Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in terms of resource consumption. This substantial size places a heavy load on memory resources, raising considerable practical concerns. In this paper, we introduce DP-MemArc, a novel training framework aimed at reducing the memory costs of large language models while emphasizing the protection of user data privacy. DP-MemArc incorporates side network or reversible network designs to support a variety of differential privacy memory-efficient fine-tuning schemes. Our approach not only achieves about 2.5 times in memory optimization but also ensures robust privacy protection, keeping user data secure and confidential. Extensive experiments have demonstrated that DP-MemArc effectively provides differential privacy-efficient fine-tuning across different task scenarios.

Extracting valuable visual cues for downstream vision tasks poses a particular challenge under unknown degradations. A straightforward solution is to preprocess images using image restoration methods, but their high computational complexity renders them unsuitable for real-time tasks. Recent efforts have aimed to enhance image representations optimized by downstream task losses. However, these approaches are confined to known single degradation scenarios, constraining their practical applicability in unpredictable environments. Therefore, we propose a Chain-of-thought Prompted Adaptive Enhancer, CPA-Enhancer, for enhancing important features crucial for downstream vision tasks under unknown degradations. Specifically, CPA-Enhancer progressively adapts its enhancement strategies under the step-by-step guidance of CoT prompts that encode degradation-related information. Overall, CPA-Enhancer is a plug-and-play lightweight enhancement model that can be integrated into any vision pipeline and trained with task-related losses, without any prior knowledge of the degradation type. Extensive experiments demonstrate that CPA-Enhancer significantly improves performance across various vision tasks under unknown degradations. The codes is available at https://github.com/zyw-stu/CPA-Enhancer.

Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1-mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA.

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing examples of tool usage and their corresponding functions, allowing LLMs to formulate plans and demonstrate the process of invoking and executing each tool. LLMs can address tasks that they cannot complete independently, thereby enhancing their potential across different tasks. However, this approach faces two key challenges. First, redundant error correction leads to unstable planning and long execution time. Additionally, designing a correct plan among multiple tools is also a challenge in tool learning. To address these issues, we propose Tool-Planner, a task-processing framework based on toolkits. Tool-Planner groups tools based on the API functions with the same function into a toolkit and allows LLMs to implement planning across the various toolkits. When a tool error occurs, the language model can reselect and adjust tools based on the toolkit. Experiments show that our approach demonstrates a high pass and win rate across different datasets and optimizes the planning scheme for tool learning in models such as GPT-4 and Claude 3, showcasing the potential of our method. Our code is public at https://github.com/OceannTwT/Tool-Planner.

Large language models (LLMs) have achieved commendable accomplishments in various natural language processing tasks.However, LLMs still encounter significant challenges when dealing with complex scenarios involving multiple entities.These challenges arise from the presence of implicit relationships that demand multi-step reasoning.In this paper, we propose a novel approach ERA-CoT, which aids LLMs in understanding context by capturing relationships between entities and supports the reasoning of diverse tasks through Chainof-Thoughts (CoT).Experimental results show that ERA-CoT demonstrates the superior performance of our proposed method compared to current CoT prompting methods, achieving a significant improvement of an average of 5.1% on GPT3.5 compared to previous SOTA baselines.Our analysis indicates that ERA-CoT increases the LLM's understanding of entity relationships, significantly improves the accuracy of question answering, and enhances the reasoning ability of LLMs. 1

Multi-beam GEO satellites are integral to modern satellite communication systems. This paper focuses on a multi-beam GEO satellite downlink TDMA/FDMA system, exploring flexible beam allocation to users. Our objective is to maximize the sum system rate, which involves joint optimization of beams, time, carriers, and power allocation. Then we address this mixed-integer non-convex problem through an iterative optimization algorithm based on the Successive Convex Approximation (SCA) and Quadratic Transformation (QT) algorithms. Our algorithm significantly reduces the average user unmet degree by 20% and enhances the system’s sum rate by 23% compared to the baseline scheme, demonstrating its effectiveness in scenarios with non-uniform user traffic distribution.

Multibeam geostationary (GEO) satellites play a pivotal role in contemporary satellite communication by ad-dressing the escalating demands. In this paper, we assume a flexible beam-user mapping scheme, wherein users have the liberty to select a specific beam for access, while power and bandwidth allocation is performed on a per-beam basis. To effectively manage radio resources and cater to user demands, we employ a Time Division Multiple (TDM) technique within each beam. To address the resource management challenge, we propose an iterative algorithm for optimizing time fraction and power. Each subproblem is transformed and solved using the Successive Convex Approximation (SCA) method and branch and bound algorithm. The results demonstrate that the proposed algorithm outperforms fixed user mapping and fixed time fraction algorithms by reducing the average user unmet degree by 4.0% and 9.9%, respectively. The flexibility inherent in user mapping and resource allocation enhances resource utilization and alleviates the pressure on satellite from higher user demands.

Drug-Drug Interaction (DDI) prediction task is helpful for better-understanding drugs. In this paper, we propose a novel drug-drug interaction prediction model based on line subgraph generation strategy, named DDI-LSG model. Our DDI-LSG model consists of three main parts which include drug relation graph construction, line subgraph generation strategy, and graph-level classification. To consider more relationships among drugs, we propose a node feature-enhancing method to encode drug features in drug relation graph construction process. To consider drugs and DDI as equivalent factors of our DDI-LSG model, we introduce line graph transformation to integrate DDI with drug feature enhancing vector. Combining Jaccard similarity with cosine similarity, we propose a line subgraph generation strategy to evaluate node relation and extract key structures around target DDI in the line graph. Then, we reformulate the DDI prediction task into a graph-level classification task for the line subgraph of the target DDI. Therefore, in the final part of our DDI-LSG model, we use a graph-level classifier to classify the line subgraphs. Our DDI-LSG model outperforms better experiment results than baselines. Ablation results have validated the node feature enhancing method and line subgraph generation strategy.