Wenjing Ma

Jiaying Lu, Jiaming Shen, Bo Xiong et al. · deepmind

Medical decision-making processes can be enhanced by comprehensive biomedical knowledge bases, which require fusing knowledge graphs constructed from different sources via a uniform index system. The index system often organizes biomedical terms in a hierarchy to provide the aligned entities with fine-grained granularity. To address the challenge of scarce supervision in the biomedical knowledge fusion (BKF) task, researchers have proposed various unsupervised methods. However, these methods heavily rely on ad-hoc lexical and structural matching algorithms, which fail to capture the rich semantics conveyed by biomedical entities and terms. Recently, neural embedding models have proved effective in semantic-rich tasks, but they rely on sufficient labeled data to be adequately trained. To bridge the gap between the scarce-labeled BKF and neural embedding models, we propose HiPrompt, a supervision-efficient knowledge fusion framework that elicits the few-shot reasoning ability of large language models through hierarchy-oriented prompts. Empirical results on the collected KG-Hi-BKF benchmark datasets demonstrate the effectiveness of HiPrompt.

Weiyu Ma, Yuqian Fu, Zecheng Zhang et al.

We introduce Attentive VLM Agent (AVA), a multimodal StarCraft II agent that aligns artificial agent perception with the human gameplay experience. Traditional frameworks such as SMAC rely on abstract state representations that diverge significantly from human perception, limiting the ecological validity of agent behavior. Our agent addresses this limitation by incorporating RGB visual inputs and natural language observations that more closely simulate human cognitive processes during gameplay. The AVA architecture consists of three integrated components: (1) a vision-language model enhanced with specialized self-attention mechanisms for strategic unit targeting and battlefield assessment, (2) a retrieval-augmented generation system that leverages domain-specific StarCraft II knowledge to inform tactical decisions, and (3) a dynamic role-based task distribution system that enables coordinated multi-agent behavior. The experimental evaluation in our proposed AVACraft environment, which contains 21 multimodal StarCraft II scenarios, demonstrates that AVA powered by foundation models (specifically Qwen-VL and GPT-4o) can execute complex tactical maneuvers without explicit training, achieving comparable performance to traditional MARL methods that require substantial training iterations. This work establishes a foundation for developing human-aligned StarCraft II agents and advances the broader research agenda of multimodal game AI. Our implementation is available at https://github.com/camel-ai/VLM-Play-StarCraft2.

Weiyu Ma, Jiwen Jiang, Haobo Fu et al.

We present an adapter-based approach for tactical conditioning of StarCraft II AI agents. Current agents, while powerful, lack the ability to adapt their strategies based on high-level tactical directives. Our method freezes a pre-trained policy network (DI-Star) and attaches lightweight adapter modules to each action head, conditioned on a tactical tensor that encodes strategic preferences. By training these adapters with KL divergence constraints, we ensure the policy maintains core competencies while exhibiting tactical variations. Experimental results show our approach successfully modulates agent behavior across tactical dimensions including aggression, expansion patterns, and technology preferences, while maintaining competitive performance. Our method enables flexible tactical control with minimal computational overhead, offering practical strategy customization for complex real-time strategy games.

Zhexiong Liu, Jing Zhang, Jiaying Lu et al.

Logic reasoning has been critically needed in problem-solving and decision-making. Although Language Models (LMs) have demonstrated capabilities of handling multiple reasoning tasks (e.g., commonsense reasoning), their ability to reason complex mathematical problems, specifically propositional logic, remains largely underexplored. This lack of exploration can be attributed to the limited availability of annotated corpora. Here, we present a well-labeled propositional logic corpus, LogicPrpBank, containing 7093 Propositional Logic Statements (PLSs) across six mathematical subjects, to study a brand-new task of reasoning logical implication and equivalence. We benchmark LogicPrpBank with widely-used LMs to show that our corpus offers a useful resource for this challenging task and there is ample room for model improvement.

Wenjing Ma, Youqing Wu, Zhaoxia Yin

With the popularization of digital information technology, the reversible data hiding in encrypted images (RDHEI) has gradually become the research hotspot of privacy protection in cloud storage. As a technology which can embed additional information in encrypted domain, extract the embedded information correctly and recover the original image without loss, RDHEI has been widely paid attention by researchers. To embed sufficient additional information in the encrypted image, a high-capacity RDHEI method using adaptive encoding is proposed in this paper. Firstly, the occurrence frequency of different prediction errors of the original image is calculated and the corresponding adaptive Huffman coding is generated. Then, the original image is encrypted with stream cipher and the encrypted pixels are marked with different Huffman codewords according to the prediction errors. Finally, additional information is embedded in the reserved room of marked pixels by bit substitution. The experimental results show that the proposed algorithm can extract the embedded information correctly and recover the original image losslessly. Compared with similar algorithms, the proposed algorithm makes full use of the characteristics of the image itself and greatly improves the embedding rate of the image. On UCID, BOSSBase, and BOWS-2 datasets, the average embedding rate of the proposed algorithm reaches 3.162 bpp, 3.917 bpp, and 3.775 bpp, which is higher than the state-of-the-art algorithm of 0.263 bpp, 0.292 bpp, and 0.280 bpp, respectively.

Youqing Wu, Wenjing Ma, Yinyin Peng et al.

As a technology that can prevent the information from being disclosed, the reversible data hiding in encrypted images (RDHEI) acts as an important role in privacy protection and information security. To make use of the image redundancy and further improve the embedding performance, a high-capacity RDHEI method based on bit-plane compression of prediction error is proposed in this paper. Firstly, the whole prediction error is calculated and divided into blocks of the same size. Then, the content owner rearranges the bit-plane of prediction error by block and compresses the bitstream with the joint encoding algorithm to reserve room. Finally, the image is encrypted and the information can be embedded into the reserved room. On the receiver side, the information extraction and the image recovery are performed separably. Experimental results show that the proposed method brings higher embedding capacity than state-of-the-art RDHEI works.