pith. sign in

Tap-vid: A benchmark for tracking any point in a video

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

2 Pith papers citing it

citation-role summary

dataset 1

citation-polarity summary

fields

cs.AI 1 cs.RO 1

years

2026 2

verdicts

UNVERDICTED 2

roles

dataset 1

polarities

use dataset 1

representative citing papers

Point Tracking Improves World Action Models

cs.RO · 2026-05-22 · unverdicted · novelty 7.0

JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.

citing papers explorer

Showing 2 of 2 citing papers.

  • Point Tracking Improves World Action Models cs.RO · 2026-05-22 · unverdicted · none · ref 56

    JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.

  • Zero-shot World Models Are Developmentally Efficient Learners cs.AI · 2026-04-11 · unverdicted · none · ref 51

    A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.