5 papers
BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration
Chence Yang, Ningxi Cheng, Arash Akbari +9
Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple tokens for parallel verification. However, existing methods often requir…
PhyWorld: Physics-Faithful World Model for Video Generation
Pu Zhao, Juyi Lin, Timothy Rupprecht +10
World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising…
Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models
Ci Zhang, Zhaojun Ding, Chence Yang +7
Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficienc…
Rethinking the Potential of Layer Freezing for Efficient DNN Training
Chence Yang, Ci Zhang, Lei Lu +11
With the growing size of deep neural networks and datasets, the computational costs of training have significantly increased. The layer-freezing technique has recently attracted gr…
Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training
Qitao Tan, Sung-En Chang, Rui Xia +10
Zeroth-order (ZO) optimization is an emerging deep neural network (DNN) training paradigm that offers computational simplicity and memory savings. However, this seemingly promising…