Author name cluster

Yang Sui

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.

13 papers

2 author rows

EAAI Journal 2026 Journal Article

A novel deep learning-based model for fault diagnosis of complex systems with high uncertainty

Tao Dai
Yang Sui
Jiasheng Yan
Jiahao Zhu
Xiaohan Li

The deterministic convolutional neural network (CNN), gated recurrent unit (GRU), and softmax classifier (SC) combination (CNN-GRU-SC) is a well-established deep learning model for fault diagnosis of complex systems. However, the model cannot accurately diagnose the faults for complex systems with high uncertainty. This research aims to propose a novel model integrating interval type-2 fuzzy set (IT2FS) to address this challenge. Specifically, IT2FS is used to define the IT2FS operations of convolution and pooling in CNN, reset and update gates and candidate hidden and hidden states in GRU, and full-connection and softmax in SC, yielding the IT2FS-CNN, IT2FS-GRU, and IT2FS-SC models, respectively. These are coupled to propose a novel IT2FS-based deep learning model for fault diagnosis of complex systems with high uncertainty. Using the dataset (2096 samples: 1404 training, 692 testing across 8 conditions) on the reactor coolant system (RCS) for AP1000 from personal computer transient analyzer (PCTRAN), the proposed model achieved accuracy of 99. 71%, recall of 99. 75%, precision of 99. 71%, F1-score of 99. 73%, and area under the curve (AUC) of 1. 00 at a lower noise level (standard deviation (SD) = 0. 1), and accuracy of 87. 14%, recall of 86. 76%, precision of 87. 49%, F1-score of 86. 28%, and AUC of 0. 98 at a higher noise level (SD = 0. 5), outperforming traditional models in identifying fault modes, locations, and severity under high uncertainty. This model enhances diagnostic reliability in engineering applications and holds promise for broader use in safety-critical systems with inherent uncertainties.

Details DOI

TMLR Journal 2026 Journal Article

A Survey of Token Compression for Efficient Multimodal Large Language Models

Kele Shao
Keda TAO
Kejia Zhang
Sicheng Feng
Mu Cai
Yuzhang Shang
Haoxuan You
Can Qin

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input. While this ability significantly enhances MLLM capabilities, it introduces substantial computational challenges, primarily due to the quadratic complexity of self-attention mechanisms with numerous input tokens. To mitigate these bottlenecks, token compression has emerged as an auspicious and critical approach, efficiently reducing the number of tokens during both training and inference. In this paper, we present the first systematic survey and synthesis of the burgeoning field of multimodal long context token compression. Recognizing that effective compression strategies are deeply tied to the unique characteristics and redundancies of each modality, we categorize existing approaches by their primary data focus, enabling researchers to quickly access and learn methods tailored to their specific area of interest: (1) image-centric compression, which addresses spatial redundancy in visual data; (2) video-centric compression, which tackles spatio-temporal redundancy in dynamic sequences; and (3) audio-centric compression, which handles temporal and spectral redundancy in acoustic signals. Beyond this modality-driven categorization, we further dissect methods based on their underlying mechanisms, including transformation-based, similarity-based, attention-based, and query-based approaches. By providing a comprehensive and structured overview, this survey aims to consolidate current progress, identify key challenges, and inspire future research directions in this rapidly evolving domain.

PDF Details

NeurIPS Conference 2025 Conference Paper

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Tianyi Zhang
Mohsen Hariri
Shaochen (Henry) Zhong
Vipin Chaudhary
Yang Sui
Xia Hu
Anshumali Shrivastava

Large-scale AI models, such as Large Language Models (LLMs) and Diffusion Models (DMs), have grown rapidly in size, creating significant challenges for efficient deployment on resource-constrained hardware. In this paper, we introduce Dynamic-Length Float (DFloat11), a lossless compression framework that reduces LLM and DM size by 30\% while preserving outputs that are bit-for-bit identical to the original model. DFloat11 is motivated by the low entropy in the BFloat16 weight representation of LLMs, which reveals significant inefficiency in the existing storage format. By applying entropy coding, DFloat11 assigns dynamic-length encodings to weights based on frequency, achieving near information-optimal compression without any loss of precision. To facilitate efficient inference with dynamic-length encodings, we develop a custom GPU kernel for fast online decompression. Our design incorporates the following: (i) compact, hierarchical lookup tables (LUTs) that fit within GPU SRAM for efficient decoding, (ii) a two-phase GPU kernel for coordinating thread read/write positions using lightweight auxiliary variables, and (iii) transformer-block-level decompression to minimize latency. Experiments on Llama 3. 3, Qwen 3, Mistral 3, FLUX. 1, and others validate our hypothesis that DFloat11 achieves around 30\% model size reduction while preserving bit-for-bit identical outputs. Compared to a potential alternative of offloading parts of an uncompressed model to the CPU to meet memory constraints, DFloat11 achieves 2. 3--46. 2$\times$ higher throughput in token generation. With a fixed GPU memory budget, DFloat11 enables 5. 7--14. 9$\times$ longer generation lengths than uncompressed models. Notably, our method enables lossless inference of Llama 3. 1 405B, an 810GB model, on a single node equipped with 8$\times$80GB GPUs.

PDF Details

TMLR Journal 2025 Journal Article

DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models

Yang Sui
Huy Phan
Jinqi Xiao
Tianfang Zhang
Zijie Tang
Cong Shi
Yan Wang
Yingying Chen

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content-generation tool. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges. In this paper, we explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the distribution discrepancy of the trigger pattern in the existing diffusion backdoor attacks. Based on this finding, we propose a trigger detection mechanism that can effectively identify the poisoned input noise. Then, from the attack side, we propose a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Our empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

PDF Details

NeurIPS Conference 2025 Conference Paper

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Kele Shao
Keda TAO
Can Qin
Haoxuan You
Yang Sui
Huan Wang

Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods offer solutions. However, approaches operating within the LLM (inner-LLM pruning), such as FastV, incur intrinsic computational overhead in shallow layers. In contrast, methods performing token pruning before the LLM (outer-LLM pruning) primarily address spatial redundancy within individual frames or limited temporal windows, neglecting the crucial global temporal dynamics and correlations across longer video sequences. This leads to sub-optimal spatio-temporal reduction and does not leverage video compressibility fully. Crucially, the synergistic potential and mutual influence of combining these strategies remain unexplored. To further reduce redundancy, we introduce HoliTom, a novel training-free holistic token merging framework. HoliTom employs outer-LLM pruning through global redundancy-aware temporal segmentation, followed by spatial-temporal merging to reduce visual tokens by over 90%, significantly alleviating the LLM's computational burden. Complementing this, we introduce a robust inner-LLM token similarity-based merging approach, designed for superior performance and compatibility with outer-LLM pruning. Evaluations demonstrate our method's promising efficiency-performance trade-off on LLaVA-OneVision-7B, reducing computational costs to 6. 9% of FLOPs while maintaining 99. 1% of the original performance. Furthermore, we achieve a 2. 28× reduction in Time-To-First-Token (TTFT) and a 1. 32× acceleration in decoding throughput, highlighting the practical benefits of our integrated pruning approach for efficient video LLMs inference.

PDF Details

TMLR Journal 2025 Journal Article

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Yang Sui
Yu-Neng Chuang
Guanchu Wang
Jiamu Zhang
Tianyi Zhang
Jiayi Yuan
Hongyi Liu
Andrew Wen

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have further improved performance in System-2 reasoning domains like mathematics and programming by harnessing supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance Chain-of-Thought (CoT) reasoning. However, while longer CoT reasoning sequences improve performance, they also introduce significant computational overhead due to lengthy and redundant outputs, known as the ''overthinking phenomenon''. Efficient Reasoning, which seeks to optimize reasoning length while preserving reasoning capabilities, offers practical benefits such as faster processing times, lower energy consumption, and improved responsiveness, especially valuable for reasoning-intensive applications. Despite its potential, efficient reasoning remains in the early stages of research. In this paper, we provide the first structured survey to systematically investigate and explore the current progress toward achieving efficient reasoning in LLMs. Overall, relying on the inherent mechanism of LLMs, we categorize existing works into several key directions: (1) model-based efficient reasoning, which considers optimizing full-length reasoning models into more concise reasoning models or directly training efficient reasoning models; (2) reasoning output-based efficient reasoning, which aims to dynamically reduce reasoning steps and length during inference; (3) input prompts-based efficient reasoning, which seeks to enhance reasoning efficiency based on input prompt properties such as difficulty or length control. Additionally, we introduce the use of efficient data for training reasoning models, explore the reasoning capabilities of small language models, and discuss evaluation methods and benchmarking.

PDF Details

NeurIPS Conference 2024 Conference Paper

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Yang Sui
Yanyu Li
Anil Kag
Yerlan Idelbayev
Junli Cao
Ju Hu
Dhritiman Sagar
Bo Yuan

Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a huge number of parameters, resulting in a significantly large model size. Saving and transferring them is a major bottleneck for various applications, especially those running on resource-constrained devices. In this work, we develop a novel weight quantization method that quantizes the UNet from Stable Diffusion v1. 5 to $1. 99$ bits, achieving a model with $7. 9\times$ smaller size while exhibiting even better generation quality than the original one. Our approach includes several novel techniques, such as assigning optimal bits to each layer, initializing the quantized model for better performance, and improving the training strategy to dramatically reduce quantization error. Furthermore, we extensively evaluate our quantized model across various benchmark datasets and through human evaluation to demonstrate its superior generation quality.

PDF Details DOI

ICML Conference 2024 Conference Paper

Combining Experimental and Historical Data for Policy Evaluation

Ting Li
Chengchun Shi
Qianglin Wen
Yang Sui
Yongli Qin
Chunbo Lai
Hongtu Zhu

This paper studies policy evaluation with multiple data sources, especially in scenarios that involve one experimental dataset with two arms, complemented by a historical dataset generated under a single control arm. We propose novel data integration methods that linearly integrate base policy value estimators constructed based on the experimental and historical data, with weights optimized to minimize the mean square error (MSE) of the resulting combined estimator. We further apply the pessimistic principle to obtain more robust estimators, and extend these developments to sequential decision making. Theoretically, we establish non-asymptotic error bounds for the MSEs of our proposed estimators, and derive their oracle, efficiency and robustness properties across a broad spectrum of reward shift scenarios. Numerical experiments and real-data-based analyses from a ridesharing company demonstrate the superior performance of the proposed estimators.

Details

ICML Conference 2023 Conference Paper

Adversarial Learning of Distributional Reinforcement Learning

Yang Sui
Yukun Huang
Hongtu Zhu
Fan Zhou 0003

Reinforcement learning (RL) has made significant advancements in artificial intelligence. However, its real-world applications are limited due to differences between simulated environments and the actual world. Consequently, it is crucial to systematically analyze how each component of the RL system can affect the final model performance. In this study, we propose an adversarial learning framework for distributional reinforcement learning, which adopts the concept of influence measure from the statistics community. This framework enables us to detect performance loss caused by either the internal policy structure or the external state observation. The proposed influence measure is based on information geometry and has desirable properties of invariance. We demonstrate that the influence measure is useful for three diagnostic tasks: identifying fragile states in trajectories, determining the instability of the policy architecture, and pinpointing anomalously sensitive policy parameters.

Details

AAAI Conference 2023 Conference Paper

CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness

Huy Phan
Miao Yin
Yang Sui
Bo Yuan
Saman Zonouz

Model compression and model defense for deep neural networks (DNNs) have been extensively and individually studied. Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks. However, the structured sparse models obtained by the existing works suffer severe performance degradation for both benign and robust accuracy, thereby causing a challenging dilemma between robustness and structuredness of compact DNNs. To address this problem, in this paper, we propose CSTAR, an efficient solution that simultaneously impose Compactness, high STructuredness and high Adversarial Robustness on the target DNN models. By formulating the structuredness and robustness requirement within the same framework, the compressed DNNs can simultaneously achieve high compression performance and strong adversarial robustness. Evaluations for various DNN models on different datasets demonstrate the effectiveness of CSTAR. Compared with the state-of-the-art robust structured pruning, CSTAR shows consistently better performance. For instance, when compressing ResNet-18 on CIFAR-10, CSTAR achieves up to 20.07% and 11.91% improvement for benign accuracy and robust accuracy, respectively. For compressing ResNet-18 with 16x compression ratio on Imagenet, CSTAR obtains 8.58% benign accuracy gain and 4.27% robust accuracy gain compared to the existing robust structured pruning.

PDF Details DOI

AAAI Conference 2023 Conference Paper

HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks

Jinqi Xiao
Chengming Zhang
Yu Gong
Miao Yin
Yang Sui
Lizhi Xiang
Dingwen Tao
Bo Yuan

Low-rank compression is an important model compression strategy for obtaining compact neural network models. In general, because the rank values directly determine the model complexity and model accuracy, proper selection of layer-wise rank is very critical and desired. To date, though many low-rank compression approaches, either selecting the ranks in a manual or automatic way, have been proposed, they suffer from costly manual trials or unsatisfied compression performance. In addition, all of the existing works are not designed in a hardware-aware way, limiting the practical performance of the compressed models on real-world hardware platforms. To address these challenges, in this paper we propose HALOC, a hardware-aware automatic low-rank compression framework. By interpreting automatic rank selection from an architecture search perspective, we develop an end-to-end solution to determine the suitable layer-wise ranks in a differentiable and hardware-aware way. We further propose design principles and mitigation strategy to efficiently explore the rank space and reduce the potential interference problem. Experimental results on different datasets and hardware platforms demonstrate the effectiveness of our proposed approach. On CIFAR-10 dataset, HALOC enables 0.07% and 0.38% accuracy increase over the uncompressed ResNet-20 and VGG-16 models with 72.20% and 86.44% fewer FLOPs, respectively. On ImageNet dataset, HALOC achieves 0.9% higher top-1 accuracy than the original ResNet-18 model with 66.16% fewer FLOPs. HALOC also shows 0.66% higher top-1 accuracy increase than the state-of-the-art automatic low-rank compression solution with fewer computational and memory costs. In addition, HALOC demonstrates the practical speedups on different hardware platforms, verified by the measurement results on desktop GPU, embedded GPU and ASIC accelerator.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Implicit Regularization in Over-Parameterized Support Vector Machine

Yang Sui
Xin He
Yang Bai

In this paper, we design a regularization-free algorithm for high-dimensional support vector machines (SVMs) by integrating over-parameterization with Nesterov's smoothing method, and provide theoretical guarantees for the induced implicit regularization phenomenon. In particular, we construct an over-parameterized hinge loss function and estimate the true parameters by leveraging regularization-free gradient descent on this loss function. The utilization of Nesterov's method enhances the computational efficiency of our algorithm, especially in terms of determining the stopping criterion and reducing computational complexity. With appropriate choices of initialization, step size, and smoothness parameter, we demonstrate that unregularized gradient descent achieves a near-oracle statistical convergence rate. Additionally, we verify our theoretical findings through a variety of numerical experiments and compare the proposed method with explicit regularization. Our results illustrate the advantages of employing implicit regularization via gradient descent in conjunction with over-parameterization in sparse SVMs.

PDF Details

NeurIPS Conference 2021 Conference Paper

CHIP: CHannel Independence-based Pruning for Compact Neural Networks

Yang Sui
Miao Yin
Yi Xie
Huy Phan
Saman Aliari Zonouz
Bo Yuan

Filter pruning has been widely used for neural network compression because of its enabled practical acceleration. To date, most of the existing filter pruning works explore the importance of filters via using intra-channel information. In this paper, starting from an inter-channel perspective, we propose to perform efficient filter pruning using Channel Independence, a metric that measures the correlations among different feature maps. The less independent feature map is interpreted as containing less useful information$/$knowledge, and hence its corresponding filter can be pruned without affecting model capacity. We systematically investigate the quantification metric, measuring scheme and sensitiveness$/$reliability of channel independence in the context of filter pruning. Our evaluation results for different models on various datasets show the superior performance of our approach. Notably, on CIFAR-10 dataset our solution can bring $0. 75\%$ and $0. 94\%$ accuracy increase over baseline ResNet-56 and ResNet-110 models, respectively, and meanwhile the model size and FLOPs are reduced by $42. 8\%$ and $47. 4\%$ (for ResNet-56) and $48. 3\%$ and $52. 1\%$ (for ResNet-110), respectively. On ImageNet dataset, our approach can achieve $40. 8\%$ and $44. 8\%$ storage and computation reductions, respectively, with $0. 15\%$ accuracy increase over the baseline ResNet-50 model. The code is available at https: //github. com/Eclipsess/CHIP_NeurIPS2021.

PDF Details