238 citations · 694 across the 33 of their papers we have counts for
33 papers
RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
Mingxuan Yan, Yuping Wang, Zechun Liu +1
To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks…
PARQ: Piecewise-Affine Regularized Quantization
Lisa Jin, Jianhao Ma, Zechun Liu +3
We develop a principled method for quantization-aware training (QAT) of large-scale machine learning models. Specifically, we show that convex, piecewise-affine regularization (PAR…
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
Xijie Huang, Zechun Liu, Shih-Yang Liu +1
Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the…
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Shih-yang Liu, Zechun Liu, Xijie Huang +2
We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values, in a post-training manner. Existing post-trainin…
Binary and Ternary Natural Language Generation
Zechun Liu, Barlas Oguz, Aasish Pappu +2
Ternary and binary neural networks enable multiplication-free computation and promise multiple orders of magnitude efficiency gains over full-precision networks if implemented on s…
Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
Xijie Huang, Zechun Liu, Shih-Yang Liu +1
Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-en…
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
Ganesh Jawahar, Haichuan Yang, Yunyang Xiong +10
Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks w…
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oguz, Changsheng Zhao +6
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break d…
SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings
Renjie Wei, Zechun Liu, Yuchen Fan +3
Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resou…
Oscillation-free Quantization for Low-bit Vision Transformers
Shih-Yang Liu, Zechun Liu, Kwang-Ting Cheng
Weight oscillation is an undesirable side effect of quantization-aware training, in which quantized weights frequently jump between two quantized levels, resulting in training inst…
SDQ: Stochastic Differentiable Quantization with Mixed Precision
Xijie Huang, Zhiqiang Shen, Shichao Li +5
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitw…
BiT: Robustly Binarized Multi-distilled Transformer
Zechun Liu, Barlas Oguz, Aasish Pappu +5
Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them increasi…
Stereo Neural Vernier Caliper
Shichao Li, Zechun Liu, Zhiqiang Shen +1
We propose a new object-centric framework for learning-based stereo 3D object detection. Previous studies build scene-centric representations that do not consider the significant v…
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
Arnav Chavan, Zhiqiang Shen, Zhuang Liu +3
This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim) framework. It can search…
Data-Free Neural Architecture Search via Recursive Label Calibration
Zechun Liu, Zhiqiang Shen, Yun Long +3
This paper aims to explore the feasibility of neural architecture search (NAS) given only a pre-trained model without using any original training data. This is an important circums…
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
Zechun Liu, Kwang-Ting Cheng, Dong Huang +2
The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i.e., uniform strategy, due to its superior represent…
Sliced Recursive Transformer
Zhiqiang Shen, Zechun Liu, Eric Xing
We present a neat yet effective recursive operation on vision transformers that can improve parameter utilization without involving additional parameters. This is achieved by shari…
How Do Adam and Training Strategies Help BNNs Optimization?
Zechun Liu, Zhiqiang Shen, Shichao Li +3
The best performing Binary Neural Networks (BNNs) are usually attained using Adam optimization and its multi-step training variants. However, to the best of our knowledge, few stud…
"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
Tianlong Chen, Zhenyu Zhang, Xu Ouyang +3
Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typica…
Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
Zhiqiang Shen, Zechun Liu, Dejia Xu +3
This work aims to empirically clarify a recently discovered perspective that label smoothing is incompatible with knowledge distillation. We begin by introducing the motivation beh…
Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning
Zhiqiang Shen, Zechun Liu, Jie Qin +2
The goal of few-shot learning is to learn a classifier that can recognize unseen classes from limited support data with labels. A common practice for this task is to train a model…
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
Zhiqiang Shen, Zechun Liu, Jie Qin +3
Previous studies dominantly target at self-supervised learning on real-valued networks and have achieved many promising results. However, on the more challenging binary neural netw…
Conditional Link Prediction of Category-Implicit Keypoint Detection
Ellen Yi-Ge, Rui Fan, Zechun Liu +1
Keypoints of objects reflect their concise abstractions, while the corresponding connection links (CL) build the skeleton by detecting the intrinsic relations between keypoints. Ex…
Weight-dependent Gates for Network Pruning
Yun Li, Zechun Liu, Weiqun Wu +4
In this paper, a simple yet effective network pruning framework is proposed to simultaneously address the problems of pruning indicator, pruning ratio, and efficiency constraint. T…