40 citations · 74 across the 7 of their papers we have counts for
7 papers
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
Shixing Yu, Promit Ghosal, Kyra Gan
A critical step for reliable large language models (LLMs) use in healthcare is to attribute predictions to their training data, akin to a medical case study. This requires token-le…
FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer
Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu +3
Vision Transformers (ViT) have recently demonstrated success across a myriad of computer vision tasks. However, their elevated computational demands pose significant challenges for…
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Kaiyu Yang, Aidan M. Swope, Alex Gu +6
Large language models (LLMs) have shown promise in proving formal theorems using proof assistants such as Lean. However, existing methods are difficult to reproduce or build on, du…
Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace
Yucong Liu, Shixing Yu, Tong Lin
In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian. This regularizer is motivated by a recent guarantee bound of th…
Meta-Interpolation: Time-Arbitrary Frame Interpolation via Dual Meta-Learning
Shixing Yu, Yiyang Ma, Wenhan Yang +2
Existing video frame interpolation methods can only interpolate the frame at a given intermediate time-step, e.g. 1/2. In this paper, we aim to explore a more generalized kind of v…
Unified Visual Transformer Compression
Shixing Yu, Tianlong Chen, Jiayi Shen +5
Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly train…
Hessian-Aware Pruning and Optimal Neural Implant
Shixing Yu, Zhewei Yao, Amir Gholami +4
Pruning is an effective method to reduce the memory footprint and FLOPs associated with neural network models. However, existing structured-pruning methods often result in signific…