Sun Yat-sen University

EWAM↗

EWAM is a WAM from Sun Yat-sen University, released September 30, 2026. It has no overall rank on the Robot Intelligence Index, which needs both a simulation and a real-robot result. Its best result is #11 of 36 on RoboTwin 2.0. Unified embodied model joining a Qwen3-VL language expert and Wan2.2 video expert via asymmetric joint attention for actions.

Release date: Sep 30, 2026

Type
WAM
Model weights
Open
License
Apache-2.0
Parameters
—
Pricing
Self-hosted
Benchmarks
2
Overall rank
Not ranked
Needs a real-robot result to rank overall.
Real robots rank
Not ranked
No real-robot results yet.
Simulation rank
#14of 49
Rating 1632 · range 6–17
Rating
1605± 12.7
10601989
Cost / task · est.
$0.024
$0.0087$17.74
Time / task · est.
26s
9.5 s1 h 22 min
Rank on each benchmark
BenchmarkScoreRank
RoboTwin 2.0Overall77.111 / 36RoboDojo SimOverall15.232 / 72

Per task attempt; the tiles show the median across benchmarks. Self-hosted compute is priced at one H100 at $3.29 per hour (Lambda on-demand, Oct 2026).

Inference

No latency or size published; built from Qwen3-VL-2B-Instruct and Wan2.2-TI2V-5B experts.