NeurIPS 2025 Knowledge Insulation - Heungwoo/research GitHub Wiki
Venue: NeurIPS 2025 (Spotlight) · Authors: Danny Driess, Jost Tobias Springenberg, Brian Ichter, Lili Yu, Adrian Li-Bell, Karl Pertsch, Allen Z. Ren, Homer Walke, Quan Vuong, Lucy Xiaoyang Shi, Sergey Levine — Physical Intelligence · arXiv: 2505.23705 (submitted 29 May 2025) Category: VLA Architecture / Training Significance: Published formalism bridging π0.5 → π0.6 → π0.7
flowchart LR
V[Vision] --> VLM[VLM backbone]
L[Language] --> VLM
VLM -- FAST-tokenized actions --> CE[Cross-entropy loss<br/>trains VLM representation]
VLM -- conditioning features --> AE[Continuous action expert<br/>flow-matching]
AE --> A[Actions]
AE -. 🚫 NO gradient propagation back to VLM .-> VLM
Training a continuous flow-matching action expert attached to a VLM has a quiet failure mode: the action-expert loss back-propagates into the VLM and corrupts language-grounded representations (the thing you paid web-scale pretraining to get). Naive joint training degrades generalization; training the VLM only on language and bolting on a frozen action head leaves performance on the table. Prior π-series work had the recipe informally; it needed to be published and ablated.
Knowledge Insulation (KI) does two things at once:
- VLM training signal via FAST-discretized actions. Continuous actions are tokenized (FAST, DCT-based) and used as discrete prediction targets for the VLM — training its representations with the stable cross-entropy objective it was built for.
- Continuous action expert attends the VLM's conditioning features and is trained with flow matching to produce continuous actions.
- The gradient from the action expert is blocked from propagating back into the VLM. The VLM is trained only by its own cross-entropy loss on FAST tokens + standard co-training tasks.
Net effect: same VLM learns from discrete action supervision AND is used as conditioning for continuous control — but its parameters are insulated from the continuous-head gradient.
- KI is built on the π0 / π0.5-FAST architecture (VLM initialized from PaliGemma, as in π0, plus a flow-matching action expert). The paper turns π0.5's two-stage "FAST-pretrain then add action expert" recipe into a single-stage one; the evaluated model is branded π0.5 + KI on the project page.
- Training speed: the KI recipe converges about as fast as the purely autoregressive π0-FAST, whereas π0 (continuous action expert only) needs roughly 7.5× as many training steps to reach comparable performance. The dual discrete+continuous objective adds ~20% per-step compute, offset by faster convergence.
- Simulation benchmarks: state-of-the-art LIBERO-90 96.0% and LIBERO-Spatial 98.0%; DROID 0.55 ± 0.09 vs π0 0.49 ± 0.09 and π0-FAST 0.45 ± 0.09.
- Generalization / language following: stop-gradient insulation plus co-training on web VLM data markedly improves instruction following and out-of-distribution object generalization; a frozen backbone reaches ~0%, confirming VLM pretraining alone lacks sufficient robotics representations.
- The recipe is later used in π0.6 (Nov 2025) and π0.7 (Apr 2026).
The cleanest published bridge from CoRL 2025 to ICLR 2026:
- π0.5 (Oral, Apr 2025) used a two-stage version (FAST-pretrain, then add action expert in post-training);
- KI (arXiv May 2025; NeurIPS 2025 Spotlight) formalizes it into a single-stage recipe and ablates it on the π0/π0.5-FAST architecture;
- π0.6 (Nov 2025) and π0.7 (Apr 2026) build on it as part of their training recipe.
Also a conceptual generalization: "insulate pretrained representations from task-specific gradients" is now the default pattern across FASTER, OmniSAT, and HyperVLA (different realizations of the same principle).
- arXiv: https://arxiv.org/abs/2505.23705
- NeurIPS virtual page: https://neurips.cc/virtual/2025/poster/117079
- OpenReview: https://openreview.net/forum?id=cb0xbZ3APM
- Project page: https://www.pi.website/research/knowledge_insulation
- OpenPi: https://github.com/Physical-Intelligence/openpi
- π0.5 (informal predecessor)
- π0.6 · π0.7 (direct descendants)
- π series evolution
- Review: VLA Architectures
← Back to NeurIPS-2025