5 papers
Continual Humanoid Motion Learning
Zhewen He, Hao Huang, Geeta Chandra Raju Bethala +4
Humanoid whole-body controllers can now track a diverse set of dynamic motions, but they are typically trained offline and then frozen, so teaching such a controller a new skill te…
Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models
Junyi Hu, Zhewen He, Zhenhua Li +1
A robot demonstration records two things in the same frames: what happened to the objects, and how one particular arm made it happen. We condition on the first. A demonstration is…
DINO Eats Geometry: Self-Supervised Sign Representations that Absorb Articulated Hand Geometry
Junyi Hu, Zhewen He, Haomian Huang +4
Handshape and orientation are geometric components of sign language, yet many sign encoders learn from appearance alone. We introduce SignDEG (DINO Eats Geometry), a temporal sign…
VTaMo: Video-Text Alignment Model for Sign Language Translation
Junyi Hu, Zhewen He, Haomian Huang +2
Sign language translation (SLT) converts continuous sign videos into spoken language text. Gloss-free approaches leverage pre-trained visual encoders and language models but rely o…
SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
Zhewen He, Junyi Hu, Haomian Huang +3
Sign language models are typically trained on datasets captured under constrained conditions, with limited viewpoint, background, and signer-identity diversity, leading to poor rob…