that does not fall into the 3 family groups? For example, KineDex (Zhang et al., 2025) and ForceMimic (Liu et al., 2025) are mentioned in Section 4.1.
5 comments
Response to wdfq: Methodological Novelty and Baseline Comparisons (2/2)
W2 / Q2: Direct comparisons with existing methods
Weakness W2: Evaluation using methods that consider the same training data is lacking. Comparison to baselines that are outside the related families should be added for complete picture of the performance of the method.
Question Q2: Have you considered other methods that learn from the multiple data that does not fall into the 3 family groups? For example, KineDex (Zhang et al., 2025) and ForceMimic (Liu et al., 2025) are mentioned in Section 4.1.
Response: We have added RDP [3], ForceMimic [2], KineDex [1], and Tactile-WAM [5], providing five existing-method comparisons alongside DreamTac [4]. We also add WAM-tac*, which jointly generates actions and tactile sequences within FastWAM, with DreamTac reported separately.
On the original four tasks, all methods use the same 150 expert demonstrations per task and evaluation protocol, with 20 real-world trials per method per task. FM, KineDex, ForceMimic, and RDP train for 50,000 steps; VLA is post-trained for 50,000 steps; WAM, DreamTac, and Tactile-WAM are post-trained for 40,000 steps. ILA's encoder/decoder is jointly pretrained on the four-task dataset for 240,000 steps and frozen during downstream training (Appendix A.1, pp. 17–18).
Among the five existing methods in Table 1, RDP has the highest average SR (71.25%). FM-ILA exceeds it on all four tasks, averaging 80.0% (+8.75 percentage points). WAM-ILA matches or exceeds the best SR of these methods on every task, averaging 73.75%. FM-ILA, VLA-ILA, and WAM-ILA outperform their direct joint action–tactile prediction variants in SR on every task. Against WAM-tac*, WAM-ILA gains 25/60/17/40 percentage points on peeling/flipping/cutting/wiping. These results support jointly encoding motion and contact as decodable policy action targets.
Table 1. Existing-method comparisons. Each cell reports SR (%) / L1 (mean ± standard deviation). SR is scored per cut for cutting and per trial otherwise. From manuscript Table 1 (p. 7).
| Method | Cucumber Peeling | Egg Flipping | Celery Cutting | Plate Wiping |
|---|---|---|---|---|
| RDP | 65% / 2.21 ± 0.40 | 80% / 1.53 ± 0.72 | 45% / 6.80 ± 2.44 | 95% / 3.65 ± 0.58 |
| ForceMimic | 30% / 2.43 ± 0.67 | 45% / 1.89 ± 0.80 | 20% / 7.76 ± 1.05 | 80% / 2.80 ± 0.70 |
| KineDex | 20% / 2.33 ± 0.62 | 70% / 2.05 ± 0.74 | 15% / 8.15 ± 1.70 | 75% / 3.08 ± 0.60 |
| DreamTac | 20% / 2.63 ± 0.68 | 25% / 2.13 ± 0.83 | 18% / 8.54 ± 2.23 | 70% / 2.92 ± 0.65 |
| Tactile-WAM | 30% / 2.29 ± 0.66 | 25% / 1.78 ± 0.88 | 25% / 8.03 ± 1.68 | 85% / 1.41 ± 0.61 |
Simulation comparisons. We also compare FastWAM-ILA, FastWAM-tac, DreamTac, Tactile-WAM, and RDP on six UniVTAC tasks [8]. All methods use the same settings and 50 demonstrations per task, with 100 evaluation trials per method per task.
Table 2. UniVTAC success rates (%, ↑). Average is the unweighted six-task mean; column maxima are bolded. From Appendix Table 9 (p. 30), where ILA denotes FastWAM-ILA.
| Method | Insert Hole | Insert Tube | Lift Can | Pull-out Key | Put Bottle | Insert HDMI | Average |
|---|---|---|---|---|---|---|---|
| RDP | 26 | 71 | 18 | 22 | 46 | 20 | 33.83 |
| DreamTac | 36 | 60 | 23 | 55 | 26 | 8 | 34.67 |
| Tactile-WAM | 33 | 82 | 13 | 28 | 41 | 25 | 37.00 |
| FastWAM-tac | 60 | 99 | 16 | 76 | 31 | 17 | 49.83 |
| FastWAM-ILA | 72 | 94 | 34 | 86 | 40 | 16 | 57.00 |
Table 2 shows that FastWAM-ILA achieves 57.00% average SR, exceeding FastWAM-tac by 7.17 percentage points and outperforming the other three methods. Together, these comparisons support interaction latents across diverse contact operations (Appendix B.8, p. 30).
References
[1] Di Zhang et al. KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation. arXiv:2505.01974, 2025.
[2] Wenhai Liu et al. ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation. ICRA, 2025.
[3] Han Xue et al. Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation. RSS, 2025.
[4] Yunfan Lou et al. Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation. arXiv:2606.08737, 2026.
[5] Siyu Wu et al. Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention. arXiv:2606.26663, 2026.
[6] Ilya Kostrikov et al. Offline Reinforcement Learning with Implicit Q-Learning. arXiv:2110.06169, 2021.
[7] Physical Intelligence et al. : a VLA That Learns From Experience. arXiv:2511.14759, 2025.
[8] Baijun Chen et al. UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking. arXiv:2602.10093, 2026.
Follow-up on Revisions and Additional Experiments
Dear Reviewer wdfq,
Thank you again for your thoughtful review. In response to your concerns, we have clarified ILA’s contribution and its distinction from existing methods, added controlled ablations, and expanded comparisons with prior approaches, including KineDex and ForceMimic, on real-robot and simulation tasks (Tables 1 and 4, and Appendix B.8).
We have submitted the updated manuscript and revised supplementary material, incorporating the corresponding clarifications and additional experimental results. Manuscript revisions are highlighted in blue.
We would be grateful if you could review our updated responses and manuscript and let us know whether these additions address your concerns. We would be happy to provide any further clarification.
We sincerely appreciate your time and consideration.
Best regards,
The authors
Response to wdfq: Methodological Novelty and Baseline Comparisons (1/2)
W1 / Q1: Novelty and distinctions from prior work
Response: Thank you for encouraging us to clarify the contribution. Our central idea is to represent the joint evolution of motion and contact as a decodable policy action, connecting action generation, expert-consistency evaluation, and offline policy improvement within the same interaction space. Sections 2–3 (pp. 3–6) clarify this formulation, and additional experiments examine its contribution.
(1) Incorporating contact evolution into the policy's action representation. Prior methods have explored tactile feedback, force–motion learning, and joint prediction of actions and tactile signals [1–5]. ILA jointly encodes temporally aligned action and tactile sequences under visual context. The resulting interaction latent becomes the generation target of the policy's action branch, and the same latent is decoded into actions, tactile deformation, and resultant-force proxies. Contact thus directly shapes the action space that the policy learns to generate. Under matched backbones, inputs, capacity, and training budgets, ILA outperforms action-only latents, separately learned action/tactile latents, and action latents with auxiliary tactile prediction. Relative to auxiliary tactile prediction, ILA improves SR by 15 and 17 percentage points on peeling and celery cutting, respectively, while reducing execution force-proxy error (main-text Table 4, p. 10). These controlled comparisons directly support the benefit of joint encoding.
(2) Using the same interaction action for evaluation and offline correction. A tactile-conditioned expert reference model evaluates the consistency of predicted interactions with the expert distribution in this generation space, providing chunk-level rewards for weighted learning from successful rollouts. For low-quality interactions in failed rollouts, observation-compatible and directionally consistent expert references provide correction targets under the current observation. Action generation, evaluation, and correction therefore operate on a common motion–contact representation. Using the same rollout corpus and a fixed latent space, our update achieves higher SR and lower execution force-proxy error than IQL [6] and RECAP [7] on all four tasks (main-text Table 1, p. 7). In the peeling ablation, adding failure correction increases SR from 80% to 85% and reduces the error from 2.89 to 0.51, supporting the contribution of reference-guided correction (main-text Table 3, p. 9).
(3) Applicability across policy architectures and transfer to new tasks. The interaction representation serves as a generation target for FM, VLA, and WAM policies. In WAM, we retain the original video branch and its generation target while replacing the action branch's target with interaction latents. Shared and task-specific representations yield comparable downstream policy performance (Appendix Table 12, p. 34). For vase wiping and carrot peeling, excluded from representation pretraining, we train new FM-ILA policies using 20 demonstrations and 16,000 steps per task, keeping the shared encoder frozen. With each policy checkpoint fixed and no additional force feedback, adapting only the decoder using ten demonstrations per task increases SR from 80%/40% to 100%/65%, respectively, and reduces execution force-proxy error (main-text Table 2, p. 9). Together, these results support the applicability of interaction representations across policy architectures and their transfer to unseen tasks with a frozen encoder.