pith. sign in

2505.14139 , archivePrefix =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.RO 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Action Emergence from Streaming Intent

cs.RO · 2026-05-12 · unverdicted · novelty 7.0 · 2 refs

A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.

Driving Intents Amplify Planning-Oriented Reinforcement Learning

cs.RO · 2026-05-12 · unverdicted · novelty 5.0 · 2 refs

DIAL expands continuous-action driving policies via intent-conditioned flow matching and multi-intent GRPO, lifting best-of-N preference scores above human demonstrations for the first time on WOD-E2E.

citing papers explorer

Showing 2 of 2 citing papers.

  • Action Emergence from Streaming Intent cs.RO · 2026-05-12 · unverdicted · none · ref 57 · 2 links

    A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.

  • Driving Intents Amplify Planning-Oriented Reinforcement Learning cs.RO · 2026-05-12 · unverdicted · none · ref 1 · 2 links

    DIAL expands continuous-action driving policies via intent-conditioned flow matching and multi-intent GRPO, lifting best-of-N preference scores above human demonstrations for the first time on WOD-E2E.