1 citations · 2 across the 10 of their papers we have counts for
11 papers
Euclid Bypass end-to-end simulations for spectroscopic galaxy clustering performance assessment
Euclid Collaboration, B. R. Granett, S. de la Torre +321
We present a simulation framework for Euclid galaxy clustering measurements that reproduces the essential behaviour of the spectroscopic reduction chain, bypassing the computation…
Rethinking Unified Memory for NPU-PIM Systems: Dual-View Memory for Dynamic Inference of LLM
Shixin Zhao, Lian Liu, Tianhua Han +3
Heterogeneous architectures that combine neural processing unit (NPU) and processing-in-memory (PIM) are increasingly adopted to accelerate LLM inference. Prior work focuses on bui…
TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading
Yudong Pan, Yintao He, Tianhua Han +7
To deploy large Mixture-of-Experts (MoE) models cost-effectively, offloading-based single-GPU heterogeneous inference is crucial. While GPU-CPU architectures that offload cold expe…
SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds
Wuxinlin Cheng, Yupeng Cao, Jinwen Wu +3
Recent strides in pretrained transformer-based language models have propelled state-of-the-art performance in numerous NLP tasks. Yet, as these models grow in size and deployment,…
Learning Multimodal Latent Generative Models with Energy-Based Prior
Shiyu Yuan, Jiali Cui, Hanao Li +1
Multimodal generative models have recently gained significant attention for their ability to learn representations across various modalities, enhancing joint and cross-generation c…
Layerwise Change of Knowledge in Neural Networks
Xu Cheng, Lei Cheng, Zhaoran Peng +3
This paper aims to explain how a deep neural network (DNN) gradually extracts new knowledge and forgets noisy features through layers in forward propagation. Up to now, although th…
Learning Multimodal Latent Space with EBM Prior and MCMC Inference
Shiyu Yuan, Carlo Lipizzi, Tian Han
Multimodal generative models are crucial for various applications. We propose an approach that combines an expressive energy-based model (EBM) prior with Markov Chain Monte Carlo (…
Learning Latent Space Hierarchical EBM Diffusion Models
Jiali Cui, Tian Han
This work studies the learning problem of the energy-based prior model and the multi-layer generator model. The multi-layer generator model, which contains multiple layers of laten…
Improving Adversarial Energy-Based Model via Diffusion Process
Cong Geng, Tian Han, Peng-Tao Jiang +4
Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to param…
Learning Energy-based Model via Dual-MCMC Teaching
Jiali Cui, Tian Han
This paper studies the fundamental learning problem of the energy-based model (EBM). Learning the EBM can be achieved using the maximum likelihood estimation (MLE), which typically…
Learning Hierarchical Features with Joint Latent Space Energy-Based Prior
Jiali Cui, Ying Nian Wu, Tian Han
This paper studies the fundamental problem of multi-layer generator models in learning hierarchical representations. The multi-layer generator model that consists of multiple layer…