Knowledge distillation (KD) is a widely adopted technique for transferring the capabilities of large teacher models to smaller student models, thereby significantly reducing inference costs and memory consumption. However, existing KD methods are all constrained by an inherent greedy optimization objective, rooted in the assumption of teacher superiority: "Trust all teacher-generated outputs (TGOs)" and "Distrust any student-generated outputs (SGOs) unsupported by the teacher". We propose ASKD, a novel KD method with adaptive skewness determined by sample quality, refining this objective to: "Learn TGOs proportionally to their quality, and distrust only low-quality unsupported SGOs". ASKD comprises three key components: (1) A reinforcement learning-style optimization formulation to mitigate the inherent approximation bias in sample-based Kullback-Leibler (KL) divergence approximations used by previous KD methods; (2) Well-designed quality supervision signals to map and achieve adaptive skewness in skewed KL loss, pioneering the usage of sample quality to adjust learning magnitudes; (3) A gradient-clip function on high-quality SGOs for findings that high-quality SGOs in KL loss fail to yield positive updates and even cause adverse effects on some samples. Extensive experiments indicate that ASKD builds high-performance student models across various tasks, including instruction following, mathematical reasoning, and code generation, outperforming state-of-the-art methods comprehensively and surpassing GRPO-like approaches that use advantages as multiplicative factors. We also provide detailed mathematical proofs demonstrating properties such as Lipschitz continuity of the update coefficient and uniform convergence of the loss function, ensuring theoretical rigor for key components of ASKD.

Large-scale wireless networks pose significant challenges in resource scheduling, where the solution space grows exponentially with network size. While network decomposition offers a promising solution by breaking networks into manageable subnetworks, existing approaches, including spectral clustering, fail to effectively capture the complex service relationships between base stations (BSs) and users, particularly in networks with massive user populations. This paper presents BSCCD (Bidirectional Spectral Co-Clustering Based Decomposition), a new decomposition scheme that addresses these challenges through two key innovations: (i) a two-round spectral co-clustering framework that captures bidirectional BS-user relationships, and (ii) a user node merging strategy that handles massive user populations. Extensive experiments on real-world datasets from multiple Chinese cities demonstrate that BSCCD reduces computation latency by up to 61.91 % compared to global optimization, while achieving more than 10 % improvement in solution quality over traditional clustering approaches. The advantage is particularly pronounced in medium-scale networks, where BSCCD outperforms traditional methods by$\mathbf{2 8. 7 6 \%}$. Our results demonstrate BSCCD's practical viability for resource scheduling in contemporary wireless networks, especially in scenarios with complex BS-user interactions and large user populations.

In serverless computing, an idle container is not recycled directly, in order to mitigate time-consuming cold container startup. These idle containers still occupy the memory, exasperating the memory shortage of today's data centers. By offloading their cold memory to remote memory pool could potentially resolve this problem. However, existing offloading policies either hurt the Quality of Service (QoS) or are too coarse-grained in serverless computing scenarios.

To reconstruct high dynamic range (HDR) video from alternating exposed low dynamic range (LDR) frames, the key is to address the misalignment and imprecise fusion caused by information loss and noise in ill-exposed regions. Following a coarse-to-fine manner, a Multi-level Spatial-Temporal feature aggregation and alignment-based Selective Residual Dense Propagation Network (MSTSRDPNet) is proposed. The Multi-level Spatial-Temporal aggregation extracts spatial-temporal features and aggregates them to mitigate information loss for fusion. The alignment-based Selective Residual Dense Propagation module reconstructs the aligned feature by using channel attention to redistribute feature weights while leveraging residual dense connections for information propagation. Experiments show that the proposed MSTSRDPNet outperforms all conventional methods on the synthetic dataset with PSNR-T, HDR-VQM, and HDR-VDP-2 scores of 44.64 dB, 86.83, and 73.9.

Recently, micro-video sharing platforms such as Kuaishou and Tiktok have become a major source of information for people's lives. Thanks to the large traffic volume, short video lifespan and streaming fashion of these services, it has become more and more pressing to improve the existing recommender systems to accommodate these challenges in a cost-effective way. In this paper, we propose a novel concept-aware denoising graph neural network (named Conde) for micro-video recommendation. Conde consists of a three-phase graph convolution process to derive user and micro-video representations: warm-up propagation, graph denoising and preference refinement. A heterogeneous tripartite graph is constructed by connecting user nodes with video nodes, and video nodes with associated concept nodes, extracted from captions and comments of the videos. To address the noisy information in the graph, we introduce a user-oriented graph denoising phase to extract a subgraph which can better reflect the user's preference. Despite the main focus of micro-video recommendation in this paper, we also show that our method can be generalized to other types of tasks. Therefore, we also conduct empirical studies on a well-known public E-commerce dataset. The experimental results suggest that the proposed Conde achieves significantly better recommendation performance than the existing state-of-the-art solutions.

Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing.However, there is currently no cross-task dataset in NLP, which hinders the development of multi-task learning.We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization.MAT-INF contains 1.07 million question-answer pairs with human-labeled categories and usergenerated question descriptions.Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question answering, and summarization.We benchmark existing methods and a novel multi-task baseline over MATINF to inspire further research.Our comprehensive comparison and experiments over MATINF and other datasets demonstrate the merits held by MAT-INF. 1