arXiv subjects

Wang Lin

Publications and source records attributed to Wang Lin.

At least 37 records · Page 2Linked to original sources

arXiv2025

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning

Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to their reliance on data-driven approximations. To address this, we propose to integrate symbolic reasoning and reinforcement learning to enforce physical consistency in video generation. We first introduce the Diffusion Timestep Tokenizer (DDT), which learns discrete, recursive visual tokens by recovering visual attributes lost during the diffusion process. The recursive visual tokens enable symbolic reasoning by a large language model. Based on it, we propose the Phys-AR framework, which consists of two stages: The first stage uses supervised fine-tuning to transfer symbolic knowledge, while the second stage applies reinforcement learning to optimize the model's reasoning abilities through reward functions based on physical conditions. Our approach allows the model to dynamically adjust and improve the physical properties of generated videos, ensuring adherence to physical laws. Experimental results demonstrate that PhysAR can generate videos that are physically consistent.

cs.CV↗

arXiv2025

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

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 task, respectively. Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order (e.g., raster scan). However, we show that spatial tokens lack the recursive structure inherent to languages, hence form an impossible language for LLM to master. In this paper, we build a proper visual language by leveraging diffusion timesteps to learn discrete, recursive visual tokens. Our proposed tokens recursively compensate for the progressive attribute loss in noisy images as timesteps increase, enabling the diffusion model to reconstruct the original image at any timestep. This approach allows us to effectively integrate the strengths of LLMs in autoregressive reasoning and diffusion models in precise image generation, achieving seamless multimodal comprehension and generation within a unified framework. Extensive experiments show that we achieve superior performance for multimodal comprehension and generation simultaneously compared with other MLLMs. Project Page: https://DDT-LLaMA.github.io/.

cs.CV↗

arXiv2025

Towards Transformer-Based Aligned Generation with Self-Coherence Guidance

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Transformer-based architectures has shown limited effectiveness. Our method addresses these challenges by directly optimizing cross-attention maps during the generation process. Specifically, we introduce Self-Coherence Guidance, a method that dynamically refines attention maps using masks derived from previous denoising steps, ensuring precise alignment without additional training. To validate our approach, we constructed more challenging benchmarks for evaluating coarse-grained attribute binding, fine-grained attribute binding, and style binding. Experimental results demonstrate the superior performance of our method, significantly surpassing other state-of-the-art methods across all evaluated tasks. Our code is available at https://scg-diffusion.github.io/scg-diffusion.

cs.CV↗

arXiv2025

Efficient Prompting for Continual Adaptation to Missing Modalities

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 downstream datasets with missing modalities, performance can degrade significantly. Current methods often aggregate various missing cases to train recovery modules or align multimodal features, resulting in suboptimal performance, high computational costs, and the risk of catastrophic forgetting in continual environments where data arrives sequentially. In this paper, we formulate the dynamic missing modality problem as a continual learning task and introduce the continual multimodal missing modality task. To address this challenge efficiently, we introduce three types of prompts: modality-specific, task-aware, and task-specific prompts. These prompts enable the model to learn intra-modality, inter-modality, intra-task, and inter-task features. Furthermore, we propose a contrastive task interaction strategy to explicitly learn prompts correlating different modalities. We conduct extensive experiments on three public datasets, where our method consistently outperforms state-of-the-art approaches.

cs.LG↗

arXiv2025

Bridging the Gap for Test-Time Multimodal Sentiment Analysis

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-world dynamic scenarios, the distribution of target data is always changing and different from the source data used to train the model, which leads to performance degradation. Common adaptation methods usually need source data, which could pose privacy issues or storage overheads. Therefore, test-time adaptation (TTA) methods are introduced to improve the performance of the model at inference time. Existing TTA methods are always based on probabilistic models and unimodal learning, and thus can not be applied to MSA which is often considered as a multimodal regression task. In this paper, we propose two strategies: Contrastive Adaptation and Stable Pseudo-label generation (CASP) for test-time adaptation for multimodal sentiment analysis. The two strategies deal with the distribution shifts for MSA by enforcing consistency and minimizing empirical risk, respectively. Extensive experiments show that CASP brings significant and consistent improvements to the performance of the model across various distribution shift settings and with different backbones, demonstrating its effectiveness and versatility. Our codes are available at https://github.com/zrguo/CASP.

cs.LG↗

arXiv2025

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining

Digital agents are increasingly employed to automate tasks in interactive digital environments such as web pages, software applications, and operating systems. While text-based agents built on Large Language Models (LLMs) often require frequent updates due to platform-specific APIs, visual agents leveraging Multimodal Large Language Models (MLLMs) offer enhanced adaptability by interacting directly with Graphical User Interfaces (GUIs). However, these agents face significant challenges in visual perception, particularly when handling high-resolution, visually complex digital environments. This paper introduces Iris, a foundational visual agent that addresses these challenges through two key innovations: Information-Sensitive Cropping (ISC) and Self-Refining Dual Learning (SRDL). ISC dynamically identifies and prioritizes visually dense regions using a edge detection algorithm, enabling efficient processing by allocating more computational resources to areas with higher information density. SRDL enhances the agent's ability to handle complex tasks by leveraging a dual-learning loop, where improvements in referring (describing UI elements) reinforce grounding (locating elements) and vice versa, all without requiring additional annotated data. Empirical evaluations demonstrate that Iris achieves state-of-the-art performance across multiple benchmarks with only 850K GUI annotations, outperforming methods using 10x more training data. These improvements further translate to significant gains in both web and OS agent downstream tasks.

cs.CV↗

arXiv2025

Low-rank Prompt Interaction for Continual Vision-Language Retrieval

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 interactions. In this paper, we innovatively propose the Low-rank Prompt Interaction (LPI) to address this general problem of multi-modal understanding, which considers both cross-modal and cross-task interactions. Specifically, as for the former, we employ multi-modal correlation modules for corresponding Transformer layers. Considering that the training parameters scale to the number of layers and tasks, we propose low-rank interaction-augmented decomposition to avoid memory explosion while enhancing the cross-modal association through sharing and separating common-specific low-rank factors. In addition, due to the multi-modal semantic differences carried by the low-rank initialization, we adopt hierarchical low-rank contrastive learning to ensure training robustness. As for the latter, we initially employ a visual analysis and identify that different tasks have clear distinctions in proximity. Therefore, we introduce explicit task contrastive constraints in the prompt learning process based on task semantic distances. Experiments on two retrieval tasks show performance improvements with the introduction of a minimal number of parameters, demonstrating the effectiveness of our method. Code is available at https://github.com/Kelvin-ywc/LPI.

cs.CV↗

arXiv2024

FlowDreamer: Exploring High Fidelity Text-to-3D Generation via Rectified Flow

Recent advances in text-to-3D generation have made significant progress. In particular, with the pretrained diffusion models, existing methods predominantly use Score Distillation Sampling (SDS) to train 3D models such as Neural RaRecent advances in text-to-3D generation have made significant progress. In particular, with the pretrained diffusion models, existing methods predominantly use Score Distillation Sampling (SDS) to train 3D models such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D GS). However, a hurdle is that they often encounter difficulties with over-smoothing textures and over-saturating colors. The rectified flow model -- which utilizes a simple ordinary differential equation (ODE) to represent a straight trajectory -- shows promise as an alternative prior to text-to-3D generation. It learns a time-independent vector field, thereby reducing the ambiguity in 3D model update gradients that are calculated using time-dependent scores in the SDS framework. In light of this, we first develop a mathematical analysis to seamlessly integrate SDS with rectified flow model, paving the way for our initial framework known as Vector Field Distillation Sampling (VFDS). However, empirical findings indicate that VFDS still results in over-smoothing outcomes. Therefore, we analyze the grounding reasons for such a failure from the perspective of ODE trajectories. On top, we propose a novel framework, named FlowDreamer, which yields high fidelity results with richer textual details and faster convergence. The key insight is to leverage the coupling and reversible properties of the rectified flow model to search for the corresponding noise, rather than using randomly sampled noise as in VFDS. Accordingly, we introduce a novel Unique Couple Matching (UCM) loss, which guides the 3D model to optimize along the same trajectory.

cs.CV↗

arXiv2024

AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding

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 focused on text-based algebra problems, neglecting the study of geometry due to the lack of high-quality geometric datasets. To address this gap, this paper introduces AutoGeo, a novel approach for automatically generating mathematical geometric images to fulfill the demand for large-scale and diverse geometric datasets. AutoGeo facilitates the creation of AutoGeo-100k, an extensive repository comprising 100k high-quality geometry image-text pairs. By leveraging precisely defined geometric clauses, AutoGeo-100k contains a wide variety of geometric shapes, including lines, polygons, circles, and complex spatial relationships, etc. Furthermore, this paper demonstrates the efficacy of AutoGeo-100k in enhancing the performance of multimodal large language models through fine-tuning. Experimental results indicate significant improvements in the model's ability in handling geometric images, as evidenced by enhanced accuracy in tasks such as geometric captioning and mathematical reasoning. This research not only fills a critical gap in the availability of geometric datasets but also paves the way for the advancement of sophisticated AI-driven tools in education and research. Project page: https://autogeo-official.github.io/.

cs.LG↗

arXiv2024

Semantic Alignment for Multimodal Large Language Models

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change captioning). Existing MLLMs typically follow a two-step process in their pipelines: first, extracting visual tokens independently for each input image, and then aligning these visual tokens from different images with the Large Language Model (LLM) in its textual feature space. However, the independent extraction of visual tokens for each image may result in different semantics being prioritized for different images in the first step, leading to a lack of preservation of linking information among images for subsequent LLM analysis. This issue becomes more serious in scenarios where significant variations exist among the images (e.g., visual storytelling). To address this challenge, we introduce Semantic Alignment for Multi-modal large language models (SAM). By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis and align the semantics of different images before feeding them into LLM. As the test bed, we propose a large-scale dataset named MmLINK consisting of 69K samples. Different from most existing datasets for MLLMs fine-tuning, our MmLINK dataset comprises multi-modal instructions with significantly diverse images. Extensive experiments on the group captioning task and the storytelling task prove the effectiveness of our SAM model, surpassing the state-of-the-art methods by a large margin (+37% for group captioning and +22% for storytelling on CIDEr score). Project page: https://mccartney01.github.io/SAM.

cs.CV↗

arXiv2024

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

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 inherently constrained by challenges such as the need for high-quality instruction pairs and the loss of visual information in image-to-text training objectives. To this end, we propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features and thus improve response accuracy. Specifically, our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens to enrich the original visual input. Moreover, an iterative strategy is further designed to extract more visual information by iteratively using the visual selector without any additional training. Notably, the training pipeline requires no additional image-text pairs, resulting in a desired instruction tuning-free property. Both qualitative and quantitative experiments demonstrate the superiority and efficiency of our VTC.

cs.CV↗

arXiv2024

EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration

Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem. However, existing generative methods typically focus solely on either behavioral or semantic aspects of item information, neglecting their complementary nature and thus resulting in limited effectiveness. To address this limitation, we introduce EAGER, a novel generative recommendation framework that seamlessly integrates both behavioral and semantic information. Specifically, we identify three key challenges in combining these two types of information: a unified generative architecture capable of handling two feature types, ensuring sufficient and independent learning for each type, and fostering subtle interactions that enhance collaborative information utilization. To achieve these goals, we propose (1) a two-stream generation architecture leveraging a shared encoder and two separate decoders to decode behavior tokens and semantic tokens with a confidence-based ranking strategy; (2) a global contrastive task with summary tokens to achieve discriminative decoding for each type of information; and (3) a semantic-guided transfer task designed to implicitly promote cross-interactions through reconstruction and estimation objectives. We validate the effectiveness of EAGER on four public benchmarks, demonstrating its superior performance compared to existing methods.

cs.IR↗

arXiv2024

Non-confusing Generation of Customized Concepts in Diffusion Models

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 the generation of customized concepts, due to the scarcity of user-provided concept visual examples. By revisiting the two major stages leading to the success of TGDMs -- 1) contrastive image-language pre-training (CLIP) for text encoder that encodes visual semantics, and 2) training TGDM that decodes the textual embeddings into pixels -- we point that existing customized generation methods only focus on fine-tuning the second stage while overlooking the first one. To this end, we propose a simple yet effective solution called CLIF: contrastive image-language fine-tuning. Specifically, given a few samples of customized concepts, we obtain non-confusing textual embeddings of a concept by fine-tuning CLIP via contrasting a concept and the over-segmented visual regions of other concepts. Experimental results demonstrate the effectiveness of CLIF in preventing the confusion of multi-customized concept generation.

cs.CV↗

arXiv2023

OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment

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 specific model of new domain, it often gets stuck in the lack of new-domain utterances, especially the labeled visual utterances. To break through this restriction, we attempt to achieve zero-shot modality transfer by maintaining the multi-modality alignment in phoneme space learned with unlabeled multimedia utterances in the high resource domain during the pre-training \cite{shi2022learning}, and propose a training system Open-modality Speech Recognition (\textbf{OpenSR}) that enables the models trained on a single modality (e.g., audio-only) applicable to more modalities (e.g., visual-only and audio-visual). Furthermore, we employ a cluster-based prompt tuning strategy to handle the domain shift for the scenarios with only common words in the new domain utterances. We demonstrate that OpenSR enables modality transfer from one to any in three different settings (zero-, few- and full-shot), and achieves highly competitive zero-shot performance compared to the existing few-shot and full-shot lip-reading methods. To the best of our knowledge, OpenSR achieves the state-of-the-art performance of word error rate in LRS2 on audio-visual speech recognition and lip-reading with 2.7\% and 25.0\%, respectively. The code and demo are available at https://github.com/Exgc/OpenSR.

cs.CL↗

arXiv2023

MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition

Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present \textbf{AVMuST-TED}, the first dataset for \textbf{A}udio-\textbf{V}isual \textbf{Mu}ltilingual \textbf{S}peech \textbf{T}ranslation, derived from \textbf{TED} talks. Nonetheless, visual speech is not as distinguishable as audio speech, making it difficult to develop a mapping from source speech phonemes to the target language text. To address this issue, we propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. To further minimize the cross-modality gap and its impact on knowledge transfer, we suggest adopting mixed speech, which is created by interpolating audio and visual streams, along with a curriculum learning strategy to adjust the mixing ratio as needed. MixSpeech enhances speech translation in noisy environments, improving BLEU scores for four languages on AVMuST-TED by +1.4 to +4.2. Moreover, it achieves state-of-the-art performance in lip reading on CMLR (11.1\%), LRS2 (25.5\%), and LRS3 (28.0\%).

cs.CV↗

arXiv2014

Impedance budget and instability estimation of the HLS-II storage ring

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 broadband impedances were obtained by FFT. Together with resistive wall wake fields, broadband impedance model for storage ring was established. Using theoretical formula, longitudinal and transverse single bunch instabilities were discussed. With carefully-designed vacuum chamber, the threshold of beam instabilities was higher than beam current goal.

physics.acc-ph↗

arXiv2014

Simulation of beam gas coulomb scattering in HALS

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, we not only simulated the beam lifetime but also explored the effect of BGCS on the beam distribution. In order to better estimate the effect on particle distribution, we study the ultra-low emittance electron beam, here we choose the HeFei Advanced Light Source (HLAS). By counting the lost particles in a certain time, the corresponding beam lifetime we simulated is 5.1078h/14.5507h in x/y, which is very close to the theoretic value (5.0555h /13.7024h in x/y). By counting the lost particles relative to the collided particles, the simulated value of the loss probability of collided particles is 1.3228e-04, which is also very close to the theoretical value (1.3824e-04). Besides, the simulation shows there is a tail in the transverse distribution due to the BGCS. The close match of the simulation with theoretic value in beam lifetime and loss probability indicates our simulation is reliable.

physics.acc-ph↗

arXiv2013

Progress on the Construction of the 100 MeV / 100 kW Electron Linac for the NSC KIPT Neutron Source

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 2012, the injector part of the accelerator was pre-installed as a testing facility in the experimental hall #2 of IHEP. The injector beam and key hardware testing results were met the design goal. Recently, the injector testing facility was disassembled and all of the components for the whole accelerator have been shipped to Ukraine from China by ocean shipping. The installation of the whole machine in KIPT will be started in June, 2013. The construction progress, the design and testing results of the injector beam and key hardware are presented.

physics.acc-ph↗