4 citations · 5 across the 12 of their papers we have counts for
12 papers
SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition
Tingyan Wen, Chenqian Yan, Xurui Peng +4
Few-step diffusion models substantially compress temporal computation, making the spatial cost of each model evaluation an increasingly dominant source of inference latency. Progre…
Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling
Wengyi Zhan, Chenqian Yan, Songwei Liu +2
Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-i…
Motion-Aware Caching for Efficient Autoregressive Video Generation
Jing Xu, Yuexiao Ma, Xuzhe Zheng +7
Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential i…
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
Kailai Feng, Yuxiang Wei, Bo Chen +5
Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of par…
S2O: Early Stopping for Sparse Attention via Online Permutation
Yu Zhang, Songwei Liu, Chenqian Yan +4
Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks…
ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
Xurui Peng, Chenqian Yan, Hong Liu +6
Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy…
Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion
Songwei Liu, Chao Zeng, Chenqian Yan +4
Diffusion models have transformed image synthesis by establishing unprecedented quality and creativity benchmarks. Nevertheless, their large-scale deployment faces challenges due t…
Penrose Tiled Low-Rank Compression and Section-Wise Q&A Fine-Tuning: A General Framework for Domain-Specific Large Language Model Adaptation
Chuan-Wei Kuo, Siyu Chen, Chenqi Yan +1
Large language models (LLMs) hold great promise for specialized scientific domains such as materials science, yet adapting them efficiently and accurately to domain-specific knowle…
Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models
Chenqian Yan, Songwei Liu, Hongjian Liu +5
Stable Diffusion Models (SDMs) have shown remarkable proficiency in image synthesis. However, their broad application is impeded by their large model sizes and intensive computatio…
FoldGPT: Simple and Effective Large Language Model Compression Scheme
Songwei Liu, Chao Zeng, Lianqiang Li +4
The demand for deploying large language models(LLMs) on mobile devices continues to increase, driven by escalating data security concerns and cloud costs. However, network bandwidt…
Differentiable Search for Finding Optimal Quantization Strategy
Lianqiang Li, Chenqian Yan, Yefei Chen
To accelerate and compress deep neural networks (DNNs), many network quantization algorithms have been proposed. Although the quantization strategy of any algorithm from the state-…
SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group Sparsity
Haitao Xu, Songwei Liu, Yuyang Xu +7
To address the challenge of increasing network size, researchers have developed sparse models through network pruning. However, maintaining model accuracy while achieving significa…