Post-Training for Robotics Foundation Models

About
Post-training is a crucial stage in robotics foundation model research: it enables robots to go beyond large-scale pretraining on expert demonstrations and further improve performance through their own interaction with the environment. By collecting interaction rollouts, distinguishing good and bad behaviors, and iteratively optimizing policies, post-training can substantially enhance precision, failure recovery, and generalization—bringing robotics foundation models closer to reliable real-world deployment.

This challenge and workshop will focus on the foundational questions and key challenges in the post-training stage of robotics foundation models. The event consists of two tightly coupled components: (1) a pre-workshop challenge and (2) an in-person workshop at RSS. The workshop program will include four parts: the pre-workshop challenge, invited speaker talks, team presentations, and a panel discussion.

We expect the workshop to (i) establish shared problem definitions and evaluation protocols for robotics foundation model post-training, (ii) surface empirical lessons and failure modes from real-robot rollouts, and (iii) catalyze reusable resources (e.g., benchmarking protocol, reports, and baselines) that enable more reproducible and scalable research in this area.

Challenge

The challenge is structured in two rounds. In Phase 1, all teams are evaluated on a standardized real-robot bimanual manipulation benchmark using a shared dataset. In Phase 2, the top teams are selected and supported in iterative rollout collection to further improve their policies via post-training.

Phase 1 — Evaluation Tracks

Phase 1 evaluates submitted policies on 3–5 standardized real-robot tasks across two ranking tracks. Teams perform offline training on the released dataset (expert data + baseline success and failure rollouts) and submit policies for benchmark evaluation.

Task Samples & Scoring

Phase 1 includes three real-robot bimanual manipulation tasks. Select a task below to view a sample rollout video and its scoring criteria.

Dataset

For Phase 1, we release a standardized real-robot bimanual dataset designed for offline training. The dataset contains four complementary components:

Tutorial Phase 2 — Iterative Improvement

Based on Phase 1 results, the top 3 teams advance to Phase 2. During this round, selected teams collect rollouts by deploying their own policies and use those rollouts to further improve performance via post-training.

• Top 3 teams selected from Phase 1 ranking
• Iterative rollout collection supported by the organizers
• Final policies presented at the workshop @ RSS 2026

Schedule Awards

Listed prizes apply to each track (Single-Task & Multi-Task).

Leaderboard

Score: progress score per task (higher is better). SR: success rate over rollouts. trials: number of evaluation rollouts per task, listed in column order insert-mouse-battery / tower-of-hanoi-game / seal-water-bottle-cap. Ranking is by Average SR first, then Average Score as a tie-breaker. In both tracks the Average is computed over all three tasks — any task a team did not evaluate (—) counts as 0. Runs with only a single rollout are excluded.

Final results. These are the final-phase evaluation results. Each policy was evaluated with up to 5 rollouts per task under a unified setting.

Registration

Team registration is now open. Please fill in the Google Form below with your team information and track preference. Submission instructions will be shared with registered teams.

Register your team

Invited Speakers

Schedule

Time	Event
9:00 - 10:30	Invited Talks Karl Pertsch · Abhishek Gupta · Jianlan Luo · more speakers TBA
10:30 - 11:00	Coffee Break & Participating Teams' Policy Deployment Demonstrations
11:00 - 12:00	Participating Team Reports
12:00 - 13:00	Panel Discussion & Audience Q&A

Discussion Topics

Discussion topics for this workshop include, but are not limited to:

Organizers


Industry Partners

Citation

If you use this dataset or reference the challenge in your research, please cite us:

@misc{posttraining_robotics_2026,
  title        = {Post-Training for Robotics Foundation Models Dataset and Challenge},
  author       = {Zhang, Shiduo and Wang, Yue and Chang, Haonan and Zhao, Hang and
                  Liu, Yicheng and Guizilini, Vitor and Bobu, Andreea and Wagenmaker, Andrew and
                  Dixit, Anushri and Yu, Chao and Shah, Dhruv and Simchowitz, Max},
  year         = {2026},
  howpublished = {RSS 2026 Workshop & Challenge},
  url          = {https://posttraining-for-robotics.github.io}
}

Contact