2 citations · 3 across the 12 of their papers we have counts for
15 papers
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset generation. H…
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
Xu Huang, Ye Huang, Zijun Liao +6
High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff between reconstruction fidelity…
FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation
Hao Liu, Chenghuan Huang, Ye Huang +6
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention r…
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Peiwen Zhang, Yufan Deng, Shangkun Sun +11
Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tuned models…
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Juncheng Ma, Jianxin Bi, Yufan Deng +19
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remai…
Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time
Ruizhi Zhang, Ye Huang, Yuangang Pan +5
While artificial intelligence has mastered structured games like chess and Go, vision-language agents still struggle in visually-driven 3D games without access to game states. Exis…
Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging
Zhilin Liu, Ye Huang, Ting Xie +3
Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly rely on text-output-based feedba…
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Kewei Zhang, Ye Huang, Yufan Deng +5
While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient…
Semantic segmentation with reward
Xie Ting, Ye Huang, Zhilin Liu +1
In real-world scenarios, pixel-level labeling is not always available. Sometimes, we need a semantic segmentation network, and even a visual encoder can have a high compatibility,…
VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer
Xikai Tang, Ye Huang, Guangqiang Yin +1
We present VPNeXt, a new and simple model for the Plain Vision Transformer (ViT). Unlike the many related studies that share the same homogeneous paradigms, VPNeXt offers a fresh p…
S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field
Zixi Liang, Guowei Xu, Haifeng Wu +3
Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learn…
Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation
Linlong Fan, Ye Huang, Yanqi Ge +2
Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging…
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Yanqi Ge, Jiaqi Liu, Qingnan Fan +6
In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while…
SSR: SAM is a Strong Regularizer for domain adaptive semantic segmentation
Yanqi Ge, Ye Huang, Wen Li +1
We introduced SSR, which utilizes SAM (segment-anything) as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domain…
Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
Yanqi Ge, Qiang Nie, Ye Huang +5
One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-bas…