Optimizing the advertiser's cumulative value of winning impressions under budget constraints poses a complex challenge in online advertising, under the paradigm of AI-Generated Bidding (AIGB). Advertisers often have personalized objectives but limited historical interaction data, resulting in few-shot scenarios where traditional reinforcement learning (RL) methods struggle to perform effectively. Large Language Models (LLMs) offer a promising alternative for AIGB by leveraging their in-context learning capabilities to generalize from limited data. However, they lack the numerical precision required for fine-grained optimization. To address this limitation, we introduce GRPO-Adaptive, an efficient LLM post-training strategy that enhances both reasoning and numerical precision by dynamically updating the reference policy during training. Built upon this foundation, we further propose DARA, a novel dual-phase framework that decomposes the decision-making process into two stages: a few-shot reasoner that generates initial plans via in-context prompting, and a fine-grained optimizer that refines these plans using feedback-driven reasoning. This separation allows DARA to combine LLMs' in-context learning strengths with precise adaptability required by AIGB tasks. Extensive experiments on both real-world and synthetic data environments demonstrate that our approach consistently outperforms existing baselines in terms of cumulative advertiser value under budget constraints.

Multi-modal Entity Linking (MEL) is a fundamental component for various downstream tasks. However, existing MEL datasets suffer from small scale, scarcity of topic types and limited coverage of tasks, making them incapable of effectively enhancing the entity linking capabilities of multi-modal models. To address these obstacles, we propose a dataset construction pipeline and publish M^3EL, a large-scale dataset for MEL. M^3EL includes 79,625 instances, covering 9 diverse multi-modal tasks, and 5 different topics. In addition, to further improve the model's adaptability to multi-modal tasks, We propose a modality-augmented training strategy. Utilizing M^3EL as a corpus, train the CLIP_ND model based on CLIP (ViT-B-32), and conduct a comparative analysis with an existing multi-modal baselines. Experimental results show that the existing models perform far below expectations (ACC of 49.4%-75.8%), After analysis, it was obtained that small dataset sizes, insufficient modality task coverage, and limited topic diversity resulted in poor generalization of multi-modal models. Our dataset effectively addresses these issues, and the CLIP_ND model fine-tuned with M^3EL shows a significant improvement in accuracy, with an average improvement of 9.3% to 25% across various tasks. Our dataset publicly available to facilitate future research.

Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllability in terms of geometry. Scene graphs provide a suitable data representation that facilitates these applications. However, current graph-based methods for scene generation are constrained to text-based inputs and exhibit insufficient adaptability to flexible user inputs, hindering the ability to precisely control object geometry. To address this issue, we propose MMGDreamer, a dual-branch diffusion model for scene generation that incorporates a novel Mixed-Modality Graph, visual enhancement module, and relation predictor. The mixed-modality graph allows object nodes to integrate textual and visual modalities, with optional relationships between nodes. It enhances adaptability to flexible user inputs and enables meticulous control over the geometry of objects in the generated scenes. The visual enhancement module enriches the visual fidelity of text-only nodes by constructing visual representations using text embeddings. Furthermore, our relation predictor leverages node representations to infer absent relationships between nodes, resulting in more coherent scene layouts. Extensive experimental results demonstrate that MMGDreamer exhibits superior control of object geometry, achieving state-of-the-art scene generation performance.

Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains.Recent research has increasingly focused on the role of token importance in improving DPO effectiveness.It is observed that identical or semantically similar content (defined as ambiguous content) frequently appears within the preference pairs.We hypothesize that the presence of ambiguous content during DPO training may introduce ambiguity, thereby limiting further improvements in alignment.Through mathematical analysis and proof-of-concept experiments, we reveal that ambiguous content may potentially introduce ambiguities, thereby degrading performance.To address this issue, we introduce Ambiguity Awareness Optimization (AAO), a simple yet effective approach that automatically reweights ambiguous content to reduce ambiguities by calculating semantic similarity from preference pairs.Through extensive experiments, we demonstrate that AAO consistently and significantly surpasses state-of-the-art approaches in performance, without markedly increasing response length, across multiple model scales and widely adopted benchmark datasets, including AlpacaEval 2, MT-Bench, and Arena-Hard.Specifically, AAO outperforms DPO by up to 8.9 points on AlpacaEval 2 and achieves an improvement of by up to 15.0 points on Arena-Hard.

Sharding blockchain networks face significant scalability challenges due to high frequencies of cross-shard transactions and uneven workload distributions among shards. To address these scalability issues, account migration offers a promising solution. However, existing migration solutions struggle with the high computational overhead and insufficient capture of complex transaction patterns. We propose AERO, a deep reinforcement learning framework to facilitate efficient account migration in sharding blockchains. AERO employs a prefix-based grouping strategy to enable group-level migration decisions and capture complex transaction patterns and relationships between accounts. We also implement a sharding blockchain system called AEROChain, which integrates AERO and aligns with the blockchain decentralization principle. Extensive evaluation with real Ethereum transaction data demonstrates that AERO improves the system throughput by 31.77% compared to existing solutions, effectively reducing cross-shard transactions and balancing shard workloads.

Adversarial distillation (AD) is a highly effective method for enhancing the robustness of small models. Contrary to expectations, a high-performing teacher model does not always result in a more robust student model. This is due to two main reasons. First, when there are significant differences in predictions between the teacher model and the student model, exact matching of predicted values using KL divergence interferes with training, leading to poor performance of existing methods. Second, matching solely based on the output prevents the student model from fully understanding the behavior of the teacher model. To address these challenges, this paper proposes a novel AD method named SmaraAD. During the training process, we facilitate the student model in better understanding the teacher model's behavior by aligning the attribution region that the student model focuses on with that of the teacher model. Concurrently, we relax the condition of exact matching in KL divergence and replace it with a more flexible matching criterion, thereby enhancing the model's robustness. Extensive experiments substantiate the effectiveness of our method in improving the robustness of small models, out-performing previous SOTA methods.

Existing adversarial example defense methods are static, meaning they remain unchanged once training is completed, regardless of how attack methods change. Consequently, static defense methods are highly vulnerable to adaptive attacks. We argue that to counter more formidable attacks, models should continually adapt to various attack methods. We propose a novel dynamic defense approach. Initially, we use Gaussian Mixture Models (GMM) to obtain structural information of the data, which is combined with model prediction information to generate pseudo-labels for optimizing inputs. Subsequently, we employ information maximization and enhanced mean predictions as optimization objectives, utilizing a hierarchical optimization approach to refine the model. Meanwhile, we propose a sample-efficient optimization strategy that reduces the total number of samples in the test data stream for reverse updating and improves the efficiency. Notably, our method can be directly applied to pre-trained models without the need for accessing training data or retraining the model. Therefore, our approach is training-data-agnostic and model-agnostic, easily applicable to existing adversarially trained models, significantly enhancing the resilience of various models against white-box, black-box, and adaptive attacks across diverse datasets. We have conducted extensive experiments to validate the state-of-the-art of our proposed method. The pseudo-code can be found in the appendix.

Blockchain sharding technology has been used to enhance the scalability of blockchain systems. As the number of shards increases, the high latency inherent in cross-shard transactions gradually becomes a bottleneck, hindering improvements in overall system efficiency. Therefore, reducing the latency of cross-shard transactions is significantly important. However, existing mechanisms for handling cross-shard transactions fail to minimize the latency of cross-shard transactions and have not fully used the bandwidth available within shards. In this paper, we introduce Presto, a protocol designed for the account-state-based blockchain, which reduces the latency of handling cross-shard transactions. Presto leverages the concept of optimistic pre-execution along with pending tree to optimize cross-shard transaction processing. Presto also employs predistribution of cross-shard transactions with Erasure Coding to efficiently utilize bandwidth resources. We have developed an prototype and conducted extensive experiments on a cloud platform. The evaluation results indicate that Presto surpasses existing solutions in terms of system throughput, transaction confirmation latency, and mempool queue size, demonstrating Presto's potential to significantly improve blockchain scalability and user experience.

The deep neural networks (DNNs) trained by adversarial training (AT) usually suffered from significant robust generalization gap, i.e., DNNs achieve high training robustness but low test robustness. In this paper, we propose a generic method to boost the robust generalization of AT methods from the novel perspective of attribution span. To this end, compared with standard DNNs, we discover that the generalization gap of adversarially trained DNNs is caused by the smaller attribution span on the input image. In other words, adversarially trained DNNs tend to focus on specific visual concepts on training images, causing its limitation on test robustness. In this way, to enhance the robustness, we propose an effective method to enlarge the learned attribution span. Besides, we use hybrid feature statistics for feature fusion to enrich the diversity of features. Extensive experiments show that our method can effectively improves robustness of adversarially trained DNNs, outperforming previous SOTA methods. Furthermore, we provide a theoretical analysis of our method to prove its effectiveness.

Public cloud GPU clusters are becoming emerging platforms for training distributed deep learning jobs. Under this training paradigm, the job scheduler is a crucial component to improve user experiences, i.e., reducing training fees and job completion time, which can also save power costs for service providers. However, the scheduling problem is known to be NP-hard. Most existing work divides it into two easier sub-tasks, i.e., ordering task and placement task, which are responsible for deciding the scheduling orders of jobs and placement orders of GPU machines, respectively. Due to the superior adaptation ability, learning-based policies can generally perform better than traditional heuristic-based methods. Nevertheless, there are still two main challenges that have not been well-solved. First, most learning-based methods only focus on ordering or placement policy independently, while ignoring their cooperation. Second, the unbalanced machine performances and resource contention impose huge overhead and uncertainty on job duration, but rarely be considered in existing work. To tackle these issues, this paper presents a dual-agent scheduler framework abstracted from the two sub-tasks to jointly learn the ordering and placement policies and make better-informed scheduling decisions. Specifically, we design an ordering agent with a scalable squeeze-and-communicate strategy for better cooperation; for the placement agent, we propose a novel Random Walk Gaussian Process to learn the performance similarities of GPU machines while being aware of the uncertain performance fluctuation. Finally, the dual-agent is jointly optimized with multi-agent reinforcement learning. Extensive experiments conducted on the real-world production cluster trace demonstrate the superiority of our model.

To solve the interference problems of wind and wave action and load movement when switching under water surface conditions in the marine environment, a study on the water surface stability prediction of the bio-inspired undulatory fin robot is carried out. Based on the fin motion equation and fluid drag theory, a water surface stability calculation model of the robot is established. The study compares the effects of different loads and heel angles on the stability of the robot's water surface under different calculation methods and verifies the validity of the model through computational fluid dynamics methods. The simulation results show that the water surface stability of the robot exhibits sinusoidal-like changes over time, which is equal to the undulatory fin period. The stability decreases with the increase of the drainage volume. When the drainage volume is constant, the stability first increases and then decreases with the increase in heel angle. The theoretical calculation results are consistent with the numerical results, which verify the effectiveness of the water surface stability prediction model proposed in this paper. It can provide a theoretical basis for the optimization design of water surface stability of the undulatory fin robot.