10 papers
Latent Projection for Latent Planning
Yoo Sung Jang, Michael Ryoo
Latent world models let an agent plan in latent space. The planner searches for an action sequence that minimizes a cost, and that cost is often the distance between the p…
SMILE: Smooth Motion for Improved Long-Horizon VLA Execution
Jongwoo Park, E-Ro Nguyen, Kanchana Ranasinghe +3
Vision-Language-Action (VLA) models reduce inference cost by executing multiple actions per call, but longer horizons often degrade accuracy because raw chunks contain jitter and o…
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…
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…
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…
Image Translation with Kernel Prediction Networks for Semantic Segmentation
Cristina Mata, Michael S. Ryoo, Henrik Turbell
Semantic segmentation relies on many dense pixel-wise annotations to achieve the best performance, but owing to the difficulty of obtaining accurate annotations for real world data…
CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings
Cristina Mata, Kanchana Ranasinghe, Michael S. Ryoo
Unsupervised domain adaptation (UDA) involves learning class semantics from labeled data within a source domain that generalize to an unseen target domain. UDA methods are particul…
Pixel Motion as Universal Representation for Robot Control
Kanchana Ranasinghe, Xiang Li, E-Ro Nguyen +3
We present LangToMo, a vision-language-action framework structured as a dual-system architecture that uses pixel motion forecasts as intermediate representations. Our high-level Sy…
LatentCRF: Continuous CRF for Efficient Latent Diffusion
Kanchana Ranasinghe, Sadeep Jayasumana, Andreas Veit +5
Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability.…
Phrase-Instance Alignment for Generalized Referring Segmentation
E-Ro Nguyen, Hieu Le, Dimitris Samaras +1
Generalized Referring expressions can describe one object, several related objects, or none at all. Existing generalized referring segmentation (GRES) models treat all cases alike,…