43 citations · 74 across the 21 of their papers we have counts for
8 papers · 1 filter
OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators
Tianyi Chen, Tianyu Ding, Zhihui Zhu +4
Compressing a predefined deep neural network (DNN) into a compact sub-network with competitive performance is crucial in the efficient machine learning realm. This topic spans vari…
The Efficiency Spectrum of Large Language Models: An Algorithmic Survey
Tianyu Ding, Tianyi Chen, Haidong Zhu +7
The rapid growth of Large Language Models (LLMs) has been a driving force in transforming various domains, reshaping the artificial general intelligence landscape. However, the inc…
DREAM: Diffusion Rectification and Estimation-Adaptive Models
Jinxin Zhou, Tianyu Ding, Tianyi Chen +4
We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantl…
CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering
Haidong Zhu, Tianyu Ding, Tianyi Chen +3
Generalizability and few-shot learning are key challenges in Neural Radiance Fields (NeRF), often due to the lack of a holistic understanding in pixel-level rendering. We introduce…
LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery
Tianyi Chen, Tianyu Ding, Badal Yadav +2
Large Language Models (LLMs) have transformed the landscape of artificial intelligence, while their enormous size presents significant challenges in terms of computational costs. W…
MMVP: Motion-Matrix-based Video Prediction
Yiqi Zhong, Luming Liang, Ilya Zharkov +1
A central challenge of video prediction lies where the system has to reason the objects' future motions from image frames while simultaneously maintaining the consistency of their…
Automated Search-Space Generation Neural Architecture Search
Tianyi Chen, Luming Liang, Tianyu Ding +1
To search an optimal sub-network within a general deep neural network (DNN), existing neural architecture search (NAS) methods typically rely on handcrafting a search space beforeh…
OTOV2: Automatic, Generic, User-Friendly
Tianyi Chen, Luming Liang, Tianyu Ding +2
The existing model compression methods via structured pruning typically require complicated multi-stage procedures. Each individual stage necessitates numerous engineering efforts…