@svlevine: Flow reversal steering allows "steering" diffusion-based VLAs with high-level actions, for example from VLM reasoning. …
Summary
Flow reversal steering enables steering diffusion-based vision-language-action models with high-level actions, such as from VLM reasoning, and allows RL in diffusion noise space for task exploration.
View Cached Full Text
Cached at: 06/12/26, 04:51 AM
Flow reversal steering allows “steering” diffusion-based VLAs with high-level actions, for example from VLM reasoning. This also lets us run RL in the diffusion noise space with exploration guided by high-level reasoning: think through a task, then practice it! 👇 https://t.co/T9hgTozpuR
Similar Articles
Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
This paper introduces FLAS, a flow-based activation steering method that learns a concept-conditioned velocity field to steer language model activations at inference time. On the AxBench benchmark, FLAS is the first learned method to consistently outperform in-context prompting on held-out concepts without per-concept tuning.
@svlevine: Diffusion (or flow) makes for excellent policies, but training them with RL is notoriously hard: BPTT is unstable, RL o…
New paper shows how to optimize flow matching actors for reinforcement learning by approximating the Jacobian of the flow denoising process with the identity matrix, making training feasible.
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
UniSteer introduces a text-guided activation flow matching method to learn a universal conditional velocity field in activation space, enabling versatile LLM behavior control and classification tasks without task-specific intervention modules.
@verityw_: Generalist robot policies learn many useful skills. How can we elicit relevant behaviors when faced with new tasks? We …
Introduces Flow Reversal Steering (FRS), a method to refine coarse actions from semantic reasoning into precise robot actions by reversing and re-denoising through a flow-matching generalist policy, improving zero-shot control and enabling policy learning.
Closed-Loop Neural Activation Control in Vision-Language-Action Models
Proposes CTRL-STEER, a closed-loop framework for adaptive steering of vision-language-action models using time-varying control signals, achieving better trade-off between concept regulation and task success without retraining.