Wushao Wen

Shanshan Zhong, Shanghua Gao, Zhongzhan Huang et al.

Large language models (LLMs) excel in various tasks but are primarily trained on text data, limiting their application scope. Expanding LLM capabilities to include vision-language understanding is vital, yet training them on multimodal data from scratch is challenging and costly. Existing instruction tuning methods, e.g., LLAVA, often connects a pretrained CLIP vision encoder and LLMs via fully fine-tuning LLMs to bridge the modality gap. However, full fine-tuning is plagued by catastrophic forgetting, i.e., forgetting previous knowledge, and high training costs particularly in the era of increasing tasks and modalities. To solve this issue, we introduce MoExtend, an effective framework designed to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. MoExtend seamlessly integrates new experts into pre-trained MoE models, endowing them with novel knowledge without the need to tune pretrained models such as MoE and vision encoders. This approach enables rapid adaptation and extension to new modal data or tasks, effectively addressing the challenge of accommodating new modalities within LLMs. Furthermore, MoExtend avoids tuning pretrained models, thus mitigating the risk of catastrophic forgetting. Experimental results demonstrate the efficacy and efficiency of MoExtend in enhancing the multimodal capabilities of LLMs, contributing to advancements in multimodal AI research. Code: https://github.com/zhongshsh/MoExtend.

Shanshan Zhong, Zhongzhan Huang, Wushao Wen et al.

The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent parameter transformations. This technique enables the mitigation of the extra costs for performance improvement during training, such as parameter size and inference time, through these transformations during inference, and therefore SRP has great potential for industrial and practical applications. The existing SRP methods have successfully considered many commonly used architectures, such as normalizations, pooling methods, and multi-branch convolution. However, the widely used attention modules which drastically slow inference speed cannot be directly implemented by SRP due to these modules usually act on the backbone network in a multiplicative manner and the modules' output is input-dependent during inference, which limits the application scenarios of SRP. In this paper, we conduct extensive experiments from a statistical perspective and discover an interesting phenomenon Stripe Observation, which reveals that channel attention values quickly approach some constant vectors during training. This observation inspires us to propose a simple-yet-effective attention-alike structural re-parameterization (ASR) that allows us to achieve SRP for a given network while enjoying the effectiveness of the attention mechanism. Extensive experiments conducted on several standard benchmarks demonstrate the effectiveness of ASR in generally improving the performance of existing backbone networks, attention modules, and SRP methods without any elaborated model crafting. We also analyze the limitations and provide experimental and theoretical evidence for the strong robustness of the proposed ASR.

Shanshan Zhong, Wushao Wen, Jinghui Qin

Attention mechanism has gained great success in vision recognition. Many works are devoted to improving the effectiveness of attention mechanism, which finely design the structure of the attention operator. These works need lots of experiments to pick out the optimal settings when scenarios change, which consumes a lot of time and computational resources. In addition, a neural network often contains many network layers, and most studies often use the same attention module to enhance different network layers, which hinders the further improvement of the performance of the self-attention mechanism. To address the above problems, we propose a self-attention module SEM. Based on the input information of the attention module and alternative attention operators, SEM can automatically decide to select and integrate attention operators to compute attention maps. The effectiveness of SEM is demonstrated by extensive experiments on widely used benchmark datasets and popular self-attention networks.

Shanshan Zhong, Wushao Wen, Jinghui Qin

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design of the pooling strategy of the attention mechanism since they adopt the global average pooling for granted, which hinders the further improvement of the performance of the attention mechanism. However, we empirically find and verify a phenomenon that the simple linear combination of global max-pooling and global min-pooling can produce pooling strategies that match or exceed the performance of global average pooling. Based on this empirical observation, we propose a simple-yet-effective attention module SPEM, which adopts a self-adaptive pooling strategy based on global max-pooling and global min-pooling and a lightweight module for producing the attention map. The effectiveness of SPEM is demonstrated by extensive experiments on widely-used benchmark datasets and popular attention networks.

Shanshan Zhong, Zhongzhan Huang, Daifeng Li et al.

Multimodal recommender systems utilize various types of information to model user preferences and item features, helping users discover items aligned with their interests. The integration of multimodal information mitigates the inherent challenges in recommender systems, e.g., the data sparsity problem and cold-start issues. However, it simultaneously magnifies certain risks from multimodal information inputs, such as information adjustment risk and inherent noise risk. These risks pose crucial challenges to the robustness of recommendation models. In this paper, we analyze multimodal recommender systems from the novel perspective of flat local minima and propose a concise yet effective gradient strategy called Mirror Gradient (MG). This strategy can implicitly enhance the model's robustness during the optimization process, mitigating instability risks arising from multimodal information inputs. We also provide strong theoretical evidence and conduct extensive empirical experiments to show the superiority of MG across various multimodal recommendation models and benchmarks. Furthermore, we find that the proposed MG can complement existing robust training methods and be easily extended to diverse advanced recommendation models, making it a promising new and fundamental paradigm for training multimodal recommender systems. The code is released at https://github.com/Qrange-group/Mirror-Gradient.

Shanshan Zhong, Wushao Wen, Jinghui Qin et al.

More and more empirical and theoretical evidence shows that deepening neural networks can effectively improve their performance under suitable training settings. However, deepening the backbone of neural networks will inevitably and significantly increase computation and parameter size. To mitigate these problems, we propose a simple-yet-effective Recurrent Attention Strategy (RAS), which implicitly increases the depth of neural networks with lightweight attention modules by local parameter sharing. The extensive experiments on three widely-used benchmark datasets demonstrate that RAS can improve the performance of neural networks at a slight addition of parameter size and computation, performing favorably against other existing well-known attention modules.

Qiuyang Lu, Fangjian Shen, Zhengkai Tang et al.

The quality and accessibility of multilingual datasets are crucial for advancing machine translation. However, previous corpora built from United Nations documents have suffered from issues such as opaque process, difficulty of reproduction, and limited scale. To address these challenges, we introduce a complete end-to-end solution, from data acquisition via web scraping to text alignment. The entire process is fully reproducible, with a minimalist single-machine example and optional distributed computing steps for scalability. At its core, we propose a new Graph-Aided Paragraph Alignment (GAPA) algorithm for efficient and flexible paragraph-level alignment. The resulting corpus contains over 713 million English tokens, more than doubling the scale of prior work. To the best of our knowledge, this represents the largest publicly available parallel corpus composed entirely of human-translated, non-AI-generated content. Our code and corpus are accessible under the MIT License.

Shanshan Zhong, Wushao Wen, Jinghui Qin et al.

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and statistically illustrate that DNNs have a serious attention bias problem on many samples from some popular datasets: (1) Position bias: DNNs fully focus on label-independent regions; (2) Range bias: The focused regions from DNN are not completely contained in the ideal region. Moreover, we find that the existing self-attention modules can alleviate these biases to a certain extent, but the biases are still non-negligible. To further mitigate them, we propose a lightweight sub-attention strategy (LSAS), which utilizes high-order sub-attention modules to improve the original self-attention modules. The effectiveness of LSAS is demonstrated by extensive experiments on widely-used benchmark datasets and popular attention networks. We release our code to help other researchers to reproduce the results of LSAS~\footnote{https://github.com/Qrange-group/LSAS}.

Shanshan Zhong, Zhongzhan Huang, Wushao Wen et al.

Diffusion models, which have emerged to become popular text-to-image generation models, can produce high-quality and content-rich images guided by textual prompts. However, there are limitations to semantic understanding and commonsense reasoning in existing models when the input prompts are concise narrative, resulting in low-quality image generation. To improve the capacities for narrative prompts, we propose a simple-yet-effective parameter-efficient fine-tuning approach called the Semantic Understanding and Reasoning adapter (SUR-adapter) for pre-trained diffusion models. To reach this goal, we first collect and annotate a new dataset SURD which consists of more than 57,000 semantically corrected multi-modal samples. Each sample contains a simple narrative prompt, a complex keyword-based prompt, and a high-quality image. Then, we align the semantic representation of narrative prompts to the complex prompts and transfer knowledge of large language models (LLMs) to our SUR-adapter via knowledge distillation so that it can acquire the powerful semantic understanding and reasoning capabilities to build a high-quality textual semantic representation for text-to-image generation. We conduct experiments by integrating multiple LLMs and popular pre-trained diffusion models to show the effectiveness of our approach in enabling diffusion models to understand and reason concise natural language without image quality degradation. Our approach can make text-to-image diffusion models easier to use with better user experience, which demonstrates our approach has the potential for further advancing the development of user-friendly text-to-image generation models by bridging the semantic gap between simple narrative prompts and complex keyword-based prompts. The code is released at https://github.com/Qrange-group/SUR-adapter.

Shanshan Zhong, Zhongzhan Huang, Shanghua Gao et al.

Chain-of-Thought (CoT) guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs -- a non-sequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study. Then to investigate LLMs' LoT ability in the Oogiri game, we first build a multimodal and multilingual Oogiri-GO dataset which contains over 130,000 samples from the Oogiri game, and observe the insufficient LoT ability or failures of most existing LLMs on the Oogiri game. Accordingly, we introduce a creative Leap-of-Thought (CLoT) paradigm to improve LLM's LoT ability. CLoT first formulates the Oogiri-GO dataset into LoT-oriented instruction tuning data to train pretrained LLM for achieving certain LoT humor generation and discrimination abilities. Then CLoT designs an explorative self-refinement that encourages the LLM to generate more creative LoT data via exploring parallels between seemingly unrelated concepts and selects high-quality data to train itself for self-refinement. CLoT not only excels in humor generation in the Oogiri game but also boosts creative abilities in various tasks like cloud guessing game and divergent association task. These findings advance our understanding and offer a pathway to improve LLMs' creative capacities for innovative applications across domains. The dataset, code, and models will be released online. https://zhongshsh.github.io/CLoT/.

Hui Wang, Jinghui Qin, Wushao Wen et al.

Multimodal data has significantly advanced recommendation systems by integrating diverse information sources to model user preferences and item characteristics. However, these systems often struggle with redundant and irrelevant information, which can degrade performance. Most existing methods either fuse multimodal information directly or use rigid architectural separation for disentanglement, failing to adequately filter noise and model the complex interplay between modalities. To address these challenges, we propose a novel framework, the Multimodal Representation-disentangled Information Bottleneck (MRdIB). Concretely, we first employ a Multimodal Information Bottleneck to compress the input representations, effectively filtering out task-irrelevant noise while preserving rich semantic information. Then, we decompose the information based on its relationship with the recommendation target into unique, redundant, and synergistic components. We achieve this decomposition with a series of constraints: a unique information learning objective to preserve modality-unique signals, a redundant information learning objective to minimize overlap, and a synergistic information learning objective to capture emergent information. By optimizing these objectives, MRdIB guides a model to learn more powerful and disentangled representations. Extensive experiments on several competitive models and three benchmark datasets demonstrate the effectiveness and versatility of our MRdIB in enhancing multimodal recommendation.

Fangjian Shen, Zifeng Liang, Chao Wang et al.

Text-to-image (T2I) models exhibit a significant yet under-explored "brand bias", a tendency to generate contents featuring dominant commercial brands from generic prompts, posing ethical and legal risks. We propose CIDER, a novel, model-agnostic framework to mitigate bias at inference-time through prompt refinement to avoid costly retraining. CIDER uses a lightweight detector to identify branded content and a Vision-Language Model (VLM) to generate stylistically divergent alternatives. We introduce the Brand Neutrality Score (BNS) to quantify this issue and perform extensive experiments on leading T2I models. Results show CIDER significantly reduces both explicit and implicit biases while maintaining image quality and aesthetic appeal. Our work offers a practical solution for more original and equitable content, contributing to the development of trustworthy generative AI.

Yifan Liu, Wenkuan Zhao, Shanshan Zhong et al.

Recent advancements in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI). Among the essential capabilities required for AGI, creativity has emerged as a critical trait for MLLMs, with association serving as its foundation. Association reflects a model' s ability to think creatively, making it vital to evaluate and understand. While several frameworks have been proposed to assess associative ability, they often overlook the inherent ambiguity in association tasks, which arises from the divergent nature of associations and undermines the reliability of evaluations. To address this issue, we decompose ambiguity into two types-internal ambiguity and external ambiguity-and introduce AssoCiAm, a benchmark designed to evaluate associative ability while circumventing the ambiguity through a hybrid computational method. We then conduct extensive experiments on MLLMs, revealing a strong positive correlation between cognition and association. Additionally, we observe that the presence of ambiguity in the evaluation process causes MLLMs' behavior to become more random-like. Finally, we validate the effectiveness of our method in ensuring more accurate and reliable evaluations. See Project Page for the data and codes.

Qingling Li, Wushao Wen, Jinghui Qin

The Aspect Sentiment Triplet Extraction (ASTE) task aims to extract aspect terms, opinion terms, and their corresponding sentiment polarity from a given sentence. It remains one of the most prominent subtasks in fine-grained sentiment analysis. Most existing approaches frame triplet extraction as a 2D table-filling process in an end-to-end manner, focusing primarily on word-level interactions while often overlooking sentence-level representations. This limitation hampers the model's ability to capture global contextual information, particularly when dealing with multi-word aspect and opinion terms in complex sentences. To address these issues, we propose boundary-driven table-filling with cross-granularity contrastive learning (BTF-CCL) to enhance the semantic consistency between sentence-level representations and word-level representations. By constructing positive and negative sample pairs, the model is forced to learn the associations at both the sentence level and the word level. Additionally, a multi-scale, multi-granularity convolutional method is proposed to capture rich semantic information better. Our approach can capture sentence-level contextual information more effectively while maintaining sensitivity to local details. Experimental results show that the proposed method achieves state-of-the-art performance on public benchmarks according to the F1 score.

Jinghui Qin, Ziwei Xie, Yukai Shi et al.

Recently, deep learning based single image super-resolution(SR) approaches have achieved great development. The state-of-the-art SR methods usually adopt a feed-forward pipeline to establish a non-linear mapping between low-res(LR) and high-res(HR) images. However, due to treating all image regions equally without considering the difficulty diversity, these approaches meet an upper bound for optimization. To address this issue, we propose a novel SR approach that discriminately processes each image region within an image by its difficulty. Specifically, we propose a dual-way SR network that one way is trained to focus on easy image regions and another is trained to handle hard image regions. To identify whether a region is easy or hard, we propose a novel image difficulty recognition network based on PSNR prior. Our SR approach that uses the region mask to adaptively enforce the dual-way SR network yields superior results. Extensive experiments on several standard benchmarks (e.g., Set5, Set14, BSD100, and Urban100) show that our approach achieves state-of-the-art performance.

Andrey Ignatov, Radu Timofte, Thang Van Vu et al.

This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, participants were solving the classical image super-resolution problem with a bicubic downscaling factor of 4. The second track was aimed at real-world photo enhancement, and the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with a DSLR camera. The target metric used in this challenge combined the runtime, PSNR scores and solutions' perceptual results measured in the user study. To ensure the efficiency of the submitted models, we additionally measured their runtime and memory requirements on Android smartphones. The proposed solutions significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.