Author name cluster

Hanyu Wang

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.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

SEAP: Sparse Expert Activation Pruning Unlocks the Brainpower of Large Language Models

Xun Liang
Hanyu Wang
Huayi Lai
Simin Niu
Shichao Song
Jiawei Yang
Jihao Zhao
Feiyu Xiong

Pruning is a promising approach to reduce the high inference cost of large language models (LLMs), but it often comes at the expense of performance. Motivated by the "functional localization" theory in neuroscience, we hypothesize that LLMs contain task-specific expert activation paths, where specific subsets of neurons are co-activated for particular tasks. This structure allows selective activation to preserve task performance while improving inference efficiency. We introduce Sparse Expert Activation Pruning (SEAP), a training-free pruning method for large language models. SEAP identifies task-relevant activation paths by analyzing the clustering patterns of hidden states and neuron activations on a multi-task calibration dataset. Cross-task transfer evaluations confirm the existence of such expert activation structures. SEAP constructs task-aware pruning masks by leveraging a task-expert calibration dataset, which provides representative samples across diverse tasks to reveal their activation signatures. It then employs a lightweight task router to dynamically select relevant computation paths based on the input task. This design significantly reduces inference cost without compromising accuracy. Experimental results show that SEAP retains model performance with only a 1.5% drop on most tasks at 20% sparsity, and at 50% sparsity, it surpasses strong pruning baselines such as WandA and FLAP by over 20%. These results highlight SEAP as a scalable and effective solution for efficient LLM inference.

PDF Details DOI

EAAI Journal 2025 Journal Article

Development of an industry-applicable two-phase flow regime identification approach using flow-induced vibration acceleration signals

Hanyu Wang
Shuichiro Miwa
Wen Zhou
Takashi Hibiki
Koji Okamoto

Accurate classification of two-phase flow regimes is essential for optimizing industrial pipeline operations and ensuring system safety. Flow-induced vibration (FIV) signals present a promising option for developing flow regime classifiers due to the non-intrusiveness and accessibility of force/acceleration sensors. However, conventional FIV measurement and classification approaches often suffer from the database’s limited representativeness and necessitate complex feature engineering, thereby impeding their practical application in industrial systems. This study proposes a novel methodology that integrates a specialized experimental setup with an end-to-end one-dimensional convolutional neural network (1D-CNN) to effectively classify two-phase flow regimes using FIV acceleration signals. Firstly, a more representative FIV acceleration database was constructed by a tightly fixed 90-degree elbow section, thereby ensuring that induced vibrations are predominantly attributable to two-phase flow rather than structural resonance. Leveraging this database, a multi-channel 1D-CNN model was developed, capable of autonomously extracting temporal patterns from high-frequency FIV signals without the necessity for extensive feature engineering. The model architecture incorporates an adaptive average pooling layer and is optimized through a Bayesian framework to enhance both computational efficiency and classification performance. Comprehensive evaluations using metrics such as precision, recall, accuracy, and F1-score demonstrate that the proposed 1D-CNN model surpasses feature-based methods. An average classification accuracy of 89. 9% was achieved across all flow regimes. Notably, the model demonstrated superior capability in distinguishing bubbly and slug flow regimes, achieving precisions of 97. 2% and 91. 7% and recalls of 94. 6% and 89. 8%, respectively. Furthermore, visualization analysis of the proposed model further reveals that convolutional kernels with varying degrees of smoothness and symmetry effectively capture dominant frequency patterns. This work not only advances the accuracy and efficiency of two-phase flow regime classification but also establishes a robust foundation for future research aimed at broadening the applicability of deep learning models in complex industrial settings involving two-phase flows.

Details DOI

AAAI Conference 2025 Conference Paper

Integrating Large Language Models and Möbius Group Transformations for Temporal Knowledge Graph Embedding on the Riemann Sphere

Sensen Zhang
Xun Liang
Simin Niu
Zhendong Niu
Bo Wu
Gengxin Hua
Long Wang
Zhenyu Guan

The significance of Temporal Knowledge Graphs (TKGs) in Artificial Intelligence (AI) lies in their capacity to incorporate time-dimensional information, support complex reasoning and prediction, optimize decision-making processes, enhance the accuracy of recommendation systems, promote multimodal data integration, and strengthen knowledge management and updates. This provides a robust foundation for various AI applications. To effectively learn and apply both static and dynamic temporal patterns for reasoning, a range of embedding methods and large language models (LLMs) have been proposed in the literature. However, these methods often rely on a single underlying embedding space, whose geometric properties severely limit their ability to model intricate temporal patterns, such as hierarchical and ring structures. To address this limitation, this paper proposes embedding TKGs into projective geometric space and leverages LLMs technology to extract crucial temporal node information, thereby constructing the 5EL model. By embedding TKGs into projective geometric space and utilizing Möbius Group transformations, we effectively model various temporal patterns. Subsequently, LLMs technology is employed to process the trained TKGs. We adopt a parameter-efficient fine-tuning strategy to align LLMs with specific task requirements, thereby enhancing the model's ability to recognize structural information of key nodes in historical chains and enriching the representation of central entities. Experimental results on five advanced TKG datasets demonstrate that our proposed 5EL model significantly outperforms existing models.

PDF Details DOI

ICLR Conference 2025 Conference Paper

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

Hanyu Wang
Saksham Suri
Yixuan Ren
Hao Chen
Abhinav Shrivastava

We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches into discrete tokens, LARP introduces a holistic tokenization scheme that gathers information from the visual content using a set of learned holistic queries. This design allows LARP to capture more global and semantic representations, rather than being limited to local patch-level information. Furthermore, it offers flexibility by supporting an arbitrary number of discrete tokens, enabling adaptive and efficient tokenization based on the specific requirements of the task. To align the discrete token space with downstream AR generation tasks, LARP integrates a lightweight AR transformer as a training-time prior model that predicts the next token on its discrete latent space. By incorporating the prior model during training, LARP learns a latent space that is not only optimized for video reconstruction but is also structured in a way that is more conducive to autoregressive generation. Moreover, this process defines a sequential order for the discrete tokens, progressively pushing them toward an optimal configuration during training, ensuring smoother and more accurate AR generation at inference time. Comprehensive experiments demonstrate LARPs strong performance, achieving state-of-the-art FVD on the UCF101 class-conditional video generation benchmark. LARP enhances the compatibility of AR models with videos and opens up the potential to build unified high-fidelity multimodal large language models (MLLMs). Project page: https://hywang66.github.io/larp/

Details

ICML Conference 2025 Conference Paper

TruthFlow: Truthful LLM Generation via Representation Flow Correction

Hanyu Wang
Bochuan Cao
Yuanpu Cao
Jinghui Chen

Large language models (LLMs) are known to struggle with consistently generating truthful responses. While various representation intervention techniques have been proposed, these methods typically apply a universal representation correction vector to all input queries, limiting their effectiveness against diverse queries in practice. In this study, we introduce TruthFlow, a novel method that leverages the Flow Matching technique for query-specific truthful representation correction. Specifically, TruthFlow first uses a flow model to learn query-specific correction vectors that transition representations from hallucinated to truthful states. Then, during inference, the trained flow model generates these correction vectors to enhance the truthfulness of LLM outputs. Experimental results demonstrate that TruthFlow significantly improves performance on open-ended generation tasks across various advanced LLMs evaluated on TruthfulQA. Moreover, the trained TruthFlow model exhibits strong transferability, performing effectively on other unseen hallucination benchmarks.

Details

NeurIPS Conference 2025 Conference Paper

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Jiaming Han
Hao Chen
Yang Zhao
Hanyu Wang
Qi Zhao
Ziyan Yang
Hao He
Xiangyu Yue

This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary. By integrating vision and text into a unified space with an expanded vocabulary, our multimodal LLM, Tar, enables cross-modal input and output through a shared interface, without the need for modality-specific designs. Additionally, we propose scale-adaptive encoding and decoding to balance efficiency and visual detail, along with a generative de-tokenizer to produce high-fidelity visual outputs. To address diverse decoding needs, we utilize two complementary de-tokenizers: a fast autoregressive model and a diffusion-based model. To enhance modality fusion, we investigate advanced pre-training tasks, demonstrating improvements in both visual understanding and generation. Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency. All code, models, and data will be made publicly available.

PDF Details

ICRA Conference 2024 Conference Paper

PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

Wenhao Yu 0010
Jie Peng 0002
Quecheng Qiu
Hanyu Wang
Lu Zhang
Jianmin Ji

Robot navigation using deep reinforcement learning (DRL) has shown great potential in improving the performance of mobile robots. Nevertheless, most existing DRL-based navigation methods primarily focus on training a policy that directly commands the robot with low-level controls, like linear and angular velocities, which leads to unstable speeds and unsmooth trajectories of the robot during the long-term execution. An alternative method is to train a DRL policy that outputs the navigation path directly. Then the robot can follow the generated path smoothly using sophisticated velocity-planning and path-following controllers, whose parameters are specified according to the hardware platform. However, two roadblocks arise for training a DRL policy that outputs paths: (1) The action space for potential paths often involves higher dimensions comparing to low-level commands, which increases the difficulties of training; (2) It takes multiple time steps to track a path instead of a single time step, which requires the path to predicate the interactions of the robot w. r. t. the dynamic environment in multiple time steps. This, in turn, amplifies the challenges associated with training. In response to these challenges, we propose PathRL, a novel DRL method that trains the policy to generate the navigation path for the robot. Specifically, we employ specific action space discretization techniques and tailored state space representation methods to address the associated challenges. Curriculum learning is employed to expedite the training process, while the reward function also takes into account the smooth transition between adjacent paths. In our experiments, PathRL achieves better success rates and reduces angular rotation variability compared to other DRL navigation methods, facilitating stable and smooth robot movement. We demonstrate the competitive edge of PathRL in both real-world scenarios and multiple challenging simulation environments.

Details

NeurIPS Conference 2021 Conference Paper

NeRV: Neural Representations for Videos

Hao Chen
Bo He
Hanyu Wang
Yixuan Ren
Ser Nam Lim
Abhinav Shrivastava

We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as input. Given a frame index, NeRV outputs the corresponding RGB image. Video encoding in NeRV is simply fitting a neural network to video frames and decoding process is a simple feedforward operation. As an image-wise implicit representation, NeRV output the whole image and shows great efficiency compared to pixel-wise implicit representation, improving the encoding speed by $\textbf{25}\times$ to $\textbf{70}\times$, the decoding speed by $\textbf{38}\times$ to $\textbf{132}\times$, while achieving better video quality. With such a representation, we can treat videos as neural networks, simplifying several video-related tasks. For example, conventional video compression methods are restricted by a long and complex pipeline, specifically designed for the task. In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H. 264, HEVC \etc). Besides compression, we demonstrate the generalization of NeRV for video denoising. The source code and pre-trained model can be found at https: //github. com/haochen-rye/NeRV. git.

PDF Details