Task scheduling has become increasingly critical for embodied AI, where agents need to follow natural language instructions and execute actions efficiently in 3D physical worlds. Existing datasets for task planning in 3D environments often simplify the problem, lacking operations research knowledge for task scheduling and 3D grounding for real-world applications. In this work, we propose Operations Research Knowledge-based 3D Grounded Task Scheduling (OKS3D), a new task that requires synerization of language understanding, 3D grounding, and efficiency optimization for embodied agents. OKS3D reflects real-world demands by requiring agents to generate efficient, step-by-step schedules that are grounded in 3D space. To facilitate research on OKS3D, we construct a large-scale dataset called OKS3D-60K, comprising 60K tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on the OKS3D-60K dataset validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency.

For industrial-scale text-to-SQL, supplying the entire database schema to Large Language Models (LLMs) is impractical due to context window limits and irrelevant noise. Schema linking, which filters the schema to a relevant subset, is therefore critical. However, existing methods incur prohibitive costs, struggle to trade off recall and noise, and scale poorly to large databases. We present AutoLink, an autonomous agent framework that reformulates schema linking as an iterative, agent-driven process. Guided by an LLM, AutoLink dynamically explores and expands the linked schema subset, progressively identifying necessary schema components without inputting the full database schema. Our experiments demonstrate AutoLink's superior performance, achieving state-of-the-art strict schema linking recall of 97.4% on Bird-Dev and 91.2% on Spider 2.0-Lite, with competitive execution accuracy, i.e., 68.7% EX on Bird-Dev (better than CHESS) and 34.9% EX on Spider 2.0-Lite (ranking 2nd on the official leaderboard). Crucially, AutoLink exhibits exceptional scalability, maintaining high recall, efficient token consumption, and robust execution accuracy on large schemas (e.g., over 3,000 columns) where existing methods severely degrade—making it a highly scalable, high-recall schema-linking solution for industrial text-to-SQL systems.

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Recently, the task of in-vehicle multi-zone speech separation (IMSS) has attracted significant interest. However, a persistent issue in this area is the cross-zone leakage problem. To address this, we present ZoneSep, a lightweight, fully end-to-end neural beamformer equipped with a post-mask decoder to suppress leakage effectively. Additionally, we propose a novel loss function, SC-SI-SDR loss, which enables simultaneous optimization of both non-silent and silent zones. Experiments on the IMSS dataset demonstrate the effectiveness of our approaches, showing that ZoneSep significantly outperforms recent advanced methods while requiring only 0.65M parameters and 4.02 GMACs. The source code is available athttps://github.com/EeLLJ/ZoneSep/.

Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal complexity. Existing Video-LLMs using uniform frame sampling often struggle to capture the query-related crucial spatiotemporal clues of videos effectively. In this paper, we introduce Q-Frame, a novel approach for adaptive frame selection and multi-resolution scaling tailored to the video's content and the specific query. Q-Frame employs a training-free, plug-and-play strategy generated by a text-image matching network like CLIP, utilizing the Gumbel-Max trick for efficient frame selection. Q-Frame allows Video-LLMs to process more frames without exceeding computational limits, thereby preserving critical temporal and spatial information. We demonstrate Q-Frame's effectiveness through extensive experiments on benchmark datasets, including MLVU, LongVideoBench, and Video-MME, illustrating its superiority over existing methods and its applicability across various video understanding tasks.

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent Reasoning (CoLaR), a novel framework that dynamically compresses reasoning processes in latent space through a two-stage training approach. First, during supervised fine-tuning, CoLaR extends beyond next-token prediction by incorporating an auxiliary next compressed embedding prediction objective. This process merges embeddings of consecutive tokens using a compression factor $c$ randomly sampled from a predefined range, and trains a specialized latent head to predict distributions of subsequent compressed embeddings. Second, we enhance CoLaR through reinforcement learning (RL) that leverages the latent head's non-deterministic nature to explore diverse reasoning paths and exploit more compact ones. This approach enables CoLaR to: i) **perform reasoning at a dense latent level** (i.e., silently), substantially reducing reasoning chain length, and ii) **dynamically adjust reasoning speed** at inference time by simply prompting the desired compression factor. Extensive experiments across four mathematical reasoning datasets demonstrate that CoLaR achieves 14.1% higher accuracy than latent-based baseline methods at comparable compression ratios, and reduces reasoning chain length by 53.3% with only 4.8% performance degradation compared to explicit CoT method. Moreover, when applied to more challenging mathematical reasoning tasks, our RL-enhanced CoLaR demonstrates performance gains of up to 5.4% while dramatically reducing latent reasoning chain length by 82.8%. The code and models will be released upon acceptance.

Temporal Video Grounding (TVG), the task of locating specific video segments based on language queries, is a core challenge in long-form video understanding. While recent Large Vision-Language Models (LVLMs) have shown early promise in tackling TVG through supervised fine-tuning (SFT), their ability to generalize remains limited. To address this, we propose a novel post-training framework that enhances the generalization capabilities of LVLMs via reinforcement learning (RL). Specifically, our contributions span three key directions: (1) Time-R1: we introduce a reasoning-guided post-training framework via RL with verifiable reward to enhance capabilities of LVLMs on the TVG task. (2) TimeRFT: we explore post-training strategies on our curated RL-friendly dataset, which trains the model to progressively comprehend more difficult samples, leading to better generalization. (3) TVGBench: we carefully construct a small but comprehensive and balanced benchmark suitable for LVLM evaluation, which is sourced from available public benchmarks. Extensive experiments demonstrate that Time-R1 achieves state-of-the-art performance across multiple downstream datasets using significantly less training data than prior LVLM approaches, while improving its general video understanding capabilities. Project Page: https://xuboshen.github.io/Time-R1/.

In the field of AI-driven human-GUI interaction automation, while rapid advances in multimodal large language models and reinforcement fine-tuning techniques have yielded remarkable progress, a fundamental challenge persists: their interaction logic significantly deviates from natural human-GUI communication patterns. To address this gap, we propose Blink–Think–Link (BTL), a brain-inspired framework for human-GUI interaction that mimics the human cognitive process between users and graphical interfaces. The system decomposes interactions into three biologically plausible phases: (1) \textbf{Blink} - rapid detection and attention to relevant screen areas, analogous to saccadic eye movements; (2) \textbf{Think} - higher-level reasoning and decision-making, mirroring cognitive planning; and (3) \textbf{Link} - generation of executable commands for precise motor control, emulating human action selection mechanisms. Additionally, we introduce two key technical innovations for BTL framework: (1) Blink Data Generation - an automated annotation pipeline specifically optimized for blink data, and (2) {BTL Reward – the first rule-based reward mechanism that enables reinforcement learning driven by both process and outcome.} Building upon this framework, we develop a GUI agent model named BTL-UI, which demonstrates competitive performance across both static GUI understanding and dynamic interaction tasks in comprehensive benchmarks. These results provide conclusive empirical validation of the framework's efficacy in developing advanced GUI agents.

Semantic segmentation is one of the key tasks in computer vision, which is to assign a category label to each pixel in an image. Despite significant progress achieved recently, most existing methods still suffer from two challenging issues: l)the size of objects and stuff in an image can be very diverse, demanding for incorporating multi-scale features into the fully convolutional networks (FCNs); 2) the pixels close to or at the boundaries of object/stuff are hard to classify due to the intrinsic weakness of convolutional networks. To address the first issue, we propose a new Multi-Receptive Field Module (MRFM), explicitly taking multi-scale features into account. For the second issue, we design an edge-aware loss which is effective in distinguishing the boundaries of object/stuff. With these two designs, our Multi Receptive Field Network achieves new state-of-the-art results on two widely-used semantic segmentation benchmark datasets. Specifically, we achieve a mean IoU of 83.0% on the Cityscapes dataset and 88.4% mean IoU on the Pascal VOC2012 dataset.

In this paper, we investigate the issue of knowledge distillation for training compact semantic segmentation networks by making use of cumbersome networks. We start from the straightforward scheme, pixel-wise distillation, which applies the distillation scheme originally introduced for image classification and performs knowledge distillation for each pixel separately. We further propose to distill the structured knowledge from cumbersome networks into compact networks, which is motivated by the fact that semantic segmentation is a structured prediction problem. We study two such structured distillation schemes: (i) pair-wise distillation that distills the pairwise similarities, and (ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by extensive experiments on three scene parsing datasets: Cityscapes, Camvid and ADE20K.

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRA-TD500, show that the proposed method achieves state-of-the-art in scene text detection.

In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation.

Scene text detection is challenging as the input may have different orientations, sizes, font styles, lighting conditions, perspective distortions and languages. This paper addresses the problem by designing a Rotational Region CNN (R2CNN). R2CNN includes a Text Region Proposal Network (Text-RPN) to estimate approximate text regions and a multitask refinement network to get the precise inclined box. Our work has the following features. First, we use a novel multi-task regression method to support arbitrarily-oriented scene text detection. Second, we introduce multiple ROIPoolings to address the scene text detection problem for the first time. Third, we use an inclined Non-Maximum Suppression (NMS) to post-process the detection candidates. Experiments show that our method outperforms the state-of-the-art on standard benchmarks: ICDAR 2013, ICDAR 2015, COCO-Text and MSRA-TD500.

Text detection and recognition in a natural environment are key components of many applications, ranging from business card digitization to shop indexation in a street. This competition aims at assessing the ability of state-of-the-art methods to detect Multi-Lingual Text (MLT) in scene images, such as in contents gathered from the Internet media and in modern cities where multiple cultures live and communicate together. This competition is an extension of the Robust Reading Competition (RRC) which has been held since 2003 both in ICDAR and in an online context. The proposed competition is presented as a new challenge of the RRC. The dataset built for this challenge largely extends the previous RRC editions in many aspects: the multi-lingual text, the size of the dataset, the multi-oriented text, the wide variety of scenes. The dataset is comprised of 18,000 images which contain text belonging to 9 languages. The challenge is comprised of three tasks related to text detection and script classification. We have received a total of 16 participations from the research and industrial communities. This paper presents the dataset, the tasks and the findings of this RRC-MLT challenge.

Text detection and recognition in scene images and videos attract much attention in computer vision recently. However, most existing text detection and recognition methods only focus on static images. In this paper an end-to-end scene text recognition method based on multi frame tracking is proposed for text in videos, in which temporal information is employed to improve performance. First, an end-to-end text recognition method based on a unified deep neural network is used to detect and recognize text in each frame of the input video. Then, multi frame text tracking is employed through associations of texts in current frame and several previous frames to obtain final results. Experiments on ICDAR datasets demonstrate that the proposed method outperforms the state-of-the-art methods in end-to-end video text recognition.

Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks. In order to obtain stronger semantic feature, we adopt ResNet as feature extraction layers and exploit multi-level feature by combining hierarchical convolutional networks. A vertical proposal mechanism is utilized to avoid proposal classification, while regression layer remains working to improve localization accuracy. Our approach evaluated on ICDAR2013 dataset achieves 0.91 F-measure, which outperforms previous state-of-the-art results in scene text detection.

Text recognition in natural scene image is an important yet challenging problem by its irregular nature. A novel method based on random projection and deep neural network(DNN) is proposed in this article. Firstly the word image is converted to multi-layers' convolutional neural network(CNN) feature sequence with sliding window. Then random projection(RP) is used to embed the original high-dimensional feature into a low-dimensional space. Finally, recurrent neural network(RNN) model is trained to recognize the text in word image based on the RP-CNN feature. The benefits of using RP is two-fold. It can preserve the geometrical relationship in dimension reduction, while reduce the computation and storage burden of the following RNN training effectively without much information loss. Moreover, RP brings information diversity with randomness which can improve the generation ability of original feature. Experiments show that recognition performance of RP-CNN feature, with 85% dimension reduction, is similar to the original high-dimensional ones. By ensemble of several RNN models based on various RP-CNN features, we obtain higher performance than single RNN based on original CNN feature. The proposed method shows competitive performance on public datasets such as SVT, ICDAR03, ICDAR13.

Writer adaptation is an important topic in handwriting recognition, which can further improve the performance of writer-independent recognizer. In this paper, we propose combining the neural network classifier with style transfer mapping (STM) for unsupervised writer adaptation, which only require writer-specific unlabeled data, and therefore is more common and efficient compared to supervised adaptation. We use some techniques like dropout, ReLU, momentum, and deeply supervised strategy to improve the performance of the neural network classifier. For a specific writer in the test data, an adaptation layer is added to the pre-trained neural network classifier. In adaptation process, only the parameters in adaptation layer are updated while other parameters of the neural network are kept unchanged. To train the adaptation layer, we use the same technology as STM learning but redefine the source point set, target point set and the corresponding confidence. Experiments on the online Chinese handwriting database CASIA-OLHWDB1.1 demonstrate that our method is very efficient and effective in improving classification accuracy. The experimental results also show that our proposed method outperforms the previous proposed learning vector quantization (LVQ) and modified quadratic discriminant function (MQDF) with STM methods for writer adaptation.