Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.RO 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

How Should Vision-Language-Action Models Use Proprioceptive State?

cs.RO · 2026-08-04 · conditional · novelty 6.0

In a flow-matching VLA, single-frame proprioceptive state works best in the VLM prefix, while 8-frame state history works best in the action prefix, with gains from genuine temporal content rather than extra tokens.

citing papers explorer

Showing 1 of 1 citing paper.

  • How Should Vision-Language-Action Models Use Proprioceptive State? cs.RO · 2026-08-04 · conditional · none · ref 12

    In a flow-matching VLA, single-frame proprioceptive state works best in the VLM prefix, while 8-frame state history works best in the action prefix, with gains from genuine temporal content rather than extra tokens.