1 citations · 2 across the 9 of their papers we have counts for
10 papers
Towards Unbiased On-Policy Distillation for Block Diffusion Language Models
Zaiquan Yang, Fei Wei, Yong Wang +6
On-policy distillation (OPD) has emerged as an effective post-training paradigm for language models, with recent efforts extending it to block diffusion language models (BDLMs). Ho…
The Past Frames the Future: Memory for Autoregressive Video Generation
Harold Haodong Chen, Rongjin Guo, Disen Lan +22
Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) vide…
GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video
Fang Liu, Jinpeng Chen, Ke Xu +7
While multimodal Large Language Models (MLLMs) excel at offline video understanding, an interesting question of how far they are from serving as a real-time procedural coach remain…
EgoCS-400K: An Egocentric Gameplay Dataset for World Models
Rongjin Guo, Dong Liang, Yuhao Liu +4
The shift from video generation to interactive world modeling places new demands on data: beyond captioned videos, world models require temporally aligned video-action-language tra…
Revisiting the Integration of Convolution and Attention for Vision Backbone
Lei Zhu, Xinjiang Wang, Wayne Zhang +1
Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate…
Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension
Zaiquan Yang, Yuhao Liu, Jiaying Lin +2
This paper explores the weakly-supervised referring image segmentation (WRIS) problem, and focuses on a challenging setup where target localization is learned directly from image-t…
Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields
Haoyuan Wang, Wenbo Hu, Lei Zhu +1
Inverse rendering aims at recovering both geometry and materials of objects. It provides a more compatible reconstruction for conventional rendering engines, compared with the neur…
Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks
Yuhao Liu, Zhanghan Ke, Fang Liu +2
Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However, due to the randomness in the diffusion process, they often struggle…
RelayAttention for Efficient Large Language Model Serving with Long System Prompts
Lei Zhu, Xinjiang Wang, Wayne Zhang +1
A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused acros…
Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning
Lei Zhu, Zhanghan Ke, Rynson Lau
Recent semi-supervised learning (SSL) methods typically include a filtering strategy to improve the quality of pseudo labels. However, these filtering strategies are usually hand-c…