Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Xinyu Chen, Yunxin Li, Haoyuan Shi, Baotian Hu, Wenhan Luo, Yaowei Wang, Min Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Despite rapid advancements in video generation models, generating coherent, long-form 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, collectively realizing multi-character, multi-scene animation. 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. Code and data for this paper are at https://animaker-dev.github.io/

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 knowledgedimension 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 Finegrained 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 imageknowledge 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.1

Seismic noise suppression refers to a data processing technique utilized to bolster the signal-to-noise ratio of recorded seismic signals. This enhancement in clarity can significantly amplify the efficacy of subsequent analysis and processing endeavors. With the advancement of deep learning, neural networks have significantly outperformed traditional denoising methods in seismic noise reduction tasks. They can process more data in less time and achieve better denoising results, moreover, they do not require limiting assumptions. In this article, we design an end-to-end seismic noise separation model based on the Wave-Unet, which is an adaptation of Unet for the 1-D time domain. Our designed model introduces the selective Kernel convolution into the Wave-Unet to enhance its performance and incorporates an attention-enhanced skip connection to bridge the semantic gap caused by the concatenation of features computed by networks of varying depths. Meanwhile, a joint loss function is used to enhance the model’s ability to learn signal frequency information. We tested our network using synthetic noisy signals and real seismic records from the STEAD dataset and compared the results with the wavelet threshold denoising method and the advanced omni-dimensional dynamic convolution (ODConv network) modules. The results demonstrate that our network performance surpasses the other two methods and can restore clean signals with high resolution without damaging the effective signal.

Current efficient approaches to building Multimodal Large Language Models (MLLMs) mainly incorporate visual information into LLMs with a simple visual mapping network such as a linear projection layer, a multilayer perceptron (MLP), or Q-former from BLIP-2. Such networks project the image feature once and do not consider the interaction between the image and the human inputs. 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. To alleviate this issue, 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 visual information. It can allow the LLM to request the desired visual information aligned with various human instructions, which we term dynamic visual information acquisition. 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 seeking, 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 multimodal benchmarks, demonstrating that it significantly improves zero-shot performances on various multimodal tasks compared to previous methods, with fewer parameters. Moreover, we also verify its effectiveness and scalability on various language models and video understanding, respectively.

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