Author name cluster

Yuhao Sun

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

TMLR Journal 2026 Journal Article

Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models

Yuhao Sun
Chengyi Cai
Jiacheng Zhang
Zesheng Ye
Xingliang Yuan
Feng Liu

Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-language models (e.g., CLIP). However, we find that both fine-grained text descriptions and localized image patches often contain redundant information, making text-visual alignment less effective. In this paper, we tackle this issue from two perspectives: \emph{view refinement} and \emph{description refinement}, termed as \textit{\textbf{Bi}-refinement for \textbf{F}ine-grained \textbf{T}ext-visual \textbf{A}lignment} (BiFTA). \emph{View refinement} removes redundant image patches with high \emph{Intersection over Union} (IoU) ratios, resulting in more distinctive visual samples. \emph{Description refinement} removes redundant text descriptions with high pairwise cosine similarity, ensuring greater diversity in the remaining descriptions. BiFTA achieves superior zero-shot performance on 6 benchmark datasets for both ViT-based and ResNet-based CLIP, justifying the necessity to remove redundant information in visual-text alignment.

PDF Details

AAAI Conference 2026 Conference Paper

Multiplicative Orthogonal Sequential Editing for Language Models

Hao-Xiang Xu
Jun-Yu Ma
Ziqi Peng
Yuhao Sun
Zhen-Hua Ling
Jia-Chen Gu

Knowledge editing aims to efficiently modify the internal knowledge of large language models (LLMs) without compromising their other capabilities. The prevailing editing paradigm, which appends an update matrix to the original parameter matrix, has been shown by some studies to damage key numerical stability indicators (such as condition number and norm), thereby reducing editing performance and general abilities, especially in sequential editing scenario. Although subsequent methods have made some improvements, they remain within the additive framework and have not fundamentally addressed this limitation. To solve this problem, we analyze it from both statistical and mathematical perspectives and conclude that multiplying the original matrix by an orthogonal matrix does not change the numerical stability of the matrix. Inspired by this, different from the previous additive editing paradigm, a multiplicative editing paradigm termed Multiplicative Orthogonal Sequential Editing (MOSE) is proposed. Specifically, we first derive the matrix update in the multiplicative form, the new knowledge is then incorporated into an orthogonal matrix, which is multiplied by the original parameter matrix. In this way, the numerical stability of the edited matrix is unchanged, thereby maintaining editing performance and general abilities. We compared MOSE with several current knowledge editing methods, systematically evaluating their impact on both editing performance and the general abilities across three different LLMs. Experimental results show that MOSE effectively limits deviations in the edited parameter matrix and maintains its numerical stability. Compared to current methods, MOSE achieves a 12.08% improvement in sequential editing performance, while retaining 95.73% of general abilities across downstream tasks.

PDF Details DOI

ICLR Conference 2025 Conference Paper

AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors

Ruoxuan Feng
Jiangyu Hu
Wenke Xia
Tianci Gao
Ao Shen
Yuhao Sun
Bin Fang 0003
Di Hu 0001

Visuo-tactile sensors aim to emulate human tactile perception, enabling robots to precisely understand and manipulate objects. Over time, numerous meticulously designed visuo-tactile sensors have been integrated into robotic systems, aiding in completing various tasks. However, the distinct data characteristics of these low-standardized visuo-tactile sensors hinder the establishment of a powerful tactile perception system. We consider that the key to addressing this issue lies in learning unified multi-sensor representations, thereby integrating the sensors and promoting tactile knowledge transfer between them. To achieve unified representation of this nature, we introduce TacQuad, an aligned multi-modal multi-sensor tactile dataset from four different visuo-tactile sensors, which enables the explicit integration of various sensors. Recognizing that humans perceive the physical environment by acquiring diverse tactile information such as texture and pressure changes, we further propose to learn unified multi-sensor representations from both static and dynamic perspectives. By integrating tactile images and videos, we present AnyTouch, a unified static-dynamic multi-sensor representation learning framework with a multi-level structure, aimed at both enhancing comprehensive perceptual abilities and enabling effective cross-sensor transfer. This multi-level architecture captures pixel-level details from tactile data via masked modeling and enhances perception and transferability by learning semantic-level sensor-agnostic features through multi-modal alignment and cross-sensor matching. We provide a comprehensive analysis of multi-sensor transferability, and validate our method on various offline datasets and in the real-world pouring task. Experimental results show that our method outperforms existing methods, exhibits outstanding static and dynamic perception capabilities across various sensors. The code, TacQuad dataset and AnyTouch model are fully available at gewu-lab.github.io/AnyTouch/.

Details

NeurIPS Conference 2025 Conference Paper

Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge

Zhenyi Zhang
Zihan Wang
Yuhao Sun
Tiejun Li
Peijie Zhou

Modeling the dynamics from sparsely time-resolved snapshot data is crucial for understanding complex cellular processes and behavior. Existing methods leverage optimal transport, Schrödinger bridge theory, or their variants to simultaneously infer stochastic, unbalanced dynamics from snapshot data. However, these approaches remain limited in their ability to account for cell-cell interactions. This integration is essential in real-world scenarios since intercellular communications are fundamental life processes and can influence cell state-transition dynamics. To address this challenge, we formulate the Unbalanced Mean-Field Schrödinger Bridge (UMFSB) framework to model unbalanced stochastic interaction dynamics from snapshot data. Inspired by this framework, we further propose CytoBridge, a deep learning algorithm designed to approximate the UMFSB problem. By explicitly modeling cellular transitions, proliferation, and interactions through neural networks, CytoBridge offers the flexibility to learn these processes directly from data. The effectiveness of our method has been extensively validated using both synthetic gene regulatory data and real scRNA-seq datasets. Compared to existing methods, CytoBridge identifies growth, transition, and interaction patterns, eliminates false transitions, and reconstructs the developmental landscape with greater accuracy. Code is available at: https: //github. com/zhenyiizhang/CytoBridge-NeurIPS.

PDF Details

ICML Conference 2025 Conference Paper

Sample-specific Noise Injection for Diffusion-based Adversarial Purification

Yuhao Sun
Jiacheng Zhang
Zesheng Ye
Chaowei Xiao
Feng Liu

Diffusion-based purification (DBP) methods aim to remove adversarial noise from the input sample by first injecting Gaussian noise through a forward diffusion process, and then recovering the clean example through a reverse generative process. In the above process, how much Gaussian noise is injected to the input sample is key to the success of DBP methods, which is controlled by a constant noise level $t*$ for all samples in existing methods. In this paper, we discover that an optimal $t*$ for each sample indeed could be different. Intuitively, the cleaner a sample is, the less the noise it should be injected, and vice versa. Motivated by this finding, we propose a new framework, called Sample-specific Score-aware Noise Injection (SSNI). Specifically, SSNI uses a pre-trained score network to estimate how much a data point deviates from the clean data distribution (i. e. , score norms). Then, based on the magnitude of score norms, SSNI applies a reweighting function to adaptively adjust $t*$ for each sample, achieving sample-specific noise injections. Empirically, incorporating our framework with existing DBP methods results in a notable improvement in both accuracy and robustness on CIFAR-10 and ImageNet-1K, highlighting the necessity to allocate distinct noise levels to different samples in DBP methods. Our code is available at: https: //github. com/tmlr-group/SSNI.

Details

NeurIPS Conference 2025 Conference Paper

Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action

Yuhao Sun
Zhenyi Zhang
Zihan Wang
Tiejun Li
Peijie Zhou

Recovering the dynamics from a few snapshots of a high-dimensional system is a challenging task in statistical physics and machine learning, with important applications in computational biology. Many algorithms have been developed to tackle this problem, based on frameworks such as optimal transport and the Schrödinger bridge. A notable recent framework is Regularized Unbalanced Optimal Transport (RUOT), which integrates both stochastic dynamics and unnormalized distributions. However, since many existing methods do not explicitly enforce optimality conditions, their solutions often struggle to satisfy the principle of least action and meet challenges to converge in a stable and reliable way. To address these issues, we propose Variational RUOT (Var-RUOT), a new framework to solve the RUOT problem. By incorporating the optimal necessary conditions for the RUOT problem into both the parameterization of the search space and the loss function design, Var-RUOT only needs to learn a scalar field to solve the RUOT problem and can search for solutions with lower action. We also examined the challenge of selecting a growth penalty function in the widely used Wasserstein-Fisher-Rao metric and proposed a solution that better aligns with biological priors in Var-RUOT. We validated the effectiveness of Var-RUOT on both simulated data and real single-cell datasets. Compared with existing algorithms, Var-RUOT can find solutions with lower action while exhibiting faster convergence and improved training stability. Our code is available at https: //github. com/ZerooVector/VarRUOT.

PDF Details

NeurIPS Conference 2023 Conference Paper

Evolving Connectivity for Recurrent Spiking Neural Networks

Guan Wang
Yuhao Sun
Sijie Cheng
Sen Song

Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics. However, the widely-used surrogate gradient-based training methods for RSNNs are inherently inaccurate and unfriendly to neuromorphic hardware. To address these limitations, we propose the evolving connectivity (EC) framework, an inference-only method for training RSNNs. The EC framework reformulates weight-tuning as a search into parameterized connection probability distributions, and employs Natural Evolution Strategies (NES) for optimizing these distributions. Our EC framework circumvents the need for gradients and features hardware-friendly characteristics, including sparse boolean connections and high scalability. We evaluate EC on a series of standard robotic locomotion tasks, where it achieves comparable performance with deep neural networks and outperforms gradient-trained RSNNs, even solving the complex 17-DoF humanoid task. Additionally, the EC framework demonstrates a two to three fold speedup in efficiency compared to directly evolving parameters. By providing a performant and hardware-friendly alternative, the EC framework lays the groundwork for further energy-efficient applications of RSNNs and advances the development of neuromorphic devices. Our code is publicly available at https: //github. com/imoneoi/EvolvingConnectivity.

PDF Details

ICRA Conference 2023 Conference Paper

Implementation and Optimization of Grasping Learning with Dual-modal Soft Gripper

Lei Zhao
Haoyue Liu
Feihan Li
Xingyu Ding
Yuhao Sun
Fuchun Sun 0001
Jianhua Shan
Qi Ye

Robust and efficient grasping of different objects is still an open problem due to the difficulty of integrating multidisciplinary knowledge such as gripper ontology design, perception, control, and learning. In recent years, learning-based methods have achieved excellent results in grasping various novel objects. However, current methods are usually limited to a single grasping mode or rely on different end effectors to grasp objects of different shapes. For human beings, our hands are capable of grasping various objects with changes in grasping methods and form of hands. In light of this, developing a gripper with similar performance could possibly improve the robot's gripping ability. In this paper, we design a dual-modal soft gripper (DSG) and propose a deep reinforcement learning (DRL) framework to implement the operations. Both of our grasping modes, namely enveloping and pinching, are achieved through the tendon drive system and the deformation of the spring steel plate, which enables the gripper to switch between the two grasping modes in real time. We also combined the cutting-edge achievements of deep learning and reinforcement learning to design an autonomous grasping algorithm based on Q-learning and a deep Q network. Moreover, to fully utilize the visual input from the sensor, we added semantic embeddings of target objects to facilitate the learning, which is especially useful in deciding the grasping method for objects previously unseen. We also evaluate our DRL framework in different scenarios, offering a detailed comparison of each grasping mode and the mixed method (with or without semantic information). Our design has proved efficient in reducing the number of failing grasping actions and improving the success rate when facing novel and tricky objects.

Details