Pith. sign in

REVIEW 6 cited by

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.04292 v2 pith:X3R5VFAU submitted 2024-02-06 cs.LG cs.AI

classification cs.LGcs.AI
keywords adaflowinferenceimitationlearningflow-basedodespolicypropose
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient policy generators while keeping the ability to generate diverse actions. To address this challenge, we propose AdaFlow, an imitation learning framework based on flow-based generative modeling. AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs), which are known as probability flows. We reveal an intriguing connection between the conditional variance of their training loss and the discretization error of the ODEs. With this insight, we propose a variance-adaptive ODE solver that can adjust its step size in the inference stage, making AdaFlow an adaptive decision-maker, offering rapid inference without sacrificing diversity. Interestingly, it automatically reduces to a one-step generator when the action distribution is uni-modal. Our comprehensive empirical evaluation shows that AdaFlow achieves high performance with fast inference speed.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A flow-matching policy guides RRT tree expansion, preserving completeness while raising success rates on out-of-distribution kinodynamic planning tasks.

  2. Extracting Visual Plans from Unlabeled Videos via Symbolic Guidance

    cs.RO 2025-05 conditional novelty 6.0 of 10

    Vis2Plan extracts object symbols from unlabeled play videos with vision models, plans symbolically with A* search, and retrieves reachable real images as subgoals for a goal-conditioned robot policy.

  3. STDArm: Transferring Visuomotor Policies From Static Data Training to Dynamic Robot Manipulation

    cs.RO 2025-04 conditional novelty 6.0 of 10

    A real-time action correction system, STDArm, transfers visuomotor policies trained on static data to moving platforms, recovering 40 to 93 percent of static success rates in three manipulation tasks without retrainin...

  4. SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment

    cs.RO 2025-11 conditional novelty 5.0 of 10

    Selective Flow Alignment replaces reflow-generated actions with nearby expert actions during training, yielding a one-step flow policy that beats diffusion baselines on 66 simulated and 7 real tasks.

  5. FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation

    cs.RO 2024-12 conditional novelty 5.0 of 10

    A consistency flow matching policy conditioned on 3D point clouds generates robot actions in a single inference step, running 7x faster than DP3 with comparable success rates.

  6. Neural SDEs as a Unified Approach to Continuous-Domain Sequence Modeling

    cs.LG 2025-01 conditional novelty 4.0 of 10

    A maximum-likelihood-trained Neural SDE with diagonal diffusion is proposed as a unified, simulation-free method for continuous-domain sequence modeling, tested on branching trajectories, Push-T imitation, and KTH/CLE...

Pith tools