13 papers
IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance
Jongwoo Park, Kanchana Ranasinghe, Jinhyeok Jang +3
Many Vision-Language-Action (VLA) models flatten image patches into a 1D token sequence, weakening the 2D spatial cues needed for precise manipulation. We introduce IVRA, a lightwe…
LACE: Latent Visual Representation for Cross-Embodiment Learning
Yoo Sung Jang, Kanchana Ranasinghe, Cristina Mata +3
Cross-embodiment learning from human demonstrations is hindered by the visual gap between human and robot embodiments. While self-supervised learning (SSL) backbones encode rich in…
Pixel Motion Diffusion is What We Need for Robot Control
E-Ro Nguyen, Yichi Zhang, Kanchana Ranasinghe +2
We present DAWN (Diffusion is All We Need for robot control), a unified diffusion-based framework for language-conditioned robotic manipulation that bridges high-level motion inten…
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya +3
Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefor…
Future Optical Flow Prediction Improves Robot Control & Video Generation
Kanchana Ranasinghe, Honglu Zhou, Yu Fang +7
Future motion representations, such as optical flow, offer immense value for control and generative tasks. However, forecasting generalizable spatially dense motion representations…
Robotic VLA Benefits from Joint Learning with Motion Image Diffusion
Yu Fang, Kanchana Ranasinghe, Le Xue +10
Vision-Language-Action (VLA) models have achieved remarkable progress in robotic manipulation by mapping multimodal observations and instructions directly to actions. However, they…