arXiv Machine Learning
ArcFlow: Training Flow Policies for Multiple Solver Budgets
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Oct 15
SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
arXiv:2604.05656v2 Announce Type: replace Abstract: Vision-language-action (VLA) models with flow-matching action heads, such as {\pi}0 and {\pi}0.5, have become a standard recipe for generalist robo...
arXiv AI
Sep 1
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
CF‑VLA introduces a two‑stage coarse‑to‑fine approach for vision‑language‑action policies, replacing multi‑step sampling with a coarse initialization that constructs an action‑aware starting point and a single‑step refinement that corrects residual errors. The coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed‑time refinement. Experiments on CALVIN and LIBERO demonstrate that CF‑VLA achieves a strong efficiency‑performance trade‑off, reducing action sampling latency by 75.4 % and achieving an 83.0 % real‑robot success rate, outperforming existing NFE=2 methods and matching or surpassing NFE=10 baselines.
arXiv AI
Jul 23
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv AI
Sep 4
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
arXiv:2609. 03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode.
arXiv AI
Sep 15
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
arXiv:2609.15883v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies...
arXiv AI
Sep 7
One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation
The paper presents a single pretrained diffusion traffic model that serves both as an ego motion planner and as a controllable generator of safety‑critical scenarios for autonomous driving. It introduces a Single‑Stream Dual‑Stream diffusion‑transformer decoder (SSDS) that fuses scene context via joint attention, improving closed‑loop performance on the nuPlan benchmark, and a training‑free guidance scheme called Decoupled Annealing Posterior Sampling with Energy (DAPSE) that injects arbitrary energy functions at inference time. Using the same model, the authors generate realistic long‑tail driving interactions—such as aggressive cut‑ins and lead‑vehicle braking—through inference‑time guidance, exposing failure modes in black‑box planners that standard benchmarks miss.