Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhaopeng Feng, Yupu Liang, Shaosheng Cao, Jiayuan Su, Jiahan Ren, Zhijie Zhou, Wenxuan Huang, Jian Wu, Zuozhu Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Weakly supervised semantic segmentation (WSSS) has garnered considerable attention due to its effective reduction of annotation costs. Most approaches utilize Class Activation Maps (CAM) to produce pseudo-labels, thereby localizing target regions using only image-level annotations. However, the prevalent methods relying on vision transformers (ViT) encounter an "over-expansion" issue, i.e., CAM incorrectly expands high activation value from the target object to the background regions, as it is difficult to learn pixel-level local intrinsic inductive bias in ViT from weak supervisions. To solve this problem, we propose a Progressive Confidence Region Expansion (PCRE) framework for WSSS, it gradually learns a faithful mask over the target region and utilizes this mask to correct the confusion in CAM. PCRE has two key components: Confidence Region Mask Expansion (CRME) and Class-Prototype Enhancement (CPE). CRME progressively expands the mask in the small region with the highest confidence, eventually encompassing the entire target, thereby avoiding unintended coverage of background areas. CPE aims to enhance mask generation in CRME by leveraging the similarity between the learned, dataset-level class prototypes and patch features as supervision to optimize the mask output from CRME. Extensive experiments demonstrate that our method outperforms the existing single-stage and multi-stage approaches on the PASCAL VOC and MS COCO benchmark. Our code is available at https://github.com/xxf011/WSSS-PCRE.

Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava.

Soccer is a globally popular sporting event, typically characterized by long matches and distinctive highlight moments. Recent advances in Multimodal Large Language Models (MLLMs) show promising capabilities in temporal grounding and video understanding. However, generating soccer commentary requires both precise temporal localization and semantically rich descriptions over long-form videos. Existing soccer MLLMs often rely on temporal priors for caption generation, which limits their ability to process the entire video in an end-to-end manner. Traditional approaches, on the other hand, follow a complex two-step paradigm that fails to capture the global context, leading to suboptimal performance. To solve the above issues, we present TimeSoccer, the first end-to-end soccer MLLM for Single-anchor Dense Video Captioning (SDVC) in full-match soccer videos. TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling across 45-minute matches. To support long video understanding of soccer matches, we introduce MoFA-Select, a training-free, motion-aware frame compression module that adaptively selects representative frames via a coarse-to-fine strategy, and incorporates complementary training paradigms to strengthen the model's ability to handle long temporal sequences. Extensive experiments demonstrate that our TimeSoccer achieves State-of-The-Art (SoTA) performance on the SDVC task in an end-to-end form, generating high-quality commentary with accurate temporal alignment and strong semantic relevance. For more information, please visit: https://vpx-ecnu.github.io/TimeSoccer-Website/.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.

Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level scientific benchmarks, scientific Multimodal Large Language Models (MLLMs) hold the potential to significantly enhance this discovery process in realistic workflows. However, current scientific benchmarks mostly focus on evaluating the knowledge understanding capabilities of MLLMs, leading to an inadequate assessment of their perception and reasoning abilities. To address this gap, we present the Scientists’ First Exam (SFE) benchmark, designed to evaluate the scientific cognitive capacities of MLLMs through three interconnected levels: scientific signal perception, scientific attribute understanding, scientific comparative reasoning. Specifically, SFE comprises 830 expert-verified VQA pairs across three question types, spanning 66 multimodal tasks across five high-value disciplines. Extensive experiments reveal that current state-of-the-art GPT-o3 and InternVL-3 achieve only 34.08% and 26.52% on SFE, highlighting significant room for MLLMs to improve in scientific realms. We hope the insights obtained in SFE will facilitate further developments in AI-enhanced scientific discoveries.

An accurate and efficient first arrival picking method of microseismic signals is essential for improving the microseismic recording processing performance. However, weak seismic magnitude and low signal-to-noise ratio (SNR) of microseismic signals make highly accurate and efficient microseismic signal processing challenging when traditional signal picking methods are used. Therefore, to use microseismic signal features effectively and improve both the accuracy and the efficiency of the first arrival picking of microseismic signals, this paper proposes a first arrival picking method of microseismic signals based on deep learning. In addition, a generative adversarial network with latent space and adaptive layer-instance normalization for microseismic signals generation (G-LA-MSG) is used to generate a large number of effective microseismic signals under unsupervised conditions to expand the microseismic data having a limited number of samples. On the basis of the sample expansion, an AND-OR grammar pyramid scene parsing network (AOG-PSPNet) is designed to select the first arrivals of microseismic signals. By adopting the AND-OR grammar block (AOGBlock) structure, the network can fully extract the sequence data features, achieve good SNR separation in a low SNR environment, and improve the accuracy of first arrivals of low SNR microseismic signals. The results of the arrival picking experiments conducted under the condition of a low SNR for synthetic microseismic records and real microseismic records show that the proposed method can achieve a superior performance compared to the commonly used deep learning-based methods for first arrival picking of microseismic signals.

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyperparameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an “initialization-expansion-merging” pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyperparameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3× faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://github.com/Osilly/TokenExpansion.