ResWAM: residual learning on frozen DINOv3 boosts VLA success with less compute
OPTML-Group · hf · 2026-11-18
ResWAM targets World-Action Models by learning visual residuals on frozen DINOv3 features — modeling what changes rather than what stays — combined with a lightweight dual-branch DiT trained via conditional flow matching, improving vision-language-action policy success while lowering training and inference compute.
More from Embodied
- HubLabs' HubEgo-100K robotics dataset trends on Hugging Face — HubLabs · 2026-11-18
- ForceHarness lifts frozen-model robot manipulation success from 3.3% to 90% — showlab · 2026-11-18
- ImpedanceMimic learns per-joint impedance as action space, beating PHC and SimPoE on force-accurate motion imitation — tweetsatpreet · 2026-11-18
- Google building new robotics model Astra with 1M-token context, config leaks — lyraxana · 2026-11-18
- GPT-6.2 Astra tops robot-code test: 2.5B net solving 79% of LIBERO, Python code hits 96.8% — burny_tech · 2026-11-18
- Bittensor subnet's zels decision model 'Jev' integrated into Even Realities glasses — markjeffrey · 2026-11-18