Author name cluster

Yi Liang

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.

6 papers

2 author rows

EAAI Journal 2026 Journal Article

A lightweight framework with adaptive feature enhancement for accurate pavement distress evaluation

Yi Liang
Jueqiang Tao
Qing Yang
Xin Qiu
Tingfeng Zhang
Yafang Liu
Heng Zhou

Timely pavement condition survey ensures optimal pavement performance and extends its service life. However, existing lightweight object detection models for pavement distress identification often struggle with a trade-off between computational efficiency and fine-grained feature extraction, fail to adapt to the irregular, elongated morphologies of cracks using fixed-grid convolutions, and are hindered by class imbalance and complex backgrounds that lead to misclassifications. To address these gaps, this study proposes the Lightweight Pavement Distress Network (LPD-Net), a crack-feature enhanced framework based on You Only Look Once version 11 (YOLOv11) for accurate pavement distress detection. Firstly, a large-scale dataset comprising depth images was constructed using a three-dimensional (3D) laser imaging sensor. Secondly, Dynamic Snake Convolution (DySConv) was integrated into the Cross Stage Partial with kernel size 2 (C3k2) module to adaptively adjust kernel sampling for better capturing crack contours and edges. Thirdly, a Bi-level Routing Attention (BRA) module was embedded to dynamically filter background noise and focus on sparse distress features, alleviating class imbalance. Lastly, a Lightweight Asymmetric Detection Head (LADH) incorporating Depthwise Separable Convolution (DSConv) was designed to reduce computational overhead while maintaining localization precision. Experimental results demonstrate that LPD-Net achieves a superior balance, reducing computational cost by 15. 9 % to 5. 3 Giga Floating Point Operations (GFLOPs) compared to the baseline while increasing mean Average Precision at 50 % intersection over union (mAP@50) by 6. 5 % to 0. 506. Measurement-oriented evaluation via Pavement Condition Index (PCI) further confirms its reliability, with 40. 72 % agreement within ± 5 PCI, aligning well with metrological standards.

Details DOI

AAAI Conference 2025 Conference Paper

M^3EL: A Multi-task Multi-topic Dataset for Multi-modal Entity Linking

Fang Wang
Shenglin Yin
Xiaoying Bai
Minghao Hu
Tianwei Yan
Yi Liang

Multi-modal Entity Linking (MEL) is a fundamental component for various downstream tasks. However, existing MEL datasets suffer from small scale, scarcity of topic types and limited coverage of tasks, making them incapable of effectively enhancing the entity linking capabilities of multi-modal models. To address these obstacles, we propose a dataset construction pipeline and publish M^3EL, a large-scale dataset for MEL. M^3EL includes 79,625 instances, covering 9 diverse multi-modal tasks, and 5 different topics. In addition, to further improve the model's adaptability to multi-modal tasks, We propose a modality-augmented training strategy. Utilizing M^3EL as a corpus, train the CLIP_ND model based on CLIP (ViT-B-32), and conduct a comparative analysis with an existing multi-modal baselines. Experimental results show that the existing models perform far below expectations (ACC of 49.4%-75.8%), After analysis, it was obtained that small dataset sizes, insufficient modality task coverage, and limited topic diversity resulted in poor generalization of multi-modal models. Our dataset effectively addresses these issues, and the CLIP_ND model fine-tuned with M^3EL shows a significant improvement in accuracy, with an average improvement of 9.3% to 25% across various tasks. Our dataset publicly available to facilitate future research.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild

Xinyu Zhao
Guoheng Sun
Ruisi Cai
Yukun Zhou
Pingzhi Li
Peihao Wang
Bowen Tan
Yexiao He

As Large Language Models (LLMs) excel across tasks and specialized domains, scaling LLMs based on existing models has gained significant attention, which is challenged by potential performance drop when combining disparate models. Various techniques have been proposed to aggregate pre-trained LLMs, including model merging, Mixture-of-Experts, and stacking. Despite their merits, a comprehensive comparison and synergistic application of them to a diverse model zoo is yet to be adequately addressed. In light of this research gap, this paper introduces $\texttt{Model-GLUE}$, a holistic LLM scaling guideline. First, our work starts with a benchmarking of existing LLM scaling techniques, especially selective merging, and variants of mixture. Utilizing the insights from the benchmark results, we formulate a strategy for the selection and aggregation of a heterogeneous model zoo characterizing different architectures and initialization. Our methodology involves clustering mergeable models, selecting a merging strategy, and integrating model clusters through model-level mixture. Finally, evidenced by our experiments on a diverse Llama-2-based model zoo, $\texttt{Model-GLUE}$ shows an average performance enhancement of 5. 61\%, achieved without additional training. Codes are available at https: //github. com/Model-GLUE/Model-GLUE.

PDF Details DOI

ICML Conference 2024 Conference Paper

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Lu Yin 0006
You Wu 0001
Zhenyu Zhang 0015
Cheng-Yu Hsieh
Yaqing Wang 0007
Yiling Jia
Gen Li 0012
Ajay Kumar Jaiswal

Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge due to their colossal model size when it comes to practical deployment. In response to this challenge, efforts have been directed toward the application of traditional network pruning techniques to LLMs, uncovering a massive number of parameters can be pruned in one-shot without hurting performance. Building upon insights gained from pre-LLM models, particularly BERT-level language models, prevailing LLM pruning strategies have consistently adhered to the practice of uniformly pruning all layers at equivalent sparsity levels, resulting in robust performance. However, this observation stands in contrast to the prevailing trends observed in the field of vision models, where non-uniform layerwise sparsity typically yields substantially improved results. To elucidate the underlying reasons for this disparity, we conduct a comprehensive analysis of the distribution of token features within LLMs. In doing so, we discover a strong correlation with the emergence of outliers, defined as features exhibiting significantly greater magnitudes compared to their counterparts in feature dimensions. Inspired by this finding, we introduce a novel LLM pruning methodology that incorporates a tailored set of non-uniform layerwise sparsity ratios specifically designed for LLM pruning, termed as O utlier W eighed L ayerwise sparsity ( OWL ). The sparsity ratio of OWL is directly proportional to the outlier ratio observed within each layer, facilitating a more effective alignment between layerwise weight sparsity and outlier ratios. Our empirical evaluation, conducted across the LLaMA-V1/V2, Vicuna, OPT, and Mistral, spanning various benchmarks, demonstrates the distinct advantages offered by OWL over previous methods. For instance, OWL exhibits a remarkable performance gain, surpassing the state-of-the-art Wanda and SparseGPT by 61. 22 and 6. 80 perplexity at a high sparsity level of 70%, respectively, while delivering 2. 6$\times$ end-to-end inference speed-up in the DeepSparse inference engine. Code is available at https: //github. com/luuyin/OWL. git.

Details

AAAI Conference 2022 Short Paper

Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)

Yi Liang
Shuai Zhao
Bo Cheng
Yuwei Yin
Hao Yang

Few-shot relation learning refers to infer facts for relations with a limited number of observed triples. Existing metriclearning methods for this problem mostly neglect entity interactions within and between triples. In this paper, we explore this kind of fine-grained semantic meanings and propose our model TransAM. Specifically, we serialize reference entities and query entities into sequence and apply transformer structure with local-global attention to capture both intra- and inter-triple entity interactions. Experiments on two public benchmark datasets NELL-One and Wiki-One with 1shot setting prove the effectiveness of TransAM.

PDF Details

NeurIPS Conference 2022 Conference Paper

Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization

Junru Wu
Yi Liang
Feng Han
Hassan Akbari
Zhangyang Wang
Cong Yu

Self-supervised pre-training recently demonstrates success on large-scale multimodal data, and state-of-the-art contrastive learning methods often enforce the feature consistency from cross-modality inputs, such as video/audio or video/text pairs. Despite its convenience to formulate and leverage in practice, such cross-modality alignment (CMA) is only a weak and noisy supervision, since two modalities can be semantically misaligned even they are temporally aligned. For example, even in the (often adopted) instructional videos, a speaker can sometimes refer to something that is not visually present in the current frame; and the semantic misalignment would only be more unpredictable for the raw videos collected from unconstrained internet sources. We conjecture that might cause conflicts and biases among modalities, and may hence prohibit CMA from scaling up to training with larger and more heterogeneous data. This paper first verifies our conjecture by observing that, even in the latest VATT pre-training using only narrated videos, there exist strong gradient conflicts between different CMA losses within the same sample triplet (video, audio, text), indicating them as the noisy source of supervision. We then propose to harmonize such gradients during pre-training, via two techniques: (i) cross-modality gradient realignment: modifying different CMA loss gradients for one sample triplet, so that their gradient directions are in more agreement; and (ii) gradient-based curriculum learning: leveraging the gradient conflict information on an indicator of sample noisiness, to develop a curriculum learning strategy to prioritize training with less noisy sample triplets. Applying those gradient harmonization techniques to pre-training VATT on the HowTo100M dataset, we consistently improve its performance on different downstream tasks. Moreover, we are able to scale VATT pre-training to more complicated non-narrative Youtube8M dataset to further improve the state-of-the-arts.

PDF Details