Author name cluster

Yuening Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICML Conference 2025 Conference Paper

FlatQuant: Flatness Matters for LLM Quantization

Yuxuan Sun
Ruikang Liu
Haoli Bai
Han Bao
Kang Zhao
Yuening Li
Jiaxin Hu
Xianzhi Yu

Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally spaced quantization points. Prior research explores various pre-quantization transformations to suppress outliers, such as per-channel scaling and Hadamard transformation. However, we observe that these transformed weights and activations can still exhibit steep and dispersed distributions. In this paper, we propose FlatQuant (Fast and Learnable Affine Transformation), a new post-training quantization approach that enhances the flatness of weights and activations. Our approach identifies optimal affine transformations for each linear layer, calibrated in hours via a lightweight objective. To reduce runtime overhead of affine transformation, we apply Kronecker product with two lightweight matrices, and fuse all operations in FlatQuant into a single kernel. Extensive experiments demonstrate that FlatQuant establishes a new state-of-the-art benchmark for quantization. For example, it achieves less than 1% accuracy drop for W4A4 quantization on the LLaMA-3-70B model, surpassing SpinQuant by 7. 5%. Additionally, it provides up to 2. 3x prefill speedup and 1. 7x decoding speedup compared to the FP16 model. Code is available at: https: //github. com/ruikangliu/FlatQuant.

Details

AAAI Conference 2022 System Paper

RES: An Interpretable Replicability Estimation System for Research Publications

Zhuoer Wang
Qizhang Feng
Mohinish Chatterjee
Xing Zhao
Yezi Liu
Yuening Li
Abhay Kumar Singh
Frank M. Shipman

Reliable and faithful research is the cornerstone of breakthrough advancements and disruptive innovations. Assessing the credibility of scientific findings and claims in research publications has long been a time-consuming and challenging task for researchers and decision-makers. In this paper, we introduce RES - an intelligent system that assists humans in analyzing the credibility of scientific findings and claims in research publications in the field of social and behavioral sciences by estimating their replicability. The pipeline of RES consists of four major modules that perform feature extraction, replicability estimation, result explanation, and sentiment analysis respectively. Our evaluation based on human experts’ assessments suggests that the RES has achieved adequate performance. The RES is also built with a Graphical User Interface (GUI) that is publicly accessible at https: //tamu-infolab. github. io/RES/.

PDF Details

IJCAI Conference 2020 Conference Paper

Dual Policy Distillation

Kwei-Herng Lai
Daochen Zha
Yuening Li
Xia Hu

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is computationally expensive. Moreover, the performance of the student model could be limited by the teacher model if the teacher model is not optimal. In the light of collaborative learning, we study the feasibility of involving joint intellectual efforts from diverse perspectives of student models. In this work, we introduce dual policy distillation (DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning. The key challenge in developing this dual learning framework is to identify the beneficial knowledge from the peer learner for contemporary learning-based reinforcement learning algorithms, since it is unclear whether the knowledge distilled from an imperfect and noisy peer learner would be helpful. To address the challenge, we theoretically justify that distilling knowledge from a peer learner will lead to policy improvement and propose a disadvantageous distillation strategy based on the theoretical results. The conducted experiments on several continuous control tasks show that the proposed framework achieves superior performance with a learning-based agent and function approximation without the use of expensive teacher models.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Kaixiong Zhou
Xiao Huang
Yuening Li
Daochen Zha
Rui Chen
Xia Hu

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because the stacked aggregators would make node representations converge to indistinguishable vectors. Several attempts have been made to tackle the issue by bringing linked node pairs close and unlinked pairs distinct. However, they often ignore the intrinsic community structures and would result in sub-optimal performance. The representations of nodes within the same community/class need be similar to facilitate the classification, while different classes are expected to be separated in embedding space. To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i. e. , differentiable group normalization (DGN). It normalizes nodes within the same group independently to increase their smoothness, and separates node distributions among different groups to significantly alleviate the over-smoothing issue. Experiments on real-world datasets demonstrate that DGN makes GNN models more robust to over-smoothing and achieves better performance with deeper GNNs.

PDF Details