Publications (41)
UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
Yaqi Zhao, Wang Lin, Zijian Zhang +5
Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic informa…
Progress on the Construction of the 100 MeV / 100 kW Electron Linac for the NSC KIPT Neutron Source
Chi Yun-Long, Pei Shi-Lun, Pei Guo-Xi +28
IHEP, China is constructing a 100 MeV / 100 kW electron Linac for NSC KIPT, Ukraine. This linac will be used as the driver of a neutron source based on a subcritical assembly. In 2…
Instruction Tuning-free Visual Token Complement for Multimodal LLMs
Dongsheng Wang, Jiequan Cui, Miaoge Li +3
As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inh…
MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition
Xize Cheng, Linjun Li, Tao Jin +7
Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and a…
Domain-of-Attraction Estimation for Uncertain Non-polynomial Systems
Min Wu, Zhengfeng Yang, Wang Lin
In this paper, we consider the problem of computing estimates of the domain-of-attraction for non-polynomial systems. A polynomial approximation technique, based on multivariate po…
Impedance budget and instability estimation of the HLS-II storage ring
Zhang Qingkun, Wang Lin, Li Weimin +1
The upgrade project of Hefei Light Source storage ring is under way. In this paper, the wake fields of new designed vacuum chambers have been simulated by CST code, and then broadb…
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
Weicai Yan, Yuhong Dai, Qi Ran +6
Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous stre…
Semileptonic Decays of and from Light-Cone Sum Rules
Wang Lin, Xiao-En Huang, Shan Cheng +1
We investigate the semileptonic decays of charmed mesons to light vector mesons within the framework of light-cone sum rules. Our calculation is performed at leading order in QCD c…
Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision
Weicai Yan, Wang Lin, Zirun Guo +5
Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fi…
Imagine Before You Draw: Visual Prompt Engineering for Image Generation
Liyu Jia, Fengda Zhang, Jiachun Pan +7
Incorporating visual semantic representations as an intermediate step before image generation can reduce the modeling difficulty between text and images, thereby improving generati…
Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
Zhiqi Ge, Juncheng Li, Xinglei Pang +7
Digital agents are increasingly employed to automate tasks in interactive digital environments such as web pages, software applications, and operating systems. While text-based age…
Exact Safety Verification of Interval Hybrid Systems Based on Symbolic-Numeric Computation
Zhengfeng Yang, Min Wu, Wang Lin
In this paper, we address the problem of safety verification of interval hybrid systems in which the coefficients are intervals instead of explicit numbers. A hybrid symbolic-numer…
Nanoplasmonic Optical Fiber Sensing of SARS-CoV-2 Nucleocapsid Protein Using an Aptamer-DNA Tetrahedron Interface
Xu Pin, Cui Jingyu, Cheng Zhi +8
Optical fiber sensing carries a number of potential advantages for diagnostics and biomarker detection and monitoring, yet particular challenges persist in linking molecular recogn…
WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
Wang Lin, Feng Wang, Majun Zhang +7
Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synth…
Low-rank Prompt Interaction for Continual Vision-Language Retrieval
Weicai Yan, Ye Wang, Wang Lin +3
Research on continual learning in multi-modal tasks has been receiving increasing attention. However, most existing work overlooks the explicit cross-modal and cross-task interacti…
Exact Safety Verification of Hybrid Systems Based on Bilinear SOS Representation
Zhengfeng Yang, Min Wu, Wang Lin
In this paper, we address the problem of safety verification of nonlinear hybrid systems. A hybrid symbolic-numeric method is presented to compute exact inequality invariants of hy…
ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
Zhipeng Bian, Jieming Zhu, Qijiong Liu +6
Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, personalized cover image generat…
IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models
Hanting Wang, Tao Jin, Wang Lin +4
Bridge models in image restoration construct a diffusion process from degraded to clear images. However, existing methods typically require training a bridge model from scratch for…
Online Controller Synthesis for Robot Collision Avoidance: A Case Study
Yuheng Fan, Wang Lin
The inherent uncertainty of dynamic environments poses significant challenges for modeling robot behavior, particularly in tasks such as collision avoidance. This paper presents an…
OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
Xize Cheng, Tao Jin, Linjun Li +3
Speech Recognition builds a bridge between the multimedia streaming (audio-only, visual-only or audio-visual) and the corresponding text transcription. However, when training the s…
EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration
Ye Wang, Jiahao Xun, Minjie Hong +8
Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem. H…
Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation
Qingsong Wang, Tao Wu, Wang Lin +4
Large Language Models (LLMs) have demonstrated strong performance in open-ended generation tasks. However, they often struggle to adapt content to users with differing cognitive ca…
Bridging the Gap for Test-Time Multimodal Sentiment Analysis
Zirun Guo, Tao Jin, Wenlong Xu +2
Multimodal sentiment analysis (MSA) is an emerging research topic that aims to understand and recognize human sentiment or emotions through multiple modalities. However, in real-wo…
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
Bohan Wang, Zhongqi Yue, Fengda Zhang +15
We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design co…
Longitudinal Single Bunch Instability Study on BEPCII
Wang Dou, Li Yong, Duan Zhe +4
In order to study the single bunch longitudinal instability in BEPCII, experiments on the positron ring (BPR) for the bunch lengthening phenomenon were made. By analyzing the exper…
Text-Guided Multi-Scale Frequency Representation Adaptation
Weicai Yan, Xinhua Ma, Wang Lin +1
Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data distributions. While these methods…
Exact Safety Verification of Hybrid Systems Using Sums-Of-Squares Representation
Wang Lin, Min Wu, Zhengfeng Yang +1
In this paper we discuss how to generate inductive invariants for safety verification of hybrid systems. A hybrid symbolic-numeric method is presented to compute inequality inducti…
AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding
Zihan Huang, Tao Wu, Wang Lin +3
With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning. However, existing research has primarily foc…
Efficient Prompting for Continual Adaptation to Missing Modalities
Zirun Guo, Shulei Wang, Wang Lin +3
Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstre…
Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
Wenkang Han, Wang Lin, Liya Hu +6
Knowledge tracing (KT) aims to predict learners' future performance based on historical learning interactions. However, existing KT models predominantly focus on data from a single…
Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
Tao Wu, Jingyuan Chen, Wang Lin +5
Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior. A major challenge in student simulation is mode…
Towards Transformer-Based Aligned Generation with Self-Coherence Guidance
Shulei Wang, Wang Lin, Hai Huang +8
We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantical…
FlowDreamer: Exploring High Fidelity Text-to-3D Generation via Rectified Flow
Hangyu Li, Xiangxiang Chu, Dingyuan Shi +1
Recent advances in text-to-3D generation have made significant progress. In particular, with the pretrained diffusion models, existing methods predominantly use Score Distillation…
Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration
Wenkang Han, Wang Lin, Yiyun Zhou +4
Face Video Restoration (FVR) aims to recover high-quality face videos from degraded versions. Traditional methods struggle to preserve fine-grained, identity-specific features when…
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
Tao Wu, Jingyuan Chen, Wang Lin +6
Distractors-incorrect yet plausible answer choices in multiple-choice questions (MCQs)-are vital in educational assessments, as they help identify student misconceptions by present…
Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
Wang Lin, Liyu Jia, Wentao Hu +6
Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapol…
From Noisy to Native: LLM-driven Graph Restoration for Test-Time Graph Domain Adaptation
Xiangwei Lv, JinLuan Yang, Wang Lin +2
Graph domain adaptation (GDA) has achieved great attention due to its effectiveness in addressing the domain shift between train and test data. A significant bottleneck in existing…
Non-confusing Generation of Customized Concepts in Diffusion Models
Wang Lin, Jingyuan Chen, Jiaxin Shi +8
We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in…
Simulation of beam gas coulomb scattering in HALS
Yu Lu-Xin, Gao Wei-Wei, Wang Lin +1
In conventional research on the beam gas coulomb scattering (BGCS), only the related beam lifetime using the analytical method is studied. In this paper, using the PIC-MCC method,…
Semantic Alignment for Multimodal Large Language Models
Tao Wu, Mengze Li, Jingyuan Chen +6
Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly…
Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
Kaihang Pan, Wang Lin, Zhongqi Yue +6
Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each ta…