Fu-Long Liu

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.

Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation

A unified spatiotemporally decoupled framework named DeMoDiff is proposed, which jointly redesigns representation and architecture and incorporates spatial-temporal masking and attention mechanisms into an autoregressive diffusion generator, achieving both generative capability and controllable editability.

MRBench: A Comprehensive Benchmark for Human Motion-Text Retrieval

This work proposes a lightweight granularity-aware model anchored at a frozen standard-caption-aligned retrieval model that improves mixed-granularity retrieval without compromising standard-caption performance, and believes that its MRBench provides a comprehensive testbed for advancing motion-language alignment evaluation.