10 papers
The Efficiency Gap in Byte Modeling
Celine Lee, Jing Nathan Yan, Chen Liang +9
Modern language models have historically relied on two dominant design choices: subword tokenization and autoregressive (AR) ordering. These design decisions bake in priors that di…
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
Youcan Xu, Jiaxin Shi, Zhen Wang +5
Camera-controlled video-to-video (V2V) generation enables dynamic viewpoint synthesis from monocular footage, holding immense potential for interactive filmmaking and live broadcas…
DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
Hengye Lyu, Zisu Li, Yue Hong +4
Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research valu…
Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
Patrick Pynadath, Jiaxin Shi, Ruqi Zhang
Diffusion language models have seen exciting recent progress, offering far more flexibility in generative trajectories than autoregressive models. This flexibility has motivated a…
Real-Time Motion-Controllable Autoregressive Video Diffusion
Kesen Zhao, Jiaxin Shi, Beier Zhu +5
Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) appro…
SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video Generation
Zisu Li, Hengye Lyu, Jiaxin Shi +4
Modeling and synthesizing complex hand-object interactions remains a significant challenge, even for state-of-the-art physics engines. Conventional simulation-based approaches rely…