12 papers
OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
Lin Zhao, Yushu Wu, Yifan Gong +2
Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. E…
Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
Zhenglun Kong, Zheng Zhan, Shiyue Hou +10
Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities…
FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
Xuan Shen, Weize Ma, Yufa Zhou +11
Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike i…
DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance
Xuan Shen, Chenxia Han, Yufa Zhou +7
Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost re…
LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers
Xuan Shen, Zhao Song, Yufa Zhou +12
Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The…
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Zheng Zhan, Yushu Wu, Yifan Gong +7
The rapid progress in artificial intelligence-generated content (AIGC), especially with diffusion models, has significantly advanced development of high-quality video generation. H…
Search for Efficient Large Language Models
Xuan Shen, Pu Zhao, Yifan Gong +7
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and disti…
Rethinking Token Reduction for State Space Models
Zheng Zhan, Yushu Wu, Zhenglun Kong +6
Recent advancements in State Space Models (SSMs) have attracted significant interest, particularly in models optimized for parallel training and handling long-range dependencies. A…
Lotus: learning-based online thermal and latency variation management for two-stage detectors on edge devices
Yifan Gong, Yushu Wu, Zheng Zhan +5
Two-stage object detectors exhibit high accuracy and precise localization, especially for identifying small objects that are favorable for various edge applications. However, the h…
Exploring Token Pruning in Vision State Space Models
Zheng Zhan, Zhenglun Kong, Yifan Gong +8
State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a ne…
AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge
Chao Wu, Yifan Gong, Liangkai Liu +7
Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the d…
Efficient Training with Denoised Neural Weights
Yifan Gong, Zheng Zhan, Yanyu Li +6
Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challengin…