Yao Mu

Enfold: Folding World-Generator Computation into Predictive Representations for Efficient Embodied Control

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control

This work presents Enfold, which transfers this computation that constructs a future into a representation predicted from the current visual context and language instruction, and recast a world generator as a source of predictive control representations if its internal structure can be enfolded into the present.

InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

InternVLA-A1.5 is presented, which builds the policy on a native VLM backbone that keeps training on VQA and subtask prediction, and attaches a lightweight unified expert for continuous action generation, and achieves the best overall results on all six simulation benchmarks.

Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

This work presents REAL, an agentic framework for open-world mobile manipulation, which establishes sim-to-real-consistent environment APIs without oracle perception and integrates a simulated user to enable human-in-the-loop interaction.

GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models

GaussianWAM is proposed, a training-time representation-enhancement framework that organizes geometric and semantic supervision through a 3D Gaussian field and improves performance on standard LIBERO and shows positive transfer trends on RoboTwin and real-world manipulation.