167 citations · 914 across the 103 of their papers we have counts for
20 papers · 1 filter
Few-Step Distillation for Text-to-Image Generation: A Practical Guide
Yifan Pu, Yizeng Han, Zhiwei Tang +4
Diffusion distillation has dramatically accelerated class-conditional image synthesis, but its applicability to open-ended text-to-image (T2I) generation is still unclear. We prese…
PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation
Xiaolong Li, Youping Gu, Xi Lin +2
Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of effic…
Geometrically-Constrained Agent for Spatial Reasoning
Zeren Chen, Xiaoya Lu, Zhijie Zheng +6
Vision Language Models (VLMs) exhibit a fundamental semantic-to-geometric gap in spatial reasoning: they excel at qualitative semantic inference but their reasoning operates within…
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
Feng Chen, Yefei He, Shaoxuan He +9
Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge t…
Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning
Ziyu Ma, Chenhui Gou, Yiming Hu +4
Large Multimodal Models (LMMs) have shown promising in-context learning (ICL) capabilities, but scaling to many-shot settings remains difficult due to limited context length and hi…
BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation
Zeyu Zhang, Jinyuan Mao, Shuning Chang +5
Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive d…
Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
Inferix Team, Tianyu Feng, Yizeng Han +13
World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic, and interactive high-quality videos.…
BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
Youping Gu, Xiaolong Li, Yuhao Hu +2
Diffusion Transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequ…
RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
Wangbo Zhao, Yizeng Han, Zhiwei Tang +7
Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse att…
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
Weijie Wang, Yeqing Chen, Zeyu Zhang +9
Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussia…
An Empirical Study on How Video-LLMs Answer Video Questions
Chenhui Gou, Ziyu Ma, Zicheng Duan +6
Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However,…
Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis
Zhuokun Chen, Jugang Fan, Zhuowei Yu +2
Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and…
R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
Zhuokun Chen, Zeren Chen, Jiahao He +4
Chain-of-thought (CoT) enhances the problem-solving ability of large language models (LLMs) but incurs substantial inference cost due to long autoregressive trajectories. Existing…
FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
Akide Liu, Zeyu Zhang, Zhexin Li +12
Diffusion generative models have become the standard for producing high-quality, coherent video content, yet their slow inference speeds and high computational demands hinder pract…
Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
Duochao Shi, Weijie Wang, Donny Y. Chen +4
Depth maps are widely used in feed-forward 3D Gaussian Splatting (3DGS) pipelines by unprojecting them into 3D point clouds for novel view synthesis. This approach offers advantage…
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
Weijie Wang, Donny Y. Chen, Zeyu Zhang +3
Feed-forward 3D Gaussian Splatting (3DGS) models have recently emerged as a promising solution for novel view synthesis, enabling one-pass inference without the need for per-scene…
Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
Feng Chen, Yefei He, Lequan Lin +4
Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods mere…
Neighboring Autoregressive Modeling for Efficient Visual Generation
Yefei He, Yuanyu He, Shaoxuan He +4
Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Spe…
Motion Anything: Any to Motion Generation
Zeyu Zhang, Yiran Wang, Wei Mao +7
Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperfo…
Are Large Vision Language Models Good Game Players?
Xinyu Wang, Bohan Zhuang, Qi Wu
Large Vision Language Models (LVLMs) have demonstrated remarkable abilities in understanding and reasoning about both visual and textual information. However, existing evaluation m…