Yunxin Li

Yunxin Li, Longyue Wang, Baotian Hu et al.

The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA). Yet, the true challenge lies in the domain of knowledge-intensive VQA tasks, which necessitate not just recognition of visual elements, but also a deep comprehension of the visual information in conjunction with a vast repository of learned knowledge. To uncover such capabilities of MLMs, particularly the newly introduced GPT-4V and Gemini, we provide an in-depth evaluation from three perspectives: 1) Commonsense Knowledge, which assesses how well models can understand visual cues and connect to general knowledge; 2) Fine-grained World Knowledge, which tests the model's skill in reasoning out specific knowledge from images, showcasing their proficiency across various specialized fields; 3) Comprehensive Knowledge with Decision-making Rationales, which examines model's capability to provide logical explanations for its inference, facilitating a deeper analysis from the interpretability perspective. Additionally, we utilize a visual knowledge-enhanced training strategy and multimodal retrieval-augmented generation approach to enhance MLMs, highlighting the future need for advancements in this research direction. Extensive experiments indicate that: a) GPT-4V demonstrates enhanced explanation generation when using composite images as few-shots; b) GPT-4V and other MLMs produce severe hallucinations when dealing with world knowledge; c) Visual knowledge enhanced training and prompting technicals present potential to improve performance. Codes: https://github.com/HITsz-TMG/Cognitive-Visual-Language-Mapper

Jinchao Li, Yunxin Li, Chenrui Zhao et al.

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across $\geq$ 3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld.

Yu Zhao, Yunxin Li, Yuxiang Wu et al.

Medical dialogue generation is an important yet challenging task. Most previous works rely on the attention mechanism and large-scale pretrained language models. However, these methods often fail to acquire pivotal information from the long dialogue history to yield an accurate and informative response, due to the fact that the medical entities usually scatters throughout multiple utterances along with the complex relationships between them. To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i.e., knowledge-aware dialogue graph encoder and recall-enhanced generator. The knowledge-aware dialogue graph encoder constructs a dialogue graph by exploiting the knowledge relationships between entities in the utterances, and encodes it with a graph attention network. Then, the recall-enhanced generator strengthens the usage of these pivotal information by generating a summary of the dialogue before producing the actual response. Experimental results on two large-scale medical dialogue datasets show that MedPIR outperforms the strong baselines in BLEU scores and medical entities F1 measure.

Qian Yang, Yunxin Li, Baotian Hu et al. · mila

Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language model to perform the relation inference and a language model to generate the corresponding explanation. However, the pre-trained vision-language models mainly build token-level alignment between text and image yet ignore the high-level semantic alignment between the phrases (chunks) and visual contents, which is critical for vision-language reasoning. Moreover, the explanation generator based only on the encoded joint representation does not explicitly consider the critical decision-making points of relation inference. Thus the generated explanations are less faithful to visual-language reasoning. To mitigate these problems, we propose a unified Chunk-aware Alignment and Lexical Constraint based method, dubbed as CALeC. It contains a Chunk-aware Semantic Interactor (arr. CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr. LeCG). Specifically, CSI exploits the sentence structure inherent in language and various image regions to build chunk-aware semantic alignment. Relation inferrer uses an attention-based reasoning network to incorporate the token-level and chunk-level vision-language representations. LeCG utilizes lexical constraints to expressly incorporate the words or chunks focused by the relation inferrer into explanation generation, improving the faithfulness and informativeness of the explanations. We conduct extensive experiments on three datasets, and experimental results indicate that CALeC significantly outperforms other competitor models on inference accuracy and quality of generated explanations.

Yunxin Li, Zhenyu Liu, Baotian Hu et al.

Recent advancements in multimodal large language models (MLLMs) have achieved significant multimodal generation capabilities, akin to GPT-4. These models predominantly map visual information into language representation space, leveraging the vast knowledge and powerful text generation abilities of LLMs to produce multimodal instruction-following responses. We could term this method as LLMs for Vision because of its employing LLMs for visual understanding and reasoning, yet observe that these MLLMs neglect the potential of harnessing visual knowledge to enhance the overall capabilities of LLMs, which could be regarded as Vision Enhancing LLMs. In this paper, we propose an approach called MKS2, aimed at enhancing LLMs through empowering Multimodal Knowledge Storage and Sharing in LLMs. Specifically, we introduce Modular Visual Memory (MVM), a component integrated into the internal blocks of LLMs, designed to store open-world visual information efficiently. Additionally, we present a soft Mixture of Multimodal Experts (MoMEs) architecture in LLMs to invoke multimodal knowledge collaboration during text generation. Our comprehensive experiments demonstrate that MKS2 substantially augments the reasoning capabilities of LLMs in contexts necessitating physical or commonsense knowledge. It also delivers competitive results on image-text understanding multimodal benchmarks. The codes will be available at: https://github.com/HITsz-TMG/MKS2-Multimodal-Knowledge-Storage-and-Sharing

Zilin Du, Yunxin Li, Xu Guo et al.

Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction. However, the task lacks annotated multimodal training data and artificially generated training data suffer from distribution shift from real-world data. In this paper, we propose Cross-modality Augmented Multimedia Event Learning (CAMEL), which successfully utilizes artificially generated multimodal training data and achieves state-of-the-art performance. We start with two labeled unimodal datasets in text and image respectively, and generate the missing modality using off-the-shelf image generators like Stable Diffusion and image captioners like BLIP. After that, we train the network on the resultant multimodal datasets. In order to learn robust features that are effective across domains, we devise an iterative and gradual training strategy. Substantial experiments show that CAMEL surpasses state-of-the-art (SOTA) baselines on the M2E2 benchmark. On multimedia events in particular, we outperform the prior SOTA by 4.2% F1 on event mention identification and by 9.8% F1 on argument identification, which indicates that CAMEL learns synergistic representations from the two modalities. Our work demonstrates a recipe to unleash the power of synthetic training data in structured prediction.

Yunxin Li, Haoyuan Shi, Baotian Hu et al.

Traditional animation generation methods depend on training generative models with human-labelled data, entailing a sophisticated multi-stage pipeline that demands substantial human effort and incurs high training costs. Due to limited prompting plans, these methods typically produce brief, information-poor, and context-incoherent animations. To overcome these limitations and automate the animation process, we pioneer the introduction of large multimodal models (LMMs) as the core processor to build an autonomous animation-making agent, named Anim-Director. This agent mainly harnesses the advanced understanding and reasoning capabilities of LMMs and generative AI tools to create animated videos from concise narratives or simple instructions. Specifically, it operates in three main stages: Firstly, the Anim-Director generates a coherent storyline from user inputs, followed by a detailed director's script that encompasses settings of character profiles and interior/exterior descriptions, and context-coherent scene descriptions that include appearing characters, interiors or exteriors, and scene events. Secondly, we employ LMMs with the image generation tool to produce visual images of settings and scenes. These images are designed to maintain visual consistency across different scenes using a visual-language prompting method that combines scene descriptions and images of the appearing character and setting. Thirdly, scene images serve as the foundation for producing animated videos, with LMMs generating prompts to guide this process. The whole process is notably autonomous without manual intervention, as the LMMs interact seamlessly with generative tools to generate prompts, evaluate visual quality, and select the best one to optimize the final output.

Yunxin Li, Shenyuan Jiang, Baotian Hu et al.

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE) architecture has been employed to efficiently scale large language and image-text models, these efforts typically involve fewer experts and limited modalities. To address this, our work presents the pioneering attempt to develop a unified MLLM with the MoE architecture, named Uni-MoE that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We also implement a sparse MoE architecture within the LLMs to enable efficient training and inference through modality-level data parallelism and expert-level model parallelism. To enhance the multi-expert collaboration and generalization, we present a progressive training strategy: 1) Cross-modality alignment using various connectors with different cross-modality data, 2) Training modality-specific experts with cross-modality instruction data to activate experts' preferences, and 3) Tuning the Uni-MoE framework utilizing Low-Rank Adaptation (LoRA) on mixed multimodal instruction data. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets. The extensive experimental results demonstrate Uni-MoE's principal advantage of significantly reducing performance bias in handling mixed multimodal datasets, alongside improved multi-expert collaboration and generalization. Our findings highlight the substantial potential of MoE frameworks in advancing MLLMs and the code is available at https://github.com/HITsz-TMG/UMOE-Scaling-Unified-Multimodal-LLMs.

Yu Zhao, Xinshuo Hu, Yunxin Li et al.

Dialog systems have achieved significant progress and have been widely used in various scenarios. The previous researches mainly focused on designing dialog generation models in a single scenario, while comprehensive abilities are required to handle tasks under various scenarios in the real world. In this paper, we propose a general Multi-Skill Dialog Framework, namely MSDF, which can be applied in different dialog tasks (e.g. knowledge grounded dialog and persona based dialog). Specifically, we propose a transferable response generator pre-trained on diverse large-scale dialog corpora as the backbone of MSDF, consisting of BERT-based encoders and a GPT-based decoder. To select the response consistent with dialog history, we propose a consistency selector trained through negative sampling. Moreover, the flexible copy mechanism of external knowledge is also employed to enhance the utilization of multiform knowledge in various scenarios. We conduct experiments on knowledge grounded dialog, recommendation dialog, and persona based dialog tasks. The experimental results indicate that our MSDF outperforms the baseline models with a large margin. In the Multi-skill Dialog of 2021 Language and Intelligence Challenge, our general MSDF won the 3rd prize, which proves our MSDF is effective and competitive.

Yunxin Li, Xinyu Chen, Baotian Hu et al.

Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected image-knowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively. The codes are available at https://github.com/HITsz-TMG/Cognitive-Visual-Language-Mapper

Yunxin Li, Baotian Hu, Wenhan Luo et al.

In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the unique features of products. For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description. However, the generated description is often inaccurate and generic since same-category products have similar copy-writings, and optimizing the overall framework on large-scale samples makes models concentrate on common words yet ignore the product features. To alleviate the issue, we present a simple and effective Multimodal In-Context Tuning approach, named ModICT, which introduces a similar product sample as the reference and utilizes the in-context learning capability of language models to produce the description. During training, we keep the visual encoder and language model frozen, focusing on optimizing the modules responsible for creating multimodal in-context references and dynamic prompts. This approach preserves the language generation prowess of large language models (LLMs), facilitating a substantial increase in description diversity. To assess the effectiveness of ModICT across various language model scales and types, we collect data from three distinct product categories within the E-commerce domain. Extensive experiments demonstrate that ModICT significantly improves the accuracy (by up to 3.3% on Rouge-L) and diversity (by up to 9.4% on D-5) of generated results compared to conventional methods. Our findings underscore the potential of ModICT as a valuable tool for enhancing automatic generation of product descriptions in a wide range of applications. Code is at: https://github.com/HITsz-TMG/Multimodal-In-Context-Tuning

Xinyu Chen, Yunxin Li, Haoyuan Shi et al.

Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are limited to a single language, typically English, and predominantly feature videos rooted in Western cultural contexts. In this paper, we present VideoVista-CulturalLingo, the first video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension. Our work differs from existing benchmarks in the following ways: 1) Cultural diversity, incorporating cultures from China, North America, and Europe; 2) Multi-linguistics, with questions presented in Chinese and English-two of the most widely spoken languages; and 3) Broad domain, featuring videos sourced from hundreds of human-created domains. VideoVista-CulturalLingo contains 1,389 videos and 3,134 QA pairs, and we have evaluated 24 recent open-source or proprietary video large models. From the experiment results, we observe that: 1) Existing models perform worse on Chinese-centric questions than Western-centric ones, particularly those related to Chinese history; 2) Current open-source models still exhibit limitations in temporal understanding, especially in the Event Localization task, achieving a maximum score of only 45.2%; 3) Mainstream models demonstrate strong performance in general scientific questions, while open-source models demonstrate weak performance in mathematics.

Yujia Qin, Yining Ye, Junjie Fang et al.

This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e.g., keyboard and mouse operations). Unlike prevailing agent frameworks that depend on heavily wrapped commercial models (e.g., GPT-4o) with expert-crafted prompts and workflows, UI-TARS is an end-to-end model that outperforms these sophisticated frameworks. Experiments demonstrate its superior performance: UI-TARS achieves SOTA performance in 10+ GUI agent benchmarks evaluating perception, grounding, and GUI task execution. Notably, in the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively). In AndroidWorld, UI-TARS achieves 46.6, surpassing GPT-4o (34.5). UI-TARS incorporates several key innovations: (1) Enhanced Perception: leveraging a large-scale dataset of GUI screenshots for context-aware understanding of UI elements and precise captioning; (2) Unified Action Modeling, which standardizes actions into a unified space across platforms and achieves precise grounding and interaction through large-scale action traces; (3) System-2 Reasoning, which incorporates deliberate reasoning into multi-step decision making, involving multiple reasoning patterns such as task decomposition, reflection thinking, milestone recognition, etc. (4) Iterative Training with Reflective Online Traces, which addresses the data bottleneck by automatically collecting, filtering, and reflectively refining new interaction traces on hundreds of virtual machines. Through iterative training and reflection tuning, UI-TARS continuously learns from its mistakes and adapts to unforeseen situations with minimal human intervention. We also analyze the evolution path of GUI agents to guide the further development of this domain.

Yunxin Li, Xinyu Chen, Shenyuan Jiang et al.

We present Uni-MoE 2.0 from the Lychee family. As a fully open-source omnimodal large model (OLM), it substantially advances Lychee's Uni-MoE series in language-centric multimodal understanding, reasoning, and generating. Based on the Qwen2.5-7B dense architecture, we build Uni-MoE-2.0-Omni from scratch through three core contributions: dynamic-capacity Mixture-of-Experts (MoE) design, a progressive training strategy enhanced with an iterative reinforcement strategy, and a carefully curated multimodal data matching technique. It is capable of omnimodal understanding, as well as generating images, text, and speech. Architecturally, our new MoE framework balances computational efficiency and capability for 10 cross-modal inputs using shared, routed, and null experts, while our Omni-Modality 3D RoPE ensures spatio-temporal cross-modality alignment in the self-attention layer. For training, following cross-modal pretraining, we use a progressive supervised fine-tuning strategy that activates modality-specific experts and is enhanced by balanced data composition and an iterative GSPO-DPO method to stabilise RL training and improve reasoning. Data-wise, the base model, trained on approximately 75B tokens of open-source multimodal data, is equipped with special speech and image generation tokens, allowing it to learn these generative tasks by conditioning its outputs on linguistic cues. Extensive evaluation across 85 benchmarks demonstrates that our model achieves SOTA or highly competitive performance against leading OLMs, surpassing Qwen2.5-Omni (trained with 1.2T tokens) on over 50 of 76 benchmarks. Key strengths include video understanding (+7% avg. of 8), omnimodallity understanding (+7% avg. of 4), and audiovisual reasoning (+4%). It also advances long-form speech processing (reducing WER by 4.2%) and leads in low-level image processing and controllable generation across 5 metrics.

Yunxin Li, Xinyu Chen, Baotian Hu et al.

Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video understanding and reasoning. To address this, we present VideoVista, a video QA benchmark that integrates challenges across diverse content categories, durations, and abilities. Specifically, VideoVista comprises 25,000 questions derived from 3,400 videos spanning 14 categories (e.g., Howto, Film, and Entertainment) with durations ranging from a few seconds to over 10 minutes. Besides, it encompasses 19 types of understanding tasks (e.g., anomaly detection, interaction understanding) and 8 reasoning tasks (e.g., logical reasoning, causal reasoning). To achieve this, we present an automatic data construction framework, leveraging powerful GPT-4o alongside advanced analysis tools (e.g., video splitting, object segmenting, and tracking). We also utilize this framework to construct training data to enhance the capabilities of video-related LMMs (Video-LMMs). Through a comprehensive and quantitative evaluation of cutting-edge models, we reveal that: 1) Video-LMMs face difficulties in fine-grained video tasks involving temporal location, object tracking, and anomaly detection; 2) Video-LMMs present inferior logical and relation reasoning abilities; 3) Open-source Video-LMMs' performance is significantly lower than GPT-4o and Gemini-1.5, lagging by 20 points. This highlights the crucial role VideoVista will play in advancing LMMs that can accurately understand videos and perform precise reasoning.

Zhenyu Liu, Yunxin Li, Baotian Hu et al.

To improve Multimodal Large Language Models' (MLLMs) ability to process images and complex instructions, researchers predominantly curate large-scale visual instruction tuning datasets, which are either sourced from existing vision tasks or synthetically generated using LLMs and image descriptions. However, they often suffer from critical flaws, including misaligned instruction-image pairs and low-quality images. Such issues hinder training efficiency and limit performance improvements, as models waste resources on noisy or irrelevant data with minimal benefit to overall capability. To address this issue, we propose a \textbf{Vi}sual-Centric \textbf{S}election approach via \textbf{A}gents Collaboration (ViSA), which centers on image quality assessment and image-instruction relevance evaluation. Specifically, our approach consists of 1) an image information quantification method via visual agents collaboration to select images with rich visual information, and 2) a visual-centric instruction quality assessment method to select high-quality instruction data related to high-quality images. Finally, we reorganize 80K instruction data from large open-source datasets. Extensive experiments demonstrate that ViSA outperforms or is comparable to current state-of-the-art models on seven benchmarks, using only 2.5\% of the original data, highlighting the efficiency of our data selection approach. Moreover, we conduct ablation studies to validate the effectiveness of each component of our method. The code is available at https://github.com/HITsz-TMG/ViSA.

Yunxin Li, Baotian Hu, Xinyu Chen et al.

Conditional inference on joint textual and visual clues is a multi-modal reasoning task that textual clues provide prior permutation or external knowledge, which are complementary with visual content and pivotal to deducing the correct option. Previous methods utilizing pretrained vision-language models (VLMs) have achieved impressive performances, yet they show a lack of multimodal context reasoning capability, especially for text-modal information. To address this issue, we propose a Multi-modal Context Reasoning approach, named ModCR. Compared to VLMs performing reasoning via cross modal semantic alignment, it regards the given textual abstract semantic and objective image information as the pre-context information and embeds them into the language model to perform context reasoning. Different from recent vision-aided language models used in natural language processing, ModCR incorporates the multi-view semantic alignment information between language and vision by introducing the learnable alignment prefix between image and text in the pretrained language model. This makes the language model well-suitable for such multi-modal reasoning scenario on joint textual and visual clues. We conduct extensive experiments on two corresponding data sets and experimental results show significantly improved performance (exact gain by 4.8% on PMR test set) compared to previous strong baselines. Code Link: \url{https://github.com/YunxinLi/Multimodal-Context-Reasoning}.

Yunxin Li, Baotian Hu, Yuxin Ding et al.

Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text. However, their performance drops drastically when confronted with linguistically complex texts that they struggle to comprehend. Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR. It contains three main components: 1) Divide: a proposition generator divides the compound proposition text into simple proposition sentences and produces their corresponding representations, 2) Conquer: a pretrained VLMs-based visual-linguistic interactor achieves the interaction between decomposed proposition sentences and images, 3) Combine: a neural-symbolic reasoner combines the above reasoning states to obtain the final solution via a neural logic reasoning approach. According to the dual-process theory, the visual-linguistic interactor and neural-symbolic reasoner could be regarded as analogical reasoning System 1 and logical reasoning System 2. We conduct extensive experiments on a challenging image retrieval from contextual descriptions data set. Experimental results and analyses indicate NDCR significantly improves performance in the complex image-text reasoning problem. Code link: https://github.com/YunxinLi/NDCR.

Jie Zhang, Xubing Yang, Rui Jiang et al.

The development of high-resolution remote sensing satellites has provided great convenience for research work related to remote sensing. Segmentation and extraction of specific targets are essential tasks when facing the vast and complex remote sensing images. Recently, the introduction of Segment Anything Model (SAM) provides a universal pre-training model for image segmentation tasks. While the direct application of SAM to remote sensing image segmentation tasks does not yield satisfactory results, we propose RSAM-Seg, which stands for Remote Sensing SAM with Semantic Segmentation, as a tailored modification of SAM for the remote sensing field and eliminates the need for manual intervention to provide prompts. Adapter-Scale, a set of supplementary scaling modules, are proposed in the multi-head attention blocks of the encoder part of SAM. Furthermore, Adapter-Feature are inserted between the Vision Transformer (ViT) blocks. These modules aim to incorporate high-frequency image information and image embedding features to generate image-informed prompts. Experiments are conducted on four distinct remote sensing scenarios, encompassing cloud detection, field monitoring, building detection and road mapping tasks . The experimental results not only showcase the improvement over the original SAM and U-Net across cloud, buildings, fields and roads scenarios, but also highlight the capacity of RSAM-Seg to discern absent areas within the ground truth of certain datasets, affirming its potential as an auxiliary annotation method. In addition, the performance in few-shot scenarios is commendable, underscores its potential in dealing with limited datasets.

Yunxin Li, Xinyu Chen, Baotain Hu et al.

Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence. Employing large language models (LLMs) for comprehending video becomes an emerging and promising method. However, this approach incurs high computational costs due to the extensive array of video tokens, experiences reduced visual clarity as a consequence of token aggregation, and confronts challenges arising from irrelevant visual tokens while answering video-related questions. To alleviate these issues, we present an Interactive Visual Adapter (IVA) within LLMs, designed to enhance interaction with fine-grained visual elements. Specifically, we first transform long videos into temporal video tokens via leveraging a visual encoder alongside a pretrained causal transformer, then feed them into LLMs with the video instructions. Subsequently, we integrated IVA, which contains a lightweight temporal frame selector and a spatial feature interactor, within the internal blocks of LLMs to capture instruction-aware and fine-grained visual signals. Consequently, the proposed video-LLM facilitates a comprehensive understanding of long video content through appropriate long video modeling and precise visual interactions. We conducted extensive experiments on nine video understanding benchmarks and experimental results show that our interactive visual adapter significantly improves the performance of video LLMs on long video QA tasks. Ablation studies further verify the effectiveness of IVA in understanding long and short video.

Zhenyu Liu, Yunxin Li, Xuanyu Zhang et al.

Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolation, hindering progress towards universal audio synthesis. This separation stems from inherent task conflicts and severe data imbalances, which impede the development of a truly unified audio generation model. To address this challenge, we propose UniMoE-Audio, a unified speech and music generation model within a novel Dynamic-Capacity Mixture-of-Experts (MoE) framework. Architecturally, UniMoE-Audio introduces a Top-P routing strategy for dynamic expert number allocation, and a hybrid expert design comprising routed experts for domain-specific knowledge, shared experts for domain-agnostic features, and null experts for adaptive computation skipping. To tackle data imbalance, we introduce a three-stage training curriculum: 1) Independent Specialist Training leverages original datasets to instill domain-specific knowledge into each "proto-expert" without interference; 2) MoE Integration and Warmup incorporates these specialists into the UniMoE-Audio architecture, warming up the gate module and shared expert using a subset of balanced dataset; and 3) Synergistic Joint Training trains the entire model end-to-end on the fully balanced dataset, fostering enhanced cross-domain synergy. Extensive experiments show that UniMoE-Audio not only achieves state-of-the-art performance on major speech and music generation benchmarks, but also demonstrates superior synergistic learning, mitigating the performance degradation typically seen in naive joint training. Our findings highlight the substantial potential of specialized MoE architecture and curated training strategies in advancing the field of universal audio generation. Homepage: https://mukioxun.github.io/Uni-MoE-site/home.html

Haoyuan Shi, Yunxin Li, Xinyu Chen et al.

Despite rapid advancements in video generation models, generating coherent storytelling videos that span multiple scenes and characters remains challenging. Current methods often rigidly convert pre-generated keyframes into fixed-length clips, resulting in disjointed narratives and pacing issues. Furthermore, the inherent instability of video generation models means that even a single low-quality clip can significantly degrade the entire output animation's logical coherence and visual continuity. To overcome these obstacles, we introduce AniMaker, a multi-agent framework enabling efficient multi-candidate clip generation and storytelling-aware clip selection, thus creating globally consistent and story-coherent animation solely from text input. The framework is structured around specialized agents, including the Director Agent for storyboard generation, the Photography Agent for video clip generation, the Reviewer Agent for evaluation, and the Post-Production Agent for editing and voiceover. Central to AniMaker's approach are two key technical components: MCTS-Gen in Photography Agent, an efficient Monte Carlo Tree Search (MCTS)-inspired strategy that intelligently navigates the candidate space to generate high-potential clips while optimizing resource usage; and AniEval in Reviewer Agent, the first framework specifically designed for multi-shot animation evaluation, which assesses critical aspects such as story-level consistency, action completion, and animation-specific features by considering each clip in the context of its preceding and succeeding clips. Experiments demonstrate that AniMaker achieves superior quality as measured by popular metrics including VBench and our proposed AniEval framework, while significantly improving the efficiency of multi-candidate generation, pushing AI-generated storytelling animation closer to production standards.

Yunxin Li, Baotian Hu, Xinyu Chen et al.

Training a Multimodal Large Language Model (MLLM) from scratch, like GPT-4, is resource-intensive. Regarding Large Language Models (LLMs) as the core processor for multimodal information, our paper introduces LMEye, a human-like eye with a play-and-plug interactive perception network, designed to enable dynamic interaction between LLMs and external vision information. Previous methods incorporate visual information into LLMs with a simple visual mapping network or Q-former from BLIP-2. Such networks project the image feature once yet do not consider the interaction between the image and the human input query. Hence, the obtained visual information without being connected to human intention may be inadequate for LLMs to generate intention-following responses, which we refer to as static visual information. LMEye addresses this issue by allowing the LLM to request the desired visual information aligned with various human instructions, which we term as the dynamic visual information interaction. Specifically, LMEye consists of a simple visual mapping network to provide the basic perception of an image for LLMs. It also contains additional modules responsible for acquiring requests from LLMs, performing request-based visual information interaction, and transmitting the resulting interacted visual information to LLMs, respectively. In this way, LLMs act to understand the human query, deliver the corresponding request to the request-based visual information interaction module, and generate the response based on the interleaved multimodal information. We evaluate LMEye through extensive experiments on some multimodal benchmarks, demonstrating that it significantly improves the zero-shot performance on various multimodal tasks compared to previous methods, with less parameters.

Yunxin Li, Qian Yang, Qingcai Chen et al.

Single online handwritten Chinese character recognition~(single OLHCCR) has achieved prominent performance. However, in real application scenarios, users always write multiple Chinese characters to form one complete sentence and the contextual information within these characters holds the significant potential to improve the accuracy, robustness and efficiency of sentence-level OLHCCR. In this work, we first propose a simple and straightforward end-to-end network, namely vanilla compositional network~(VCN) to tackle the sentence-level OLHCCR. It couples convolutional neural network with sequence modeling architecture to exploit the handwritten character's previous contextual information. Although VCN performs much better than the state-of-the-art single OLHCCR model, it exposes high fragility when confronting with not well written characters such as sloppy writing, missing or broken strokes. To improve the robustness of sentence-level OLHCCR, we further propose a novel deep spatial-temporal fusion network~(DSTFN). It utilizes a pre-trained autoregresssive framework as the backbone component, which projects each Chinese character into word embeddings, and integrates the spatial glyph features of handwritten characters and their contextual information multiple times at multi-layer fusion module. We also construct a large-scale sentence-level handwriting dataset, named as CSOHD to evaluate models. Extensive experiment results demonstrate that DSTFN achieves the state-of-the-art performance, which presents strong robustness compared with VCN and exiting single OLHCCR models. The in-depth empirical analysis and case studies indicate that DSTFN can significantly improve the efficiency of handwriting input, with the handwritten Chinese character with incomplete strokes being recognized precisely.

Yunxin Li, Yu Zhao, Baotian Hu et al.

Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters. The typical method to utilize the glyph features is by incorporating them into the character embedding space. Inspired by previous methods, we innovatively propose a Chinese pre-trained representation model named as GlyphCRM, which abandons the ID-based character embedding method yet solely based on sequential character images. We render each character into a binary grayscale image and design two-channel position feature maps for it. Formally, we first design a two-layer residual convolutional neural network, namely HanGlyph to generate the initial glyph representation of Chinese characters, and subsequently adopt multiple bidirectional encoder Transformer blocks as the superstructure to capture the context-sensitive information. Meanwhile, we feed the glyph features extracted from each layer of the HanGlyph module into the underlying Transformer blocks by skip-connection method to fully exploit the glyph features of Chinese characters. As the HanGlyph module can obtain a sufficient glyph representation of any Chinese character, the long-standing out-of-vocabulary problem could be effectively solved. Extensive experimental results indicate that GlyphCRM substantially outperforms the previous BERT-based state-of-the-art model on 9 fine-tuning tasks, and it has strong transferability and generalization on specialized fields and low-resource tasks. We hope this work could spark further research beyond the realms of well-established representation of Chinese texts.