LeWAM: JEPA latent space world action model released
What happened
Shashank Hegde and other authors propose LeWAM: a bidirectional Transformer trained end-to-end on a decoder-free JEPA latent space, supporting four modes simultaneously: forward, reverse, inverse dynamics, and policy prediction. The authors report that linear probe experiments show LeWAM's latent space reads robot and object states better than the forward-only Le World Model, and its degree of ignoring visual distractors is comparable to LeWM and clearly better than reconstruction-based WAM. In closed-loop evaluation, LeWAM performs comparably to a conventional flow-matching policy with the same encoder and the same scale, while additionally providing a world model; the authors also report that planning in the noise space of the policy head can improve the closed-loop performance of this type of WAM.
AI 根据报道生成 · 2 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROLeWAM: Robot planning method based on JEPA world action model and diffusion-guided MPC
The authors propose LeWAM, a bidirectional Transformer trained end-to-end on a decoder-free JEPA latent space that supports four modes: forward, backward, inverse dynamics, and policy prediction. Linear probe experiments show that LeWAM's latent space reads robot and object state better than the forward-only Le World Model, and that its degree of ignoring visual distractors is comparable to LeWM and clearly better than reconstruction-based WAM.
Activity for this event
- Current
- 3
- Peak
- 10Nov 9 14:00
- Past 24 hours
- -50%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.