Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

While Large Language Models (LLMs) possess remarkable generative capabilities, generating diversified and engaging ad headlines in industrial applications remains challenging. Conventional training paradigms often suffer from mode collapse, converging on dominant data patterns and yielding homogeneous outputs. Meanwhile, existing diversity-enhancing techniques like stochastic decoding frequently compromise semantic coherence and controllability. To break this trade-off, we propose DIVER, an automated training framework that internalizes diversity as an intrinsic model capability. DIVER employs an automatic data pipeline to synthesize high-quality, multi-faceted training pairs and utilizes multi-objective reinforcement learning to effectively co-optimize diversity with advertising metrics such as faithfulness and click-through rate (CTR). Unlike personalized approaches, our framework generates diverse content for general users without relying on heavy and costly user-behavior modeling, ensuring efficient inference for large-scale real-time systems. Real-world deployment on Xiaohongshu's Explore Feed demonstrates significant commercial impact, increasing advertiser value (ADVV) by 4.0% and CTR by 1.4%.

A major challenge in Fine-Grained Visual Classification (FGVC) is distinguishing various categories with high inter-class similarity by learning the feature that differentiates the details. Conventional cross-entropy trained Convolutional Neural Network (CNN) fails this challenge as they may suffer from producing inter-class invariant features in FGVC. In this work, we innovatively propose to regularize the training of CNN by enforcing the uniqueness of the features of each category from an information-theoretic perspective. To achieve this goal, we formulate a minimax loss based on a game-theoretic framework, where a Nash equilibrium is proved to be consistent with this regularization objective. Besides, to avoid getting a solution that produces redundant features, we present a Feature Redundancy Loss (FRL) based on the normalized inner product between each selected feature map pair to complement the proposed minimax loss. The proposed method is versatile, as it can be utilized as a regularizer for features in the mid-level or the penultimate layer, and can be combined with any architectures. Extensive experimental results on several influential benchmarks along with visualization show that our method obtains significant improvement over the baseline model without extra cost and achieves state-of-the-art results.

This paper introduces a soft active surface gripper designed to manipulate fragile objects safely. This gripper consists of two fingers, each equipped with two compliant pneumatic actuators and a soft active surface. The gripper utilizes the elastic belt as its soft active surface, which is driven by a motor, and the opening angle of the elastic band is controlled by pneumatic actuators. The novel design allows for the passive deformation of both the soft active surface and the compliant pneumatic actuator, enabling adaptation to various object shapes and demonstrating superior handling capabilities for delicate items. By synchronizing the opening and closing of the pneumatic fingers with the conveying motion of the active surface, the active surface gripper realizes three degrees of freedom (DOF) for in-plane manipulation, specifically two translational movements and one rotational movement. A prototype gripper has been designed and fabricated for in-plane manipulation experiments with fragile objects, including strawberries, miniature cupcakes, and pears. Experimental results demonstrate that the gripper can execute in-plane in-hand manipulation of fragile objects with varying geometries and dimensions while maintaining secure and robust handling, preventing object slippage and preserving surface integrity without causing damage.

Transformers have shown remarkable progress on computer vision tasks in the past year. Compared to their CNN counterparts, transformers usually need the help of distillation to achieve comparable results on middle or small sized datasets. Meanwhile, recent researches discover that when transformers are trained with supervised and self-supervised manner respectively, the captured patterns are quite different both qualitatively and quantitatively. These findings motivate us to introduce an self-supervised teaching assistant (SSTA) besides the commonly used supervised teacher to improve the performance of transformers. Specifically, we propose a head-level knowledge distillation method that selects the most important head of the supervised teacher and self-supervised teaching assistant, and let the student mimic the attention distribution of these two heads, so as to make the student focus on the relationship between tokens deemed by the teacher and the teacher assistant. Extensive experiments verify the effectiveness of SSTA and demonstrate that the proposed SSTA is a good compensation to the supervised teacher. Meanwhile, some analytical experiments towards multiple perspectives (e.g. prediction, shape bias, robustness, and transferability to downstream tasks) with supervised teachers, self-supervised teaching assistants and students are inductive and may inspire future researches.

A new method was developed to increase the saliency of changing variables in a cardiovascular visualization for use by anesthesiologists in the operating room (OR). Clinically meaningful changes in patient physiology were identified and then mapped to the inherent psychophysical properties of the visualization. A long history of psychophysical research has provided an understanding of the parameters within which the human information processing system is able to detect changes in the size, shape and color of visual objects (Gescheider, 1976, Spence, 1990, and Baird, 1970). These detection thresholds are known as just noticeable differences (JNDs) which characterize the amount of change in an object's attribute that is recognizable 50% of the time. A prototype version of the display has been demonstrated to facilitate anesthesiologist's performance while reducing cognitive workload during simulated cardiac events (Agutter et al., 2002). In order to further improve the utility of the new cardiovascular visualization, the clinically relevant changes in cardiovascular variables are mapped to noticeable perceptual changes in the representational elements of the display. The results of the method described in this paper are used to merge information from the psychophysical properties of the cardiovascular visualization, with clinically relevant changes in the patient's cardiovascular physiology as measured by the clinical meaningfulness questionnaire. The result of this combination will create a visualization that is sensitive to changes in the cardiovascular health of the patient and communicates this information to the user in a meaningful, salient and intuitive manner.