collaborators

7 papers

cs.LG2026

Cache: Accelerating World Action Models with Cross Inference Chunk Cache

Weisen Zhao, Lam Nguyen, Zhicong Lu +1

World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them lea…

cs.CV2026

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion

Kunyang Li, Mubarak Shah, Yuzhang Shang

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic comput…

cs.CL2026

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload

Zhiben Chen, Youpeng Zhao, Yang Sui +2

Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive (AR) models, offering better hardware utilization and bidirectional context thro…

cs.CV2026

Aero-World: Action-Conditioned Aerial Video Generation from Inertial Controls

Abdul Mohaimen Al Radi, Kunyang Li, Yuzhang Shang +2

Foundation video models produce visually impressive results, but their use in embodied AI remains limited because they are primarily trained on natural language rather than low-lev…

cs.RO2026

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform

Yu Shang, Yinzhou Tang, Yiding Ma +22

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, ex…

cs.CL2026

Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights

Wenrui Bao, Huan Wang, Jian Wang +3

Multi-agent LLM systems usually collaborate by exchanging natural-language messages. This interface is simple and interpretable, but it forces each sender's intermediate computatio…