Code summarization has long been viewed as a challenge in software engineering because of the difficulties of understanding source code and generating natural language. Some mainstream methods combine abstract syntax trees with language models to capture the structural information of the source code and generate relatively satisfactory comments. However, these methods are still deficient in code understanding and limited by the long dependency problem. In this paper, we propose a novel model called Fret, which stands for Functional REinforced Transformer with BERT. The model provides a new way to generate code comments by learning code functionalities and deepening code understanding while alleviating the problem of long dependency. For this purpose, a novel reinforcer is proposed for learning the functional contents of code so that more accurate summaries to describe the code functionalities can be generated. In addition, a more efficient algorithm is newly designed to capture the source code structure. The experimental results show that the effectiveness of our model is remarkable. Fret significantly outperforms all the state-of-the-art methods we examine. It pushes the BLEU-4 score to 24.32 for Java code summarization (14.23% absolute improvement) and the ROUGE-L score to 40.12 for Python. An ablation test is also conducted to further explore the impact of each component of our method.

Multi-label image classification poses a formidable challenge due to the presence of multiple objects in each image, rendering it notably complex to decipher the visual content comprehensively. Discriminating between multiple objects necessitates the establishment of robust visual label dependencies. Previous methods attempt to formulate cross-modal interaction or one-shot co-occurrence relationship guidance. However, it not only exhibits limitations when handling occluded or blurry objects but also fails to fully leverage the diverse hierarchical properties for sustainably guiding the learning process of label dependencies. To sustainably establish hierarchical visual label dependencies, this paper introduces a Pyramidal Cross-modal Transformer framework for MLIC tasks. Specifically, the pyramidal visual guidance layer parses the visual features into a multi-resolution pyramid structure, allowing the updated visual-related information to provide sustained guidance for label semantics. This surpasses the conventional pre-processing of co-occurrence relationships. Besides, the hybrid modal interaction layer is proposed to effectively mitigate the semantic disparities between visual and label information with modal-blended indiscriminate attention, replacing vanilla self-attention. Several combination blocks consisting of these two layers are integrated and embedded within the encoder-decoder structure to facilitate the exploration of meticulous visual label dependencies. Extensive experiments on two widely-used benchmarks, including MS-COCO and PASCAL VOC 2007, consistently demonstrate that PCMT could provide state-of-the-art results.

Large Language Models (LLMs) are capable of generating syntactically correct and functionally complete programs, greatly streamlining software development. However, recent studies reveal that these programs typically execute substantially slower than human-optimized counterparts. Existing approaches to bridging this efficiency gap typically involve either iteratively optimizing code after generation or fine-tuning models on corpora of efficient code. Yet, these methods expose the model to efficiency signals only by mimicking complete, optimized solutions, without explicitly encoding the structural code patterns essential for achieving high runtime performance. Addressing this gap presents two core challenges: (1) extracting and representing latent, efficiency-oriented structural patterns embedded within complex syntax and control flows, and (2) effectively learning these patterns without destabilizing the semantic training of LLMs. To tackle these challenges, we propose EffiSkel, an effi ciency skel eton-guided framework that explicitly extracts and learns efficiency skeletons—abstract, reusable structural patterns underpinning efficient code—by leveraging three complementary strategies: lexical analysis based on token-frequency saliency, syntactic analysis using similarity over Abstract Syntax Trees (ASTs), and dynamic line-level profiling of execution time. These skeletons are integrated into a multi-task learning regime that jointly optimizes code generation and skeleton prediction, introducing an explicit inductive bias toward efficiency-aware code generation. Experiments across multiple programming languages and benchmarks demonstrate that EffiSkel significantly enhances both functional correctness and efficiency, resulting on Mercury with DeepSeek-Coder (6.7B) a +11.11% (vs. EffiCoder) and +3.71% (vs. CodeDPO) higher Efficiency Ratio (ER), and a +0.36 (vs. EffiCoder) and +0.22 (vs. CodeDPO) increase in Average Speedup (AS). These results highlight the effectiveness of explicitly modeling efficiency skeletons in improving the runtime performance of code generated by LLMs.