5 papers
Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation
Chengqun Yang, Liang Xu, Yanping Li +4
Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For representation, Vector Quantizat…
Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control
Weili Zeng, Yitong Xing, Fulong Liu +10
World generative models are typically used through what they produce: a rendered future, a video-conditioned action, or latent context computed by a costly generative branch. We ar…
When Good Enough Is Optimal: Multiplication-Only Matrix Inversion Approximation for Quantized Gated DeltaNet
Luoming Zhang, Yuwei Ren, Kui Zhang +7
Matrix inversion in chunk-wise parallel linear attention is a major bottleneck for long-context modeling, particularly on NPUs, where forward-substitution-based methods exhibit lim…
Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive Remedy
Weili Zeng, Yichao Yan
Flow matching has recently emerged as a powerful alternative to diffusion models, providing a continuous-time formulation for generative modeling and representation learning. Yet,…
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
Weili Zeng, Ziyuan Huang, Kaixiang Ji +1
Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution,…